feat(lowest_latency.py): support expanded time window for latency based routing

uses a 1hr avg. of latency for deployments, to determine which to route to

https://github.com/BerriAI/litellm/issues/1361

litellm/router_strategy/lowest_latency.py

@@ -142,7 +142,7 @@ class LowestLatencyLoggingHandler(CustomLogger):
                 continue  # skip to next one
             
             # get average latency 
-            total = 0.0
+            total = 0
             for _call_latency in item_latency:
                 if isinstance(_call_latency, timedelta):
                     total += float(_call_latency.total_seconds())