Vision model support for Qwen-OAuth (#525)

* refactor: openaiContentGenerator

* refactor: optimize stream handling

* refactor: re-organize refactored files

* fix: unit test cases

* feat: `/model` command for switching to vision model

* fix: lint error

* feat: add image tokenizer to fit vlm context window

* fix: lint and type errors

* feat: add `visionModelPreview` to control default visibility of vision models

* fix: remove deprecated files

* fix: align supported image formats with bailian doc

packages/cli/src/ui/components/ModelSelectionDialog.test.tsx

@@ -0,0 +1,246 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import React from 'react';
+import { render } from 'ink-testing-library';
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { ModelSelectionDialog } from './ModelSelectionDialog.js';
+import type { AvailableModel } from '../models/availableModels.js';
+import type { RadioSelectItem } from './shared/RadioButtonSelect.js';
+
+// Mock the useKeypress hook
+const mockUseKeypress = vi.hoisted(() => vi.fn());
+vi.mock('../hooks/useKeypress.js', () => ({
+  useKeypress: mockUseKeypress,
+}));
+
+// Mock the RadioButtonSelect component
+const mockRadioButtonSelect = vi.hoisted(() => vi.fn());
+vi.mock('./shared/RadioButtonSelect.js', () => ({
+  RadioButtonSelect: mockRadioButtonSelect,
+}));
+
+describe('ModelSelectionDialog', () => {
+  const mockAvailableModels: AvailableModel[] = [
+    { id: 'qwen3-coder-plus', label: 'qwen3-coder-plus' },
+    { id: 'qwen-vl-max-latest', label: 'qwen-vl-max', isVision: true },
+    { id: 'gpt-4', label: 'GPT-4' },
+  ];
+
+  const mockOnSelect = vi.fn();
+  const mockOnCancel = vi.fn();
+
+  beforeEach(() => {
+    vi.clearAllMocks();
+
+    // Mock RadioButtonSelect to return a simple div
+    mockRadioButtonSelect.mockReturnValue(
+      React.createElement('div', { 'data-testid': 'radio-select' }),
+    );
+  });
+
+  it('should setup escape key handler to call onCancel', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    expect(mockUseKeypress).toHaveBeenCalledWith(expect.any(Function), {
+      isActive: true,
+    });
+
+    // Simulate escape key press
+    const keypressHandler = mockUseKeypress.mock.calls[0][0];
+    keypressHandler({ name: 'escape' });
+
+    expect(mockOnCancel).toHaveBeenCalled();
+  });
+
+  it('should not call onCancel for non-escape keys', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const keypressHandler = mockUseKeypress.mock.calls[0][0];
+    keypressHandler({ name: 'enter' });
+
+    expect(mockOnCancel).not.toHaveBeenCalled();
+  });
+
+  it('should set correct initial index for current model', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen-vl-max-latest"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.initialIndex).toBe(1); // qwen-vl-max-latest is at index 1
+  });
+
+  it('should set initial index to 0 when current model is not found', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="non-existent-model"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.initialIndex).toBe(0);
+  });
+
+  it('should call onSelect when a model is selected', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(typeof callArgs.onSelect).toBe('function');
+
+    // Simulate selection
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+    onSelectCallback('qwen-vl-max-latest');
+
+    expect(mockOnSelect).toHaveBeenCalledWith('qwen-vl-max-latest');
+  });
+
+  it('should handle empty models array', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={[]}
+        currentModel=""
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.items).toEqual([]);
+    expect(callArgs.initialIndex).toBe(0);
+  });
+
+  it('should create correct option items with proper labels', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const expectedItems = [
+      {
+        label: 'qwen3-coder-plus (current)',
+        value: 'qwen3-coder-plus',
+      },
+      {
+        label: 'qwen-vl-max [Vision]',
+        value: 'qwen-vl-max-latest',
+      },
+      {
+        label: 'GPT-4',
+        value: 'gpt-4',
+      },
+    ];
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.items).toEqual(expectedItems);
+  });
+
+  it('should show vision indicator for vision models', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="gpt-4"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    const visionModelItem = callArgs.items.find(
+      (item: RadioSelectItem<string>) => item.value === 'qwen-vl-max-latest',
+    );
+
+    expect(visionModelItem?.label).toContain('[Vision]');
+  });
+
+  it('should show current indicator for the current model', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen-vl-max-latest"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    const currentModelItem = callArgs.items.find(
+      (item: RadioSelectItem<string>) => item.value === 'qwen-vl-max-latest',
+    );
+
+    expect(currentModelItem?.label).toContain('(current)');
+  });
+
+  it('should pass isFocused prop to RadioButtonSelect', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.isFocused).toBe(true);
+  });
+
+  it('should handle multiple onSelect calls correctly', () => {
+    render(
+      <ModelSelectionDialog
+        availableModels={mockAvailableModels}
+        currentModel="qwen3-coder-plus"
+        onSelect={mockOnSelect}
+        onCancel={mockOnCancel}
+      />,
+    );
+
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+
+    // Call multiple times
+    onSelectCallback('qwen3-coder-plus');
+    onSelectCallback('qwen-vl-max-latest');
+    onSelectCallback('gpt-4');
+
+    expect(mockOnSelect).toHaveBeenCalledTimes(3);
+    expect(mockOnSelect).toHaveBeenNthCalledWith(1, 'qwen3-coder-plus');
+    expect(mockOnSelect).toHaveBeenNthCalledWith(2, 'qwen-vl-max-latest');
+    expect(mockOnSelect).toHaveBeenNthCalledWith(3, 'gpt-4');
+  });
+});

