From b993c62144e992d2f084717cb5fa2271684b0063 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Wed, 24 Jan 2024 15:58:07 -0800
Subject: [PATCH] (fix) only alert users when requests are hanging

---
 litellm/proxy/proxy_server.py |  4 ++++
 litellm/proxy/utils.py        | 19 +++++++++++--------
 2 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/litellm/proxy/proxy_server.py b/litellm/proxy/proxy_server.py
index ca58371f454..d8365404c60 100644
--- a/litellm/proxy/proxy_server.py
+++ b/litellm/proxy/proxy_server.py
@@ -1863,6 +1863,8 @@ async def chat_completion(
         else:  # router is not set
             response = await litellm.acompletion(**data)
 
+        # Post Call Processing
+        data["litellm_status"] = "success"  # used for alerting
         if hasattr(response, "_hidden_params"):
             model_id = response._hidden_params.get("model_id", None) or ""
         else:
@@ -2048,6 +2050,7 @@ async def embeddings(
             response = await litellm.aembedding(**data)
 
         ### ALERTING ###
+        data["litellm_status"] = "success"  # used for alerting
         end_time = time.time()
         asyncio.create_task(
             proxy_logging_obj.response_taking_too_long(
@@ -2163,6 +2166,7 @@ async def image_generation(
             response = await litellm.aimage_generation(**data)
 
         ### ALERTING ###
+        data["litellm_status"] = "success"  # used for alerting
         end_time = time.time()
         asyncio.create_task(
             proxy_logging_obj.response_taking_too_long(
diff --git a/litellm/proxy/utils.py b/litellm/proxy/utils.py
index ebc2dbc0541..d638d162d47 100644
--- a/litellm/proxy/utils.py
+++ b/litellm/proxy/utils.py
@@ -158,14 +158,17 @@ class ProxyLogging:
             await asyncio.sleep(
                 self.alerting_threshold
             )  # Set it to 5 minutes - i'd imagine this might be different for streaming, non-streaming, non-completion (embedding + img) requests
-
-            alerting_message = (
-                f"Requests are hanging - {self.alerting_threshold}s+ request time"
-            )
-            await self.alerting_handler(
-                message=alerting_message + request_info,
-                level="Medium",
-            )
+            if (
+                request_data is not None
+                and request_data.get("litellm_status", "") != "success"
+            ):
+                alerting_message = (
+                    f"Requests are hanging - {self.alerting_threshold}s+ request time"
+                )
+                await self.alerting_handler(
+                    message=alerting_message + request_info,
+                    level="Medium",
+                )
 
         elif (
             type == "slow_response" and start_time is not None and end_time is not None