diff --git a/any-discipline-budget.json b/any-discipline-budget.json
index d78b15e3653..477ad5cb95a 100644
--- a/any-discipline-budget.json
+++ b/any-discipline-budget.json
@@ -1,7 +1,7 @@
 {
   "litellm/__init__.py": {
-    "baseline": 801,
-    "slack": 401
+    "baseline": 740,
+    "slack": 370
   },
   "litellm/_lazy_imports.py": {
     "baseline": 55,
@@ -16,11 +16,11 @@
     "slack": 208
   },
   "litellm/_redis_credential_provider.py": {
-    "baseline": 20,
+    "baseline": 19,
     "slack": 10
   },
   "litellm/_service_logger.py": {
-    "baseline": 96,
+    "baseline": 95,
     "slack": 48
   },
   "litellm/_uuid.py": {
@@ -52,8 +52,8 @@
     "slack": 43
   },
   "litellm/a2a_protocol/main.py": {
-    "baseline": 209,
-    "slack": 105
+    "baseline": 208,
+    "slack": 104
   },
   "litellm/a2a_protocol/providers/bedrock_agentcore/config.py": {
     "baseline": 15,
@@ -80,24 +80,24 @@
     "slack": 6
   },
   "litellm/a2a_protocol/providers/pydantic_ai_agents/transformation.py": {
-    "baseline": 142,
-    "slack": 71
+    "baseline": 139,
+    "slack": 70
   },
   "litellm/a2a_protocol/providers/watsonx_orchestrate/config.py": {
     "baseline": 13,
     "slack": 7
   },
   "litellm/a2a_protocol/providers/watsonx_orchestrate/handler.py": {
-    "baseline": 118,
-    "slack": 59
+    "baseline": 107,
+    "slack": 54
   },
   "litellm/a2a_protocol/providers/watsonx_orchestrate/transformation.py": {
-    "baseline": 60,
-    "slack": 30
+    "baseline": 58,
+    "slack": 29
   },
   "litellm/a2a_protocol/streaming_iterator.py": {
-    "baseline": 57,
-    "slack": 29
+    "baseline": 56,
+    "slack": 28
   },
   "litellm/a2a_protocol/utils.py": {
     "baseline": 36,
@@ -112,16 +112,16 @@
     "slack": 13
   },
   "litellm/anthropic_interface/exceptions/exceptions.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/anthropic_interface/messages/__init__.py": {
     "baseline": 17,
     "slack": 9
   },
   "litellm/assistants/main.py": {
-    "baseline": 398,
-    "slack": 199
+    "baseline": 382,
+    "slack": 191
   },
   "litellm/assistants/utils.py": {
     "baseline": 94,
@@ -136,8 +136,8 @@
     "slack": 65
   },
   "litellm/batches/main.py": {
-    "baseline": 240,
-    "slack": 120
+    "baseline": 221,
+    "slack": 111
   },
   "litellm/budget_manager.py": {
     "baseline": 117,
@@ -148,8 +148,8 @@
     "slack": 8
   },
   "litellm/caching/azure_blob_cache.py": {
-    "baseline": 77,
-    "slack": 39
+    "baseline": 74,
+    "slack": 37
   },
   "litellm/caching/base_cache.py": {
     "baseline": 2,
@@ -160,55 +160,55 @@
     "slack": 189
   },
   "litellm/caching/caching_handler.py": {
-    "baseline": 337,
-    "slack": 169
+    "baseline": 336,
+    "slack": 168
   },
   "litellm/caching/disk_cache.py": {
     "baseline": 75,
     "slack": 38
   },
   "litellm/caching/dual_cache.py": {
-    "baseline": 192,
-    "slack": 96
+    "baseline": 189,
+    "slack": 95
   },
   "litellm/caching/gcs_cache.py": {
     "baseline": 92,
     "slack": 46
   },
   "litellm/caching/in_memory_cache.py": {
-    "baseline": 173,
-    "slack": 87
+    "baseline": 172,
+    "slack": 86
   },
   "litellm/caching/llm_caching_handler.py": {
     "baseline": 32,
     "slack": 16
   },
   "litellm/caching/qdrant_semantic_cache.py": {
-    "baseline": 359,
-    "slack": 180
+    "baseline": 357,
+    "slack": 179
   },
   "litellm/caching/redis_cache.py": {
-    "baseline": 588,
-    "slack": 294
+    "baseline": 583,
+    "slack": 292
   },
   "litellm/caching/redis_cluster_cache.py": {
     "baseline": 35,
     "slack": 18
   },
   "litellm/caching/redis_semantic_cache.py": {
-    "baseline": 194,
-    "slack": 97
+    "baseline": 188,
+    "slack": 94
   },
   "litellm/caching/s3_cache.py": {
     "baseline": 138,
     "slack": 69
   },
   "litellm/completion_extras/litellm_responses_transformation/handler.py": {
-    "baseline": 187,
-    "slack": 94
+    "baseline": 177,
+    "slack": 89
   },
   "litellm/completion_extras/litellm_responses_transformation/transformation.py": {
-    "baseline": 562,
+    "baseline": 561,
     "slack": 281
   },
   "litellm/compression/compress.py": {
@@ -244,8 +244,8 @@
     "slack": 43
   },
   "litellm/containers/main.py": {
-    "baseline": 278,
-    "slack": 139
+    "baseline": 219,
+    "slack": 110
   },
   "litellm/containers/utils.py": {
     "baseline": 30,
@@ -256,64 +256,64 @@
     "slack": 214
   },
   "litellm/endpoints/speech/speech_to_completion_bridge/handler.py": {
-    "baseline": 59,
-    "slack": 30
+    "baseline": 51,
+    "slack": 26
   },
   "litellm/endpoints/speech/speech_to_completion_bridge/transformation.py": {
     "baseline": 31,
     "slack": 16
   },
   "litellm/evals/main.py": {
-    "baseline": 522,
-    "slack": 261
+    "baseline": 500,
+    "slack": 250
   },
   "litellm/exceptions.py": {
     "baseline": 481,
     "slack": 241
   },
   "litellm/experimental_mcp_client/client.py": {
-    "baseline": 174,
-    "slack": 87
+    "baseline": 172,
+    "slack": 86
   },
   "litellm/experimental_mcp_client/tools.py": {
     "baseline": 47,
     "slack": 24
   },
   "litellm/files/main.py": {
-    "baseline": 257,
-    "slack": 129
+    "baseline": 241,
+    "slack": 121
   },
   "litellm/files/streaming.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 45,
+    "slack": 23
   },
   "litellm/files/types.py": {
-    "baseline": 4,
-    "slack": 2
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/fine_tuning/main.py": {
-    "baseline": 167,
-    "slack": 84
+    "baseline": 157,
+    "slack": 79
   },
   "litellm/google_genai/adapters/handler.py": {
     "baseline": 49,
     "slack": 25
   },
   "litellm/google_genai/adapters/transformation.py": {
-    "baseline": 325,
-    "slack": 163
+    "baseline": 324,
+    "slack": 162
   },
   "litellm/google_genai/main.py": {
-    "baseline": 179,
-    "slack": 90
+    "baseline": 171,
+    "slack": 86
   },
   "litellm/google_genai/streaming_iterator.py": {
     "baseline": 56,
     "slack": 28
   },
   "litellm/images/main.py": {
-    "baseline": 326,
-    "slack": 163
+    "baseline": 311,
+    "slack": 156
   },
   "litellm/images/utils.py": {
     "baseline": 28,
@@ -328,12 +328,12 @@
     "slack": 24
   },
   "litellm/integrations/SlackAlerting/slack_alerting.py": {
-    "baseline": 644,
-    "slack": 322
+    "baseline": 635,
+    "slack": 318
   },
   "litellm/integrations/SlackAlerting/utils.py": {
-    "baseline": 15,
-    "slack": 8
+    "baseline": 14,
+    "slack": 7
   },
   "litellm/integrations/additional_logging_utils.py": {
     "baseline": 1,
@@ -364,8 +364,8 @@
     "slack": 18
   },
   "litellm/integrations/arize/arize_phoenix.py": {
-    "baseline": 159,
-    "slack": 80
+    "baseline": 158,
+    "slack": 79
   },
   "litellm/integrations/arize/arize_phoenix_client.py": {
     "baseline": 12,
@@ -380,7 +380,7 @@
     "slack": 43
   },
   "litellm/integrations/azure_sentinel/azure_sentinel.py": {
-    "baseline": 84,
+    "baseline": 83,
     "slack": 42
   },
   "litellm/integrations/azure_storage/azure_storage.py": {
@@ -416,8 +416,8 @@
     "slack": 4
   },
   "litellm/integrations/cloudzero/cz_stream_api.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 46,
+    "slack": 23
   },
   "litellm/integrations/cloudzero/database.py": {
     "baseline": 9,
@@ -436,7 +436,7 @@
     "slack": 20
   },
   "litellm/integrations/custom_guardrail.py": {
-    "baseline": 304,
+    "baseline": 303,
     "slack": 152
   },
   "litellm/integrations/custom_logger.py": {
@@ -452,8 +452,8 @@
     "slack": 1
   },
   "litellm/integrations/datadog/datadog.py": {
-    "baseline": 266,
-    "slack": 133
+    "baseline": 264,
+    "slack": 132
   },
   "litellm/integrations/datadog/datadog_cost_management.py": {
     "baseline": 79,
@@ -476,8 +476,8 @@
     "slack": 2
   },
   "litellm/integrations/datadog/datadog_team_handler.py": {
-    "baseline": 14,
-    "slack": 7
+    "baseline": 10,
+    "slack": 5
   },
   "litellm/integrations/deepeval/api.py": {
     "baseline": 31,
@@ -488,8 +488,8 @@
     "slack": 66
   },
   "litellm/integrations/deepeval/types.py": {
-    "baseline": 16,
-    "slack": 8
+    "baseline": 12,
+    "slack": 6
   },
   "litellm/integrations/dotprompt/__init__.py": {
     "baseline": 19,
@@ -515,37 +515,33 @@
     "baseline": 16,
     "slack": 8
   },
-  "litellm/integrations/focus/destinations/base.py": {
-    "baseline": 3,
-    "slack": 2
-  },
   "litellm/integrations/focus/destinations/factory.py": {
     "baseline": 50,
     "slack": 25
   },
   "litellm/integrations/focus/destinations/gcs_destination.py": {
-    "baseline": 16,
+    "baseline": 15,
     "slack": 8
   },
   "litellm/integrations/focus/destinations/mavvrik_destination.py": {
-    "baseline": 49,
-    "slack": 25
+    "baseline": 40,
+    "slack": 20
   },
   "litellm/integrations/focus/destinations/s3_destination.py": {
-    "baseline": 27,
-    "slack": 14
-  },
-  "litellm/integrations/focus/destinations/vantage_destination.py": {
-    "baseline": 25,
+    "baseline": 26,
     "slack": 13
   },
+  "litellm/integrations/focus/destinations/vantage_destination.py": {
+    "baseline": 19,
+    "slack": 10
+  },
   "litellm/integrations/focus/export_engine.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 44,
+    "slack": 22
   },
   "litellm/integrations/focus/focus_logger.py": {
-    "baseline": 30,
-    "slack": 15
+    "baseline": 23,
+    "slack": 12
   },
   "litellm/integrations/focus/schema.py": {
     "baseline": 76,
@@ -564,28 +560,32 @@
     "slack": 55
   },
   "litellm/integrations/galileo.py": {
-    "baseline": 381,
-    "slack": 191
+    "baseline": 370,
+    "slack": 185
   },
   "litellm/integrations/gcs_bucket/gcs_bucket.py": {
-    "baseline": 104,
-    "slack": 52
+    "baseline": 99,
+    "slack": 50
   },
   "litellm/integrations/gcs_bucket/gcs_bucket_base.py": {
-    "baseline": 48,
-    "slack": 24
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/integrations/gcs_bucket/gcs_bucket_mock_client.py": {
     "baseline": 60,
     "slack": 30
   },
   "litellm/integrations/gcs_pubsub/pub_sub.py": {
-    "baseline": 56,
-    "slack": 28
+    "baseline": 54,
+    "slack": 27
   },
   "litellm/integrations/generic_api/generic_api_callback.py": {
-    "baseline": 198,
-    "slack": 99
+    "baseline": 196,
+    "slack": 98
+  },
+  "litellm/integrations/generic_prompt_management/__init__.py": {
+    "baseline": 7,
+    "slack": 4
   },
   "litellm/integrations/generic_prompt_management/generic_prompt_manager.py": {
     "baseline": 51,
@@ -616,8 +616,8 @@
     "slack": 2
   },
   "litellm/integrations/humanloop.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 43,
+    "slack": 22
   },
   "litellm/integrations/lago.py": {
     "baseline": 123,
@@ -648,8 +648,8 @@
     "slack": 60
   },
   "litellm/integrations/langsmith.py": {
-    "baseline": 245,
-    "slack": 123
+    "baseline": 244,
+    "slack": 122
   },
   "litellm/integrations/langsmith_mock_client.py": {
     "baseline": 5,
@@ -672,24 +672,24 @@
     "slack": 141
   },
   "litellm/integrations/logfire_logger.py": {
-    "baseline": 88,
-    "slack": 44
+    "baseline": 86,
+    "slack": 43
   },
   "litellm/integrations/lunary.py": {
     "baseline": 126,
     "slack": 63
   },
   "litellm/integrations/mavvrik_focus/mavvrik_focus_logger.py": {
-    "baseline": 32,
-    "slack": 16
+    "baseline": 25,
+    "slack": 13
   },
   "litellm/integrations/mlflow.py": {
     "baseline": 239,
     "slack": 120
   },
   "litellm/integrations/mock_client_factory.py": {
-    "baseline": 88,
-    "slack": 44
+    "baseline": 86,
+    "slack": 43
   },
   "litellm/integrations/newrelic/newrelic.py": {
     "baseline": 274,
@@ -708,12 +708,12 @@
     "slack": 2
   },
   "litellm/integrations/opentelemetry_utils/gen_ai_semconv.py": {
-    "baseline": 64,
+    "baseline": 63,
     "slack": 32
   },
   "litellm/integrations/opik/opik.py": {
-    "baseline": 82,
-    "slack": 41
+    "baseline": 80,
+    "slack": 40
   },
   "litellm/integrations/opik/opik_payload_builder/api.py": {
     "baseline": 53,
@@ -728,8 +728,8 @@
     "slack": 9
   },
   "litellm/integrations/opik/opik_payload_builder/types.py": {
-    "baseline": 24,
-    "slack": 12
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/integrations/opik/utils.py": {
     "baseline": 76,
@@ -768,16 +768,12 @@
     "slack": 3
   },
   "litellm/integrations/otel/model/metadata.py": {
-    "baseline": 42,
-    "slack": 21
+    "baseline": 31,
+    "slack": 16
   },
   "litellm/integrations/otel/model/payloads.py": {
-    "baseline": 67,
-    "slack": 34
-  },
-  "litellm/integrations/otel/model/spans.py": {
-    "baseline": 3,
-    "slack": 2
+    "baseline": 40,
+    "slack": 20
   },
   "litellm/integrations/otel/model/utils.py": {
     "baseline": 4,
@@ -788,8 +784,8 @@
     "slack": 7
   },
   "litellm/integrations/otel/plumbing/metrics.py": {
-    "baseline": 115,
-    "slack": 58
+    "baseline": 109,
+    "slack": 55
   },
   "litellm/integrations/otel/plumbing/providers.py": {
     "baseline": 2,
@@ -840,8 +836,8 @@
     "slack": 2
   },
   "litellm/integrations/prometheus.py": {
-    "baseline": 1095,
-    "slack": 548
+    "baseline": 1088,
+    "slack": 544
   },
   "litellm/integrations/prometheus_helpers/__init__.py": {
     "baseline": 11,
@@ -864,24 +860,24 @@
     "slack": 32
   },
   "litellm/integrations/prompt_management_base.py": {
-    "baseline": 27,
-    "slack": 14
+    "baseline": 20,
+    "slack": 10
   },
   "litellm/integrations/rubrik.py": {
-    "baseline": 205,
-    "slack": 103
+    "baseline": 203,
+    "slack": 102
   },
   "litellm/integrations/s3.py": {
     "baseline": 120,
     "slack": 60
   },
   "litellm/integrations/s3_v2.py": {
-    "baseline": 242,
+    "baseline": 241,
     "slack": 121
   },
   "litellm/integrations/sqs.py": {
-    "baseline": 120,
-    "slack": 60
+    "baseline": 117,
+    "slack": 59
   },
   "litellm/integrations/supabase.py": {
     "baseline": 79,
@@ -892,20 +888,20 @@
     "slack": 65
   },
   "litellm/integrations/vantage/vantage_logger.py": {
-    "baseline": 22,
-    "slack": 11
+    "baseline": 20,
+    "slack": 10
   },
   "litellm/integrations/vector_store_integrations/vector_store_pre_call_hook.py": {
-    "baseline": 75,
-    "slack": 38
+    "baseline": 74,
+    "slack": 37
   },
   "litellm/integrations/weave/weave_otel.py": {
     "baseline": 108,
     "slack": 54
   },
   "litellm/integrations/websearch_interception/handler.py": {
-    "baseline": 447,
-    "slack": 224
+    "baseline": 430,
+    "slack": 215
   },
   "litellm/integrations/websearch_interception/tools.py": {
     "baseline": 36,
@@ -916,24 +912,24 @@
     "slack": 93
   },
   "litellm/integrations/weights_biases.py": {
-    "baseline": 107,
-    "slack": 54
+    "baseline": 106,
+    "slack": 53
   },
   "litellm/interactions/agents/http_handler.py": {
-    "baseline": 170,
-    "slack": 85
+    "baseline": 165,
+    "slack": 83
   },
   "litellm/interactions/agents/main.py": {
-    "baseline": 194,
-    "slack": 97
+    "baseline": 189,
+    "slack": 95
   },
   "litellm/interactions/http_handler.py": {
-    "baseline": 158,
-    "slack": 79
+    "baseline": 154,
+    "slack": 77
   },
   "litellm/interactions/litellm_responses_transformation/handler.py": {
-    "baseline": 23,
-    "slack": 12
+    "baseline": 22,
+    "slack": 11
   },
   "litellm/interactions/litellm_responses_transformation/streaming_iterator.py": {
     "baseline": 35,
@@ -944,8 +940,8 @@
     "slack": 66
   },
   "litellm/interactions/main.py": {
-    "baseline": 153,
-    "slack": 77
+    "baseline": 147,
+    "slack": 74
   },
   "litellm/interactions/streaming_iterator.py": {
     "baseline": 48,
@@ -960,13 +956,13 @@
     "slack": 3
   },
   "litellm/litellm_core_utils/asyncify.py": {
-    "baseline": 21,
-    "slack": 11
-  },
-  "litellm/litellm_core_utils/audio_utils/utils.py": {
     "baseline": 19,
     "slack": 10
   },
+  "litellm/litellm_core_utils/audio_utils/utils.py": {
+    "baseline": 16,
+    "slack": 8
+  },
   "litellm/litellm_core_utils/cli_token_utils.py": {
     "baseline": 7,
     "slack": 4
@@ -976,8 +972,8 @@
     "slack": 4
   },
   "litellm/litellm_core_utils/completion_timeout.py": {
-    "baseline": 5,
-    "slack": 3
+    "baseline": 4,
+    "slack": 2
   },
   "litellm/litellm_core_utils/core_helpers.py": {
     "baseline": 192,
@@ -1020,8 +1016,8 @@
     "slack": 29
   },
   "litellm/litellm_core_utils/get_blog_posts.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/litellm_core_utils/get_litellm_params.py": {
     "baseline": 45,
@@ -1060,7 +1056,7 @@
     "slack": 31
   },
   "litellm/litellm_core_utils/litellm_logging.py": {
-    "baseline": 2348,
+    "baseline": 2347,
     "slack": 1174
   },
   "litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py": {
@@ -1072,15 +1068,15 @@
     "slack": 1
   },
   "litellm/litellm_core_utils/llm_cost_calc/utils.py": {
-    "baseline": 55,
-    "slack": 28
+    "baseline": 42,
+    "slack": 21
   },
   "litellm/litellm_core_utils/llm_request_utils.py": {
     "baseline": 37,
     "slack": 19
   },
   "litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py": {
-    "baseline": 336,
+    "baseline": 335,
     "slack": 168
   },
   "litellm/litellm_core_utils/llm_response_utils/get_api_base.py": {
@@ -1108,8 +1104,8 @@
     "slack": 91
   },
   "litellm/litellm_core_utils/logging_worker.py": {
-    "baseline": 103,
-    "slack": 52
+    "baseline": 91,
+    "slack": 46
   },
   "litellm/litellm_core_utils/model_param_helper.py": {
     "baseline": 41,
@@ -1120,12 +1116,12 @@
     "slack": 26
   },
   "litellm/litellm_core_utils/prompt_templates/common_utils.py": {
-    "baseline": 362,
+    "baseline": 361,
     "slack": 181
   },
   "litellm/litellm_core_utils/prompt_templates/factory.py": {
-    "baseline": 1452,
-    "slack": 726
+    "baseline": 1445,
+    "slack": 723
   },
   "litellm/litellm_core_utils/prompt_templates/huggingface_template_handler.py": {
     "baseline": 30,
@@ -1136,8 +1132,8 @@
     "slack": 10
   },
   "litellm/litellm_core_utils/realtime_streaming.py": {
-    "baseline": 631,
-    "slack": 316
+    "baseline": 614,
+    "slack": 307
   },
   "litellm/litellm_core_utils/redact_messages.py": {
     "baseline": 195,
@@ -1148,7 +1144,7 @@
     "slack": 5
   },
   "litellm/litellm_core_utils/safe_json_dumps.py": {
-    "baseline": 64,
+    "baseline": 63,
     "slack": 32
   },
   "litellm/litellm_core_utils/safe_json_loads.py": {
@@ -1168,7 +1164,7 @@
     "slack": 157
   },
   "litellm/litellm_core_utils/streaming_handler.py": {
-    "baseline": 1020,
+    "baseline": 1019,
     "slack": 510
   },
   "litellm/litellm_core_utils/token_counter.py": {
@@ -1184,8 +1180,8 @@
     "slack": 4
   },
   "litellm/llms/a2a/chat/guardrail_translation/handler.py": {
-    "baseline": 158,
-    "slack": 79
+    "baseline": 155,
+    "slack": 78
   },
   "litellm/llms/a2a/chat/streaming_iterator.py": {
     "baseline": 13,
@@ -1220,20 +1216,20 @@
     "slack": 6
   },
   "litellm/llms/anthropic/batches/handler.py": {
-    "baseline": 30,
-    "slack": 15
+    "baseline": 28,
+    "slack": 14
   },
   "litellm/llms/anthropic/batches/transformation.py": {
     "baseline": 55,
     "slack": 28
   },
   "litellm/llms/anthropic/chat/guardrail_translation/handler.py": {
-    "baseline": 181,
-    "slack": 91
+    "baseline": 175,
+    "slack": 88
   },
   "litellm/llms/anthropic/chat/handler.py": {
-    "baseline": 390,
-    "slack": 195
+    "baseline": 388,
+    "slack": 194
   },
   "litellm/llms/anthropic/chat/transformation.py": {
     "baseline": 770,
@@ -1264,8 +1260,8 @@
     "slack": 10
   },
   "litellm/llms/anthropic/experimental_pass_through/adapters/handler.py": {
-    "baseline": 228,
-    "slack": 114
+    "baseline": 225,
+    "slack": 113
   },
   "litellm/llms/anthropic/experimental_pass_through/adapters/streaming_iterator.py": {
     "baseline": 434,
@@ -1284,20 +1280,16 @@
     "slack": 50
   },
   "litellm/llms/anthropic/experimental_pass_through/context_management/editors/compact.py": {
-    "baseline": 420,
-    "slack": 210
+    "baseline": 413,
+    "slack": 207
   },
   "litellm/llms/anthropic/experimental_pass_through/context_management/placeholders.py": {
     "baseline": 3,
     "slack": 2
   },
-  "litellm/llms/anthropic/experimental_pass_through/context_management/result.py": {
-    "baseline": 2,
-    "slack": 1
-  },
   "litellm/llms/anthropic/experimental_pass_through/messages/agentic_streaming_iterator.py": {
-    "baseline": 193,
-    "slack": 97
+    "baseline": 192,
+    "slack": 96
   },
   "litellm/llms/anthropic/experimental_pass_through/messages/fake_stream_iterator.py": {
     "baseline": 78,
@@ -1336,8 +1328,8 @@
     "slack": 125
   },
   "litellm/llms/anthropic/files/handler.py": {
-    "baseline": 54,
-    "slack": 27
+    "baseline": 52,
+    "slack": 26
   },
   "litellm/llms/anthropic/files/transformation.py": {
     "baseline": 47,
@@ -1360,24 +1352,24 @@
     "slack": 37
   },
   "litellm/llms/azure/assistants.py": {
-    "baseline": 114,
-    "slack": 57
+    "baseline": 101,
+    "slack": 51
   },
   "litellm/llms/azure/audio_transcription/transformation.py": {
     "baseline": 37,
     "slack": 19
   },
   "litellm/llms/azure/audio_transcriptions.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 46,
+    "slack": 23
   },
   "litellm/llms/azure/azure.py": {
-    "baseline": 459,
-    "slack": 230
+    "baseline": 453,
+    "slack": 227
   },
   "litellm/llms/azure/batches/handler.py": {
-    "baseline": 21,
-    "slack": 11
+    "baseline": 15,
+    "slack": 8
   },
   "litellm/llms/azure/chat/gpt_5_transformation.py": {
     "baseline": 29,
@@ -1396,8 +1388,8 @@
     "slack": 7
   },
   "litellm/llms/azure/common_utils.py": {
-    "baseline": 221,
-    "slack": 111
+    "baseline": 217,
+    "slack": 109
   },
   "litellm/llms/azure/completion/handler.py": {
     "baseline": 129,
@@ -1412,16 +1404,16 @@
     "slack": 3
   },
   "litellm/llms/azure/exception_mapping.py": {
-    "baseline": 36,
+    "baseline": 35,
     "slack": 18
   },
   "litellm/llms/azure/files/handler.py": {
-    "baseline": 27,
-    "slack": 14
+    "baseline": 15,
+    "slack": 8
   },
   "litellm/llms/azure/fine_tuning/handler.py": {
-    "baseline": 21,
-    "slack": 11
+    "baseline": 15,
+    "slack": 8
   },
   "litellm/llms/azure/image_edit/transformation.py": {
     "baseline": 19,
@@ -1464,12 +1456,12 @@
     "slack": 3
   },
   "litellm/llms/azure_ai/agents/handler.py": {
-    "baseline": 293,
-    "slack": 147
+    "baseline": 292,
+    "slack": 146
   },
   "litellm/llms/azure_ai/agents/transformation.py": {
-    "baseline": 49,
-    "slack": 25
+    "baseline": 48,
+    "slack": 24
   },
   "litellm/llms/azure_ai/anthropic/count_tokens/handler.py": {
     "baseline": 20,
@@ -1484,8 +1476,8 @@
     "slack": 4
   },
   "litellm/llms/azure_ai/anthropic/handler.py": {
-    "baseline": 101,
-    "slack": 51
+    "baseline": 100,
+    "slack": 50
   },
   "litellm/llms/azure_ai/anthropic/messages_transformation.py": {
     "baseline": 44,
@@ -1508,8 +1500,8 @@
     "slack": 4
   },
   "litellm/llms/azure_ai/embed/handler.py": {
-    "baseline": 79,
-    "slack": 40
+    "baseline": 77,
+    "slack": 39
   },
   "litellm/llms/azure_ai/image_edit/flux2_transformation.py": {
     "baseline": 26,
@@ -1532,12 +1524,12 @@
     "slack": 44
   },
   "litellm/llms/azure_ai/ocr/document_intelligence/transformation.py": {
-    "baseline": 126,
-    "slack": 63
+    "baseline": 124,
+    "slack": 62
   },
   "litellm/llms/azure_ai/ocr/transformation.py": {
-    "baseline": 12,
-    "slack": 6
+    "baseline": 9,
+    "slack": 5
   },
   "litellm/llms/azure_ai/rerank/transformation.py": {
     "baseline": 12,
@@ -1560,11 +1552,11 @@
     "slack": 3
   },
   "litellm/llms/base_llm/audio_transcription/transformation.py": {
-    "baseline": 10,
+    "baseline": 9,
     "slack": 5
   },
   "litellm/llms/base_llm/base_model_iterator.py": {
-    "baseline": 86,
+    "baseline": 85,
     "slack": 43
   },
   "litellm/llms/base_llm/base_utils.py": {
@@ -1596,8 +1588,8 @@
     "slack": 1
   },
   "litellm/llms/base_llm/files/azure_blob_storage_backend.py": {
-    "baseline": 54,
-    "slack": 27
+    "baseline": 50,
+    "slack": 25
   },
   "litellm/llms/base_llm/files/transformation.py": {
     "baseline": 2,
@@ -1632,8 +1624,8 @@
     "slack": 8
   },
   "litellm/llms/base_llm/managed_resources/base_managed_resource.py": {
-    "baseline": 111,
-    "slack": 56
+    "baseline": 108,
+    "slack": 54
   },
   "litellm/llms/base_llm/managed_resources/isolation.py": {
     "baseline": 13,
@@ -1644,8 +1636,8 @@
     "slack": 9
   },
   "litellm/llms/base_llm/ocr/transformation.py": {
-    "baseline": 13,
-    "slack": 7
+    "baseline": 9,
+    "slack": 5
   },
   "litellm/llms/base_llm/passthrough/transformation.py": {
     "baseline": 4,
@@ -1668,16 +1660,16 @@
     "slack": 14
   },
   "litellm/llms/base_llm/search/transformation.py": {
-    "baseline": 8,
-    "slack": 4
+    "baseline": 4,
+    "slack": 2
   },
   "litellm/llms/base_llm/skills/transformation.py": {
     "baseline": 2,
     "slack": 1
   },
   "litellm/llms/base_llm/text_to_speech/transformation.py": {
-    "baseline": 19,
-    "slack": 10
+    "baseline": 16,
+    "slack": 8
   },
   "litellm/llms/base_llm/vector_store/transformation.py": {
     "baseline": 7,
@@ -1696,8 +1688,8 @@
     "slack": 10
   },
   "litellm/llms/bedrock/base_aws_llm.py": {
-    "baseline": 341,
-    "slack": 171
+    "baseline": 338,
+    "slack": 169
   },
   "litellm/llms/bedrock/batches/handler.py": {
     "baseline": 78,
@@ -1712,20 +1704,20 @@
     "slack": 98
   },
   "litellm/llms/bedrock/chat/converse_handler.py": {
-    "baseline": 152,
-    "slack": 76
+    "baseline": 148,
+    "slack": 74
   },
   "litellm/llms/bedrock/chat/converse_transformation.py": {
-    "baseline": 527,
-    "slack": 264
+    "baseline": 521,
+    "slack": 261
   },
   "litellm/llms/bedrock/chat/invoke_agent/transformation.py": {
     "baseline": 65,
     "slack": 33
   },
   "litellm/llms/bedrock/chat/invoke_handler.py": {
-    "baseline": 634,
-    "slack": 317
+    "baseline": 631,
+    "slack": 316
   },
   "litellm/llms/bedrock/chat/invoke_transformations/amazon_ai21_transformation.py": {
     "baseline": 36,
@@ -1780,15 +1772,15 @@
     "slack": 20
   },
   "litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude3_transformation.py": {
-    "baseline": 139,
-    "slack": 70
+    "baseline": 137,
+    "slack": 69
   },
   "litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py": {
     "baseline": 192,
     "slack": 96
   },
   "litellm/llms/bedrock/chat/mantle/transformation.py": {
-    "baseline": 24,
+    "baseline": 23,
     "slack": 12
   },
   "litellm/llms/bedrock/claude_platform/common_utils.py": {
@@ -1832,7 +1824,7 @@
     "slack": 11
   },
   "litellm/llms/bedrock/embed/amazon_titan_v2_transformation.py": {
-    "baseline": 46,
+    "baseline": 45,
     "slack": 23
   },
   "litellm/llms/bedrock/embed/cohere_transformation.py": {
@@ -1848,8 +1840,8 @@
     "slack": 29
   },
   "litellm/llms/bedrock/files/handler.py": {
-    "baseline": 33,
-    "slack": 17
+    "baseline": 31,
+    "slack": 16
   },
   "litellm/llms/bedrock/files/transformation.py": {
     "baseline": 218,
@@ -1860,12 +1852,12 @@
     "slack": 78
   },
   "litellm/llms/bedrock/image_edit/handler.py": {
-    "baseline": 56,
-    "slack": 28
+    "baseline": 51,
+    "slack": 26
   },
   "litellm/llms/bedrock/image_edit/stability_transformation.py": {
-    "baseline": 87,
-    "slack": 44
+    "baseline": 86,
+    "slack": 43
   },
   "litellm/llms/bedrock/image_generation/amazon_nova_canvas_transformation.py": {
     "baseline": 79,
@@ -1888,8 +1880,8 @@
     "slack": 1
   },
   "litellm/llms/bedrock/image_generation/image_handler.py": {
-    "baseline": 59,
-    "slack": 30
+    "baseline": 54,
+    "slack": 27
   },
   "litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py": {
     "baseline": 237,
@@ -1900,8 +1892,8 @@
     "slack": 9
   },
   "litellm/llms/bedrock/passthrough/guardrail_translation/handler.py": {
-    "baseline": 337,
-    "slack": 169
+    "baseline": 335,
+    "slack": 168
   },
   "litellm/llms/bedrock/passthrough/transformation.py": {
     "baseline": 36,
@@ -1936,24 +1928,24 @@
     "slack": 32
   },
   "litellm/llms/black_forest_labs/image_edit/handler.py": {
-    "baseline": 126,
-    "slack": 63
+    "baseline": 123,
+    "slack": 62
   },
   "litellm/llms/black_forest_labs/image_edit/transformation.py": {
     "baseline": 45,
     "slack": 23
   },
   "litellm/llms/black_forest_labs/image_generation/handler.py": {
-    "baseline": 130,
-    "slack": 65
+    "baseline": 127,
+    "slack": 64
   },
   "litellm/llms/black_forest_labs/image_generation/transformation.py": {
     "baseline": 49,
     "slack": 25
   },
   "litellm/llms/brave/search/transformation.py": {
-    "baseline": 71,
-    "slack": 36
+    "baseline": 52,
+    "slack": 26
   },
   "litellm/llms/bytez/chat/transformation.py": {
     "baseline": 128,
@@ -2024,7 +2016,7 @@
     "slack": 26
   },
   "litellm/llms/cohere/rerank/guardrail_translation/handler.py": {
-    "baseline": 16,
+    "baseline": 15,
     "slack": 8
   },
   "litellm/llms/cohere/rerank/transformation.py": {
@@ -2056,12 +2048,12 @@
     "slack": 9
   },
