fix: display correct quota values in limit toast (#383)

- Parse JSON error response from server to get actual used/limit values
- Previously showed 0/0 due to race condition (config fetch vs error)
- AI SDK puts full response body in error.message for non-OK responses
- Updated all quota toasts (request, token, TPM) to use server values

components/chat-panel.tsx

@@ -557,12 +557,32 @@ Continue from EXACTLY where you stopped.`,
         },
         onError: (error) => {
             // Handle server-side quota limit (429 response)
+            // AI SDK puts the full response body in error.message for non-OK responses
+            try {
+                const data = JSON.parse(error.message)
+                if (data.type === "request") {
+                    quotaManager.showQuotaLimitToast(data.used, data.limit)
+                    return
+                }
+                if (data.type === "token") {
+                    quotaManager.showTokenLimitToast(data.used, data.limit)
+                    return
+                }
+                if (data.type === "tpm") {
+                    quotaManager.showTPMLimitToast(data.limit)
+                    return
+                }
+            } catch {
+                // Not JSON, fall through to string matching for backwards compatibility
+            }
+
+            // Fallback to string matching
             if (error.message.includes("Daily request limit")) {
                 quotaManager.showQuotaLimitToast()
                 return
             }
             if (error.message.includes("Daily token limit")) {
-                quotaManager.showTokenLimitToast(dailyTokenLimit)
+                quotaManager.showTokenLimitToast()
                 return
             }
             if (

lib/use-quota-manager.tsx

@@ -18,36 +18,39 @@ export interface QuotaConfig {
  * This hook only provides UI feedback when limits are exceeded.
  */
 export function useQuotaManager(config: QuotaConfig): {
-    showQuotaLimitToast: () => void
+    showQuotaLimitToast: (used?: number, limit?: number) => void
-    showTokenLimitToast: (used: number) => void
+    showTokenLimitToast: (used?: number, limit?: number) => void
-    showTPMLimitToast: () => void
+    showTPMLimitToast: (limit?: number) => void
 } {
     const { dailyRequestLimit, dailyTokenLimit, tpmLimit } = config
     const dict = useDictionary()
 
     // Show quota limit toast (request-based)
-    const showQuotaLimitToast = useCallback(() => {
+    const showQuotaLimitToast = useCallback(
+        (used?: number, limit?: number) => {
             toast.custom(
                 (t) => (
                     <QuotaLimitToast
-                    used={dailyRequestLimit}
+                        used={used ?? dailyRequestLimit}
-                    limit={dailyRequestLimit}
+                        limit={limit ?? dailyRequestLimit}
                         onDismiss={() => toast.dismiss(t)}
                     />
                 ),
                 { duration: 15000 },
             )
-    }, [dailyRequestLimit])
+        },
+        [dailyRequestLimit],
+    )
 
     // Show token limit toast
     const showTokenLimitToast = useCallback(
-        (used: number) => {
+        (used?: number, limit?: number) => {
             toast.custom(
                 (t) => (
                     <QuotaLimitToast
                         type="token"
-                        used={used}
+                        used={used ?? dailyTokenLimit}
-                        limit={dailyTokenLimit}
+                        limit={limit ?? dailyTokenLimit}
                         onDismiss={() => toast.dismiss(t)}
                     />
                 ),
@@ -58,15 +61,21 @@ export function useQuotaManager(config: QuotaConfig): {
     )
 
     // Show TPM limit toast
-    const showTPMLimitToast = useCallback(() => {
+    const showTPMLimitToast = useCallback(
+        (limit?: number) => {
+            const effectiveLimit = limit ?? tpmLimit
             const limitDisplay =
-            tpmLimit >= 1000 ? `${tpmLimit / 1000}k` : String(tpmLimit)
+                effectiveLimit >= 1000
+                    ? `${effectiveLimit / 1000}k`
+                    : String(effectiveLimit)
             const message = formatMessage(dict.quota.tpmMessageDetailed, {
                 limit: limitDisplay,
                 seconds: 60,
             })
             toast.error(message, { duration: 8000 })
-    }, [tpmLimit, dict])
+        },
+        [tpmLimit, dict],
+    )
 
     return {
         showQuotaLimitToast,