fix(antigravity): fetch default mapping from API and sync Redis on rate limit

1. Frontend: replace hardcoded antigravityDefaultMappings with async
   fetch from GET /admin/accounts/antigravity/default-model-mapping,
   eliminating the duplicate data source that caused frontend/backend
   mapping inconsistency.

2. Backend: convert handleSmartRetry and antigravityRetryLoop from
   standalone functions to AntigravityGatewayService methods, enabling
   Redis cache sync (updateAccountModelRateLimitInCache) after both
   rate-limit write paths — long-delay branch and retry-exhausted branch.

frontend/src/api/admin/accounts.ts

@@ -387,6 +387,17 @@ export async function importData(payload: {
   return data
 }
 
+/**
+ * Get Antigravity default model mapping from backend
+ * @returns Default model mapping (from -> to)
+ */
+export async function getAntigravityDefaultModelMapping(): Promise<Record<string, string>> {
+  const { data } = await apiClient.get<Record<string, string>>(
+    '/admin/accounts/antigravity/default-model-mapping'
+  )
+  return data
+}
+
 export const accountsAPI = {
   list,
   getById,
@@ -412,7 +423,8 @@ export const accountsAPI = {
   bulkUpdate,
   syncFromCrs,
   exportData,
-  importData
+  importData,
+  getAntigravityDefaultModelMapping
 }
 
 export default accountsAPI