   "litellm/llms/custom_httpx/aiohttp_handler.py": {
-    "baseline": 187,
-    "slack": 94
+    "baseline": 183,
+    "slack": 92
   },
   "litellm/llms/custom_httpx/aiohttp_transport.py": {
-    "baseline": 40,
-    "slack": 20
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/llms/custom_httpx/async_client_cleanup.py": {
     "baseline": 42,
@@ -2072,16 +2064,16 @@
     "slack": 85
   },
   "litellm/llms/custom_httpx/http_handler.py": {
-    "baseline": 339,
-    "slack": 170
+    "baseline": 320,
+    "slack": 160
   },
   "litellm/llms/custom_httpx/httpx_handler.py": {
     "baseline": 22,
     "slack": 11
   },
   "litellm/llms/custom_httpx/llm_http_handler.py": {
-    "baseline": 3900,
-    "slack": 1950
+    "baseline": 3836,
+    "slack": 1918
   },
   "litellm/llms/custom_httpx/mock_transport.py": {
     "baseline": 13,
@@ -2091,17 +2083,13 @@
     "baseline": 10,
     "slack": 5
   },
-  "litellm/llms/dashscope/chat/transformation.py": {
-    "baseline": 1,
-    "slack": 1
-  },
   "litellm/llms/dashscope/common_utils.py": {
     "baseline": 2,
     "slack": 1
   },
   "litellm/llms/dashscope/cost_calculator.py": {
-    "baseline": 49,
-    "slack": 25
+    "baseline": 45,
+    "slack": 23
   },
   "litellm/llms/dashscope/embed/transformation.py": {
     "baseline": 44,
@@ -2116,7 +2104,7 @@
     "slack": 30
   },
   "litellm/llms/databricks/chat/transformation.py": {
-    "baseline": 168,
+    "baseline": 167,
     "slack": 84
   },
   "litellm/llms/databricks/common_utils.py": {
@@ -2160,8 +2148,8 @@
     "slack": 34
   },
   "litellm/llms/deepseek/chat/transformation.py": {
-    "baseline": 51,
-    "slack": 26
+    "baseline": 50,
+    "slack": 25
   },
   "litellm/llms/deepseek/messages/transformation.py": {
     "baseline": 35,
@@ -2176,24 +2164,24 @@
     "slack": 38
   },
   "litellm/llms/docker_model_runner/chat/transformation.py": {
-    "baseline": 15,
-    "slack": 8
+    "baseline": 14,
+    "slack": 7
   },
   "litellm/llms/duckduckgo/search/transformation.py": {
-    "baseline": 67,
-    "slack": 34
+    "baseline": 61,
+    "slack": 31
   },
   "litellm/llms/elevenlabs/audio_transcription/transformation.py": {
     "baseline": 44,
     "slack": 22
   },
   "litellm/llms/elevenlabs/text_to_speech/transformation.py": {
-    "baseline": 94,
+    "baseline": 93,
     "slack": 47
   },
   "litellm/llms/exa_ai/search/transformation.py": {
-    "baseline": 40,
-    "slack": 20
+    "baseline": 24,
+    "slack": 12
   },
   "litellm/llms/fal_ai/cost_calculator.py": {
     "baseline": 2,
@@ -2244,16 +2232,16 @@
     "slack": 13
   },
   "litellm/llms/fastcrw/search/transformation.py": {
-    "baseline": 27,
-    "slack": 14
+    "baseline": 23,
+    "slack": 12
   },
   "litellm/llms/featherless_ai/chat/transformation.py": {
     "baseline": 34,
     "slack": 17
   },
   "litellm/llms/firecrawl/search/transformation.py": {
-    "baseline": 55,
-    "slack": 28
+    "baseline": 45,
+    "slack": 23
   },
   "litellm/llms/fireworks_ai/chat/transformation.py": {
     "baseline": 124,
@@ -2300,7 +2288,7 @@
     "slack": 20
   },
   "litellm/llms/gemini/google_genai/transformation.py": {
-    "baseline": 84,
+    "baseline": 83,
     "slack": 42
   },
   "litellm/llms/gemini/image_edit/cost_calculator.py": {
@@ -2308,7 +2296,7 @@
     "slack": 1
   },
   "litellm/llms/gemini/image_edit/transformation.py": {
-    "baseline": 44,
+    "baseline": 43,
     "slack": 22
   },
   "litellm/llms/gemini/image_generation/cost_calculator.py": {
@@ -2340,7 +2328,7 @@
     "slack": 39
   },
   "litellm/llms/gigachat/authenticator.py": {
-    "baseline": 42,
+    "baseline": 41,
     "slack": 21
   },
   "litellm/llms/gigachat/chat/streaming.py": {
@@ -2356,8 +2344,8 @@
     "slack": 17
   },
   "litellm/llms/gigachat/file_handler.py": {
-    "baseline": 47,
-    "slack": 24
+    "baseline": 45,
+    "slack": 23
   },
   "litellm/llms/github_copilot/authenticator.py": {
     "baseline": 35,
@@ -2380,8 +2368,8 @@
     "slack": 35
   },
   "litellm/llms/google_pse/search/transformation.py": {
-    "baseline": 61,
-    "slack": 31
+    "baseline": 36,
+    "slack": 18
   },
   "litellm/llms/gradient_ai/chat/transformation.py": {
     "baseline": 21,
@@ -2392,20 +2380,20 @@
     "slack": 7
   },
   "litellm/llms/groq/chat/transformation.py": {
-    "baseline": 55,
-    "slack": 28
+    "baseline": 54,
+    "slack": 27
   },
   "litellm/llms/groq/stt/transformation.py": {
     "baseline": 31,
     "slack": 16
   },
   "litellm/llms/heroku/chat/transformation.py": {
-    "baseline": 2,
+    "baseline": 1,
     "slack": 1
   },
   "litellm/llms/hosted_vllm/chat/transformation.py": {
-    "baseline": 80,
-    "slack": 40
+    "baseline": 71,
+    "slack": 36
   },
   "litellm/llms/hosted_vllm/embedding/transformation.py": {
     "baseline": 19,
@@ -2432,16 +2420,16 @@
     "slack": 8
   },
   "litellm/llms/huggingface/embedding/handler.py": {
-    "baseline": 157,
-    "slack": 79
+    "baseline": 156,
+    "slack": 78
   },
   "litellm/llms/huggingface/embedding/transformation.py": {
     "baseline": 224,
     "slack": 112
   },
   "litellm/llms/huggingface/rerank/transformation.py": {
-    "baseline": 70,
-    "slack": 35
+    "baseline": 67,
+    "slack": 34
   },
   "litellm/llms/hyperbolic/chat/transformation.py": {
     "baseline": 1,
@@ -2500,8 +2488,8 @@
     "slack": 33
   },
   "litellm/llms/linkup/search/transformation.py": {
-    "baseline": 43,
-    "slack": 22
+    "baseline": 31,
+    "slack": 16
   },
   "litellm/llms/litellm_proxy/chat/transformation.py": {
     "baseline": 21,
@@ -2520,8 +2508,8 @@
     "slack": 56
   },
   "litellm/llms/litellm_proxy/skills/handler.py": {
-    "baseline": 67,
-    "slack": 34
+    "baseline": 66,
+    "slack": 33
   },
   "litellm/llms/litellm_proxy/skills/prompt_injection.py": {
     "baseline": 54,
@@ -2532,8 +2520,8 @@
     "slack": 30
   },
   "litellm/llms/litellm_proxy/skills/transformation.py": {
-    "baseline": 57,
-    "slack": 29
+    "baseline": 45,
+    "slack": 23
   },
   "litellm/llms/lm_studio/chat/transformation.py": {
     "baseline": 25,
@@ -2576,19 +2564,19 @@
     "slack": 17
   },
   "litellm/llms/mistral/chat/transformation.py": {
-    "baseline": 183,
-    "slack": 92
+    "baseline": 180,
+    "slack": 90
   },
   "litellm/llms/mistral/ocr/guardrail_translation/handler.py": {
-    "baseline": 39,
-    "slack": 20
+    "baseline": 37,
+    "slack": 19
   },
   "litellm/llms/mistral/ocr/transformation.py": {
     "baseline": 22,
     "slack": 11
   },
   "litellm/llms/modelscope/chat/transformation.py": {
-    "baseline": 12,
+    "baseline": 11,
     "slack": 6
   },
   "litellm/llms/modelscope/image_generation/transformation.py": {
@@ -2596,7 +2584,7 @@
     "slack": 17
   },
   "litellm/llms/moonshot/chat/transformation.py": {
-    "baseline": 54,
+    "baseline": 53,
     "slack": 27
   },
   "litellm/llms/morph/chat/transformation.py": {
@@ -2640,16 +2628,16 @@
     "slack": 2
   },
   "litellm/llms/nvidia_nim/rerank/transformation.py": {
-    "baseline": 58,
-    "slack": 29
+    "baseline": 48,
+    "slack": 24
   },
   "litellm/llms/nvidia_riva/audio_transcription/audio_utils.py": {
-    "baseline": 89,
-    "slack": 45
+    "baseline": 85,
+    "slack": 43
   },
   "litellm/llms/nvidia_riva/audio_transcription/handler.py": {
-    "baseline": 142,
-    "slack": 71
+    "baseline": 140,
+    "slack": 70
   },
   "litellm/llms/nvidia_riva/audio_transcription/transformation.py": {
     "baseline": 83,
@@ -2672,8 +2660,8 @@
     "slack": 80
   },
   "litellm/llms/oci/common_utils.py": {
-    "baseline": 221,
-    "slack": 111
+    "baseline": 217,
+    "slack": 109
   },
   "litellm/llms/oci/embed/transformation.py": {
     "baseline": 45,
@@ -2716,25 +2704,25 @@
     "slack": 4
   },
   "litellm/llms/openai/chat/gpt_transformation.py": {
-    "baseline": 132,
-    "slack": 66
+    "baseline": 129,
+    "slack": 65
   },
   "litellm/llms/openai/chat/guardrail_translation/handler.py": {
-    "baseline": 196,
-    "slack": 98
+    "baseline": 188,
+    "slack": 94
   },
   "litellm/llms/openai/chat/o_series_transformation.py": {
-    "baseline": 20,
+    "baseline": 19,
     "slack": 10
   },
   "litellm/llms/openai/common_utils.py": {
-    "baseline": 46,
-    "slack": 23
-  },
-  "litellm/llms/openai/completion/guardrail_translation/handler.py": {
     "baseline": 43,
     "slack": 22
   },
+  "litellm/llms/openai/completion/guardrail_translation/handler.py": {
+    "baseline": 40,
+    "slack": 20
+  },
   "litellm/llms/openai/completion/handler.py": {
     "baseline": 140,
     "slack": 70
@@ -2756,16 +2744,16 @@
     "slack": 3
   },
   "litellm/llms/openai/embeddings/guardrail_translation/handler.py": {
-    "baseline": 35,
-    "slack": 18
+    "baseline": 33,
+    "slack": 17
   },
   "litellm/llms/openai/evals/transformation.py": {
     "baseline": 73,
     "slack": 37
   },
   "litellm/llms/openai/fine_tuning/handler.py": {
-    "baseline": 36,
-    "slack": 18
+    "baseline": 30,
+    "slack": 15
   },
   "litellm/llms/openai/image_edit/dalle2_transformation.py": {
     "baseline": 46,
@@ -2792,20 +2780,20 @@
     "slack": 12
   },
   "litellm/llms/openai/image_generation/guardrail_translation/handler.py": {
-    "baseline": 14,
+    "baseline": 13,
     "slack": 7
   },
   "litellm/llms/openai/image_variations/handler.py": {
-    "baseline": 69,
-    "slack": 35
+    "baseline": 68,
+    "slack": 34
   },
   "litellm/llms/openai/image_variations/transformation.py": {
     "baseline": 6,
     "slack": 3
   },
   "litellm/llms/openai/openai.py": {
-    "baseline": 664,
-    "slack": 332
+    "baseline": 626,
+    "slack": 313
   },
   "litellm/llms/openai/realtime/handler.py": {
     "baseline": 31,
@@ -2828,15 +2816,15 @@
     "slack": 43
   },
   "litellm/llms/openai/responses/guardrail_translation/handler.py": {
-    "baseline": 256,
-    "slack": 128
+    "baseline": 247,
+    "slack": 124
   },
   "litellm/llms/openai/responses/transformation.py": {
     "baseline": 126,
     "slack": 63
   },
   "litellm/llms/openai/speech/guardrail_translation/handler.py": {
-    "baseline": 14,
+    "baseline": 13,
     "slack": 7
   },
   "litellm/llms/openai/transcriptions/gpt_transformation.py": {
@@ -2844,16 +2832,16 @@
     "slack": 2
   },
   "litellm/llms/openai/transcriptions/guardrail_translation/handler.py": {
-    "baseline": 17,
-    "slack": 9
+    "baseline": 16,
+    "slack": 8
   },
   "litellm/llms/openai/transcriptions/handler.py": {
     "baseline": 74,
     "slack": 37
   },
   "litellm/llms/openai/transcriptions/whisper_transformation.py": {
-    "baseline": 23,
-    "slack": 12
+    "baseline": 22,
+    "slack": 11
   },
   "litellm/llms/openai/vector_store_files/transformation.py": {
     "baseline": 42,
@@ -2868,8 +2856,8 @@
     "slack": 77
   },
   "litellm/llms/openai_like/chat/handler.py": {
-    "baseline": 113,
-    "slack": 57
+    "baseline": 110,
+    "slack": 55
   },
   "litellm/llms/openai_like/chat/transformation.py": {
     "baseline": 36,
@@ -2884,7 +2872,7 @@
     "slack": 37
   },
   "litellm/llms/openai_like/embedding/handler.py": {
-    "baseline": 56,
+    "baseline": 55,
     "slack": 28
   },
   "litellm/llms/openai_like/json_loader.py": {
@@ -2896,8 +2884,8 @@
     "slack": 1
   },
   "litellm/llms/openrouter/chat/transformation.py": {
-    "baseline": 88,
-    "slack": 44
+    "baseline": 74,
+    "slack": 37
   },
   "litellm/llms/openrouter/embedding/transformation.py": {
     "baseline": 27,
@@ -2928,12 +2916,12 @@
     "slack": 13
   },
   "litellm/llms/parallel_ai/search/transformation.py": {
-    "baseline": 55,
-    "slack": 28
+    "baseline": 39,
+    "slack": 20
   },
   "litellm/llms/pass_through/guardrail_translation/handler.py": {
-    "baseline": 84,
-    "slack": 42
+    "baseline": 82,
+    "slack": 41
   },
   "litellm/llms/perplexity/chat/transformation.py": {
     "baseline": 59,
@@ -2952,8 +2940,8 @@
     "slack": 11
   },
   "litellm/llms/perplexity/search/transformation.py": {
-    "baseline": 29,
-    "slack": 15
+    "baseline": 24,
+    "slack": 12
   },
   "litellm/llms/petals/common_utils.py": {
     "baseline": 1,
@@ -2972,8 +2960,8 @@
     "slack": 5
   },
   "litellm/llms/predibase/chat/handler.py": {
-    "baseline": 98,
-    "slack": 49
+    "baseline": 96,
+    "slack": 48
   },
   "litellm/llms/predibase/chat/transformation.py": {
     "baseline": 116,
@@ -3008,12 +2996,12 @@
     "slack": 23
   },
   "litellm/llms/reducto/ocr/transformation.py": {
-    "baseline": 53,
-    "slack": 27
+    "baseline": 50,
+    "slack": 25
   },
   "litellm/llms/replicate/chat/handler.py": {
-    "baseline": 139,
-    "slack": 70
+    "baseline": 136,
+    "slack": 68
   },
   "litellm/llms/replicate/chat/transformation.py": {
     "baseline": 76,
@@ -3028,20 +3016,20 @@
     "slack": 1
   },
   "litellm/llms/runwayml/image_generation/transformation.py": {
-    "baseline": 80,
-    "slack": 40
+    "baseline": 78,
+    "slack": 39
   },
   "litellm/llms/runwayml/text_to_speech/transformation.py": {
-    "baseline": 116,
-    "slack": 58
+    "baseline": 114,
+    "slack": 57
   },
   "litellm/llms/runwayml/videos/transformation.py": {
     "baseline": 125,
     "slack": 63
   },
   "litellm/llms/s3_vectors/vector_stores/transformation.py": {
-    "baseline": 71,
-    "slack": 36
+    "baseline": 67,
+    "slack": 34
   },
   "litellm/llms/sagemaker/chat/handler.py": {
     "baseline": 81,
@@ -3092,36 +3080,36 @@
     "slack": 50
   },
   "litellm/llms/sap/chat/models.py": {
-    "baseline": 95,
-    "slack": 48
+    "baseline": 54,
+    "slack": 27
   },
   "litellm/llms/sap/chat/transformation.py": {
     "baseline": 182,
     "slack": 91
   },
   "litellm/llms/sap/credentials.py": {
-    "baseline": 61,
-    "slack": 31
+    "baseline": 58,
+    "slack": 29
   },
   "litellm/llms/sap/embed/transformation.py": {
-    "baseline": 82,
-    "slack": 41
+    "baseline": 65,
+    "slack": 33
   },
   "litellm/llms/scaleway/audio_transcription/transformation.py": {
     "baseline": 30,
     "slack": 15
   },
   "litellm/llms/searchapi/search/transformation.py": {
-    "baseline": 58,
-    "slack": 29
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/llms/searxng/search/transformation.py": {
-    "baseline": 43,
-    "slack": 22
+    "baseline": 36,
+    "slack": 18
   },
   "litellm/llms/serper/search/transformation.py": {
-    "baseline": 37,
-    "slack": 19
+    "baseline": 29,
+    "slack": 15
   },
   "litellm/llms/snowflake/chat/transformation.py": {
     "baseline": 244,
@@ -3140,12 +3128,12 @@
     "slack": 13
   },
   "litellm/llms/soniox/audio_transcription/handler.py": {
-    "baseline": 196,
-    "slack": 98
+    "baseline": 192,
+    "slack": 96
   },
   "litellm/llms/soniox/audio_transcription/transformation.py": {
-    "baseline": 107,
-    "slack": 54
+    "baseline": 106,
+    "slack": 53
   },
   "litellm/llms/soniox/common_utils.py": {
     "baseline": 68,
@@ -3160,8 +3148,8 @@
     "slack": 21
   },
   "litellm/llms/tavily/search/transformation.py": {
-    "baseline": 38,
-    "slack": 19
+    "baseline": 23,
+    "slack": 12
   },
   "litellm/llms/together_ai/chat.py": {
     "baseline": 14,
@@ -3176,7 +3164,7 @@
     "slack": 5
   },
   "litellm/llms/together_ai/rerank/handler.py": {
-    "baseline": 18,
+    "baseline": 17,
     "slack": 9
   },
   "litellm/llms/together_ai/rerank/transformation.py": {
@@ -3188,7 +3176,7 @@
     "slack": 1
   },
   "litellm/llms/topaz/image_variations/transformation.py": {
-    "baseline": 18,
+    "baseline": 17,
     "slack": 9
   },
   "litellm/llms/triton/common_utils.py": {
@@ -3228,8 +3216,8 @@
     "slack": 3
   },
   "litellm/llms/vertex_ai/batches/handler.py": {
-    "baseline": 118,
-    "slack": 59
+    "baseline": 115,
+    "slack": 58
   },
   "litellm/llms/vertex_ai/batches/transformation.py": {
     "baseline": 10,
@@ -3244,27 +3232,27 @@
     "slack": 8
   },
   "litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py": {
-    "baseline": 85,
-    "slack": 43
+    "baseline": 83,
+    "slack": 42
   },
   "litellm/llms/vertex_ai/cost_calculator.py": {
     "baseline": 4,
     "slack": 2
   },
   "litellm/llms/vertex_ai/count_tokens/handler.py": {
-    "baseline": 9,
-    "slack": 5
+    "baseline": 8,
+    "slack": 4
   },
   "litellm/llms/vertex_ai/files/handler.py": {
-    "baseline": 28,
-    "slack": 14
+    "baseline": 21,
+    "slack": 11
   },
   "litellm/llms/vertex_ai/files/transformation.py": {
     "baseline": 177,
     "slack": 89
   },
   "litellm/llms/vertex_ai/fine_tuning/handler.py": {
-    "baseline": 56,
+    "baseline": 55,
     "slack": 28
   },
   "litellm/llms/vertex_ai/gemini/transformation.py": {
@@ -3272,12 +3260,12 @@
     "slack": 156
   },
   "litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py": {
-    "baseline": 912,
-    "slack": 456
+    "baseline": 907,
+    "slack": 454
   },
   "litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_handler.py": {
-    "baseline": 82,
-    "slack": 41
+    "baseline": 77,
+    "slack": 39
   },
   "litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py": {
     "baseline": 32,
@@ -3292,12 +3280,12 @@
     "slack": 1
   },
   "litellm/llms/vertex_ai/image_edit/vertex_gemini_transformation.py": {
-    "baseline": 70,
+    "baseline": 69,
     "slack": 35
   },
   "litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py": {
-    "baseline": 85,
-    "slack": 43
+    "baseline": 84,
+    "slack": 42
   },
   "litellm/llms/vertex_ai/image_generation/image_generation_handler.py": {
     "baseline": 71,
@@ -3312,7 +3300,7 @@
     "slack": 25
   },
   "litellm/llms/vertex_ai/multimodal_embeddings/embedding_handler.py": {
-    "baseline": 50,
+    "baseline": 49,
     "slack": 25
   },
   "litellm/llms/vertex_ai/multimodal_embeddings/transformation.py": {
@@ -3324,12 +3312,12 @@
     "slack": 33
   },
   "litellm/llms/vertex_ai/ocr/transformation.py": {
-    "baseline": 20,
-    "slack": 10
+    "baseline": 17,
+    "slack": 9
   },
   "litellm/llms/vertex_ai/rag_engine/ingestion.py": {
-    "baseline": 58,
-    "slack": 29
+    "baseline": 56,
+    "slack": 28
   },
   "litellm/llms/vertex_ai/rag_engine/transformation.py": {
     "baseline": 14,
@@ -3344,8 +3332,8 @@
     "slack": 33
   },
   "litellm/llms/vertex_ai/text_to_speech/text_to_speech_handler.py": {
-    "baseline": 48,
-    "slack": 24
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/llms/vertex_ai/text_to_speech/transformation.py": {
     "baseline": 84,
@@ -3384,7 +3372,7 @@
     "slack": 28
   },
   "litellm/llms/vertex_ai/vertex_ai_partner_models/count_tokens/handler.py": {
-    "baseline": 24,
+    "baseline": 23,
     "slack": 12
   },
   "litellm/llms/vertex_ai/vertex_ai_partner_models/gpt_oss/transformation.py": {
@@ -3404,17 +3392,13 @@
     "slack": 10
   },
   "litellm/llms/vertex_ai/vertex_embeddings/embedding_handler.py": {
-    "baseline": 46,
-    "slack": 23
+    "baseline": 44,
+    "slack": 22
   },
   "litellm/llms/vertex_ai/vertex_embeddings/transformation.py": {
     "baseline": 84,
     "slack": 42
   },
-  "litellm/llms/vertex_ai/vertex_embeddings/types.py": {
-    "baseline": 16,
-    "slack": 8
-  },
   "litellm/llms/vertex_ai/vertex_gemma_models/main.py": {
     "baseline": 16,
     "slack": 8
@@ -3424,8 +3408,8 @@
     "slack": 43
   },
   "litellm/llms/vertex_ai/vertex_llm_base.py": {
-    "baseline": 305,
-    "slack": 153
+    "baseline": 301,
+    "slack": 151
   },
   "litellm/llms/vertex_ai/vertex_model_garden/main.py": {
     "baseline": 17,
@@ -3496,12 +3480,12 @@
     "slack": 22
   },
   "litellm/llms/watsonx/common_utils.py": {
-    "baseline": 101,
-    "slack": 51
+    "baseline": 100,
+    "slack": 50
   },
   "litellm/llms/watsonx/completion/transformation.py": {
-    "baseline": 117,
-    "slack": 59
+    "baseline": 116,
+    "slack": 58
   },
   "litellm/llms/watsonx/embed/transformation.py": {
     "baseline": 22,
@@ -3528,8 +3512,8 @@
     "slack": 3
   },
   "litellm/llms/xai/oauth.py": {
-    "baseline": 84,
-    "slack": 42
+    "baseline": 81,
+    "slack": 41
   },
   "litellm/llms/xai/realtime/handler.py": {
     "baseline": 1,
@@ -3544,87 +3528,51 @@
     "slack": 6
   },
   "litellm/llms/you_com/search/transformation.py": {
-    "baseline": 49,
-    "slack": 25
+    "baseline": 41,
+    "slack": 21
   },
   "litellm/main.py": {
-    "baseline": 3138,
-    "slack": 1569
-  },
-  "litellm/models/access_group.py": {
-    "baseline": 2,
-    "slack": 1
+    "baseline": 3102,
+    "slack": 1551
   },
   "litellm/models/base.py": {
     "baseline": 12,
     "slack": 6
   },
-  "litellm/models/budget.py": {
-    "baseline": 1,
-    "slack": 1
-  },
-  "litellm/models/config.py": {
-    "baseline": 2,
-    "slack": 1
-  },
   "litellm/models/credentials.py": {
-    "baseline": 8,
-    "slack": 4
-  },
-  "litellm/models/end_user.py": {
-    "baseline": 6,
+    "baseline": 5,
     "slack": 3
   },
-  "litellm/models/managed_files.py": {
-    "baseline": 21,
-    "slack": 11
-  },
-  "litellm/models/mcp_server.py": {
-    "baseline": 3,
-    "slack": 2
-  },
-  "litellm/models/model.py": {
-    "baseline": 18,
-    "slack": 9
-  },
-  "litellm/models/object_permission.py": {
-    "baseline": 1,
-    "slack": 1
-  },
-  "litellm/models/organization.py": {
+  "litellm/models/end_user.py": {
     "baseline": 4,
     "slack": 2
   },
+  "litellm/models/model.py": {
+    "baseline": 15,
+    "slack": 8
+  },
+  "litellm/models/organization.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/models/organization_membership.py": {
-    "baseline": 9,
-    "slack": 5
-  },
-  "litellm/models/project.py": {
-    "baseline": 1,
-    "slack": 1
-  },
-  "litellm/models/skills.py": {
-    "baseline": 1,
-    "slack": 1
+    "baseline": 5,
+    "slack": 3
   },
   "litellm/models/spend_logs.py": {
-    "baseline": 11,
-    "slack": 6
-  },
-  "litellm/models/tag.py": {
-    "baseline": 9,
-    "slack": 5
-  },
-  "litellm/models/team.py": {
-    "baseline": 42,
-    "slack": 21
-  },
-  "litellm/models/team_membership.py": {
     "baseline": 2,
     "slack": 1
   },
+  "litellm/models/tag.py": {
+    "baseline": 8,
+    "slack": 4
+  },
+  "litellm/models/team.py": {
+    "baseline": 37,
+    "slack": 19
+  },
   "litellm/models/user.py": {
-    "baseline": 18,
+    "baseline": 17,
     "slack": 9
   },
   "litellm/models/verification_token.py": {
@@ -3632,12 +3580,12 @@
     "slack": 5
   },
   "litellm/ocr/main.py": {
-    "baseline": 80,
-    "slack": 40
+    "baseline": 77,
+    "slack": 39
   },
   "litellm/passthrough/main.py": {
-    "baseline": 100,
-    "slack": 50
+    "baseline": 91,
+    "slack": 46
   },
   "litellm/passthrough/timeout_utils.py": {
     "baseline": 15,
@@ -3648,15 +3596,15 @@
     "slack": 21
   },
   "litellm/proxy/_experimental/mcp_server/auth/token_exchange.py": {
-    "baseline": 21,
-    "slack": 11
+    "baseline": 20,
+    "slack": 10
   },
   "litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py": {
-    "baseline": 175,
-    "slack": 88
+    "baseline": 154,
+    "slack": 77
   },
   "litellm/proxy/_experimental/mcp_server/byok_oauth_endpoints.py": {
-    "baseline": 58,
+    "baseline": 57,
     "slack": 29
   },
   "litellm/proxy/_experimental/mcp_server/cost_calculator.py": {
@@ -3664,32 +3612,32 @@
     "slack": 4
   },
   "litellm/proxy/_experimental/mcp_server/db.py": {
-    "baseline": 428,
-    "slack": 214
+    "baseline": 424,
+    "slack": 212
   },
   "litellm/proxy/_experimental/mcp_server/discoverable_endpoints.py": {
-    "baseline": 193,
-    "slack": 97
+    "baseline": 189,
+    "slack": 95
   },
   "litellm/proxy/_experimental/mcp_server/elicitation_handler.py": {
     "baseline": 57,
     "slack": 29
   },
   "litellm/proxy/_experimental/mcp_server/guardrail_translation/handler.py": {
-    "baseline": 21,
-    "slack": 11
+    "baseline": 20,
+    "slack": 10
   },
   "litellm/proxy/_experimental/mcp_server/mcp_debug.py": {
     "baseline": 10,
     "slack": 5
   },
   "litellm/proxy/_experimental/mcp_server/mcp_server_manager.py": {
-    "baseline": 877,
-    "slack": 439
+    "baseline": 833,
+    "slack": 417
   },
   "litellm/proxy/_experimental/mcp_server/oauth2_token_cache.py": {
-    "baseline": 36,
-    "slack": 18
+    "baseline": 32,
+    "slack": 16
   },
   "litellm/proxy/_experimental/mcp_server/oauth_utils.py": {
     "baseline": 21,
@@ -3700,24 +3648,24 @@
     "slack": 107
   },
   "litellm/proxy/_experimental/mcp_server/rest_endpoints.py": {
-    "baseline": 288,
-    "slack": 144
+    "baseline": 277,
+    "slack": 139
   },
   "litellm/proxy/_experimental/mcp_server/sampling_handler.py": {
-    "baseline": 541,
-    "slack": 271
+    "baseline": 533,
+    "slack": 267
   },
   "litellm/proxy/_experimental/mcp_server/semantic_tool_filter.py": {
-    "baseline": 98,
-    "slack": 49
+    "baseline": 96,
+    "slack": 48
   },
   "litellm/proxy/_experimental/mcp_server/server.py": {
-    "baseline": 971,
-    "slack": 486
+    "baseline": 914,
+    "slack": 457
   },
   "litellm/proxy/_experimental/mcp_server/sse_transport.py": {
-    "baseline": 61,
-    "slack": 31
+    "baseline": 53,
+    "slack": 27
   },
   "litellm/proxy/_experimental/mcp_server/tool_registry.py": {
     "baseline": 9,
@@ -3728,16 +3676,16 @@
     "slack": 23
   },
   "litellm/proxy/_experimental/mcp_server/ui_session_utils.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 10,
+    "slack": 5
   },
   "litellm/proxy/_experimental/mcp_server/utils.py": {
     "baseline": 99,
     "slack": 50
   },
   "litellm/proxy/_lazy_features.py": {
-    "baseline": 84,
-    "slack": 42
+    "baseline": 79,
+    "slack": 40
   },
   "litellm/proxy/_lazy_openapi_snapshot.py": {
     "baseline": 72,
@@ -3748,8 +3696,8 @@
     "slack": 5
   },
   "litellm/proxy/_types.py": {
-    "baseline": 848,
-    "slack": 424
+    "baseline": 501,
+    "slack": 251
   },
   "litellm/proxy/a2a/agent_card.py": {
     "baseline": 51,
@@ -3760,36 +3708,36 @@
     "slack": 9
   },
   "litellm/proxy/a2a/endpoints.py": {
-    "baseline": 12,
-    "slack": 6
+    "baseline": 10,
+    "slack": 5
   },
   "litellm/proxy/agent_endpoints/a2a_endpoints.py": {
-    "baseline": 333,
-    "slack": 167
+    "baseline": 324,
+    "slack": 162
   },
   "litellm/proxy/agent_endpoints/a2a_routing.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 10,
+    "slack": 5
   },
   "litellm/proxy/agent_endpoints/agent_registry.py": {
-    "baseline": 143,
-    "slack": 72
+    "baseline": 140,
+    "slack": 70
   },
   "litellm/proxy/agent_endpoints/auth/agent_permission_handler.py": {
-    "baseline": 36,
-    "slack": 18
+    "baseline": 23,
+    "slack": 12
   },
   "litellm/proxy/agent_endpoints/databricks_oauth.py": {
-    "baseline": 36,
-    "slack": 18
+    "baseline": 30,
+    "slack": 15
   },
   "litellm/proxy/agent_endpoints/endpoints.py": {
-    "baseline": 222,
-    "slack": 111
+    "baseline": 208,
+    "slack": 104
   },
   "litellm/proxy/agent_endpoints/model_list_helpers.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 5,
+    "slack": 3
   },
   "litellm/proxy/analytics_endpoints/analytics_endpoints.py": {
     "baseline": 13,
@@ -3800,32 +3748,32 @@
     "slack": 113
   },
   "litellm/proxy/anthropic_endpoints/endpoints.py": {
-    "baseline": 77,
-    "slack": 39
+    "baseline": 73,
+    "slack": 37
   },
   "litellm/proxy/anthropic_endpoints/skills_endpoints.py": {
-    "baseline": 106,
-    "slack": 53
+    "baseline": 103,
+    "slack": 52
   },
   "litellm/proxy/auth/auth_checks.py": {
-    "baseline": 654,
-    "slack": 327
+    "baseline": 601,
+    "slack": 301
   },
   "litellm/proxy/auth/auth_checks_organization.py": {
     "baseline": 7,
     "slack": 4
   },
   "litellm/proxy/auth/auth_exception_handler.py": {
-    "baseline": 15,
-    "slack": 8
+    "baseline": 14,
+    "slack": 7
   },
   "litellm/proxy/auth/auth_utils.py": {
-    "baseline": 276,
-    "slack": 138
+    "baseline": 274,
+    "slack": 137
   },
   "litellm/proxy/auth/handle_jwt.py": {
-    "baseline": 378,
-    "slack": 189
+    "baseline": 359,
+    "slack": 180
   },
   "litellm/proxy/auth/ip_address_utils.py": {
     "baseline": 17,
@@ -3836,8 +3784,8 @@
     "slack": 32
   },
   "litellm/proxy/auth/login_utils.py": {
-    "baseline": 40,
-    "slack": 20
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/proxy/auth/model_checks.py": {
     "baseline": 52,
@@ -3864,12 +3812,12 @@
     "slack": 10
   },
   "litellm/proxy/auth/user_api_key_auth.py": {
-    "baseline": 590,
-    "slack": 295
+    "baseline": 535,
+    "slack": 268
   },
   "litellm/proxy/batches_endpoints/endpoints.py": {
-    "baseline": 344,
-    "slack": 172
+    "baseline": 330,
+    "slack": 165
   },
   "litellm/proxy/caching_routes.py": {
     "baseline": 105,
@@ -3904,8 +3852,8 @@
     "slack": 50
   },
   "litellm/proxy/client/cli/commands/models.py": {
-    "baseline": 151,
-    "slack": 76
+    "baseline": 145,
+    "slack": 73
   },
   "litellm/proxy/client/cli/commands/teams.py": {
     "baseline": 66,
@@ -3956,8 +3904,8 @@
     "slack": 5
   },
   "litellm/proxy/common_request_processing.py": {
-    "baseline": 753,
-    "slack": 377
+    "baseline": 720,
+    "slack": 360
   },
   "litellm/proxy/common_utils/admin_ui_utils.py": {
     "baseline": 9,
@@ -3968,8 +3916,8 @@
     "slack": 2
   },
   "litellm/proxy/common_utils/cache_coordinator.py": {
-    "baseline": 23,
