fallback to flash for TerminalQuota errors (#13791)

packages/cli/src/ui/components/ProQuotaDialog.tsx

@@ -12,7 +12,7 @@ import { theme } from '../semantic-colors.js';
 import {
   DEFAULT_GEMINI_FLASH_LITE_MODEL,
   DEFAULT_GEMINI_FLASH_MODEL,
-  PREVIEW_GEMINI_MODEL,
+  DEFAULT_GEMINI_MODEL,
   UserTierId,
 } from '@google/gemini-cli-core';
 
@@ -127,7 +127,7 @@ export function ProQuotaDialog({
         <RadioButtonSelect items={items} onSelect={handleSelect} />
       </Box>
       <Text color={theme.text.primary}>
-        {failedModel === PREVIEW_GEMINI_MODEL && !isModelNotFoundError
+        {fallbackModel === DEFAULT_GEMINI_MODEL && !isModelNotFoundError
           ? 'Note: We will periodically retry Preview Model to see if congestion has cleared.'
           : 'Note: You can always use /model to select a different option.'}
       </Text>

packages/cli/src/ui/hooks/useQuotaAndFallback.test.ts

@@ -27,6 +27,8 @@ import {
   RetryableQuotaError,
   PREVIEW_GEMINI_MODEL,
   ModelNotFoundError,
+  DEFAULT_GEMINI_MODEL,
+  DEFAULT_GEMINI_FLASH_MODEL,
 } from '@google/gemini-cli-core';
 import { useQuotaAndFallback } from './useQuotaAndFallback.js';
 import type { UseHistoryManagerReturn } from './useHistoryManager.js';
@@ -432,7 +434,7 @@ To disable Gemini 3, disable "Preview features" in /settings.`,
       await act(() => {
         promise = handler(
           PREVIEW_GEMINI_MODEL,
-          'gemini-flash',
+          DEFAULT_GEMINI_MODEL,
           new Error('preview model failed'),
         );
       });
@@ -447,7 +449,42 @@ To disable Gemini 3, disable "Preview features" in /settings.`,
       const lastCall = (mockHistoryManager.addItem as Mock).mock.calls[0][0];
       expect(lastCall.type).toBe(MessageType.INFO);
       expect(lastCall.text).toContain(
-        `Switched to fallback model gemini-flash. We will periodically check if ${PREVIEW_GEMINI_MODEL} is available again.`,
+        `Switched to fallback model gemini-2.5-pro. We will periodically check if ${PREVIEW_GEMINI_MODEL} is available again.`,
+      );
+    });
+
+    it('should show a special message when falling back from the preview model, but do not show periodical check message for flash model fallback', async () => {
+      const { result } = renderHook(() =>
+        useQuotaAndFallback({
+          config: mockConfig,
+          historyManager: mockHistoryManager,
+          userTier: UserTierId.FREE,
+          setModelSwitchedFromQuotaError: mockSetModelSwitchedFromQuotaError,
+        }),
+      );
+
+      const handler = setFallbackHandlerSpy.mock
+        .calls[0][0] as FallbackModelHandler;
+      let promise: Promise<FallbackIntent | null>;
+      await act(() => {
+        promise = handler(
+          PREVIEW_GEMINI_MODEL,
+          DEFAULT_GEMINI_FLASH_MODEL,
+          new Error('preview model failed'),
+        );
+      });
+
+      await act(() => {
+        result.current.handleProQuotaChoice('retry_always');
+      });
+
+      await promise!;
+
+      expect(mockHistoryManager.addItem).toHaveBeenCalledTimes(1);
+      const lastCall = (mockHistoryManager.addItem as Mock).mock.calls[0][0];
+      expect(lastCall.type).toBe(MessageType.INFO);
+      expect(lastCall.text).toContain(
+        `Switched to fallback model gemini-2.5-flash.`,
       );
     });
   });

packages/cli/src/ui/hooks/useQuotaAndFallback.ts

@@ -13,6 +13,7 @@ import {
   ModelNotFoundError,
   type UserTierId,
   PREVIEW_GEMINI_MODEL,
+  DEFAULT_GEMINI_MODEL,
 } from '@google/gemini-cli-core';
 import { useCallback, useEffect, useRef, useState } from 'react';
 import { type UseHistoryManagerReturn } from './useHistoryManager.js';
@@ -55,11 +56,16 @@ export function useQuotaAndFallback({
       let message: string;
       let isTerminalQuotaError = false;
       let isModelNotFoundError = false;
+      const usageLimitReachedModel =
+        failedModel === DEFAULT_GEMINI_MODEL ||
+        failedModel === PREVIEW_GEMINI_MODEL
+          ? 'all Pro models'
+          : failedModel;
       if (error instanceof TerminalQuotaError) {
         isTerminalQuotaError = true;
         // Common part of the message for both tiers
         const messageLines = [
-          `Usage limit reached for ${failedModel}.`,
+          `Usage limit reached for ${usageLimitReachedModel}.`,
           error.retryDelayMs ? getResetTimeMessage(error.retryDelayMs) : null,
           `/stats for usage details`,
           `/auth to switch to API key.`,
@@ -116,10 +122,13 @@ export function useQuotaAndFallback({
       if (choice === 'retry_always') {
         // If we were recovering from a Preview Model failure, show a specific message.
         if (proQuotaRequest.failedModel === PREVIEW_GEMINI_MODEL) {
+          const showPeriodicalCheckMessage =
+            !proQuotaRequest.isModelNotFoundError &&
+            proQuotaRequest.fallbackModel === DEFAULT_GEMINI_MODEL;
           historyManager.addItem(
             {
               type: MessageType.INFO,
-              text: `Switched to fallback model ${proQuotaRequest.fallbackModel}. ${!proQuotaRequest.isModelNotFoundError ? `We will periodically check if ${PREVIEW_GEMINI_MODEL} is available again.` : ''}`,
+              text: `Switched to fallback model ${proQuotaRequest.fallbackModel}. ${showPeriodicalCheckMessage ? `We will periodically check if ${PREVIEW_GEMINI_MODEL} is available again.` : ''}`,
             },
             Date.now(),
           );