fix(dashboard): stabilize usage tab loading and refresh behavior

Prevent repeated provider-limit refresh requests by guarding the bulk
refresh flow with a ref-backed lock instead of a stale callback
dependency.

Also avoid tying eval data loading to translation updates and replace the
fetch failure path with a static error so the effect runs predictably.
Refresh English cost dashboard copy to provide clearer labels and empty
state messaging.

src/app/(dashboard)/dashboard/usage/components/EvalsTab.tsx

@@ -353,7 +353,7 @@ export default function EvalsTab() {
       try {
         const response = await fetch("/api/evals");
         if (!response.ok) {
-          throw new Error(t("notifyEvalRunFailed"));
+          throw new Error("Eval load failed");
         }
 
         const payload = (await response.json()) as EvalsDashboardPayload;
@@ -380,7 +380,8 @@ export default function EvalsTab() {
     return () => {
       isMounted = false;
     };
-  }, [notify, t]);
+    // eslint-disable-next-line react-hooks/exhaustive-deps
+  }, []);
 
   useEffect(() => {
     if (targetOptions.length === 0) return;

src/app/(dashboard)/dashboard/usage/components/ProviderLimits/index.tsx

@@ -238,8 +238,10 @@ export default function ProviderLimits() {
     [fetchQuota]
   );
 
+  const refreshingAllRef = useRef(false);
   const refreshAll = useCallback(async () => {
-    if (refreshingAll) return;
+    if (refreshingAllRef.current) return;
+    refreshingAllRef.current = true;
     setRefreshingAll(true);
     try {
       const response = await fetch("/api/usage/provider-limits", { method: "POST" });
@@ -256,9 +258,10 @@ export default function ProviderLimits() {
     } catch (error) {
       console.error("Error refreshing all:", error);
     } finally {
+      refreshingAllRef.current = false;
       setRefreshingAll(false);
     }
-  }, [refreshingAll, applyCachedQuotaState, fetchConnections]);
+  }, [applyCachedQuotaState, fetchConnections]);
 
   useEffect(() => {
     const init = async () => {

src/i18n/messages/en.json

@@ -1784,29 +1784,35 @@
   },
   "costs": {
     "title": "Costs",
+    "pageDescription": "Track spending, analyze trends, and manage your AI budget across all providers",
+    "overview": "Overview",
     "budget": "Budget",
     "totalCost": "Total Cost",
     "breakdown": "Cost Breakdown",
     "noData": "No cost data",
     "byModel": "By Model",
     "byProvider": "By Provider",
-    "spend30d": "Spend30D",
+    "range7d": "7 Days",
+    "range30d": "30 Days",
+    "range90d": "90 Days",
+    "rangeAll": "All Time",
+    "spend30d": "Spend 30D",
     "activeModels": "Active Models",
     "selectedWindow": "Selected Window",
     "activeProviders": "Active Providers",
-    "overviewTitle": "Overview Title",
-    "spend7d": "Spend7D",
-    "avgCostPerRequest": "Avg Cost Per Request",
-    "noCostDataDescription": "No Cost Data Description",
+    "overviewTitle": "Cost Overview",
+    "spend7d": "Spend 7D",
+    "avgCostPerRequest": "Avg Cost / Request",
+    "noCostDataDescription": "Start making requests to see cost data appear here. Costs are tracked automatically for all providers.",
     "spendToday": "Spend Today",
-    "overviewLoadFailed": "Overview Load Failed",
-    "overviewDescription": "Overview Description",
+    "overviewLoadFailed": "Failed to load cost overview",
+    "overviewDescription": "Real-time spending breakdown across all connected providers and models",
     "providerShare": "Provider Share",
     "topProviders": "Top Providers",
     "costTrend": "Cost Trend",
-    "noCostDataTitle": "No Cost Data Title",
+    "noCostDataTitle": "No cost data yet",
     "topModels": "Top Models",
-    "requestsInWindow": "Requests In Window"
+    "requestsInWindow": "Requests in Window"
   },
   "endpoint": {
     "title": "API Endpoint",