-    "slack": 12
+    "baseline": 18,
+    "slack": 9
   },
   "litellm/proxy/common_utils/cache_pydantic_utils.py": {
     "baseline": 15,
@@ -3992,16 +3940,16 @@
     "slack": 9
   },
   "litellm/proxy/common_utils/expired_ui_session_key_cleanup_manager.py": {
-    "baseline": 39,
-    "slack": 20
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/proxy/common_utils/get_routes.py": {
     "baseline": 45,
     "slack": 23
   },
   "litellm/proxy/common_utils/http_parsing_utils.py": {
-    "baseline": 177,
-    "slack": 89
+    "baseline": 176,
+    "slack": 88
   },
   "litellm/proxy/common_utils/key_rotation_manager.py": {
     "baseline": 66,
@@ -4032,12 +3980,12 @@
     "slack": 2
   },
   "litellm/proxy/common_utils/rbac_utils.py": {
-    "baseline": 8,
+    "baseline": 7,
     "slack": 4
   },
   "litellm/proxy/common_utils/reset_budget_job.py": {
-    "baseline": 539,
-    "slack": 270
+    "baseline": 535,
+    "slack": 268
   },
   "litellm/proxy/common_utils/swagger_utils.py": {
     "baseline": 10,
@@ -4060,19 +4008,19 @@
     "slack": 2
   },
   "litellm/proxy/container_endpoints/endpoints.py": {
-    "baseline": 85,
-    "slack": 43
+    "baseline": 80,
+    "slack": 40
   },
   "litellm/proxy/container_endpoints/handler_factory.py": {
-    "baseline": 120,
-    "slack": 60
+    "baseline": 114,
+    "slack": 57
   },
   "litellm/proxy/container_endpoints/ownership.py": {
-    "baseline": 167,
-    "slack": 84
+    "baseline": 164,
+    "slack": 82
   },
   "litellm/proxy/credential_endpoints/endpoints.py": {
-    "baseline": 118,
+    "baseline": 117,
     "slack": 59
   },
   "litellm/proxy/custom_hooks/custom_ui_sso_hook.py": {
@@ -4096,44 +4044,44 @@
     "slack": 22
   },
   "litellm/proxy/db/db_spend_update_writer.py": {
-    "baseline": 347,
-    "slack": 174
+    "baseline": 308,
+    "slack": 154
   },
   "litellm/proxy/db/db_transaction_queue/base_update_queue.py": {
     "baseline": 22,
     "slack": 11
   },
   "litellm/proxy/db/db_transaction_queue/daily_spend_update_queue.py": {
-    "baseline": 22,
+    "baseline": 21,
     "slack": 11
   },
   "litellm/proxy/db/db_transaction_queue/pod_lock_manager.py": {
-    "baseline": 35,
-    "slack": 18
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/proxy/db/db_transaction_queue/redis_update_buffer.py": {
-    "baseline": 140,
-    "slack": 70
+    "baseline": 130,
+    "slack": 65
   },
   "litellm/proxy/db/db_transaction_queue/spend_log_cleanup.py": {
-    "baseline": 24,
-    "slack": 12
+    "baseline": 16,
+    "slack": 8
   },
   "litellm/proxy/db/db_transaction_queue/spend_logs_partition_manager.py": {
-    "baseline": 19,
-    "slack": 10
+    "baseline": 18,
+    "slack": 9
   },
   "litellm/proxy/db/db_transaction_queue/spend_update_queue.py": {
-    "baseline": 25,
-    "slack": 13
+    "baseline": 24,
+    "slack": 12
   },
   "litellm/proxy/db/db_url_settings.py": {
     "baseline": 1,
     "slack": 1
   },
   "litellm/proxy/db/dynamo_db.py": {
-    "baseline": 27,
-    "slack": 14
+    "baseline": 26,
+    "slack": 13
   },
   "litellm/proxy/db/exception_handler.py": {
     "baseline": 39,
@@ -4144,24 +4092,24 @@
     "slack": 26
   },
   "litellm/proxy/db/prisma_client.py": {
-    "baseline": 51,
-    "slack": 26
+    "baseline": 40,
+    "slack": 20
   },
   "litellm/proxy/db/routing_prisma_wrapper.py": {
-    "baseline": 46,
-    "slack": 23
+    "baseline": 41,
+    "slack": 21
   },
   "litellm/proxy/db/spend_counter_reseed.py": {
-    "baseline": 65,
-    "slack": 33
+    "baseline": 59,
+    "slack": 30
   },
   "litellm/proxy/db/spend_log_tool_index.py": {
     "baseline": 83,
     "slack": 42
   },
   "litellm/proxy/db/tool_registry_writer.py": {
-    "baseline": 145,
-    "slack": 73
+    "baseline": 144,
+    "slack": 72
   },
   "litellm/proxy/discovery_endpoints/ui_discovery_endpoints.py": {
     "baseline": 17,
@@ -4192,8 +4140,8 @@
     "slack": 4
   },
   "litellm/proxy/fine_tuning_endpoints/endpoints.py": {
-    "baseline": 222,
-    "slack": 111
+    "baseline": 218,
+    "slack": 109
   },
   "litellm/proxy/google_endpoints/agents_endpoints.py": {
     "baseline": 158,
@@ -4208,68 +4156,104 @@
     "slack": 59
   },
   "litellm/proxy/guardrails/guardrail_endpoints.py": {
-    "baseline": 610,
-    "slack": 305
+    "baseline": 579,
+    "slack": 290
   },
   "litellm/proxy/guardrails/guardrail_helpers.py": {
     "baseline": 27,
     "slack": 14
   },
+  "litellm/proxy/guardrails/guardrail_hooks/aim/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/aim/aim.py": {
-    "baseline": 139,
-    "slack": 70
+    "baseline": 138,
+    "slack": 69
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/akto/__init__.py": {
+    "baseline": 7,
+    "slack": 4
   },
   "litellm/proxy/guardrails/guardrail_hooks/akto/akto.py": {
-    "baseline": 127,
-    "slack": 64
+    "baseline": 123,
+    "slack": 62
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/aporia_ai/__init__.py": {
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/aporia_ai/aporia_ai.py": {
-    "baseline": 66,
+    "baseline": 65,
     "slack": 33
   },
+  "litellm/proxy/guardrails/guardrail_hooks/azure/__init__.py": {
+    "baseline": 5,
+    "slack": 3
+  },
   "litellm/proxy/guardrails/guardrail_hooks/azure/base.py": {
     "baseline": 18,
     "slack": 9
   },
   "litellm/proxy/guardrails/guardrail_hooks/azure/prompt_shield.py": {
-    "baseline": 9,
-    "slack": 5
+    "baseline": 8,
+    "slack": 4
   },
   "litellm/proxy/guardrails/guardrail_hooks/azure/text_moderation.py": {
-    "baseline": 33,
-    "slack": 17
+    "baseline": 30,
+    "slack": 15
   },
   "litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py": {
-    "baseline": 271,
-    "slack": 136
+    "baseline": 260,
+    "slack": 130
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/block_code_execution/__init__.py": {
+    "baseline": 14,
+    "slack": 7
   },
   "litellm/proxy/guardrails/guardrail_hooks/block_code_execution/block_code_execution.py": {
     "baseline": 27,
     "slack": 14
   },
+  "litellm/proxy/guardrails/guardrail_hooks/cato_networks/__init__.py": {
+    "baseline": 2,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py": {
-    "baseline": 402,
-    "slack": 201
+    "baseline": 397,
+    "slack": 199
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/cisco_ai_defense/__init__.py": {
+    "baseline": 49,
+    "slack": 25
   },
   "litellm/proxy/guardrails/guardrail_hooks/cisco_ai_defense/cisco_ai_defense.py": {
-    "baseline": 756,
-    "slack": 378
+    "baseline": 746,
+    "slack": 373
   },
   "litellm/proxy/guardrails/guardrail_hooks/cisco_ai_defense/cisco_ai_defense_mcp.py": {
-    "baseline": 324,
-    "slack": 162
+    "baseline": 319,
+    "slack": 160
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/__init__.py": {
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/crowdstrike_aidr/crowdstrike_aidr.py": {
-    "baseline": 104,
-    "slack": 52
+    "baseline": 99,
+    "slack": 50
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/custom_code/__init__.py": {
+    "baseline": 4,
+    "slack": 2
   },
   "litellm/proxy/guardrails/guardrail_hooks/custom_code/custom_code_guardrail.py": {
-    "baseline": 68,
+    "baseline": 67,
     "slack": 34
   },
   "litellm/proxy/guardrails/guardrail_hooks/custom_code/primitives.py": {
-    "baseline": 102,
-    "slack": 51
+    "baseline": 100,
+    "slack": 50
   },
   "litellm/proxy/guardrails/guardrail_hooks/custom_code/sandbox.py": {
     "baseline": 34,
@@ -4279,13 +4263,33 @@
     "baseline": 21,
     "slack": 11
   },
+  "litellm/proxy/guardrails/guardrail_hooks/deepkeep/__init__.py": {
+    "baseline": 4,
+    "slack": 2
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py": {
+    "baseline": 86,
+    "slack": 43
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/dynamoai/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/dynamoai/dynamoai.py": {
-    "baseline": 83,
-    "slack": 42
+    "baseline": 80,
+    "slack": 40
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/enkryptai/__init__.py": {
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/enkryptai/enkryptai.py": {
-    "baseline": 79,
-    "slack": 40
+    "baseline": 75,
+    "slack": 38
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/generic_guardrail_api/__init__.py": {
+    "baseline": 6,
+    "slack": 3
   },
   "litellm/proxy/guardrails/guardrail_hooks/generic_guardrail_api/generic_guardrail_api.py": {
     "baseline": 107,
@@ -4299,24 +4303,40 @@
     "baseline": 154,
     "slack": 77
   },
+  "litellm/proxy/guardrails/guardrail_hooks/guardrails_ai/__init__.py": {
+    "baseline": 2,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/guardrails_ai/guardrails_ai.py": {
-    "baseline": 59,
-    "slack": 30
+    "baseline": 45,
+    "slack": 23
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/__init__.py": {
+    "baseline": 4,
+    "slack": 2
   },
   "litellm/proxy/guardrails/guardrail_hooks/hiddenlayer/hiddenlayer.py": {
-    "baseline": 194,
-    "slack": 97
+    "baseline": 192,
+    "slack": 96
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/ibm_guardrails/__init__.py": {
+    "baseline": 18,
+    "slack": 9
   },
   "litellm/proxy/guardrails/guardrail_hooks/ibm_guardrails/ibm_detector.py": {
-    "baseline": 66,
-    "slack": 33
+    "baseline": 60,
+    "slack": 30
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/javelin/__init__.py": {
+    "baseline": 3,
+    "slack": 2
   },
   "litellm/proxy/guardrails/guardrail_hooks/javelin/javelin.py": {
-    "baseline": 57,
-    "slack": 29
+    "baseline": 56,
+    "slack": 28
   },
   "litellm/proxy/guardrails/guardrail_hooks/lakera_ai.py": {
-    "baseline": 92,
+    "baseline": 91,
     "slack": 46
   },
   "litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py": {
@@ -4328,8 +4348,12 @@
     "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/lasso/lasso.py": {
-    "baseline": 373,
-    "slack": 187
+    "baseline": 364,
+    "slack": 182
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/__init__.py": {
+    "baseline": 8,
+    "slack": 4
   },
   "litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/competitor_intent/airline.py": {
     "baseline": 56,
@@ -4340,8 +4364,8 @@
     "slack": 17
   },
   "litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/content_filter.py": {
-    "baseline": 275,
-    "slack": 138
+    "baseline": 270,
+    "slack": 135
   },
   "litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/guardrail_benchmarks/test_eval.py": {
     "baseline": 194,
@@ -4355,49 +4379,89 @@
     "baseline": 84,
     "slack": 42
   },
+  "litellm/proxy/guardrails/guardrail_hooks/mcp_end_user_permission/__init__.py": {
+    "baseline": 4,
+    "slack": 2
+  },
   "litellm/proxy/guardrails/guardrail_hooks/mcp_end_user_permission/mcp_end_user_permission.py": {
-    "baseline": 29,
-    "slack": 15
+    "baseline": 25,
+    "slack": 13
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/__init__.py": {
+    "baseline": 27,
+    "slack": 14
   },
   "litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/mcp_jwt_signer.py": {
     "baseline": 202,
     "slack": 101
   },
+  "litellm/proxy/guardrails/guardrail_hooks/mcp_security/__init__.py": {
+    "baseline": 2,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/mcp_security/mcp_security_guardrail.py": {
     "baseline": 21,
     "slack": 11
   },
+  "litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/__init__.py": {
+    "baseline": 13,
+    "slack": 7
+  },
   "litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py": {
-    "baseline": 160,
+    "baseline": 159,
     "slack": 80
   },
   "litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/purview_dlp.py": {
-    "baseline": 131,
-    "slack": 66
+    "baseline": 130,
+    "slack": 65
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/model_armor/__init__.py": {
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/model_armor/model_armor.py": {
-    "baseline": 196,
+    "baseline": 195,
     "slack": 98
   },
+  "litellm/proxy/guardrails/guardrail_hooks/noma/__init__.py": {
+    "baseline": 6,
+    "slack": 3
+  },
   "litellm/proxy/guardrails/guardrail_hooks/noma/noma.py": {
-    "baseline": 202,
-    "slack": 101
+    "baseline": 191,
+    "slack": 96
   },
   "litellm/proxy/guardrails/guardrail_hooks/noma/noma_v2.py": {
     "baseline": 69,
     "slack": 35
   },
+  "litellm/proxy/guardrails/guardrail_hooks/onyx/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/onyx/onyx.py": {
     "baseline": 23,
     "slack": 12
   },
+  "litellm/proxy/guardrails/guardrail_hooks/openai/__init__.py": {
+    "baseline": 17,
+    "slack": 9
+  },
   "litellm/proxy/guardrails/guardrail_hooks/openai/moderations.py": {
-    "baseline": 48,
+    "baseline": 47,
     "slack": 24
   },
+  "litellm/proxy/guardrails/guardrail_hooks/ovalix/__init__.py": {
+    "baseline": 11,
+    "slack": 6
+  },
   "litellm/proxy/guardrails/guardrail_hooks/ovalix/ovalix.py": {
-    "baseline": 34,
-    "slack": 17
+    "baseline": 32,
+    "slack": 16
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/pangea/__init__.py": {
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/pangea/pangea.py": {
     "baseline": 83,
@@ -4408,32 +4472,60 @@
     "slack": 2
   },
   "litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py": {
-    "baseline": 656,
-    "slack": 328
+    "baseline": 651,
+    "slack": 326
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/pillar/__init__.py": {
+    "baseline": 24,
+    "slack": 12
   },
   "litellm/proxy/guardrails/guardrail_hooks/pillar/pillar.py": {
-    "baseline": 181,
-    "slack": 91
+    "baseline": 180,
+    "slack": 90
   },
   "litellm/proxy/guardrails/guardrail_hooks/presidio.py": {
-    "baseline": 462,
-    "slack": 231
+    "baseline": 435,
+    "slack": 218
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/prompt_security/__init__.py": {
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/prompt_security/prompt_security.py": {
-    "baseline": 259,
-    "slack": 130
+    "baseline": 255,
+    "slack": 128
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/promptguard/__init__.py": {
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/proxy/guardrails/guardrail_hooks/promptguard/promptguard.py": {
     "baseline": 41,
     "slack": 21
   },
+  "litellm/proxy/guardrails/guardrail_hooks/qohash/__init__.py": {
+    "baseline": 3,
+    "slack": 2
+  },
   "litellm/proxy/guardrails/guardrail_hooks/qohash/qohash.py": {
     "baseline": 14,
     "slack": 7
   },
+  "litellm/proxy/guardrails/guardrail_hooks/qualifire/__init__.py": {
+    "baseline": 10,
+    "slack": 5
+  },
   "litellm/proxy/guardrails/guardrail_hooks/qualifire/qualifire.py": {
-    "baseline": 127,
-    "slack": 64
+    "baseline": 126,
+    "slack": 63
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/rubrik/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
+  "litellm/proxy/guardrails/guardrail_hooks/semantic_guard/__init__.py": {
+    "baseline": 7,
+    "slack": 4
   },
   "litellm/proxy/guardrails/guardrail_hooks/semantic_guard/route_loader.py": {
     "baseline": 40,
@@ -4447,6 +4539,10 @@
     "baseline": 210,
     "slack": 105
   },
+  "litellm/proxy/guardrails/guardrail_hooks/tool_policy/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/tool_policy/tool_policy_guardrail.py": {
     "baseline": 73,
     "slack": 37
@@ -4455,14 +4551,26 @@
     "baseline": 144,
     "slack": 72
   },
+  "litellm/proxy/guardrails/guardrail_hooks/vigil_guard/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/vigil_guard/vigil_guard.py": {
-    "baseline": 118,
+    "baseline": 117,
     "slack": 59
   },
+  "litellm/proxy/guardrails/guardrail_hooks/xecguard/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/xecguard/xecguard.py": {
     "baseline": 221,
     "slack": 111
   },
+  "litellm/proxy/guardrails/guardrail_hooks/zscaler_ai_guard/__init__.py": {
+    "baseline": 1,
+    "slack": 1
+  },
   "litellm/proxy/guardrails/guardrail_hooks/zscaler_ai_guard/zscaler_ai_guard.py": {
     "baseline": 194,
     "slack": 97
@@ -4484,8 +4592,8 @@
     "slack": 15
   },
   "litellm/proxy/guardrails/usage_endpoints.py": {
-    "baseline": 454,
-    "slack": 227
+    "baseline": 414,
+    "slack": 207
   },
   "litellm/proxy/guardrails/usage_tracking.py": {
     "baseline": 85,
@@ -4496,20 +4604,20 @@
     "slack": 151
   },
   "litellm/proxy/health_check_utils/shared_health_check_manager.py": {
-    "baseline": 85,
-    "slack": 43
+    "baseline": 81,
+    "slack": 41
   },
   "litellm/proxy/health_endpoints/_health_endpoints.py": {
-    "baseline": 686,
-    "slack": 343
+    "baseline": 676,
+    "slack": 338
   },
   "litellm/proxy/hooks/azure_content_safety.py": {
     "baseline": 86,
     "slack": 43
   },
   "litellm/proxy/hooks/batch_rate_limiter.py": {
-    "baseline": 111,
-    "slack": 56
+    "baseline": 99,
+    "slack": 50
   },
   "litellm/proxy/hooks/batch_redis_get.py": {
     "baseline": 50,
@@ -4520,56 +4628,56 @@
     "slack": 7
   },
   "litellm/proxy/hooks/dynamic_rate_limiter.py": {
-    "baseline": 42,
-    "slack": 21
-  },
-  "litellm/proxy/hooks/dynamic_rate_limiter_v3.py": {
-    "baseline": 112,
-    "slack": 56
-  },
-  "litellm/proxy/hooks/key_management_event_hooks.py": {
-    "baseline": 114,
-    "slack": 57
-  },
-  "litellm/proxy/hooks/litellm_skills/main.py": {
-    "baseline": 389,
-    "slack": 195
-  },
-  "litellm/proxy/hooks/max_budget_limiter.py": {
-    "baseline": 5,
-    "slack": 3
-  },
-  "litellm/proxy/hooks/max_budget_per_session_limiter.py": {
-    "baseline": 73,
-    "slack": 37
-  },
-  "litellm/proxy/hooks/max_iterations_limiter.py": {
     "baseline": 37,
     "slack": 19
   },
-  "litellm/proxy/hooks/mcp_semantic_filter/hook.py": {
-    "baseline": 105,
+  "litellm/proxy/hooks/dynamic_rate_limiter_v3.py": {
+    "baseline": 106,
     "slack": 53
   },
+  "litellm/proxy/hooks/key_management_event_hooks.py": {
+    "baseline": 112,
+    "slack": 56
+  },
+  "litellm/proxy/hooks/litellm_skills/main.py": {
+    "baseline": 383,
+    "slack": 192
+  },
+  "litellm/proxy/hooks/max_budget_limiter.py": {
+    "baseline": 4,
+    "slack": 2
+  },
+  "litellm/proxy/hooks/max_budget_per_session_limiter.py": {
+    "baseline": 70,
+    "slack": 35
+  },
+  "litellm/proxy/hooks/max_iterations_limiter.py": {
+    "baseline": 34,
+    "slack": 17
+  },
+  "litellm/proxy/hooks/mcp_semantic_filter/hook.py": {
+    "baseline": 104,
+    "slack": 52
+  },
   "litellm/proxy/hooks/model_max_budget_limiter.py": {
-    "baseline": 115,
-    "slack": 58
+    "baseline": 113,
+    "slack": 57
   },
   "litellm/proxy/hooks/parallel_request_limiter.py": {
-    "baseline": 417,
-    "slack": 209
+    "baseline": 408,
+    "slack": 204
   },
   "litellm/proxy/hooks/parallel_request_limiter_v3.py": {
-    "baseline": 630,
-    "slack": 315
+    "baseline": 593,
+    "slack": 297
   },
   "litellm/proxy/hooks/prompt_injection_detection.py": {
-    "baseline": 23,
-    "slack": 12
+    "baseline": 22,
+    "slack": 11
   },
   "litellm/proxy/hooks/proxy_track_cost_callback.py": {
-    "baseline": 204,
-    "slack": 102
+    "baseline": 193,
+    "slack": 97
   },
   "litellm/proxy/hooks/rate_limiter_utils.py": {
     "baseline": 14,
@@ -4580,35 +4688,35 @@
     "slack": 29
   },
   "litellm/proxy/hooks/sensitive_data_routing.py": {
-    "baseline": 30,
-    "slack": 15
+    "baseline": 27,
+    "slack": 14
   },
   "litellm/proxy/hooks/user_management_event_hooks.py": {
-    "baseline": 18,
+    "baseline": 17,
     "slack": 9
   },
   "litellm/proxy/image_endpoints/endpoints.py": {
-    "baseline": 125,
-    "slack": 63
+    "baseline": 118,
+    "slack": 59
   },
   "litellm/proxy/lambda.py": {
     "baseline": 1,
     "slack": 1
   },
   "litellm/proxy/litellm_pre_call_utils.py": {
-    "baseline": 912,
+    "baseline": 911,
     "slack": 456
   },
   "litellm/proxy/management_endpoints/access_group_endpoints.py": {
-    "baseline": 277,
-    "slack": 139
+    "baseline": 256,
+    "slack": 128
   },
   "litellm/proxy/management_endpoints/budget_management_endpoints.py": {
     "baseline": 70,
     "slack": 35
   },
   "litellm/proxy/management_endpoints/cache_settings_endpoints.py": {
-    "baseline": 154,
+    "baseline": 153,
     "slack": 77
   },
   "litellm/proxy/management_endpoints/callback_management_endpoints.py": {
@@ -4620,64 +4728,64 @@
     "slack": 223
   },
   "litellm/proxy/management_endpoints/common_utils.py": {
-    "baseline": 147,
-    "slack": 74
+    "baseline": 146,
+    "slack": 73
   },
   "litellm/proxy/management_endpoints/compliance_endpoints.py": {
     "baseline": 8,
     "slack": 4
   },
   "litellm/proxy/management_endpoints/config_override_endpoints.py": {
-    "baseline": 165,
-    "slack": 83
+    "baseline": 163,
+    "slack": 82
   },
   "litellm/proxy/management_endpoints/cost_tracking_settings.py": {
     "baseline": 104,
     "slack": 52
   },
   "litellm/proxy/management_endpoints/customer_endpoints.py": {
-    "baseline": 198,
-    "slack": 99
+    "baseline": 195,
+    "slack": 98
   },
   "litellm/proxy/management_endpoints/fallback_management_endpoints.py": {
     "baseline": 50,
     "slack": 25
   },
   "litellm/proxy/management_endpoints/internal_user_endpoints.py": {
-    "baseline": 720,
-    "slack": 360
+    "baseline": 707,
+    "slack": 354
   },
   "litellm/proxy/management_endpoints/jwt_key_mapping_endpoints.py": {
     "baseline": 83,
     "slack": 42
   },
   "litellm/proxy/management_endpoints/key_management_endpoints.py": {
-    "baseline": 1565,
-    "slack": 783
+    "baseline": 1499,
+    "slack": 750
   },
   "litellm/proxy/management_endpoints/mcp_management_endpoints.py": {
-    "baseline": 625,
-    "slack": 313
+    "baseline": 564,
+    "slack": 282
   },
   "litellm/proxy/management_endpoints/model_access_group_management_endpoints.py": {
-    "baseline": 163,
-    "slack": 82
+    "baseline": 154,
+    "slack": 77
   },
   "litellm/proxy/management_endpoints/model_management_endpoints.py": {
-    "baseline": 389,
-    "slack": 195
+    "baseline": 367,
+    "slack": 184
   },
   "litellm/proxy/management_endpoints/organization_endpoints.py": {
-    "baseline": 322,
-    "slack": 161
+    "baseline": 308,
+    "slack": 154
   },
   "litellm/proxy/management_endpoints/policy_endpoints/ai_policy_suggester.py": {
     "baseline": 34,
     "slack": 17
   },
   "litellm/proxy/management_endpoints/policy_endpoints/endpoints.py": {
-    "baseline": 286,
-    "slack": 143
+    "baseline": 260,
+    "slack": 130
   },
   "litellm/proxy/management_endpoints/router_settings_endpoints.py": {
     "baseline": 37,
@@ -4688,8 +4796,8 @@
     "slack": 15
   },
   "litellm/proxy/management_endpoints/scim/scim_v2.py": {
-    "baseline": 640,
-    "slack": 320
+    "baseline": 600,
+    "slack": 300
   },
   "litellm/proxy/management_endpoints/sso/custom_microsoft_sso.py": {
     "baseline": 5,
@@ -4700,72 +4808,72 @@
     "slack": 1
   },
   "litellm/proxy/management_endpoints/tag_management_endpoints.py": {
-    "baseline": 207,
-    "slack": 104
+    "baseline": 198,
+    "slack": 99
   },
   "litellm/proxy/management_endpoints/team_callback_endpoints.py": {
-    "baseline": 127,
-    "slack": 64
+    "baseline": 122,
+    "slack": 61
   },
   "litellm/proxy/management_endpoints/team_endpoints.py": {
-    "baseline": 1236,
-    "slack": 618
+    "baseline": 1179,
+    "slack": 590
   },
   "litellm/proxy/management_endpoints/tool_management_endpoints.py": {
-    "baseline": 172,
-    "slack": 86
+    "baseline": 157,
+    "slack": 79
   },
   "litellm/proxy/management_endpoints/types.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 6,
+    "slack": 3
   },
   "litellm/proxy/management_endpoints/ui_sso.py": {
-    "baseline": 1009,
-    "slack": 505
+    "baseline": 985,
+    "slack": 493
   },
   "litellm/proxy/management_endpoints/usage_endpoints/ai_usage_chat.py": {
-    "baseline": 163,
-    "slack": 82
+    "baseline": 141,
+    "slack": 71
   },
   "litellm/proxy/management_endpoints/usage_endpoints/endpoints.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 5,
+    "slack": 3
   },
   "litellm/proxy/management_endpoints/user_agent_analytics_endpoints.py": {
-    "baseline": 176,
-    "slack": 88
+    "baseline": 156,
+    "slack": 78
   },
   "litellm/proxy/management_endpoints/workflow_management_endpoints.py": {
-    "baseline": 147,
-    "slack": 74
+    "baseline": 140,
+    "slack": 70
   },
   "litellm/proxy/management_helpers/audit_logs.py": {
-    "baseline": 30,
-    "slack": 15
+    "baseline": 28,
+    "slack": 14
   },
   "litellm/proxy/management_helpers/object_permission_utils.py": {
-    "baseline": 145,
-    "slack": 73
+    "baseline": 140,
+    "slack": 70
   },
   "litellm/proxy/management_helpers/team_member_permission_checks.py": {
-    "baseline": 4,
-    "slack": 2
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/proxy/management_helpers/user_invitation.py": {
     "baseline": 12,
     "slack": 6
   },
   "litellm/proxy/management_helpers/utils.py": {
-    "baseline": 277,
-    "slack": 139
+    "baseline": 276,
+    "slack": 138
   },
   "litellm/proxy/mcp_tools.py": {
     "baseline": 4,
     "slack": 2
   },
   "litellm/proxy/memory/memory_endpoints.py": {
-    "baseline": 178,
-    "slack": 89
+    "baseline": 172,
+    "slack": 86
   },
   "litellm/proxy/middleware/in_flight_requests_middleware.py": {
     "baseline": 15,
@@ -4776,48 +4884,48 @@
     "slack": 13
   },
   "litellm/proxy/middleware/request_size_limit_middleware.py": {
-    "baseline": 29,
-    "slack": 15
+    "baseline": 27,
+    "slack": 14
   },
   "litellm/proxy/ocr_endpoints/endpoints.py": {
-    "baseline": 50,
-    "slack": 25
+    "baseline": 47,
+    "slack": 24
   },
   "litellm/proxy/openai_evals_endpoints/endpoints.py": {
-    "baseline": 265,
-    "slack": 133
+    "baseline": 256,
+    "slack": 128
   },
   "litellm/proxy/openai_files_endpoints/common_utils.py": {
-    "baseline": 206,
-    "slack": 103
+    "baseline": 201,
+    "slack": 101
   },
   "litellm/proxy/openai_files_endpoints/file_content_streaming_handler.py": {
-    "baseline": 35,
-    "slack": 18
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/proxy/openai_files_endpoints/files_endpoints.py": {
-    "baseline": 427,
-    "slack": 214
+    "baseline": 405,
+    "slack": 203
   },
   "litellm/proxy/openai_files_endpoints/storage_backend_service.py": {
-    "baseline": 22,
-    "slack": 11
+    "baseline": 20,
+    "slack": 10
   },
   "litellm/proxy/pass_through_endpoints/jsonpath_extractor.py": {
     "baseline": 13,
     "slack": 7
   },
   "litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py": {
-    "baseline": 375,
-    "slack": 188
+    "baseline": 361,
+    "slack": 181
   },
   "litellm/proxy/pass_through_endpoints/llm_provider_handlers/anthropic_passthrough_logging_handler.py": {
     "baseline": 164,
     "slack": 82
   },
   "litellm/proxy/pass_through_endpoints/llm_provider_handlers/assembly_passthrough_logging_handler.py": {
-    "baseline": 45,
-    "slack": 23
+    "baseline": 39,
+    "slack": 20
   },
   "litellm/proxy/pass_through_endpoints/llm_provider_handlers/base_passthrough_logging_handler.py": {
     "baseline": 32,
@@ -4847,17 +4955,13 @@
     "baseline": 163,
     "slack": 82
   },
-  "litellm/proxy/pass_through_endpoints/managed_id_codec.py": {
-    "baseline": 3,
-    "slack": 2
-  },
   "litellm/proxy/pass_through_endpoints/managed_id_rewriter.py": {
-    "baseline": 312,
-    "slack": 156
+    "baseline": 302,
+    "slack": 151
   },
   "litellm/proxy/pass_through_endpoints/pass_through_endpoints.py": {
-    "baseline": 937,
-    "slack": 469
+    "baseline": 894,
+    "slack": 447
   },
   "litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py": {
     "baseline": 14,
@@ -4868,40 +4972,40 @@
     "slack": 14
   },
   "litellm/proxy/pass_through_endpoints/streaming_handler.py": {
-    "baseline": 35,
-    "slack": 18
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/proxy/pass_through_endpoints/success_handler.py": {
-    "baseline": 113,
-    "slack": 57
+    "baseline": 112,
+    "slack": 56
   },
   "litellm/proxy/policy_engine/attachment_registry.py": {
-    "baseline": 83,
-    "slack": 42
+    "baseline": 81,
+    "slack": 41
   },
   "litellm/proxy/policy_engine/init_policies.py": {
-    "baseline": 71,
-    "slack": 36
+    "baseline": 69,
+    "slack": 35
   },
   "litellm/proxy/policy_engine/pipeline_executor.py": {
     "baseline": 55,
     "slack": 28
   },
   "litellm/proxy/policy_engine/policy_endpoints.py": {
-    "baseline": 84,
-    "slack": 42
+    "baseline": 65,
+    "slack": 33
   },
   "litellm/proxy/policy_engine/policy_registry.py": {
-    "baseline": 257,
-    "slack": 129
+    "baseline": 255,
+    "slack": 128
   },
   "litellm/proxy/policy_engine/policy_resolve_endpoints.py": {
-    "baseline": 187,
-    "slack": 94
+    "baseline": 185,
+    "slack": 93
   },
   "litellm/proxy/policy_engine/policy_validator.py": {
-    "baseline": 13,
-    "slack": 7
+    "baseline": 12,
+    "slack": 6
   },
   "litellm/proxy/post_call_rules.py": {
     "baseline": 7,
@@ -4920,8 +5024,8 @@
     "slack": 2
   },
   "litellm/proxy/prompts/prompt_endpoints.py": {
-    "baseline": 181,
-    "slack": 91
+    "baseline": 176,
+    "slack": 88
   },