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

@@ -0,0 +1,87 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type React from 'react';
+import { Box, Text } from 'ink';
+import { Colors } from '../colors.js';
+import {
+  RadioButtonSelect,
+  type RadioSelectItem,
+} from './shared/RadioButtonSelect.js';
+import { useKeypress } from '../hooks/useKeypress.js';
+import type { AvailableModel } from '../models/availableModels.js';
+
+export interface ModelSelectionDialogProps {
+  availableModels: AvailableModel[];
+  currentModel: string;
+  onSelect: (modelId: string) => void;
+  onCancel: () => void;
+}
+
+export const ModelSelectionDialog: React.FC<ModelSelectionDialogProps> = ({
+  availableModels,
+  currentModel,
+  onSelect,
+  onCancel,
+}) => {
+  useKeypress(
+    (key) => {
+      if (key.name === 'escape') {
+        onCancel();
+      }
+    },
+    { isActive: true },
+  );
+
+  const options: Array<RadioSelectItem<string>> = availableModels.map(
+    (model) => {
+      const visionIndicator = model.isVision ? ' [Vision]' : '';
+      const currentIndicator = model.id === currentModel ? ' (current)' : '';
+      return {
+        label: `${model.label}${visionIndicator}${currentIndicator}`,
+        value: model.id,
+      };
+    },
+  );
+
+  const initialIndex = Math.max(
+    0,
+    availableModels.findIndex((model) => model.id === currentModel),
+  );
+
+  const handleSelect = (modelId: string) => {
+    onSelect(modelId);
+  };
+
+  return (
+    <Box
+      flexDirection="column"
+      borderStyle="round"
+      borderColor={Colors.AccentBlue}
+      padding={1}
+      width="100%"
+      marginLeft={1}
+    >
+      <Box flexDirection="column" marginBottom={1}>
+        <Text bold>Select Model</Text>
+        <Text>Choose a model for this session:</Text>
+      </Box>
+
+      <Box marginBottom={1}>
+        <RadioButtonSelect
+          items={options}
+          initialIndex={initialIndex}
+          onSelect={handleSelect}
+          isFocused
+        />
+      </Box>
+
+      <Box>
+        <Text color={Colors.Gray}>Press Enter to select, Esc to cancel</Text>
+      </Box>
+    </Box>
+  );
+};

