From c0b4797adefa8cb18fa90d1a641f97eae7f734d2 Mon Sep 17 00:00:00 2001 From: Ishaan Jaffer Date: Wed, 25 Feb 2026 11:14:59 -0800 Subject: [PATCH] fix(agent-monitoring): stack metric cards label/value vertically for proper alignment --- .../src/components/AgentMonitoring.tsx | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/ui/litellm-dashboard/src/components/AgentMonitoring.tsx b/ui/litellm-dashboard/src/components/AgentMonitoring.tsx index 4215fb3fbbc..72871f9db84 100644 --- a/ui/litellm-dashboard/src/components/AgentMonitoring.tsx +++ b/ui/litellm-dashboard/src/components/AgentMonitoring.tsx @@ -203,13 +203,13 @@ function AgentDetail({ agentId, onBack, accessToken, token, userRole, userID, al This agent is described as "answer member questions about insurance claims" but is calling exec, write, and fetch_claims. On every request, the gateway embeds the agent description and the tools called, then computes cosine similarity between them. This agent is scoring 0.08 — far outside the 0.82–0.95 range we see for healthy claims agents.

-
- Similarity — description vs tools called - 0.08 +
+ Similarity — description vs tools + 0.08
-
- Expected range for this agent type - 0.82 – 0.95 +
+ Expected range for this agent type + 0.82 – 0.95