   "litellm/proxy/prompts/prompt_registry.py": {
     "baseline": 70,
@@ -4932,64 +5036,60 @@
     "slack": 154
   },
   "litellm/proxy/proxy_server.py": {
-    "baseline": 5145,
-    "slack": 2573
+    "baseline": 5015,
+    "slack": 2508
   },
   "litellm/proxy/public_endpoints/public_endpoints.py": {
     "baseline": 165,
     "slack": 83
   },
   "litellm/proxy/rag_endpoints/endpoints.py": {
-    "baseline": 249,
-    "slack": 125
-  },
-  "litellm/proxy/realtime_endpoints/endpoints.py": {
-    "baseline": 243,
+    "baseline": 244,
     "slack": 122
   },
+  "litellm/proxy/realtime_endpoints/endpoints.py": {
+    "baseline": 237,
+    "slack": 119
+  },
   "litellm/proxy/rerank_endpoints/endpoints.py": {
-    "baseline": 53,
-    "slack": 27
+    "baseline": 51,
+    "slack": 26
   },
   "litellm/proxy/response_api_endpoints/endpoints.py": {
-    "baseline": 322,
-    "slack": 161
+    "baseline": 302,
+    "slack": 151
   },
   "litellm/proxy/response_polling/background_streaming.py": {
-    "baseline": 162,
-    "slack": 81
+    "baseline": 155,
+    "slack": 78
   },
   "litellm/proxy/response_polling/polling_handler.py": {
-    "baseline": 82,
+    "baseline": 81,
     "slack": 41
   },
   "litellm/proxy/route_llm_request.py": {
-    "baseline": 138,
+    "baseline": 137,
     "slack": 69
   },
   "litellm/proxy/search_endpoints/endpoints.py": {
-    "baseline": 59,
-    "slack": 30
+    "baseline": 55,
+    "slack": 28
   },
   "litellm/proxy/search_endpoints/search_tool_management.py": {
-    "baseline": 95,
-    "slack": 48
+    "baseline": 85,
+    "slack": 43
   },
   "litellm/proxy/search_endpoints/search_tool_registry.py": {
     "baseline": 53,
     "slack": 27
   },
-  "litellm/proxy/shutdown/graceful_shutdown_manager.py": {
-    "baseline": 1,
-    "slack": 1
-  },
   "litellm/proxy/spend_tracking/budget_reservation.py": {
-    "baseline": 245,
-    "slack": 123
+    "baseline": 222,
+    "slack": 111
   },
   "litellm/proxy/spend_tracking/cloudzero_endpoints.py": {
-    "baseline": 121,
-    "slack": 61
+    "baseline": 120,
+    "slack": 60
   },
   "litellm/proxy/spend_tracking/cold_storage_handler.py": {
     "baseline": 3,
@@ -5000,152 +5100,152 @@
     "slack": 2
   },
   "litellm/proxy/spend_tracking/spend_management_endpoints.py": {
-    "baseline": 980,
-    "slack": 490
+    "baseline": 974,
+    "slack": 487
   },
   "litellm/proxy/spend_tracking/spend_tracking_utils.py": {
     "baseline": 274,
     "slack": 137
   },
   "litellm/proxy/spend_tracking/vantage_endpoints.py": {
-    "baseline": 177,
-    "slack": 89
+    "baseline": 176,
+    "slack": 88
   },
   "litellm/proxy/types_utils/utils.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 9,
+    "slack": 5
   },
   "litellm/proxy/ui_crud_endpoints/proxy_setting_endpoints.py": {
-    "baseline": 481,
-    "slack": 241
+    "baseline": 477,
+    "slack": 239
   },
   "litellm/proxy/utils.py": {
-    "baseline": 1731,
-    "slack": 866
+    "baseline": 1683,
+    "slack": 842
   },
   "litellm/proxy/vector_store_endpoints/endpoints.py": {
-    "baseline": 163,
-    "slack": 82
+    "baseline": 161,
+    "slack": 81
   },
   "litellm/proxy/vector_store_endpoints/management_endpoints.py": {
-    "baseline": 248,
-    "slack": 124
+    "baseline": 234,
+    "slack": 117
   },
   "litellm/proxy/vector_store_endpoints/utils.py": {
-    "baseline": 37,
-    "slack": 19
+    "baseline": 32,
+    "slack": 16
   },
   "litellm/proxy/vector_store_files_endpoints/endpoints.py": {
-    "baseline": 292,
-    "slack": 146
+    "baseline": 274,
+    "slack": 137
   },
   "litellm/proxy/vertex_ai_endpoints/langfuse_endpoints.py": {
     "baseline": 38,
     "slack": 19
   },
   "litellm/proxy/video_endpoints/endpoints.py": {
-    "baseline": 238,
-    "slack": 119
+    "baseline": 229,
+    "slack": 115
   },
   "litellm/proxy/video_endpoints/utils.py": {
     "baseline": 27,
     "slack": 14
   },
   "litellm/proxy_auth/credentials.py": {
-    "baseline": 16,
-    "slack": 8
+    "baseline": 14,
+    "slack": 7
   },
   "litellm/rag/__init__.py": {
     "baseline": 7,
     "slack": 4
   },
   "litellm/rag/ingestion/base_ingestion.py": {
-    "baseline": 64,
-    "slack": 32
+    "baseline": 59,
+    "slack": 30
   },
   "litellm/rag/ingestion/bedrock_ingestion.py": {
-    "baseline": 273,
-    "slack": 137
+    "baseline": 267,
+    "slack": 134
   },
   "litellm/rag/ingestion/file_parsers/pdf_parser.py": {
     "baseline": 19,
     "slack": 10
   },
   "litellm/rag/ingestion/gemini_ingestion.py": {
-    "baseline": 64,
-    "slack": 32
+    "baseline": 60,
+    "slack": 30
   },
   "litellm/rag/ingestion/openai_ingestion.py": {
     "baseline": 31,
     "slack": 16
   },
   "litellm/rag/ingestion/s3_vectors_ingestion.py": {
-    "baseline": 252,
-    "slack": 126
+    "baseline": 250,
+    "slack": 125
   },
   "litellm/rag/ingestion/vertex_ai_ingestion.py": {
-    "baseline": 134,
-    "slack": 67
+    "baseline": 130,
+    "slack": 65
   },
   "litellm/rag/main.py": {
-    "baseline": 108,
-    "slack": 54
+    "baseline": 102,
+    "slack": 51
   },
   "litellm/rag/rag_query.py": {
     "baseline": 51,
     "slack": 26
   },
   "litellm/realtime_api/main.py": {
-    "baseline": 165,
-    "slack": 83
+    "baseline": 160,
+    "slack": 80
   },
   "litellm/repositories/base_repository.py": {
     "baseline": 54,
     "slack": 27
   },
   "litellm/repositories/budget_repository.py": {
-    "baseline": 29,
-    "slack": 15
+    "baseline": 25,
+    "slack": 13
   },
   "litellm/repositories/config_repository.py": {
-    "baseline": 94,
-    "slack": 47
+    "baseline": 89,
+    "slack": 45
   },
   "litellm/repositories/credentials_repository.py": {
     "baseline": 28,
     "slack": 14
   },
   "litellm/repositories/model_repository.py": {
-    "baseline": 77,
-    "slack": 39
+    "baseline": 72,
+    "slack": 36
   },
   "litellm/repositories/object_permission_repository.py": {
-    "baseline": 29,
-    "slack": 15
+    "baseline": 25,
+    "slack": 13
   },
   "litellm/repositories/organization_repository.py": {
-    "baseline": 28,
-    "slack": 14
+    "baseline": 23,
+    "slack": 12
   },
   "litellm/repositories/project_repository.py": {
-    "baseline": 42,
-    "slack": 21
+    "baseline": 37,
+    "slack": 19
   },
   "litellm/repositories/table_repositories.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 6,
+    "slack": 3
   },
   "litellm/repositories/team_repository.py": {
-    "baseline": 163,
-    "slack": 82
+    "baseline": 149,
+    "slack": 75
   },
   "litellm/repositories/user_repository.py": {
-    "baseline": 81,
-    "slack": 41
+    "baseline": 73,
+    "slack": 37
   },
   "litellm/repositories/verification_token_repository.py": {
-    "baseline": 116,
-    "slack": 58
+    "baseline": 108,
+    "slack": 54
   },
   "litellm/rerank_api/main.py": {
     "baseline": 129,
@@ -5156,72 +5256,72 @@
     "slack": 7
   },
   "litellm/responses/file_search/emulated_handler.py": {
-    "baseline": 280,
+    "baseline": 279,
     "slack": 140
   },
   "litellm/responses/litellm_completion_transformation/handler.py": {
-    "baseline": 28,
+    "baseline": 27,
     "slack": 14
   },
   "litellm/responses/litellm_completion_transformation/session_handler.py": {
-    "baseline": 43,
-    "slack": 22
+    "baseline": 42,
+    "slack": 21
   },
   "litellm/responses/litellm_completion_transformation/streaming_iterator.py": {
-    "baseline": 152,
+    "baseline": 151,
     "slack": 76
   },
   "litellm/responses/litellm_completion_transformation/transformation.py": {
-    "baseline": 555,
-    "slack": 278
+    "baseline": 552,
+    "slack": 276
   },
   "litellm/responses/main.py": {
-    "baseline": 567,
-    "slack": 284
+    "baseline": 548,
+    "slack": 274
   },
   "litellm/responses/mcp/chat_completions_handler.py": {
     "baseline": 367,
     "slack": 184
   },
   "litellm/responses/mcp/litellm_proxy_mcp_handler.py": {
-    "baseline": 454,
-    "slack": 227
+    "baseline": 445,
+    "slack": 223
   },
   "litellm/responses/mcp/mcp_streaming_iterator.py": {
-    "baseline": 202,
-    "slack": 101
+    "baseline": 193,
+    "slack": 97
   },
   "litellm/responses/sse_output_recovery.py": {
     "baseline": 48,
     "slack": 24
   },
   "litellm/responses/streaming_iterator.py": {
-    "baseline": 990,
-    "slack": 495
+    "baseline": 977,
+    "slack": 489
   },
   "litellm/responses/utils.py": {
-    "baseline": 295,
-    "slack": 148
+    "baseline": 294,
+    "slack": 147
   },
   "litellm/router.py": {
-    "baseline": 4343,
-    "slack": 2172
+    "baseline": 4303,
+    "slack": 2152
   },
   "litellm/router_strategy/adaptive_router/adaptive_router.py": {
-    "baseline": 48,
-    "slack": 24
+    "baseline": 44,
+    "slack": 22
   },
   "litellm/router_strategy/adaptive_router/bandit.py": {
-    "baseline": 3,
-    "slack": 2
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/router_strategy/adaptive_router/hooks.py": {
-    "baseline": 143,
-    "slack": 72
+    "baseline": 142,
+    "slack": 71
   },
   "litellm/router_strategy/adaptive_router/signals.py": {
-    "baseline": 42,
-    "slack": 21
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/router_strategy/adaptive_router/update_queue.py": {
     "baseline": 30,
@@ -5232,24 +5332,24 @@
     "slack": 22
   },
   "litellm/router_strategy/auto_router/litellm_encoder.py": {
-    "baseline": 19,
-    "slack": 10
+    "baseline": 16,
+    "slack": 8
   },
   "litellm/router_strategy/base_routing_strategy.py": {
-    "baseline": 114,
-    "slack": 57
+    "baseline": 111,
+    "slack": 56
   },
   "litellm/router_strategy/budget_limiter.py": {
-    "baseline": 347,
-    "slack": 174
+    "baseline": 342,
+    "slack": 171
   },
   "litellm/router_strategy/complexity_router/complexity_router.py": {
     "baseline": 59,
     "slack": 30
   },
   "litellm/router_strategy/complexity_router/evals/eval_complexity_router.py": {
-    "baseline": 24,
-    "slack": 12
+    "baseline": 21,
+    "slack": 11
   },
   "litellm/router_strategy/least_busy.py": {
     "baseline": 155,
@@ -5308,20 +5408,20 @@
     "slack": 32
   },
   "litellm/router_utils/cooldown_cache.py": {
-    "baseline": 42,
-    "slack": 21
+    "baseline": 38,
+    "slack": 19
   },
   "litellm/router_utils/cooldown_callbacks.py": {
     "baseline": 22,
     "slack": 11
   },
   "litellm/router_utils/cooldown_handlers.py": {
-    "baseline": 26,
-    "slack": 13
+    "baseline": 24,
+    "slack": 12
   },
   "litellm/router_utils/fallback_event_handlers.py": {
-    "baseline": 56,
-    "slack": 28
+    "baseline": 54,
+    "slack": 27
   },
   "litellm/router_utils/get_retry_from_policy.py": {
     "baseline": 3,
@@ -5332,35 +5432,35 @@
     "slack": 11
   },
   "litellm/router_utils/health_state_cache.py": {
-    "baseline": 22,
-    "slack": 11
+    "baseline": 19,
+    "slack": 10
   },
   "litellm/router_utils/pattern_match_deployments.py": {
     "baseline": 41,
     "slack": 21
   },
   "litellm/router_utils/pre_call_checks/deployment_affinity_check.py": {
-    "baseline": 112,
+    "baseline": 111,
     "slack": 56
   },
   "litellm/router_utils/pre_call_checks/encrypted_content_affinity_check.py": {
-    "baseline": 86,
-    "slack": 43
+    "baseline": 84,
+    "slack": 42
   },
   "litellm/router_utils/pre_call_checks/model_rate_limit_check.py": {
-    "baseline": 134,
+    "baseline": 133,
     "slack": 67
   },
   "litellm/router_utils/pre_call_checks/prompt_caching_deployment_check.py": {
-    "baseline": 35,
-    "slack": 18
+    "baseline": 34,
+    "slack": 17
   },
   "litellm/router_utils/pre_call_checks/responses_api_deployment_check.py": {
     "baseline": 13,
     "slack": 7
   },
   "litellm/router_utils/prompt_caching_cache.py": {
-    "baseline": 44,
+    "baseline": 43,
     "slack": 22
   },
   "litellm/router_utils/router_callbacks/track_deployment_metrics.py": {
@@ -5372,28 +5472,28 @@
     "slack": 31
   },
   "litellm/scheduler.py": {
-    "baseline": 54,
-    "slack": 27
+    "baseline": 47,
+    "slack": 24
   },
   "litellm/search/cost_calculator.py": {
     "baseline": 16,
     "slack": 8
   },
   "litellm/search/main.py": {
-    "baseline": 57,
-    "slack": 29
+    "baseline": 55,
+    "slack": 28
   },
   "litellm/secret_managers/aws_secret_manager.py": {
     "baseline": 28,
     "slack": 14
   },
   "litellm/secret_managers/aws_secret_manager_v2.py": {
-    "baseline": 132,
-    "slack": 66
+    "baseline": 122,
+    "slack": 61
   },
   "litellm/secret_managers/base_secret_manager.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 9,
+    "slack": 5
   },
   "litellm/secret_managers/custom_secret_manager_loader.py": {
     "baseline": 19,
@@ -5432,380 +5532,168 @@
     "slack": 55
   },
   "litellm/skills/main.py": {
-    "baseline": 215,
-    "slack": 108
+    "baseline": 207,
+    "slack": 104
   },
   "litellm/timeout.py": {
     "baseline": 70,
     "slack": 35
   },
-  "litellm/types/access_group.py": {
-    "baseline": 10,
-    "slack": 5
+  "litellm/types/agents.py": {
+    "baseline": 23,
+    "slack": 12
   },
-  "litellm/types/adapter.py": {
+  "litellm/types/caching.py": {
+    "baseline": 3,
+    "slack": 2
+  },
+  "litellm/types/completion.py": {
     "baseline": 2,
     "slack": 1
   },
-  "litellm/types/agents.py": {
-    "baseline": 117,
-    "slack": 59
-  },
-  "litellm/types/caching.py": {
-    "baseline": 21,
-    "slack": 11
-  },
-  "litellm/types/completion.py": {
-    "baseline": 33,
-    "slack": 17
-  },
-  "litellm/types/compression.py": {
-    "baseline": 7,
-    "slack": 4
-  },
   "litellm/types/containers/main.py": {
-    "baseline": 96,
-    "slack": 48
-  },
-  "litellm/types/embedding.py": {
-    "baseline": 1,
-    "slack": 1
+    "baseline": 62,
+    "slack": 31
   },
   "litellm/types/files.py": {
-    "baseline": 12,
-    "slack": 6
-  },
-  "litellm/types/google_genai/main.py": {
-    "baseline": 11,
-    "slack": 6
-  },
-  "litellm/types/guardrails.py": {
-    "baseline": 81,
-    "slack": 41
-  },
-  "litellm/types/images/main.py": {
-    "baseline": 12,
-    "slack": 6
-  },
-  "litellm/types/integrations/anthropic_cache_control_hook.py": {
-    "baseline": 6,
-    "slack": 3
-  },
-  "litellm/types/integrations/argilla.py": {
-    "baseline": 5,
-    "slack": 3
-  },
-  "litellm/types/integrations/arize.py": {
     "baseline": 4,
     "slack": 2
   },
-  "litellm/types/integrations/arize_phoenix.py": {
-    "baseline": 2,
+  "litellm/types/google_genai/main.py": {
+    "baseline": 9,
+    "slack": 5
+  },
+  "litellm/types/guardrails.py": {
+    "baseline": 48,
+    "slack": 24
+  },
+  "litellm/types/integrations/anthropic_cache_control_hook.py": {
+    "baseline": 1,
     "slack": 1
   },
-  "litellm/types/integrations/base_health_check.py": {
+  "litellm/types/integrations/arize.py": {
     "baseline": 2,
     "slack": 1
   },
-  "litellm/types/integrations/compression_interception.py": {
-    "baseline": 5,
-    "slack": 3
-  },
   "litellm/types/integrations/custom_logger.py": {
     "baseline": 3,
     "slack": 2
   },
   "litellm/types/integrations/datadog.py": {
-    "baseline": 6,
-    "slack": 3
-  },
-  "litellm/types/integrations/datadog_cost_management.py": {
-    "baseline": 7,
-    "slack": 4
-  },
-  "litellm/types/integrations/datadog_llm_obs.py": {
-    "baseline": 39,
-    "slack": 20
-  },
-  "litellm/types/integrations/datadog_metrics.py": {
-    "baseline": 8,
-    "slack": 4
-  },
-  "litellm/types/integrations/gcs_bucket.py": {
-    "baseline": 6,
-    "slack": 3
-  },
-  "litellm/types/integrations/langfuse.py": {
-    "baseline": 8,
-    "slack": 4
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/types/integrations/langfuse_otel.py": {
     "baseline": 2,
     "slack": 1
   },
-  "litellm/types/integrations/langsmith.py": {
-    "baseline": 12,
-    "slack": 6
-  },
-  "litellm/types/integrations/pagerduty.py": {
-    "baseline": 31,
-    "slack": 16
-  },
-  "litellm/types/integrations/posthog.py": {
-    "baseline": 5,
-    "slack": 3
-  },
   "litellm/types/integrations/prometheus.py": {
-    "baseline": 60,
-    "slack": 30
-  },
-  "litellm/types/integrations/rag/bedrock_knowledgebase.py": {
-    "baseline": 47,
-    "slack": 24
-  },
-  "litellm/types/integrations/s3_v2.py": {
-    "baseline": 3,
-    "slack": 2
-  },
-  "litellm/types/integrations/slack_alerting.py": {
-    "baseline": 22,
-    "slack": 11
-  },
-  "litellm/types/integrations/websearch_interception.py": {
-    "baseline": 2,
-    "slack": 1
+    "baseline": 51,
+    "slack": 26
   },
   "litellm/types/interactions/generated.py": {
-    "baseline": 77,
-    "slack": 39
-  },
-  "litellm/types/litellm_core_utils/streaming_chunk_builder_utils.py": {
-    "baseline": 8,
-    "slack": 4
-  },
-  "litellm/types/llms/aiml.py": {
-    "baseline": 10,
-    "slack": 5
+    "baseline": 69,
+    "slack": 35
   },
   "litellm/types/llms/anthropic.py": {
-    "baseline": 258,
-    "slack": 129
+    "baseline": 11,
+    "slack": 6
   },
   "litellm/types/llms/anthropic_messages/anthropic_response.py": {
-    "baseline": 26,
-    "slack": 13
-  },
-  "litellm/types/llms/anthropic_skills.py": {
-    "baseline": 21,
-    "slack": 11
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/types/llms/azure_ai.py": {
-    "baseline": 7,
-    "slack": 4
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/types/llms/base.py": {
     "baseline": 29,
     "slack": 15
   },
   "litellm/types/llms/bedrock.py": {
-    "baseline": 402,
-    "slack": 201
-  },
-  "litellm/types/llms/bedrock_agentcore.py": {
-    "baseline": 28,
-    "slack": 14
-  },
-  "litellm/types/llms/bedrock_invoke_agents.py": {
-    "baseline": 46,
-    "slack": 23
-  },
-  "litellm/types/llms/cohere.py": {
-    "baseline": 46,
-    "slack": 23
+    "baseline": 36,
+    "slack": 18
   },
   "litellm/types/llms/custom_http.py": {
     "baseline": 1,
     "slack": 1
   },
-  "litellm/types/llms/custom_llm.py": {
+  "litellm/types/llms/databricks.py": {
     "baseline": 2,
     "slack": 1
   },
-  "litellm/types/llms/databricks.py": {
-    "baseline": 36,
-    "slack": 18
-  },
   "litellm/types/llms/gemini.py": {
-    "baseline": 64,
-    "slack": 32
-  },
-  "litellm/types/llms/langgraph.py": {
-    "baseline": 19,
-    "slack": 10
-  },
-  "litellm/types/llms/mistral.py": {
-    "baseline": 9,
-    "slack": 5
+    "baseline": 4,
+    "slack": 2
   },
   "litellm/types/llms/oci.py": {
-    "baseline": 62,
-    "slack": 31
-  },
-  "litellm/types/llms/ollama.py": {
-    "baseline": 12,
-    "slack": 6
+    "baseline": 3,
+    "slack": 2
   },
   "litellm/types/llms/openai.py": {
-    "baseline": 750,
-    "slack": 375
+    "baseline": 132,
+    "slack": 66
   },
   "litellm/types/llms/openai_evals.py": {
-    "baseline": 68,
-    "slack": 34
-  },
-  "litellm/types/llms/openrouter.py": {
     "baseline": 3,
     "slack": 2
   },
-  "litellm/types/llms/recraft.py": {
-    "baseline": 21,
-    "slack": 11
-  },
-  "litellm/types/llms/rerank.py": {
-    "baseline": 3,
-    "slack": 2
-  },
-  "litellm/types/llms/stability.py": {
-    "baseline": 60,
-    "slack": 30
-  },
   "litellm/types/llms/vertex_ai.py": {
-    "baseline": 347,
-    "slack": 174
-  },
-  "litellm/types/llms/vertex_ai_text_to_speech.py": {
-    "baseline": 9,
-    "slack": 5
-  },
-  "litellm/types/llms/watsonx.py": {
-    "baseline": 14,
-    "slack": 7
-  },
-  "litellm/types/llms/xai.py": {
-    "baseline": 12,
-    "slack": 6
-  },
-  "litellm/types/management_endpoints/cache_settings_endpoints.py": {
-    "baseline": 5,
-    "slack": 3
+    "baseline": 18,
+    "slack": 9
   },
   "litellm/types/management_endpoints/router_settings_endpoints.py": {
-    "baseline": 23,
-    "slack": 12
+    "baseline": 18,
+    "slack": 9
   },
   "litellm/types/mcp.py": {
-    "baseline": 34,
-    "slack": 17
-  },
-  "litellm/types/mcp_server/mcp_server_manager.py": {
-    "baseline": 3,
-    "slack": 2
-  },
-  "litellm/types/mcp_server/mcp_toolset.py": {
     "baseline": 6,
     "slack": 3
   },
-  "litellm/types/mcp_server/tool_registry.py": {
+  "litellm/types/memory_management.py": {
+    "baseline": 2,
+    "slack": 1
+  },
+  "litellm/types/prompts/init_prompts.py": {
     "baseline": 10,
     "slack": 5
   },
-  "litellm/types/memory_management.py": {
-    "baseline": 9,
-    "slack": 5
-  },
-  "litellm/types/passthrough_endpoints/pass_through_endpoints.py": {
-    "baseline": 5,
-    "slack": 3
-  },
-  "litellm/types/prompts/init_prompts.py": {
-    "baseline": 19,
-    "slack": 10
-  },
   "litellm/types/proxy/claude_code_endpoints.py": {
-    "baseline": 25,
-    "slack": 13
+    "baseline": 13,
+    "slack": 7
   },
   "litellm/types/proxy/cloudzero_endpoints.py": {
-    "baseline": 6,
-    "slack": 3
-  },
-  "litellm/types/proxy/compliance_endpoints.py": {
-    "baseline": 8,
-    "slack": 4
-  },
-  "litellm/types/proxy/control_plane_endpoints.py": {
-    "baseline": 3,
-    "slack": 2
-  },
-  "litellm/types/proxy/discovery_endpoints/ui_discovery_endpoints.py": {
-    "baseline": 5,
-    "slack": 3
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/azure/azure_prompt_shield.py": {
-    "baseline": 5,
-    "slack": 3
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/azure/azure_text_moderation.py": {
-    "baseline": 12,
-    "slack": 6
+    "baseline": 3,
+    "slack": 2
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/base.py": {
     "baseline": 2,
     "slack": 1
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py": {
-    "baseline": 60,
-    "slack": 30
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/block_code_execution.py": {
-    "baseline": 12,
-    "slack": 6
+    "baseline": 6,
+    "slack": 3
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/cisco_ai_defense.py": {
     "baseline": 5,
     "slack": 3
   },
-  "litellm/types/proxy/guardrails/guardrail_hooks/dynamoai.py": {
-    "baseline": 31,
-    "slack": 16
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/enkryptai.py": {
-    "baseline": 29,
-    "slack": 15
-  },
   "litellm/types/proxy/guardrails/guardrail_hooks/generic_guardrail_api.py": {
-    "baseline": 20,
-    "slack": 10
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/ibm/ibm_detector.py": {
-    "baseline": 15,
-    "slack": 8
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/javelin.py": {
-    "baseline": 34,
-    "slack": 17
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py": {
-    "baseline": 24,
-    "slack": 12
+    "baseline": 5,
+    "slack": 3
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/litellm_content_filter.py": {
-    "baseline": 36,
-    "slack": 18
-  },
-  "litellm/types/proxy/guardrails/guardrail_hooks/presidio.py": {
-    "baseline": 10,
-    "slack": 5
+    "baseline": 7,
+    "slack": 4
   },
   "litellm/types/proxy/guardrails/guardrail_hooks/tool_permission.py": {
     "baseline": 22,
@@ -5816,156 +5704,120 @@
     "slack": 1
   },
   "litellm/types/proxy/litellm_pre_call_utils.py": {
-    "baseline": 2,
+    "baseline": 1,
     "slack": 1
   },
   "litellm/types/proxy/management_endpoints/common_daily_activity.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 1,
+    "slack": 1
   },
   "litellm/types/proxy/management_endpoints/config_overrides.py": {
     "baseline": 3,
     "slack": 2
   },
   "litellm/types/proxy/management_endpoints/internal_user_endpoints.py": {
-    "baseline": 27,
-    "slack": 14
-  },
-  "litellm/types/proxy/management_endpoints/key_management_endpoints.py": {
-    "baseline": 11,
-    "slack": 6
-  },
-  "litellm/types/proxy/management_endpoints/model_management_endpoints.py": {
-    "baseline": 11,
-    "slack": 6
+    "baseline": 17,
+    "slack": 9
   },
   "litellm/types/proxy/management_endpoints/scim_v2.py": {
-    "baseline": 45,
-    "slack": 23
-  },
-  "litellm/types/proxy/management_endpoints/team_endpoints.py": {
-    "baseline": 20,
-    "slack": 10
+    "baseline": 25,
+    "slack": 13
   },
   "litellm/types/proxy/management_endpoints/ui_sso.py": {
-    "baseline": 16,
-    "slack": 8
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/types/proxy/policy_engine/pipeline_types.py": {
-    "baseline": 8,
-    "slack": 4
+    "baseline": 3,
+    "slack": 2
   },
   "litellm/types/proxy/policy_engine/policy_types.py": {
     "baseline": 1,
     "slack": 1
   },
   "litellm/types/proxy/policy_engine/resolver_types.py": {
-    "baseline": 30,
-    "slack": 15
+    "baseline": 16,
+    "slack": 8
   },
   "litellm/types/proxy/policy_engine/validation_types.py": {
     "baseline": 5,
     "slack": 3
   },
-  "litellm/types/proxy/prompt_endpoints.py": {
+  "litellm/types/proxy/vantage_endpoints.py": {
+    "baseline": 2,
+    "slack": 1
+  },
+  "litellm/types/rag.py": {
     "baseline": 1,
     "slack": 1
   },
-  "litellm/types/proxy/public_endpoints/public_endpoints.py": {
-    "baseline": 22,
-    "slack": 11
+  "litellm/types/realtime.py": {
+    "baseline": 4,
+    "slack": 2
   },
-  "litellm/types/proxy/ui_sso.py": {
+  "litellm/types/rerank.py": {
+    "baseline": 8,
+    "slack": 4
+  },
+  "litellm/types/responses/main.py": {
     "baseline": 12,
     "slack": 6
   },
-  "litellm/types/proxy/vantage_endpoints.py": {
+  "litellm/types/router.py": {
+    "baseline": 103,
+    "slack": 52
+  },
+  "litellm/types/services.py": {
+    "baseline": 10,
+    "slack": 5
+  },
+  "litellm/types/tool_management.py": {
     "baseline": 6,
     "slack": 3
   },
-  "litellm/types/rag.py": {
-    "baseline": 78,
-    "slack": 39
-  },
-  "litellm/types/realtime.py": {
-    "baseline": 28,
-    "slack": 14
-  },
-  "litellm/types/rerank.py": {
-    "baseline": 29,
-    "slack": 15
-  },
-  "litellm/types/responses/main.py": {
-    "baseline": 49,
-    "slack": 25
-  },
-  "litellm/types/router.py": {
-    "baseline": 194,
-    "slack": 97
-  },
-  "litellm/types/search.py": {
-    "baseline": 21,
-    "slack": 11
-  },
-  "litellm/types/services.py": {
-    "baseline": 13,
-    "slack": 7
-  },
-  "litellm/types/tag_management.py": {
-    "baseline": 5,
-    "slack": 3
-  },
-  "litellm/types/tool_management.py": {
-    "baseline": 27,
-    "slack": 14
-  },
   "litellm/types/utils.py": {
-    "baseline": 1085,
-    "slack": 543
-  },
-  "litellm/types/vector_store_files.py": {
-    "baseline": 38,
-    "slack": 19
+    "baseline": 637,
+    "slack": 319
   },
   "litellm/types/vector_stores.py": {
-    "baseline": 118,
-    "slack": 59
+    "baseline": 9,
+    "slack": 5
   },
   "litellm/types/videos/main.py": {
-    "baseline": 59,
-    "slack": 30
+    "baseline": 33,
+    "slack": 17
   },
   "litellm/types/videos/utils.py": {
-    "baseline": 5,
-    "slack": 3
+    "baseline": 2,
+    "slack": 1
   },
   "litellm/utils.py": {
-    "baseline": 3367,
-    "slack": 1684
+    "baseline": 3362,
+    "slack": 1681
   },
   "litellm/vector_store_files/main.py": {
-    "baseline": 244,
-    "slack": 122
+    "baseline": 232,
+    "slack": 116
   },
   "litellm/vector_store_files/utils.py": {
     "baseline": 17,
     "slack": 9
   },
   "litellm/vector_stores/main.py": {
-    "baseline": 268,
-    "slack": 134
+    "baseline": 260,
+    "slack": 130
   },
   "litellm/vector_stores/utils.py": {
     "baseline": 19,
     "slack": 10
   },
   "litellm/vector_stores/vector_store_registry.py": {
-    "baseline": 94,
-    "slack": 47
+    "baseline": 92,
+    "slack": 46
   },
   "litellm/videos/main.py": {
-    "baseline": 513,
-    "slack": 257
+    "baseline": 479,
+    "slack": 240
   },
   "litellm/videos/utils.py": {
     "baseline": 54,
diff --git a/litellm/integrations/custom_guardrail.py b/litellm/integrations/custom_guardrail.py
index bc55cf2ed63..e85074d1932 100644
--- a/litellm/integrations/custom_guardrail.py
+++ b/litellm/integrations/custom_guardrail.py
@@ -83,7 +83,9 @@ class CustomGuardrail(CustomLogger):
         self,
         guardrail_name: str | None = None,
         supported_event_hooks: list[GuardrailEventHooks] | None = None,
-        event_hook: Union[GuardrailEventHooks, list[GuardrailEventHooks], Mode] | None = None,
+        event_hook: (
+            Union[GuardrailEventHooks, list[GuardrailEventHooks], Mode] | None
+        ) = None,
         default_on: bool = False,
         mask_request_content: bool = False,
         mask_response_content: bool = False,
@@ -115,7 +117,9 @@ class CustomGuardrail(CustomLogger):
         """
         self.guardrail_name = guardrail_name
         self.supported_event_hooks = supported_event_hooks
-        self.event_hook: Union[GuardrailEventHooks, list[GuardrailEventHooks], Mode] | None = event_hook
+        self.event_hook: (
+            Union[GuardrailEventHooks, list[GuardrailEventHooks], Mode] | None
+        ) = event_hook
         self.default_on: bool = default_on
         self.mask_request_content: bool = mask_request_content
         self.mask_response_content: bool = mask_response_content
@@ -124,9 +128,7 @@ class CustomGuardrail(CustomLogger):
         self.on_violation: str | None = on_violation
         self.realtime_violation_message: str | None = realtime_violation_message
         self.on_sensitive_data: str | None = on_sensitive_data
-        self.sensitive_data_route_to_model: str | None = (
-            sensitive_data_route_to_model
-        )
+        self.sensitive_data_route_to_model: str | None = sensitive_data_route_to_model
         self.sticky_session_routing: bool = sticky_session_routing
 
