litellm-enterprise 0.1.12__tar.gz → 0.1.28__tar.gz

{litellm_enterprise-0.1.12 → litellm_enterprise-0.1.28}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.1
 Name: litellm-enterprise
-Version: 0.1.12
+Version: 0.1.28
 Summary: Package for LiteLLM Enterprise features
 Author: BerriAI
 Requires-Python: >=3.8, !=2.7.*, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*, !=3.5.*, !=3.6.*, !=3.7.*
@@ -9,7 +9,6 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
 Project-URL: Documentation, https://docs.litellm.ai
 Project-URL: Homepage, https://litellm.ai
 Project-URL: Repository, https://github.com/BerriAI/litellm

{litellm_enterprise-0.1.12 → litellm_enterprise-0.1.28}/litellm_enterprise/enterprise_callbacks/callback_controls.py

@@ -1,3 +1,5 @@
+from typing import List, Optional
+
 import litellm
 from litellm._logging import verbose_logger
 from litellm.constants import X_LITELLM_DISABLE_CALLBACKS
@@ -6,15 +8,18 @@ from litellm.litellm_core_utils.llm_request_utils import (
     get_proxy_server_request_headers,
 )
 from litellm.proxy._types import CommonProxyErrors
+from litellm.types.utils import StandardCallbackDynamicParams
 
 
 class EnterpriseCallbackControls:
     @staticmethod
-    def is_callback_disabled_via_headers(
-            callback: litellm.CALLBACK_TYPES, litellm_params: dict
+    def is_callback_disabled_dynamically(
+            callback: litellm.CALLBACK_TYPES, 
+            litellm_params: dict,
+            standard_callback_dynamic_params: StandardCallbackDynamicParams
         ) -> bool:
             """
-            Check if a callback is disabled via the x-litellm-disable-callbacks header.
+            Check if a callback is disabled via the x-litellm-disable-callbacks header or via `litellm_disabled_callbacks` in standard_callback_dynamic_params.
             
             Args:
                 callback: The callback to check (can be string, CustomLogger instance, or callable)
@@ -28,18 +33,16 @@ class EnterpriseCallbackControls:
             )
 
             try:
-                request_headers = get_proxy_server_request_headers(litellm_params)
-                disabled_callbacks = request_headers.get(X_LITELLM_DISABLE_CALLBACKS, None)
+                disabled_callbacks = EnterpriseCallbackControls.get_disabled_callbacks(litellm_params, standard_callback_dynamic_params)
                 verbose_logger.debug(f"Dynamically disabled callbacks from {X_LITELLM_DISABLE_CALLBACKS}: {disabled_callbacks}")
                 verbose_logger.debug(f"Checking if {callback} is disabled via headers. Disable callbacks from headers: {disabled_callbacks}")
                 if disabled_callbacks is not None:
                     #########################################################
                     # premium user check
                     #########################################################
-                    if not EnterpriseCallbackControls._premium_user_check():
+                    if not EnterpriseCallbackControls._should_allow_dynamic_callback_disabling():
                         return False
                     #########################################################
-                    disabled_callbacks = set([cb.strip().lower() for cb in disabled_callbacks.split(",")])
                     if isinstance(callback, str):
                         if callback.lower() in disabled_callbacks:
                             verbose_logger.debug(f"Not logging to {callback} because it is disabled via {X_LITELLM_DISABLE_CALLBACKS}")
@@ -56,10 +59,40 @@ class EnterpriseCallbackControls:
                     f"Error checking disabled callbacks header: {str(e)}"
                 )
                 return False
+    @staticmethod
+    def get_disabled_callbacks(litellm_params: dict, standard_callback_dynamic_params: StandardCallbackDynamicParams) -> Optional[List[str]]:
+        """
+        Get the disabled callbacks from the standard callback dynamic params.
+        """
+
+        #########################################################
+        # check if disabled via headers
+        #########################################################
+        request_headers = get_proxy_server_request_headers(litellm_params)
+        disabled_callbacks = request_headers.get(X_LITELLM_DISABLE_CALLBACKS, None)
+        if disabled_callbacks is not None:
+            disabled_callbacks = set([cb.strip().lower() for cb in disabled_callbacks.split(",")])
+            return list(disabled_callbacks)
+        
+
+        #########################################################
+        # check if disabled via request body
+        #########################################################
+        if standard_callback_dynamic_params.get("litellm_disabled_callbacks", None) is not None:
+            return standard_callback_dynamic_params.get("litellm_disabled_callbacks", None)
+        
+        return None
     
     @staticmethod
-    def _premium_user_check():
+    def _should_allow_dynamic_callback_disabling():
+        import litellm
         from litellm.proxy.proxy_server import premium_user
+
+        # Check if admin has disabled this feature
+        if litellm.allow_dynamic_callback_disabling is not True:
+            verbose_logger.debug("Dynamic callback disabling is disabled by admin via litellm.allow_dynamic_callback_disabling")
+            return False
+        
         if premium_user:
             return True
         verbose_logger.warning(f"Disabling callbacks using request headers is an enterprise feature. {CommonProxyErrors.not_premium_user.value}")

{litellm_enterprise-0.1.12 → litellm_enterprise-0.1.28}/litellm_enterprise/enterprise_callbacks/llama_guard.py

