diff --git a/gateway/routes/allowlist.py b/gateway/routes/allowlist.py
index 792a56a2cd8..a80bbc9ca19 100644
--- a/gateway/routes/allowlist.py
+++ b/gateway/routes/allowlist.py
@@ -54,6 +54,7 @@ GATEWAY_PATH_PREFIXES: tuple[str, ...] = (
     "/messages",
     "/v1/skills",
     "/v1/a2a/",
+    "/a2a/",
     # LiteLLM-native LLM surface
     "/v1/rerank",
     "/v2/rerank",
diff --git a/helm/litellm/templates/ingress.yaml b/helm/litellm/templates/ingress.yaml
index 30a8e7c974b..b7c78d3fdad 100644
--- a/helm/litellm/templates/ingress.yaml
+++ b/helm/litellm/templates/ingress.yaml
@@ -19,7 +19,7 @@
     "/v1/fine-tuning" "/fine-tuning" "/v1/responses" "/responses" "/v1/threads" "/threads"
     "/v1/assistants" "/assistants" "/v1/vector_stores" "/vector_stores" "/v1/indexes"
     "/v1/models" "/models" "/openai" "/engines"
-    "/v1/messages" "/messages" "/v1/skills" "/v1/a2a"
+    "/v1/messages" "/messages" "/v1/skills" "/v1/a2a" "/a2a"
     "/v1/rerank" "/v2/rerank" "/rerank" "/v1/ocr" "/ocr" "/v1/rag" "/rag"
     "/v1/video" "/v1/videos" "/video" "/videos" "/v1/search" "/search"
     "/v1/containers" "/containers" "/v1/evals" "/v1/memory" "/queue/chat"
diff --git a/ui/litellm-dashboard/src/app/(dashboard)/cost-optimization/_components/CacheLeakageCard.tsx b/ui/litellm-dashboard/src/app/(dashboard)/cost-optimization/_components/CacheLeakageCard.tsx
index 4f1cfc49569..bb2cb865877 100644
--- a/ui/litellm-dashboard/src/app/(dashboard)/cost-optimization/_components/CacheLeakageCard.tsx
+++ b/ui/litellm-dashboard/src/app/(dashboard)/cost-optimization/_components/CacheLeakageCard.tsx
@@ -105,10 +105,9 @@ const CacheLeakageCard: React.FC<CacheLeakageCardProps> = ({ activity }) => {
           <div className="flex flex-col gap-4 md:flex-row md:items-start md:justify-between">
             <div className="min-w-0">
               <CardTitle>Cache leakage by {dimension === "model" ? "model" : "virtual key"}</CardTitle>
-              <p className="mt-1 text-sm text-muted-foreground">
+              <p className="mt-1 text-sm text-muted-foreground line-clamp-2">
                 {subject} sending large volumes of uncached input with a low cache hit rate are likely missing prompt
                 caching. Potential savings is approximate: uncached input priced at the realized cache-read discount.
-                {dimension === "model" ? " Limited to Anthropic (Claude) models, which support prompt caching." : ""}
               </p>
             </div>
             <div className="shrink-0">
@@ -118,7 +117,6 @@ const CacheLeakageCard: React.FC<CacheLeakageCardProps> = ({ activity }) => {
           <Tabs
             value={dimension}
             onValueChange={(value) => setDimension(value === "model" ? "model" : "key")}
-            className="mt-3"
           >
             <TabsList>
               <TabsTrigger value="key">By virtual key</TabsTrigger>
diff --git a/ui/litellm-dashboard/src/components/ui/card.tsx b/ui/litellm-dashboard/src/components/ui/card.tsx
index 3fc0aa65264..1490c2ee908 100644
--- a/ui/litellm-dashboard/src/components/ui/card.tsx
+++ b/ui/litellm-dashboard/src/components/ui/card.tsx
@@ -9,7 +9,7 @@ const Card = React.forwardRef<HTMLDivElement, React.ComponentPropsWithoutRef<"di
       data-slot="card"
       data-size={size}
       className={cn(
-        "group/card flex flex-col gap-(--card-spacing) overflow-hidden rounded-xl bg-card py-(--card-spacing) text-sm text-card-foreground shadow-xs ring-1 ring-foreground/10 [--card-spacing:--spacing(6)] has-[>img:first-child]:pt-0 data-[size=sm]:[--card-spacing:--spacing(4)] *:[img:first-child]:rounded-t-xl *:[img:last-child]:rounded-b-xl",
+        "group/card flex flex-col gap-(--card-spacing) rounded-xl bg-card py-(--card-spacing) text-sm text-card-foreground shadow-xs ring-1 ring-foreground/10 [--card-spacing:--spacing(6)] has-[>img:first-child]:pt-0 data-[size=sm]:[--card-spacing:--spacing(4)] *:[img:first-child]:rounded-t-xl *:[img:last-child]:rounded-b-xl",
         className,
       )}
       {...props}