         if supported_event_hooks:
diff --git a/litellm/integrations/otel/plumbing/metrics.py b/litellm/integrations/otel/plumbing/metrics.py
index cec17013737..e35237edd25 100644
--- a/litellm/integrations/otel/plumbing/metrics.py
+++ b/litellm/integrations/otel/plumbing/metrics.py
@@ -81,9 +81,7 @@ class GenAIMetricRecorder:
     survives.
     """
 
-    def __init__(
-        self, metrics: GenAIMetrics, callback_name: str | None = None
-    ) -> None:
+    def __init__(self, metrics: GenAIMetrics, callback_name: str | None = None) -> None:
         self._metrics = metrics
         self._callback_name = callback_name
         self._include: frozenset[str] | None = None
diff --git a/litellm/llms/anthropic/chat/transformation.py b/litellm/llms/anthropic/chat/transformation.py
index 124f7654cf4..658dbc27145 100644
--- a/litellm/llms/anthropic/chat/transformation.py
+++ b/litellm/llms/anthropic/chat/transformation.py
@@ -1251,9 +1251,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     def map_response_format_to_anthropic_output_format(
         self, value: dict | None
     ) -> AnthropicOutputSchema | None:
-        json_schema: dict | None = self._extract_json_schema_from_response_format(
-            value
-        )
+        json_schema: dict | None = self._extract_json_schema_from_response_format(value)
         if json_schema is None:
             return None
 
