Prometheus - fix request increment + add route tracking for streaming requests (#11731)

* fix(prometheus.py): remove request increment from inside the log success event

it's only done on post-call success/failure

* fix(litellm_logging.py): add additional validation step for checking if 'stream' is true

prevent double counting on non-stream requests

* test: add unit testing to ensure stream is not incorrectly set to true

* feat(litellm_logging.py): emit request route in standard logging payload

used by prometheus streaming metrics for route

* fix: fix otel test

* fix: fix linting errors

* test: update test

* fix: fix linting error

Author: krrishdholakia

enterprise/litellm_enterprise/enterprise_callbacks/pagerduty/pagerduty.py

@@ -115,6 +115,7 @@ async def async_log_failure_event(self, kwargs, response_obj, start_time, end_ti
                 user_api_key_team_alias=_meta.get("user_api_key_team_alias"),
                 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"),
             )
         )
 
@@ -195,6 +196,7 @@ async def hanging_response_handler(
                 user_api_key_team_alias=user_api_key_dict.team_alias,
                 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,
             )
         )
 

litellm/integrations/prometheus.py

@@ -583,6 +583,9 @@ async def async_log_success_event(self, kwargs, response_obj, start_time, end_ti
                 metadata=standard_logging_payload["metadata"].get("requester_metadata")
                 or {}
             ),
+            route=standard_logging_payload["metadata"].get(
+                "user_api_key_request_route"
+            ),
         )
 
         if (
@@ -795,8 +798,6 @@ def _increment_top_level_request_and_spend_metrics(
             enum_values=enum_values,
         )
 
-        self.litellm_proxy_total_requests_metric.labels(**_labels).inc()
-
         self.litellm_spend_metric.labels(
             end_user_id,
             user_api_key,

litellm/litellm_core_utils/litellm_logging.py

@@ -3544,6 +3544,7 @@ def get_standard_logging_metadata(
             vector_store_request_metadata=vector_store_request_metadata,
             usage_object=usage_object,
             requester_custom_headers=None,
+            user_api_key_request_route=None,
         )
         if isinstance(metadata, dict):
             # Filter the metadata dictionary to include only the specified keys
@@ -3967,7 +3968,7 @@ def get_standard_logging_object_payload(
         if (
             kwargs.get("complete_streaming_response") is not None
             or kwargs.get("async_complete_streaming_response") is not None
-        ):
+        ) and kwargs.get("stream") is True:
             stream = True
 
         payload: StandardLoggingPayload = StandardLoggingPayload(
@@ -4069,6 +4070,7 @@ def get_standard_logging_metadata(
         vector_store_request_metadata=None,
         usage_object=None,
         requester_custom_headers=None,
+        user_api_key_request_route=None,
     )
     if isinstance(metadata, dict):
         # Filter the metadata dictionary to include only the specified keys