fix use thread_pool_executor for pass through logging

Author: ishaan-jaff

litellm/proxy/pass_through_endpoints/success_handler.py

@@ -18,6 +18,7 @@
 from litellm.proxy._types import PassThroughEndpointLoggingResultValues
 from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
 from litellm.types.utils import StandardPassThroughResponseObject
+from litellm.utils import executor as thread_pool_executor
 
 from .llm_provider_handlers.anthropic_passthrough_logging_handler import (
     AnthropicPassthroughLoggingHandler,
@@ -93,15 +94,16 @@ async def pass_through_async_success_handler(
             standard_logging_response_object = StandardPassThroughResponseObject(
                 response=httpx_response.text
             )
-        threading.Thread(
-            target=logging_obj.success_handler,
+        thread_pool_executor.submit(
+            logging_obj.success_handler,
             args=(
                 standard_logging_response_object,
                 start_time,
                 end_time,
                 cache_hit,
             ),
-        ).start()
+        )
+
         await logging_obj.async_success_handler(
             result=(
                 json.dumps(result)

litellm/proxy/proxy_config.yaml

@@ -21,4 +21,5 @@ router_settings:
   redis_password: os.environ/REDIS_PASSWORD
 
 litellm_settings:
-  callbacks: ["prometheus"]
+  callbacks: ["prometheus"]
+  success_callback: ["langfuse"]