@@ -1287,9 +1285,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
         ):  # value is a no-op
             return None
 
-        json_schema: dict | None = self._extract_json_schema_from_response_format(
-            value
-        )
+        json_schema: dict | None = self._extract_json_schema_from_response_format(value)
         if json_schema is None:
             return None
         """
@@ -2071,16 +2067,15 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
 
         first_json = tool_calls[json_indices[0]]
         json_msg = AnthropicConfig._convert_tool_response_to_message([first_json])
-        extra_content: str | None = (
-            json_msg.content if json_msg is not None else None
-        )
+        extra_content: str | None = json_msg.content if json_msg is not None else None
         filtered_tools = [t for i, t in enumerate(tool_calls) if i not in json_indices]
         return None, filtered_tools, extra_content
 
     def extract_response_content(self, completion_response: dict) -> tuple[
         str,
         list[Any] | None,
-        list[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]] | None,
+        list[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]]
+        | None,
         str | None,
         list[ChatCompletionToolCallChunk],
         list[Any] | None,
@@ -2089,7 +2084,12 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
     ]:
         text_content = ""
         citations: list[Any] | None = None
-        thinking_blocks: list[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]] | None = None
+        thinking_blocks: (
+            list[
+                Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
+            ]
+            | None
+        ) = None
         reasoning_content: str | None = None
         tool_calls: list[ChatCompletionToolCallChunk] = []
         web_search_results: list[Any] | None = None
@@ -2364,7 +2364,12 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
         self,
         completion_response: dict,
         citations: list[Any] | None,
-        thinking_blocks: list[Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]] | None,
+        thinking_blocks: (
+            list[
+                Union[ChatCompletionThinkingBlock, ChatCompletionRedactedThinkingBlock]
+            ]
+            | None
+        ),
         web_search_results: list[Any] | None,
         tool_results: list[Any] | None,
         compaction_blocks: list[Any] | None,
@@ -2606,9 +2611,7 @@ class AnthropicConfig(AnthropicModelInfo, BaseConfig):
 
         """
         ## HANDLE JSON MODE - anthropic returns single function call
-        json_mode_content_str: str | None = tool_calls[0]["function"].get(
-            "arguments"
-        )
+        json_mode_content_str: str | None = tool_calls[0]["function"].get("arguments")
         try:
             if json_mode_content_str is not None:
                 args = json.loads(json_mode_content_str)
diff --git a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
index 8e9cd87b4c1..ba60267fb4d 100644
--- a/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
+++ b/litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py
@@ -252,7 +252,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         if isinstance(response_format, dict):
             return response_format
 
-        if isinstance(response_format, type) and issubclass(response_format, _BaseModel):
+        if isinstance(response_format, type) and issubclass(
+            response_format, _BaseModel
+        ):
             schema = response_format.model_json_schema()
             return {
                 "type": "json_schema",
@@ -285,7 +287,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         return False
 
     @staticmethod
-    def _forward_gemini_function_call_id(model: str, custom_llm_provider: str | None = None) -> bool:
+    def _forward_gemini_function_call_id(
+        model: str, custom_llm_provider: str | None = None
+    ) -> bool:
         """
         Whether to include `id` on function_call / function_response parts.
 
@@ -340,7 +344,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             supported_params.append("thinking")
         return supported_params
 
-    def map_tool_choice_values(self, model: str, tool_choice: Union[str, dict]) -> ToolConfig | None:
+    def map_tool_choice_values(
+        self, model: str, tool_choice: Union[str, dict]
+    ) -> ToolConfig | None:
         if tool_choice == "none":
             return ToolConfig(functionCallingConfig=FunctionCallingConfig(mode="NONE"))
         elif tool_choice == "required":
@@ -350,7 +356,11 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         elif isinstance(tool_choice, dict):
             # only supported for anthropic + mistral models - https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ToolChoice.html
             name = tool_choice.get("function", {}).get("name", "")
-            return ToolConfig(functionCallingConfig=FunctionCallingConfig(mode="ANY", allowed_function_names=[name]))
+            return ToolConfig(
+                functionCallingConfig=FunctionCallingConfig(
+                    mode="ANY", allowed_function_names=[name]
+                )
+            )
         else:
             raise litellm.utils.UnsupportedParamsError(
                 message="VertexAI doesn't support tool_choice={}. Supported tool_choice values=['auto', 'required', json object]. To drop it from the call, set `litellm.drop_params = True.".format(
@@ -398,12 +408,16 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             return
 
         search_tool_keys = cls._search_tool_keys()
-        has_function_declarations = any(isinstance(tool, dict) and tool.get("function_declarations") for tool in tools)
+        has_function_declarations = any(
+            isinstance(tool, dict) and tool.get("function_declarations")
+            for tool in tools
+        )
         if not has_function_declarations:
             return
 
         has_search_tools = any(
-            isinstance(tool, dict) and any(key in tool for key in search_tool_keys) for tool in tools
+            isinstance(tool, dict) and any(key in tool for key in search_tool_keys)
+            for tool in tools
         )
         if not has_search_tools:
             return
@@ -416,7 +430,11 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             "send a request without function calling tools."
         )
         optional_params["tools"] = [
-            tool for tool in tools if not (isinstance(tool, dict) and any(key in tool for key in search_tool_keys))
+            tool
+            for tool in tools
+            if not (
+                isinstance(tool, dict) and any(key in tool for key in search_tool_keys)
+            )
         ]
 
     def _map_service_tier_param(self, value: str, optional_params: dict) -> None:
@@ -460,13 +478,19 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         # Transform excluded_predefined_functions to camelCase
         if "excluded_predefined_functions" in computer_use_config:
-            transformed_config["excludedPredefinedFunctions"] = computer_use_config["excluded_predefined_functions"]
+            transformed_config["excludedPredefinedFunctions"] = computer_use_config[
+                "excluded_predefined_functions"
+            ]
         elif "excludedPredefinedFunctions" in computer_use_config:
-            transformed_config["excludedPredefinedFunctions"] = computer_use_config["excludedPredefinedFunctions"]
+            transformed_config["excludedPredefinedFunctions"] = computer_use_config[
+                "excludedPredefinedFunctions"
+            ]
 
         return transformed_config
 
-    def _extract_google_maps_retrieval_config(self, google_maps_config: dict) -> tuple[dict, dict | None]:
+    def _extract_google_maps_retrieval_config(
+        self, google_maps_config: dict
+    ) -> tuple[dict, dict | None]:
         """
         Extract location configuration from googleMaps tool for Vertex AI toolConfig.
 
