feat(models): support Gemini 3.1 Pro Preview and fixes (#19676)

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

@@ -155,9 +155,10 @@ describe('useQuotaAndFallback', () => {
         expect(request?.isTerminalQuotaError).toBe(true);
 
         const message = request!.message;
-        expect(message).toContain('Usage limit reached for gemini-pro.');
+        expect(message).toContain('Usage limit reached for all Pro models.');
         expect(message).toContain('Access resets at'); // From getResetTimeMessage
         expect(message).toContain('/stats model for usage details');
+        expect(message).toContain('/model to switch models.');
         expect(message).toContain('/auth to switch to API key.');
 
         expect(mockHistoryManager.addItem).not.toHaveBeenCalled();
@@ -176,6 +177,77 @@ describe('useQuotaAndFallback', () => {
         expect(mockHistoryManager.addItem).toHaveBeenCalledTimes(1);
       });
 
+      it('should show the model name for a terminal quota error on a non-pro model', async () => {
+        const { result } = renderHook(() =>
+          useQuotaAndFallback({
+            config: mockConfig,
+            historyManager: mockHistoryManager,
+            userTier: UserTierId.FREE,
+            setModelSwitchedFromQuotaError: mockSetModelSwitchedFromQuotaError,
+            onShowAuthSelection: mockOnShowAuthSelection,
+          }),
+        );
+
+        const handler = setFallbackHandlerSpy.mock
+          .calls[0][0] as FallbackModelHandler;
+
+        let promise: Promise<FallbackIntent | null>;
+        const error = new TerminalQuotaError(
+          'flash quota',
+          mockGoogleApiError,
+          1000 * 60 * 5,
+        );
+        act(() => {
+          promise = handler('gemini-flash', 'gemini-pro', error);
+        });
+
+        const request = result.current.proQuotaRequest;
+        expect(request).not.toBeNull();
+        expect(request?.failedModel).toBe('gemini-flash');
+
+        const message = request!.message;
+        expect(message).toContain('Usage limit reached for gemini-flash.');
+        expect(message).not.toContain('all Pro models');
+
+        act(() => {
+          result.current.handleProQuotaChoice('retry_later');
+        });
+
+        await promise!;
+      });
+
+      it('should handle terminal quota error without retry delay', async () => {
+        const { result } = renderHook(() =>
+          useQuotaAndFallback({
+            config: mockConfig,
+            historyManager: mockHistoryManager,
+            userTier: UserTierId.FREE,
+            setModelSwitchedFromQuotaError: mockSetModelSwitchedFromQuotaError,
+            onShowAuthSelection: mockOnShowAuthSelection,
+          }),
+        );
+
+        const handler = setFallbackHandlerSpy.mock
+          .calls[0][0] as FallbackModelHandler;
+
+        let promise: Promise<FallbackIntent | null>;
+        const error = new TerminalQuotaError('no delay', mockGoogleApiError);
+        act(() => {
+          promise = handler('gemini-pro', 'gemini-flash', error);
+        });
+
+        const request = result.current.proQuotaRequest;
+        const message = request!.message;
+        expect(message).not.toContain('Access resets at');
+        expect(message).toContain('Usage limit reached for all Pro models.');
+
+        act(() => {
+          result.current.handleProQuotaChoice('retry_later');
+        });
+
+        await promise!;
+      });
+
       it('should handle race conditions by stopping subsequent requests', async () => {
         const { result } = renderHook(() =>
           useQuotaAndFallback({