@@ -23,9 +23,7 @@ import litellm
 from litellm._logging import verbose_proxy_logger
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.proxy._types import UserAPIKeyAuth
-from litellm.types.utils import Choices, ModelResponse
-
-litellm.set_verbose = True
+from litellm.types.utils import CallTypesLiteral, Choices, ModelResponse
 
 
 class _ENTERPRISE_LlamaGuard(CustomLogger):
@@ -100,14 +98,7 @@ class _ENTERPRISE_LlamaGuard(CustomLogger):
         self,
         data: dict,
         user_api_key_dict: UserAPIKeyAuth,
-        call_type: Literal[
-            "completion",
-            "embeddings",
-            "image_generation",
-            "moderation",
-            "audio_transcription",
-            "responses",
-        ],
+        call_type: CallTypesLiteral,
     ):
         """
         - Calls the Llama Guard Endpoint

{litellm_enterprise-0.1.12 → litellm_enterprise-0.1.28}/litellm_enterprise/enterprise_callbacks/llm_guard.py

@@ -17,10 +17,9 @@ from litellm._logging import verbose_proxy_logger
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.proxy._types import UserAPIKeyAuth
 from litellm.secret_managers.main import get_secret_str
+from litellm.types.utils import CallTypesLiteral
 from litellm.utils import get_formatted_prompt
 
-litellm.set_verbose = True
-
 
 class _ENTERPRISE_LLMGuard(CustomLogger):
     # Class variables or attributes
@@ -65,7 +64,7 @@ class _ENTERPRISE_LLMGuard(CustomLogger):
                         analyze_url, json=analyze_payload
                     ) as response:
                         redacted_text = await response.json()
-                verbose_proxy_logger.info(
+                verbose_proxy_logger.debug(
                     f"LLM Guard: Received response - {redacted_text}"
                 )
                 if redacted_text is not None:
@@ -122,14 +121,7 @@ class _ENTERPRISE_LLMGuard(CustomLogger):
         self,
         data: dict,
         user_api_key_dict: UserAPIKeyAuth,
-        call_type: Literal[
-            "completion",
-            "embeddings",
-            "image_generation",
-            "moderation",
-            "audio_transcription",
-            "responses",
-        ],
+        call_type: CallTypesLiteral,
     ):
         """
         - Calls the LLM Guard Endpoint

{litellm_enterprise-0.1.12 → litellm_enterprise-0.1.28}/litellm_enterprise/enterprise_callbacks/pagerduty/pagerduty.py

@@ -31,6 +31,7 @@ from litellm.types.integrations.pagerduty import (
     PagerDutyRequestBody,
 )
 from litellm.types.utils import (
+    CallTypesLiteral,
     StandardLoggingPayload,
     StandardLoggingPayloadErrorInformation,
 )
@@ -109,6 +110,9 @@ class PagerDutyAlerting(SlackAlerting):
                 error_llm_provider=error_info.get("llm_provider"),
                 user_api_key_hash=_meta.get("user_api_key_hash"),
                 user_api_key_alias=_meta.get("user_api_key_alias"),
+                user_api_key_spend=_meta.get("user_api_key_spend"),
+                user_api_key_max_budget=_meta.get("user_api_key_max_budget"),
+                user_api_key_budget_reset_at=_meta.get("user_api_key_budget_reset_at"),
                 user_api_key_org_id=_meta.get("user_api_key_org_id"),
                 user_api_key_team_id=_meta.get("user_api_key_team_id"),
                 user_api_key_user_id=_meta.get("user_api_key_user_id"),
@@ -116,6 +120,7 @@ class PagerDutyAlerting(SlackAlerting):
                 user_api_key_end_user_id=_meta.get("user_api_key_end_user_id"),
                 user_api_key_user_email=_meta.get("user_api_key_user_email"),
                 user_api_key_request_route=_meta.get("user_api_key_request_route"),
+                user_api_key_auth_metadata=_meta.get("user_api_key_auth_metadata"),
             )
         )
 
@@ -138,16 +143,7 @@ class PagerDutyAlerting(SlackAlerting):
         user_api_key_dict: UserAPIKeyAuth,
         cache: DualCache,
         data: dict,
-        call_type: Literal[
-            "completion",
-            "text_completion",
-            "embeddings",
-            "image_generation",
-            "moderation",
-            "audio_transcription",
-            "pass_through_endpoint",
-            "rerank",
-        ],
+        call_type: CallTypesLiteral,
     ) -> Optional[Union[Exception, str, dict]]:
         """
         Example of detecting hanging requests by waiting a given threshold.
@@ -190,6 +186,13 @@ class PagerDutyAlerting(SlackAlerting):
                 error_llm_provider="HangingRequest",
                 user_api_key_hash=user_api_key_dict.api_key,
                 user_api_key_alias=user_api_key_dict.key_alias,
+                user_api_key_spend=user_api_key_dict.spend,
+                user_api_key_max_budget=user_api_key_dict.max_budget,
+                user_api_key_budget_reset_at=(
+                    user_api_key_dict.budget_reset_at.isoformat()
+                    if user_api_key_dict.budget_reset_at
+                    else None
+                ),
                 user_api_key_org_id=user_api_key_dict.org_id,
                 user_api_key_team_id=user_api_key_dict.team_id,
                 user_api_key_user_id=user_api_key_dict.user_id,
@@ -197,6 +200,7 @@ class PagerDutyAlerting(SlackAlerting):
                 user_api_key_end_user_id=user_api_key_dict.end_user_id,
                 user_api_key_user_email=user_api_key_dict.user_email,
                 user_api_key_request_route=user_api_key_dict.request_route,
+                user_api_key_auth_metadata=user_api_key_dict.metadata,
             )
         )