@@ -499,7 +523,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         # Remove location fields from tool definition
         cleaned_config = {
-            k: v for k, v in google_maps_config.items() if k not in ["latitude", "longitude", "languageCode"]
+            k: v
+            for k, v in google_maps_config.items()
+            if k not in ["latitude", "longitude", "languageCode"]
         }
 
         return cleaned_config, retrieval_config
@@ -516,7 +542,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             Optional[dict]: The tool value if found, None otherwise
         """
         # Convert camelCase to underscore_case
-        underscore_name = "".join(["_" + c.lower() if c.isupper() else c for c in tool_name]).lstrip("_")
+        underscore_name = "".join(
+            ["_" + c.lower() if c.isupper() else c for c in tool_name]
+        ).lstrip("_")
         # Try both camelCase and underscore_case variants
 
         if tool.get(tool_name) is not None:
@@ -560,8 +588,14 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 urlContext,
             ]
         )
-        server_side_tool_invocations = optional_params.get("include_server_side_tool_invocations", False)
-        if gtool_func_declarations and has_search_tools and not server_side_tool_invocations:
+        server_side_tool_invocations = optional_params.get(
+            "include_server_side_tool_invocations", False
+        )
+        if (
+            gtool_func_declarations
+            and has_search_tools
+            and not server_side_tool_invocations
+        ):
             verbose_logger.warning(
                 "Vertex AI does not support mixing function declarations with "
                 "search tools (googleSearch, enterpriseWebSearch, urlContext, "
@@ -617,7 +651,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     and _openai_function_object["parameters"] is not None
                     and isinstance(_openai_function_object["parameters"], dict)
                 ):  # OPENAI accepts JSON Schema, Google accepts OpenAPI schema.
-                    _openai_function_object["parameters"] = _build_vertex_schema(_openai_function_object["parameters"])
+                    _openai_function_object["parameters"] = _build_vertex_schema(
+                        _openai_function_object["parameters"]
+                    )
 
                 openai_function_object = _openai_function_object
 
@@ -633,43 +669,68 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 "web_search",
                 "web_search_preview",
             ):
-                verbose_logger.info(f"Gemini: Transforming OpenAI-style '{tool['type']}' tool to googleSearch")
+                verbose_logger.info(
+                    f"Gemini: Transforming OpenAI-style '{tool['type']}' tool to googleSearch"
+                )
                 tool = {VertexToolName.GOOGLE_SEARCH.value: {}}
             # Handle tools with 'type' field (OpenAI spec compliance) Ignore this field -> https://github.com/BerriAI/litellm/issues/14644#issuecomment-3342061838
             elif "type" in tool:
                 tool = {k: tool[k] for k in tool if k != "type"}
             tool_name = list(tool.keys())[0] if len(tool.keys()) == 1 else None
             if tool_name and (
-                tool_name == "codeExecution" or tool_name == VertexToolName.CODE_EXECUTION.value
+                tool_name == "codeExecution"
+                or tool_name == VertexToolName.CODE_EXECUTION.value
             ):  # code_execution maintained for backwards compatibility
                 code_execution = self.get_tool_value(tool, "codeExecution")
-            elif tool_name and (tool_name == VertexToolName.GOOGLE_SEARCH.value or tool_name == "google_search"):
+            elif tool_name and (
+                tool_name == VertexToolName.GOOGLE_SEARCH.value
+                or tool_name == "google_search"
+            ):
                 googleSearch = self.get_tool_value(tool, tool_name)
             elif tool_name and (
-                tool_name == VertexToolName.GOOGLE_SEARCH_RETRIEVAL.value or tool_name == "google_search_retrieval"
+                tool_name == VertexToolName.GOOGLE_SEARCH_RETRIEVAL.value
+                or tool_name == "google_search_retrieval"
             ):
                 googleSearchRetrieval = self.get_tool_value(tool, tool_name)
             elif tool_name and (
-                tool_name == VertexToolName.ENTERPRISE_WEB_SEARCH.value or tool_name == "enterprise_web_search"
+                tool_name == VertexToolName.ENTERPRISE_WEB_SEARCH.value
+                or tool_name == "enterprise_web_search"
             ):
                 enterpriseWebSearch = self.get_tool_value(tool, tool_name)
-            elif tool_name and (tool_name == VertexToolName.URL_CONTEXT.value or tool_name == "urlContext"):
+            elif tool_name and (
+                tool_name == VertexToolName.URL_CONTEXT.value
+                or tool_name == "urlContext"
+            ):
                 urlContext = self.get_tool_value(tool, tool_name)
-            elif tool_name and (tool_name == VertexToolName.GOOGLE_MAPS.value or tool_name == "google_maps"):
-                google_maps_value = self.get_tool_value(tool, VertexToolName.GOOGLE_MAPS.value)
+            elif tool_name and (
+                tool_name == VertexToolName.GOOGLE_MAPS.value
+                or tool_name == "google_maps"
+            ):
+                google_maps_value = self.get_tool_value(
+                    tool, VertexToolName.GOOGLE_MAPS.value
+                )
 
                 # Extract and transform location configuration for toolConfig
                 if google_maps_value is not None:
                     (
                         googleMaps,
                         google_maps_retrieval_config,
-                    ) = self._extract_google_maps_retrieval_config(google_maps_config=google_maps_value)
-            elif tool_name and (tool_name == VertexToolName.COMPUTER_USE.value or tool_name == "computer_use"):
-                computer_use_value = self.get_tool_value(tool, VertexToolName.COMPUTER_USE.value)
+                    ) = self._extract_google_maps_retrieval_config(
+                        google_maps_config=google_maps_value
+                    )
+            elif tool_name and (
+                tool_name == VertexToolName.COMPUTER_USE.value
+                or tool_name == "computer_use"
+            ):
+                computer_use_value = self.get_tool_value(
+                    tool, VertexToolName.COMPUTER_USE.value
+                )
 
                 # Transform Computer Use configuration to Gemini API format
                 if computer_use_value is not None:
-                    computerUse = self._transform_computer_use_config(computer_use_config=computer_use_value)
+                    computerUse = self._transform_computer_use_config(
+                        computer_use_config=computer_use_value
+                    )
                 else:
                     # Empty config - Gemini will use defaults
                     computerUse = {}
@@ -725,11 +786,15 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             _tools_list.append(search_tool)
         if googleSearchRetrieval is not None:
             retrieval_tool = Tools()
-            retrieval_tool[VertexToolName.GOOGLE_SEARCH_RETRIEVAL.value] = googleSearchRetrieval
+            retrieval_tool[VertexToolName.GOOGLE_SEARCH_RETRIEVAL.value] = (
+                googleSearchRetrieval
+            )
             _tools_list.append(retrieval_tool)
         if enterpriseWebSearch is not None:
             enterprise_tool = Tools()
-            enterprise_tool[VertexToolName.ENTERPRISE_WEB_SEARCH.value] = enterpriseWebSearch
+            enterprise_tool[VertexToolName.ENTERPRISE_WEB_SEARCH.value] = (
+                enterpriseWebSearch
+            )
             _tools_list.append(enterprise_tool)
         if code_execution is not None:
             code_tool = Tools()
@@ -752,7 +817,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         if google_maps_retrieval_config is not None:
             if "toolConfig" not in optional_params:
                 optional_params["toolConfig"] = {}
-            optional_params["toolConfig"]["retrievalConfig"] = google_maps_retrieval_config
+            optional_params["toolConfig"][
+                "retrievalConfig"
+            ] = google_maps_retrieval_config
 
         return _tools_list
 
@@ -761,13 +828,19 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         if isinstance(old_schema, list):
             for item in old_schema:
                 if isinstance(item, dict):
-                    item = _build_vertex_schema(parameters=item, add_property_ordering=True)
+                    item = _build_vertex_schema(
+                        parameters=item, add_property_ordering=True
+                    )
 
         elif isinstance(old_schema, dict):
-            old_schema = _build_vertex_schema(parameters=old_schema, add_property_ordering=True)
+            old_schema = _build_vertex_schema(
+                parameters=old_schema, add_property_ordering=True
+            )
         return old_schema
 
-    def apply_response_schema_transformation(self, value: dict, optional_params: dict, model: str):
+    def apply_response_schema_transformation(
+        self, value: dict, optional_params: dict, model: str
+    ):
         new_value = deepcopy(value)
         # remove 'strict' from json schema (not supported by Gemini)
         new_value = _remove_strict_from_schema(new_value)
@@ -803,13 +876,17 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 # - Standard JSON Schema format (lowercase types)
                 # - Supports additionalProperties
                 # - No propertyOrdering needed
-                optional_params["response_json_schema"] = _build_json_schema(deepcopy(schema))
+                optional_params["response_json_schema"] = _build_json_schema(
+                    deepcopy(schema)
+                )
             else:
                 # Use responseSchema (default, backwards compatible)
                 # - OpenAPI-style format (uppercase types)
                 # - No additionalProperties support
                 # - Requires propertyOrdering
-                optional_params["response_schema"] = self._map_response_schema(value=schema)
+                optional_params["response_schema"] = self._map_response_schema(
+                    value=schema
+                )
 
     @staticmethod
     def _map_reasoning_effort_to_thinking_budget(
@@ -824,7 +901,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             elif model and "gemini-2.5-pro" in model.lower():
                 budget = DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_PRO
             elif model and "gemini-2.5-flash" in model.lower():
-                budget = DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH
+                budget = (
+                    DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET_GEMINI_2_5_FLASH
+                )
             else:
                 budget = DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET
 
@@ -877,7 +956,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         # Check if this is gemini-3-flash which supports MINIMAL thinking level
         # Covers gemini-3-flash, gemini-3-flash-preview, gemini-3.1-flash, gemini-3.1-flash-lite-preview,
         # gemini-3.5-flash, and any future 3.x-flash variants.
-        is_gemini3flash = model and ("flash" in model.lower() and "gemini-3" in model.lower())
+        is_gemini3flash = model and (
+            "flash" in model.lower() and "gemini-3" in model.lower()
+        )
         is_gemini31pro = model and ("gemini-3.1-pro-preview" in model.lower())
         if reasoning_effort == "minimal":
             if is_gemini3flash:
@@ -971,14 +1052,20 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     params["includeThoughts"] = True
                     # Follow provider defaults unless explicitly opted into legacy behavior.
                     if litellm.enable_gemini_default_thinking_level_low is True:
-                        is_gemini3flash = "gemini-3" in model.lower() and "flash" in model.lower()
-                        params["thinkingLevel"] = "minimal" if is_gemini3flash else "low"
+                        is_gemini3flash = (
+                            "gemini-3" in model.lower() and "flash" in model.lower()
+                        )
+                        params["thinkingLevel"] = (
+                            "minimal" if is_gemini3flash else "low"
+                        )
             else:
                 # Thinking disabled
                 params["includeThoughts"] = False
         else:
             # For older Gemini models, use thinkingBudget
-            if thinking_enabled and not VertexGeminiConfig._is_thinking_budget_zero(thinking_budget):
+            if thinking_enabled and not VertexGeminiConfig._is_thinking_budget_zero(
+                thinking_budget
+            ):
                 params["includeThoughts"] = True
             if thinking_budget is not None and isinstance(thinking_budget, int):
                 params["thinkingBudget"] = thinking_budget
@@ -1085,7 +1172,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         model: str,
         drop_params: bool,
     ) -> dict:
-        self._apply_include_server_side_tool_invocations(non_default_params, optional_params)
+        self._apply_include_server_side_tool_invocations(
+            non_default_params, optional_params
+        )
         gemini_sampling_params_warned: bool = False
         for param, value in non_default_params.items():
             if param == "temperature":
@@ -1106,7 +1195,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                         gemini_sampling_params_warned = True
                 optional_params["temperature"] = value
             elif param == "top_p":
-                if VertexGeminiConfig._is_gemini_3_or_newer(model) and not gemini_sampling_params_warned:
+                if (
+                    VertexGeminiConfig._is_gemini_3_or_newer(model)
+                    and not gemini_sampling_params_warned
+                ):
                     verbose_logger.warning(
                         "DeprecationWarning: `temperature`, `top_p`, and `top_k` continue to "
                         f"function for Gemini 3+ ({model}) but are planned for removal in a "
@@ -1116,7 +1208,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     gemini_sampling_params_warned = True
                 optional_params["top_p"] = value
             elif param == "top_k":
-                if VertexGeminiConfig._is_gemini_3_or_newer(model) and not gemini_sampling_params_warned:
+                if (
+                    VertexGeminiConfig._is_gemini_3_or_newer(model)
+                    and not gemini_sampling_params_warned
+                ):
                     verbose_logger.warning(
                         "DeprecationWarning: `temperature`, `top_p`, and `top_k` continue to "
                         f"function for Gemini 3+ ({model}) but are planned for removal in a "
@@ -1141,7 +1236,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             elif param == "max_tokens" or param == "max_completion_tokens":
                 optional_params["max_output_tokens"] = value
             elif param == "response_format" and isinstance(value, dict):  # type: ignore
-                self.apply_response_schema_transformation(value=value, optional_params=optional_params, model=model)
+                self.apply_response_schema_transformation(
+                    value=value, optional_params=optional_params, model=model
+                )
             elif param == "frequency_penalty":
                 if self._supports_penalty_parameters(model):
                     optional_params["frequency_penalty"] = value
@@ -1152,11 +1249,21 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 optional_params["responseLogprobs"] = value
             elif param == "top_logprobs":
                 optional_params["logprobs"] = value
-            elif (param == "tools" or param == "functions") and isinstance(value, list) and value:
+            elif (
+                (param == "tools" or param == "functions")
+                and isinstance(value, list)
+                and value
+            ):
                 # Pass optional_params so _map_function can add toolConfig if needed
-                mapped_tools = self._map_function(value=value, optional_params=optional_params)
-                optional_params = self._add_tools_to_optional_params(optional_params, mapped_tools)
-            elif param == "tool_choice" and (isinstance(value, str) or isinstance(value, dict)):
+                mapped_tools = self._map_function(
+                    value=value, optional_params=optional_params
+                )
+                optional_params = self._add_tools_to_optional_params(
+                    optional_params, mapped_tools
+                )
+            elif param == "tool_choice" and (
+                isinstance(value, str) or isinstance(value, dict)
+            ):
                 _tool_choice_value = self.map_tool_choice_values(
                     model=model,
                     tool_choice=value,  # type: ignore
@@ -1164,7 +1271,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 if _tool_choice_value is not None:
                     optional_params["tool_choice"] = _tool_choice_value
             elif param == "parallel_tool_calls":
-                tools_list = non_default_params.get("tools", non_default_params.get("functions"))
+                tools_list = non_default_params.get(
+                    "tools", non_default_params.get("functions")
+                )
                 num_tools = len(tools_list) if isinstance(tools_list, list) else 0
                 # Gemini does not support parallel_tool_calls=False with multiple
                 # tools. Drop the param instead of failing — Responses API clients
@@ -1190,12 +1299,16 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                         param_description="thinking_budget",
                     )
                     if VertexGeminiConfig._is_gemini_3_or_newer(model):
-                        optional_params["thinkingConfig"] = VertexGeminiConfig._map_reasoning_effort_to_thinking_level(
-                            effort_value, model
+                        optional_params["thinkingConfig"] = (
+                            VertexGeminiConfig._map_reasoning_effort_to_thinking_level(
+                                effort_value, model
+                            )
                         )
                     else:
-                        optional_params["thinkingConfig"] = VertexGeminiConfig._map_reasoning_effort_to_thinking_budget(
-                            effort_value, model
+                        optional_params["thinkingConfig"] = (
+                            VertexGeminiConfig._map_reasoning_effort_to_thinking_budget(
+                                effort_value, model
+                            )
                         )
             elif param == "thinking":
                 # Validate no conflict with thinking_level
@@ -1204,16 +1317,20 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     param_name="thinking",
                     param_description="thinking_budget",
                 )
-                optional_params["thinkingConfig"] = VertexGeminiConfig._map_thinking_param(
-                    cast(AnthropicThinkingParam, value),
-                    model=model,
+                optional_params["thinkingConfig"] = (
+                    VertexGeminiConfig._map_thinking_param(
+                        cast(AnthropicThinkingParam, value),
+                        model=model,
+                    )
                 )
             elif param == "modalities" and isinstance(value, list):
                 response_modalities = self.map_response_modalities(value)
                 optional_params["responseModalities"] = response_modalities
             elif param == "web_search_options" and isinstance(value, dict):
                 _tools = self._map_web_search_options(value)
-                optional_params = self._add_tools_to_optional_params(optional_params, [_tools])
+                optional_params = self._add_tools_to_optional_params(
+                    optional_params, [_tools]
+                )
             elif param == "service_tier" and isinstance(value, str):
                 self._map_service_tier_param(value, optional_params)
             elif param == "include_server_side_tool_invocations" and value is True:
@@ -1356,7 +1473,11 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         """
         from litellm.litellm_core_utils.core_helpers import _FINISH_REASON_MAP
 
-        return {k: v for k, v in _FINISH_REASON_MAP.items() if k in VertexGeminiConfig._GEMINI_FINISH_REASON_KEYS}
+        return {
+            k: v
+            for k, v in _FINISH_REASON_MAP.items()
+            if k in VertexGeminiConfig._GEMINI_FINISH_REASON_KEYS
+        }
 
     def translate_exception_str(self, exception_string: str):
         if (
@@ -1368,7 +1489,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             )
         return exception_string
 
-    def get_assistant_content_message(self, parts: list[HttpxPartType]) -> tuple[str | None, str | None]:
+    def get_assistant_content_message(
+        self, parts: list[HttpxPartType]
+    ) -> tuple[str | None, str | None]:
         content_str: str | None = None
         reasoning_content_str: str | None = None
 
@@ -1380,7 +1503,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 if text_content.startswith("data:audio") and ";base64," in text_content:
                     try:
                         if is_base64_encoded(text_content):
-                            media_type, _ = text_content.split("data:")[1].split(";base64,")
+                            media_type, _ = text_content.split("data:")[1].split(
+                                ";base64,"
+                            )
                             if media_type.startswith("audio/"):
                                 continue
                     except (ValueError, IndexError):
@@ -1409,7 +1534,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         return content_str, reasoning_content_str
 
-    def _extract_thinking_blocks_from_parts(self, parts: list[HttpxPartType]) -> list[ChatCompletionThinkingBlock]:
+    def _extract_thinking_blocks_from_parts(
+        self, parts: list[HttpxPartType]
+    ) -> list[ChatCompletionThinkingBlock]:
         """Extract thinking blocks from parts if present.
 
         Per Google's docs (https://ai.google.dev/gemini-api/docs/thinking):
@@ -1432,7 +1559,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 thinking_blocks.append(block)
         return thinking_blocks
 
-    def _extract_thought_signatures_from_parts(self, parts: list[HttpxPartType]) -> list[str] | None:
+    def _extract_thought_signatures_from_parts(
+        self, parts: list[HttpxPartType]
+    ) -> list[str] | None:
         """Extract thoughtSignature values from parts.
 
         Per Google's docs, thoughtSignature is returned for multi-turn context preservation
@@ -1510,7 +1639,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         return invocations if invocations else None
 
-    def _extract_image_response_from_parts(self, parts: list[HttpxPartType]) -> list[ImageURLListItem] | None:
+    def _extract_image_response_from_parts(
+        self, parts: list[HttpxPartType]
+    ) -> list[ImageURLListItem] | None:
         """Extract image response from parts if present"""
         images: list[ImageURLListItem] = []
         for part in parts:
@@ -1530,7 +1661,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     )
         return images
 
-    def _extract_audio_response_from_parts(self, parts: list[HttpxPartType]) -> ChatCompletionAudioResponse | None:
+    def _extract_audio_response_from_parts(
+        self, parts: list[HttpxPartType]
+    ) -> ChatCompletionAudioResponse | None:
         """Extract audio response from parts if present"""
         for part in parts:
             if "text" in part:
@@ -1539,7 +1672,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 if text_content.startswith("data:audio") and ";base64," in text_content:
                     try:
                         if is_base64_encoded(text_content):
-                            media_type, audio_data = text_content.split("data:")[1].split(";base64,")
+                            media_type, audio_data = text_content.split("data:")[
+                                1
+                            ].split(";base64,")
 
                             if media_type.startswith("audio/"):
                                 expires_at = int(time.time()) + (24 * 60 * 60)
@@ -1562,7 +1697,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     expires_at = int(time.time()) + (24 * 60 * 60)
                     transcript = ""  # Gemini doesn't provide transcript
 
-                    return ChatCompletionAudioResponse(data=data, expires_at=expires_at, transcript=transcript)
+                    return ChatCompletionAudioResponse(
+                        data=data, expires_at=expires_at, transcript=transcript
+                    )
 
         return None
 
@@ -1582,7 +1719,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             if "functionCall" in part:
                 _function_chunk: ChatCompletionToolCallFunctionChunk = {
                     "name": part["functionCall"]["name"],
-                    "arguments": json.dumps(part["functionCall"]["args"], ensure_ascii=False),
+                    "arguments": json.dumps(
+                        part["functionCall"]["args"], ensure_ascii=False
+                    ),
                 }
                 # Extract thought signature if present
                 thought_signature = part.get("thoughtSignature")
@@ -1596,7 +1735,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     if thought_signature:
                         if "provider_specific_fields" not in function_dict:
                             function_dict["provider_specific_fields"] = {}
-                        function_dict["provider_specific_fields"]["thought_signature"] = thought_signature
+                        function_dict["provider_specific_fields"][
+                            "thought_signature"
+                        ] = thought_signature
                     function = cast(ChatCompletionToolCallFunctionChunk, function_dict)
                 else:
                     _tool_response_chunk: ChatCompletionToolCallChunk = {
@@ -1615,8 +1756,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                         _tool_response_chunk["provider_specific_fields"] = {  # type: ignore
                             "thought_signature": thought_signature
                         }
-                        _tool_response_chunk["id"] = _encode_tool_call_id_with_signature(
-                            _tool_response_chunk["id"] or "", thought_signature
+                        _tool_response_chunk["id"] = (
+                            _encode_tool_call_id_with_signature(
+                                _tool_response_chunk["id"] or "", thought_signature
+                            )
                         )
                     _tools.append(_tool_response_chunk)
                 cumulative_tool_call_idx += 1
@@ -1637,11 +1780,19 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         logprobs_list: list[ChatCompletionTokenLogprob] = []
         for index, candidate in enumerate(logprobs_result["chosenCandidates"]):
             top_logprobs: list[TopLogprob] = []
-            if "topCandidates" in logprobs_result and index < len(logprobs_result["topCandidates"]):
-                top_candidates_for_index = logprobs_result["topCandidates"][index]["candidates"]
+            if "topCandidates" in logprobs_result and index < len(
+                logprobs_result["topCandidates"]
+            ):
+                top_candidates_for_index = logprobs_result["topCandidates"][index][
+                    "candidates"
+                ]
 
                 for options in top_candidates_for_index:
-                    top_logprobs.append(TopLogprob(token=options["token"], logprob=options["logProbability"]))
+                    top_logprobs.append(
+                        TopLogprob(
+                            token=options["token"], logprob=options["logProbability"]
+                        )
+                    )
             logprobs_list.append(
                 ChatCompletionTokenLogprob(
                     token=candidate["token"],
@@ -1676,8 +1827,12 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         ## GET USAGE ##
         usage = Usage(
-            prompt_tokens=completion_response["usageMetadata"].get("promptTokenCount", 0),
-            completion_tokens=completion_response["usageMetadata"].get("candidatesTokenCount", 0),
+            prompt_tokens=completion_response["usageMetadata"].get(
+                "promptTokenCount", 0
+            ),
+            completion_tokens=completion_response["usageMetadata"].get(
+                "candidatesTokenCount", 0
+            ),
             total_tokens=completion_response["usageMetadata"].get("totalTokenCount", 0),
         )
 
@@ -1710,8 +1865,12 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         ## GET USAGE ##
         usage = Usage(
-            prompt_tokens=completion_response["usageMetadata"].get("promptTokenCount", 0),
-            completion_tokens=completion_response["usageMetadata"].get("candidatesTokenCount", 0),
+            prompt_tokens=completion_response["usageMetadata"].get(
+                "promptTokenCount", 0
+            ),
+            completion_tokens=completion_response["usageMetadata"].get(
+                "candidatesTokenCount", 0
+            ),
             total_tokens=completion_response["usageMetadata"].get("totalTokenCount", 0),
         )
 
@@ -1739,10 +1898,17 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
     @staticmethod
     def _calculate_usage(
-        completion_response: Union[GenerateContentResponseBody, BidiGenerateContentServerMessage],
+        completion_response: Union[
+            GenerateContentResponseBody, BidiGenerateContentServerMessage
+        ],
     ) -> Usage:
-        if completion_response is not None and "usageMetadata" not in completion_response:
-            raise ValueError(f"usageMetadata not found in completion_response. Got={completion_response}")
+        if (
+            completion_response is not None
+            and "usageMetadata" not in completion_response
+        ):
+            raise ValueError(
+                f"usageMetadata not found in completion_response. Got={completion_response}"
+            )
         cached_tokens: int | None = None
         # Separate variables for prompt tokens by modality
         prompt_audio_tokens: int | None = None
@@ -1771,11 +1937,17 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 modality = str(detail.get("modality", "")).upper()
                 token_count = _get_token_count(detail)
                 if modality == "TEXT":
-                    response_tokens_details.text_tokens = (response_tokens_details.text_tokens or 0) + token_count
+                    response_tokens_details.text_tokens = (
+                        response_tokens_details.text_tokens or 0
+                    ) + token_count
                 elif modality == "AUDIO":
-                    response_tokens_details.audio_tokens = (response_tokens_details.audio_tokens or 0) + token_count
+                    response_tokens_details.audio_tokens = (
+                        response_tokens_details.audio_tokens or 0
+                    ) + token_count
                 elif modality == "DOCUMENT":
-                    response_tokens_details.text_tokens = (response_tokens_details.text_tokens or 0) + token_count
+                    response_tokens_details.text_tokens = (
+                        response_tokens_details.text_tokens or 0
+                    ) + token_count
 
         #########################################################
 
@@ -1787,15 +1959,25 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 modality = str(detail.get("modality", "")).upper()
                 token_count = _get_token_count(detail)
                 if modality == "TEXT":
-                    response_tokens_details.text_tokens = (response_tokens_details.text_tokens or 0) + token_count
+                    response_tokens_details.text_tokens = (
+                        response_tokens_details.text_tokens or 0
+                    ) + token_count
                 elif modality == "AUDIO":
-                    response_tokens_details.audio_tokens = (response_tokens_details.audio_tokens or 0) + token_count
+                    response_tokens_details.audio_tokens = (
+                        response_tokens_details.audio_tokens or 0
+                    ) + token_count
                 elif modality == "IMAGE":
-                    response_tokens_details.image_tokens = (response_tokens_details.image_tokens or 0) + token_count
+                    response_tokens_details.image_tokens = (
+                        response_tokens_details.image_tokens or 0
+                    ) + token_count
                 elif modality == "VIDEO":
-                    response_tokens_details.video_tokens = (response_tokens_details.video_tokens or 0) + token_count
+                    response_tokens_details.video_tokens = (
+                        response_tokens_details.video_tokens or 0
+                    ) + token_count
                 elif modality == "DOCUMENT":
-                    response_tokens_details.text_tokens = (response_tokens_details.text_tokens or 0) + token_count
+                    response_tokens_details.text_tokens = (
+                        response_tokens_details.text_tokens or 0
+                    ) + token_count
 
         # Calculate text_tokens if not explicitly provided in candidatesTokensDetails
         # candidatesTokenCount includes all modalities, so: text = total - (image + audio + video)
@@ -1808,7 +1990,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 completion_audio_tokens = response_tokens_details.audio_tokens or 0
                 completion_video_tokens = response_tokens_details.video_tokens or 0
                 calculated_text_tokens = (
-                    candidates_token_count - completion_image_tokens - completion_audio_tokens - completion_video_tokens
+                    candidates_token_count
+                    - completion_image_tokens
+                    - completion_audio_tokens
+                    - completion_video_tokens
                 )
                 response_tokens_details.text_tokens = calculated_text_tokens
         #########################################################
@@ -1889,8 +2074,13 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             video_tokens=prompt_video_tokens,
         )
 
-        completion_tokens = response_tokens or completion_response["usageMetadata"].get("candidatesTokenCount", 0)
-        if not VertexGeminiConfig.is_candidate_token_count_inclusive(usage_metadata) and reasoning_tokens:
+        completion_tokens = response_tokens or completion_response["usageMetadata"].get(
+            "candidatesTokenCount", 0
+        )
+        if (
+            not VertexGeminiConfig.is_candidate_token_count_inclusive(usage_metadata)
+            and reasoning_tokens
+        ):
             completion_tokens = reasoning_tokens + completion_tokens
         ## GET USAGE ##
         usage = Usage(
@@ -1971,7 +2161,11 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
     def _calculate_web_search_requests(grounding_metadata: list[dict]) -> int | None:
         web_search_requests: int | None = None
 
-        if grounding_metadata and isinstance(grounding_metadata, list) and len(grounding_metadata) > 0:
+        if (
+            grounding_metadata
+            and isinstance(grounding_metadata, list)
+            and len(grounding_metadata) > 0
+        ):
             for grounding_metadata_item in grounding_metadata:
                 web_search_queries = grounding_metadata_item.get("webSearchQueries")
                 if web_search_queries and web_search_requests:
@@ -2085,10 +2279,14 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
     ) -> None:
         setattr(model_response, "vertex_ai_grounding_metadata", grounding_metadata)  # type: ignore
         if grounding_metadata:
-            model_response._hidden_params["vertex_ai_grounding_metadata"] = grounding_metadata
+            model_response._hidden_params["vertex_ai_grounding_metadata"] = (
+                grounding_metadata
+            )
         setattr(model_response, "vertex_ai_url_context_metadata", url_context_metadata)  # type: ignore
         if url_context_metadata:
-            model_response._hidden_params["vertex_ai_url_context_metadata"] = url_context_metadata
+            model_response._hidden_params["vertex_ai_url_context_metadata"] = (
+                url_context_metadata
+            )
         setattr(model_response, "vertex_ai_safety_ratings", safety_ratings)  # type: ignore
         setattr(model_response, "vertex_ai_safety_results", safety_ratings)  # type: ignore
         if safety_ratings:
@@ -2096,7 +2294,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             model_response._hidden_params["vertex_ai_safety_results"] = safety_ratings
         setattr(model_response, "vertex_ai_citation_metadata", citation_metadata)  # type: ignore
         if citation_metadata:
-            model_response._hidden_params["vertex_ai_citation_metadata"] = citation_metadata
+            model_response._hidden_params["vertex_ai_citation_metadata"] = (
+                citation_metadata
+            )
 
     def apply_assembled_streaming_response_metadata(
         self,
@@ -2229,35 +2429,51 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                 (
                     content,
                     reasoning_content,
-                ) = VertexGeminiConfig().get_assistant_content_message(parts=candidate["content"]["parts"])
-
-                audio_response = VertexGeminiConfig()._extract_audio_response_from_parts(
-                    parts=candidate["content"]["parts"]
-                )
-                image_response = VertexGeminiConfig()._extract_image_response_from_parts(
+                ) = VertexGeminiConfig().get_assistant_content_message(
                     parts=candidate["content"]["parts"]
                 )
 
-                thinking_blocks = VertexGeminiConfig()._extract_thinking_blocks_from_parts(
-                    parts=candidate["content"]["parts"]
+                audio_response = (
+                    VertexGeminiConfig()._extract_audio_response_from_parts(
+                        parts=candidate["content"]["parts"]
+                    )
+                )
+                image_response = (
+                    VertexGeminiConfig()._extract_image_response_from_parts(
+                        parts=candidate["content"]["parts"]
+                    )
+                )
+
+                thinking_blocks = (
+                    VertexGeminiConfig()._extract_thinking_blocks_from_parts(
+                        parts=candidate["content"]["parts"]
+                    )
                 )
 
                 # Extract thoughtSignatures from parts (can exist without thought: true)
-                thought_signatures = VertexGeminiConfig()._extract_thought_signatures_from_parts(
-                    parts=candidate["content"]["parts"]
+                thought_signatures = (
+                    VertexGeminiConfig()._extract_thought_signatures_from_parts(
+                        parts=candidate["content"]["parts"]
+                    )
                 )
 
                 # Extract server-side tool invocations (context circulation)
-                server_side_tool_invocations = VertexGeminiConfig._extract_server_side_tool_invocations(
-                    parts=candidate["content"]["parts"]
+                server_side_tool_invocations = (
+                    VertexGeminiConfig._extract_server_side_tool_invocations(
+                        parts=candidate["content"]["parts"]
+                    )
                 )
 
                 if audio_response is not None:
-                    cast(dict[str, Any], chat_completion_message)["audio"] = audio_response
+                    cast(dict[str, Any], chat_completion_message)[
+                        "audio"
+                    ] = audio_response
                     chat_completion_message["content"] = None  # OpenAI spec
                 if image_response is not None:
                     # Handle image response - combine with text content into structured format
-                    cast(dict[str, Any], chat_completion_message)["images"] = image_response
+                    cast(dict[str, Any], chat_completion_message)[
+                        "images"
+                    ] = image_response
                 if content is not None:
                     chat_completion_message["content"] = content
 
@@ -2265,9 +2481,11 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     chat_completion_message["reasoning_content"] = reasoning_content
 
                 if candidate_grounding_metadata:
-                    annotations = VertexGeminiConfig._convert_grounding_metadata_to_annotations(
-                        grounding_metadata=candidate_grounding_metadata,
-                        content_text=content,
+                    annotations = (
+                        VertexGeminiConfig._convert_grounding_metadata_to_annotations(
+                            grounding_metadata=candidate_grounding_metadata,
+                            content_text=content,
+                        )
                     )
                     if annotations:
                         chat_completion_message["annotations"] = annotations  # type: ignore
@@ -2297,7 +2515,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
                 # Convert thinking_blocks to reasoning_content for streaming
                 # This ensures reasoning_content is available in streaming responses
-                if isinstance(model_response, ModelResponseStream) and reasoning_content is None:
+                if (
+                    isinstance(model_response, ModelResponseStream)
+                    and reasoning_content is None
+                ):
                     reasoning_content_parts = []
                     for block in thinking_blocks:
                         thinking_text = block.get("thinking")
@@ -2318,9 +2539,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             if server_side_tool_invocations is not None:
                 if "provider_specific_fields" not in chat_completion_message:
                     chat_completion_message["provider_specific_fields"] = {}
-                chat_completion_message["provider_specific_fields"]["server_side_tool_invocations"] = (
-                    server_side_tool_invocations  # type: ignore
-                )
+                chat_completion_message["provider_specific_fields"][
+                    "server_side_tool_invocations"
+                ] = server_side_tool_invocations  # type: ignore
 
             if isinstance(model_response, ModelResponseStream):
                 choice = VertexGeminiConfig._create_streaming_choice(
@@ -2413,7 +2634,10 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         model_response.model = model
 
         ## CHECK IF RESPONSE FLAGGED
-        if "promptFeedback" in completion_response and "blockReason" in completion_response["promptFeedback"]:
+        if (
+            "promptFeedback" in completion_response
+            and "blockReason" in completion_response["promptFeedback"]
+        ):
             return self._handle_blocked_response(
                 model_response=model_response,
                 completion_response=completion_response,
@@ -2421,8 +2645,13 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
 
         _candidates = completion_response.get("candidates")
         if _candidates and len(_candidates) > 0:
-            content_policy_violations = VertexGeminiConfig().get_flagged_finish_reasons()
-            if "finishReason" in _candidates[0] and _candidates[0]["finishReason"] in content_policy_violations.keys():
+            content_policy_violations = (
+                VertexGeminiConfig().get_flagged_finish_reasons()
+            )
+            if (
+                "finishReason" in _candidates[0]
+                and _candidates[0]["finishReason"] in content_policy_violations.keys()
+            ):
                 return self._handle_content_policy_violation(
                     model_response=model_response,
                     completion_response=completion_response,
@@ -2444,24 +2673,38 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
                     safety_ratings,
                     citation_metadata,
                     _,  # cumulative_tool_call_index not needed in non-streaming
-                ) = VertexGeminiConfig._process_candidates(_candidates, model_response, logging_obj.optional_params)
+                ) = VertexGeminiConfig._process_candidates(
+                    _candidates, model_response, logging_obj.optional_params
+                )
 
-            usage = VertexGeminiConfig._calculate_usage(completion_response=completion_response)
+            usage = VertexGeminiConfig._calculate_usage(
+                completion_response=completion_response
+            )
 
-            web_search_requests = VertexGeminiConfig._calculate_web_search_requests(grounding_metadata)
+            web_search_requests = VertexGeminiConfig._calculate_web_search_requests(
+                grounding_metadata
+            )
             if web_search_requests is not None:
-                cast(PromptTokensDetailsWrapper, usage.prompt_tokens_details).web_search_requests = web_search_requests
+                cast(
+                    PromptTokensDetailsWrapper, usage.prompt_tokens_details
+                ).web_search_requests = web_search_requests
 
             setattr(model_response, "usage", usage)
 
             ## ADD METADATA TO RESPONSE ##
 
             setattr(model_response, "vertex_ai_grounding_metadata", grounding_metadata)
-            model_response._hidden_params["vertex_ai_grounding_metadata"] = grounding_metadata
+            model_response._hidden_params["vertex_ai_grounding_metadata"] = (
+                grounding_metadata
+            )
 
-            setattr(model_response, "vertex_ai_url_context_metadata", url_context_metadata)
+            setattr(
+                model_response, "vertex_ai_url_context_metadata", url_context_metadata
+            )
 
-            model_response._hidden_params["vertex_ai_url_context_metadata"] = url_context_metadata
+            model_response._hidden_params["vertex_ai_url_context_metadata"] = (
+                url_context_metadata
+            )
 
             setattr(model_response, "vertex_ai_safety_results", safety_ratings)
             model_response._hidden_params["vertex_ai_safety_results"] = (
@@ -2475,9 +2718,13 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
             )
 
             ## ADD TRAFFIC TYPE ##
-            traffic_type = completion_response.get("usageMetadata", {}).get("trafficType")
+            traffic_type = completion_response.get("usageMetadata", {}).get(
+                "trafficType"
+            )
             if traffic_type:
-                model_response._hidden_params.setdefault("provider_specific_fields", {})["traffic_type"] = traffic_type
+                model_response._hidden_params.setdefault(
+                    "provider_specific_fields", {}
+                )["traffic_type"] = traffic_type
 
             ## ADD SERVICE TIER ##
             if getattr(raw_response, "headers", None):
@@ -2514,7 +2761,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
     def get_error_class(
         self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers]
     ) -> BaseLLMException:
-        return VertexAIError(message=error_message, status_code=status_code, headers=headers)
+        return VertexAIError(
+            message=error_message, status_code=status_code, headers=headers
+        )
 
     def transform_request(
         self,
@@ -2524,7 +2773,9 @@ class VertexGeminiConfig(VertexAIBaseConfig, BaseConfig):
         litellm_params: dict,
         headers: dict,
     ) -> dict:
-        raise NotImplementedError("Vertex AI has a custom implementation of transform_request. Needs sync + async.")
+        raise NotImplementedError(
+            "Vertex AI has a custom implementation of transform_request. Needs sync + async."
+        )
 
     def validate_environment(
         self,
@@ -2567,7 +2818,9 @@ async def make_call(
         )
 
     try:
-        response = await client.post(api_base, headers=headers, data=data, stream=True, logging_obj=logging_obj)
+        response = await client.post(
+            api_base, headers=headers, data=data, stream=True, logging_obj=logging_obj
+        )
         response.raise_for_status()
     except httpx.HTTPStatusError as e:
         exception_string = str(await e.response.aread())
@@ -2616,7 +2869,9 @@ def make_sync_call(
     if client is None:
         client = HTTPHandler()  # Create a new client if none provided
 
-    response = client.post(api_base, headers=headers, data=data, stream=True, logging_obj=logging_obj)
+    response = client.post(
+        api_base, headers=headers, data=data, stream=True, logging_obj=logging_obj
+    )
 
     if response.status_code != 200 and response.status_code != 201:
         raise VertexAIError(
@@ -2673,7 +2928,9 @@ class VertexLLM(VertexBase):
         gemini_api_key: str | None = None,
         extra_headers: dict | None = None,
     ) -> CustomStreamWrapper:
-        should_use_v1beta1_features = self.is_using_v1beta1_features(optional_params=optional_params)
+        should_use_v1beta1_features = self.is_using_v1beta1_features(
+            optional_params=optional_params
+        )
 
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
@@ -2730,7 +2987,11 @@ class VertexLLM(VertexBase):
             completion_stream=None,
             make_call=partial(
                 make_call,
-                gemini_client=(client if client is not None and isinstance(client, AsyncHTTPHandler) else None),
+                gemini_client=(
+                    client
+                    if client is not None and isinstance(client, AsyncHTTPHandler)
+                    else None
+                ),
                 api_base=api_base,
                 headers=headers,
                 data=request_body_str,
@@ -2769,7 +3030,9 @@ class VertexLLM(VertexBase):
         gemini_api_key: str | None = None,
         extra_headers: dict | None = None,
     ) -> Union[ModelResponse, CustomStreamWrapper]:
-        should_use_v1beta1_features = self.is_using_v1beta1_features(optional_params=optional_params)
+        should_use_v1beta1_features = self.is_using_v1beta1_features(
+            optional_params=optional_params
+        )
 
         _auth_header, vertex_project = await self._ensure_access_token_async(
             credentials=vertex_credentials,
@@ -2814,7 +3077,9 @@ class VertexLLM(VertexBase):
         if timeout:
             _async_client_params["timeout"] = timeout
         if client is None or not isinstance(client, AsyncHTTPHandler):
-            client = get_async_httpx_client(params=_async_client_params, llm_provider=litellm.LlmProviders.VERTEX_AI)
+            client = get_async_httpx_client(
+                params=_async_client_params, llm_provider=litellm.LlmProviders.VERTEX_AI
+            )
         else:
             client = client  # type: ignore
         ## LOGGING
@@ -2953,7 +3218,9 @@ class VertexLLM(VertexBase):
                 extra_headers=extra_headers,
             )
 
-        should_use_v1beta1_features = self.is_using_v1beta1_features(optional_params=optional_params)
+        should_use_v1beta1_features = self.is_using_v1beta1_features(
+            optional_params=optional_params
+        )
 
         _auth_header, vertex_project = self._ensure_access_token(
             credentials=vertex_credentials,
@@ -3012,7 +3279,11 @@ class VertexLLM(VertexBase):
                 completion_stream=None,
                 make_call=partial(
                     make_sync_call,
-                    gemini_client=(client if client is not None and isinstance(client, HTTPHandler) else None),
+                    gemini_client=(
+                        client
+                        if client is not None and isinstance(client, HTTPHandler)
+                        else None
+                    ),
                     api_base=url,
                     data=request_data_str,
                     model=model,
@@ -3142,7 +3413,11 @@ class ModelResponseIterator:
         # to correctly set finish_reason="tool_calls" per the OpenAI spec.
         if not self.has_seen_tool_calls:
             for choice in model_response.choices:
-                if hasattr(choice, "delta") and choice.delta and choice.delta.tool_calls:
+                if (
+                    hasattr(choice, "delta")
+                    and choice.delta
+                    and choice.delta.tool_calls
+                ):
                     self.has_seen_tool_calls = True
                     break
 
@@ -3162,7 +3437,9 @@ class ModelResponseIterator:
                     if self.has_seen_tool_calls:
                         mapped_finish_reason = "tool_calls"
                     else:
-                        mapped_finish_reason = VertexGeminiConfig._check_finish_reason(None, finish_reason_str)
+                        mapped_finish_reason = VertexGeminiConfig._check_finish_reason(
+                            None, finish_reason_str
+                        )
                 choice = StreamingChoices(
                     finish_reason=mapped_finish_reason,
                     index=candidate.get("index", 0),
@@ -3210,13 +3487,19 @@ class ModelResponseIterator:
             completion_response=processed_chunk,
         )
 
-        web_search_requests = VertexGeminiConfig._calculate_web_search_requests(grounding_metadata)
+        web_search_requests = VertexGeminiConfig._calculate_web_search_requests(
+            grounding_metadata
+        )
         if web_search_requests is not None:
-            cast(PromptTokensDetailsWrapper, usage.prompt_tokens_details).web_search_requests = web_search_requests
+            cast(
+                PromptTokensDetailsWrapper, usage.prompt_tokens_details
+            ).web_search_requests = web_search_requests
 
         traffic_type = processed_chunk.get("usageMetadata", {}).get("trafficType")
         if traffic_type:
-            model_response._hidden_params.setdefault("provider_specific_fields", {})["traffic_type"] = traffic_type
+            model_response._hidden_params.setdefault("provider_specific_fields", {})[
+                "traffic_type"
+            ] = traffic_type
 
         service_tier = self.response_headers.get("x-gemini-service-tier")
         if service_tier:
@@ -3263,7 +3546,9 @@ class ModelResponseIterator:
                     citation_metadata,
                 ) = self._apply_stream_candidates(_candidates, model_response)
 
-            usage = self._apply_stream_usage_metadata(processed_chunk, model_response, grounding_metadata)
+            usage = self._apply_stream_usage_metadata(
+                processed_chunk, model_response, grounding_metadata
+            )
 
             setattr(model_response, "usage", usage)  # type: ignore
 
@@ -3295,7 +3580,9 @@ class ModelResponseIterator:
 
         return self.chunk_parser(chunk=json_chunk)
 
-    def handle_accumulated_json_chunk(self, chunk: str) -> Optional["ModelResponseStream"]:
+    def handle_accumulated_json_chunk(
+        self, chunk: str
+    ) -> Optional["ModelResponseStream"]:
         chunk = litellm.CustomStreamWrapper._strip_sse_data_from_chunk(chunk) or ""
         message = chunk.replace("\n\n", "")
 
@@ -3311,7 +3598,9 @@ class ModelResponseIterator:
             # If it's not valid JSON yet, continue to the next event
             return None
 
-    def _common_chunk_parsing_logic(self, chunk: str) -> Optional["ModelResponseStream"]:
+    def _common_chunk_parsing_logic(
+        self, chunk: str
+    ) -> Optional["ModelResponseStream"]:
         try:
             chunk = litellm.CustomStreamWrapper._strip_sse_data_from_chunk(chunk) or ""
             if len(chunk) > 0:
@@ -3381,12 +3670,16 @@ class ModelResponseIterator:
             try:
                 await iterator.aclose()  # any-ok: untyped stream
             except Exception as e:  # noqa: BLE001
-                verbose_logger.debug("ModelResponseIterator.aclose: error closing iterator: %s", e)
+                verbose_logger.debug(
+                    "ModelResponseIterator.aclose: error closing iterator: %s", e
+                )
         if self.response is not None:
             try:
                 await self.response.aclose()
             except Exception as e:  # noqa: BLE001
-                verbose_logger.debug("ModelResponseIterator.aclose: error closing response: %s", e)
+                verbose_logger.debug(
+                    "ModelResponseIterator.aclose: error closing response: %s", e
+                )
 
     def close(self) -> None:
         iterator = getattr(  # any-ok: untyped stream
@@ -3401,9 +3694,13 @@ class ModelResponseIterator:
             try:
                 iterator.close()  # any-ok: untyped stream
             except Exception as e:  # noqa: BLE001
-                verbose_logger.debug("ModelResponseIterator.close: error closing iterator: %s", e)
+                verbose_logger.debug(
+                    "ModelResponseIterator.close: error closing iterator: %s", e
+                )
         if self.response is not None:
             try:
                 self.response.close()
             except Exception as e:  # noqa: BLE001
-                verbose_logger.debug("ModelResponseIterator.close: error closing response: %s", e)
+                verbose_logger.debug(
+                    "ModelResponseIterator.close: error closing response: %s", e
+                )
diff --git a/litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py b/litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py
index d40124b9921..e20dd831861 100644
--- a/litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py
+++ b/litellm/proxy/guardrails/guardrail_hooks/deepkeep/deepkeep.py
@@ -73,7 +73,7 @@ class DeepKeepGuardrail(CustomGuardrail):
         firewall_id: str | None = None,
         unreachable_fallback: Literal["fail_closed", "fail_open"] = "fail_closed",
         extra_headers: dict[str, str] | None = None,
-        **kwargs,
+        **kwargs: Any,
     ):
         self.async_handler = get_async_httpx_client(
             llm_provider=httpxSpecialProvider.GuardrailCallback