packages/cli/src/ui/components/ModelSwitchDialog.test.tsx

@@ -0,0 +1,185 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import React from 'react';
+import { render } from 'ink-testing-library';
+import { describe, it, expect, vi, beforeEach } from 'vitest';
+import { ModelSwitchDialog, VisionSwitchOutcome } from './ModelSwitchDialog.js';
+
+// Mock the useKeypress hook
+const mockUseKeypress = vi.hoisted(() => vi.fn());
+vi.mock('../hooks/useKeypress.js', () => ({
+  useKeypress: mockUseKeypress,
+}));
+
+// Mock the RadioButtonSelect component
+const mockRadioButtonSelect = vi.hoisted(() => vi.fn());
+vi.mock('./shared/RadioButtonSelect.js', () => ({
+  RadioButtonSelect: mockRadioButtonSelect,
+}));
+
+describe('ModelSwitchDialog', () => {
+  const mockOnSelect = vi.fn();
+
+  beforeEach(() => {
+    vi.clearAllMocks();
+
+    // Mock RadioButtonSelect to return a simple div
+    mockRadioButtonSelect.mockReturnValue(
+      React.createElement('div', { 'data-testid': 'radio-select' }),
+    );
+  });
+
+  it('should setup RadioButtonSelect with correct options', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const expectedItems = [
+      {
+        label: 'Switch for this request only',
+        value: VisionSwitchOutcome.SwitchOnce,
+      },
+      {
+        label: 'Switch session to vision model',
+        value: VisionSwitchOutcome.SwitchSessionToVL,
+      },
+      {
+        label: 'Do not switch, show guidance',
+        value: VisionSwitchOutcome.DisallowWithGuidance,
+      },
+    ];
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.items).toEqual(expectedItems);
+    expect(callArgs.initialIndex).toBe(0);
+    expect(callArgs.isFocused).toBe(true);
+  });
+
+  it('should call onSelect when an option is selected', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(typeof callArgs.onSelect).toBe('function');
+
+    // Simulate selection of "Switch for this request only"
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+    onSelectCallback(VisionSwitchOutcome.SwitchOnce);
+
+    expect(mockOnSelect).toHaveBeenCalledWith(VisionSwitchOutcome.SwitchOnce);
+  });
+
+  it('should call onSelect with SwitchSessionToVL when second option is selected', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+    onSelectCallback(VisionSwitchOutcome.SwitchSessionToVL);
+
+    expect(mockOnSelect).toHaveBeenCalledWith(
+      VisionSwitchOutcome.SwitchSessionToVL,
+    );
+  });
+
+  it('should call onSelect with DisallowWithGuidance when third option is selected', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+    onSelectCallback(VisionSwitchOutcome.DisallowWithGuidance);
+
+    expect(mockOnSelect).toHaveBeenCalledWith(
+      VisionSwitchOutcome.DisallowWithGuidance,
+    );
+  });
+
+  it('should setup escape key handler to call onSelect with DisallowWithGuidance', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    expect(mockUseKeypress).toHaveBeenCalledWith(expect.any(Function), {
+      isActive: true,
+    });
+
+    // Simulate escape key press
+    const keypressHandler = mockUseKeypress.mock.calls[0][0];
+    keypressHandler({ name: 'escape' });
+
+    expect(mockOnSelect).toHaveBeenCalledWith(
+      VisionSwitchOutcome.DisallowWithGuidance,
+    );
+  });
+
+  it('should not call onSelect for non-escape keys', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const keypressHandler = mockUseKeypress.mock.calls[0][0];
+    keypressHandler({ name: 'enter' });
+
+    expect(mockOnSelect).not.toHaveBeenCalled();
+  });
+
+  it('should set initial index to 0 (first option)', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.initialIndex).toBe(0);
+  });
+
+  describe('VisionSwitchOutcome enum', () => {
+    it('should have correct enum values', () => {
+      expect(VisionSwitchOutcome.SwitchOnce).toBe('switch_once');
+      expect(VisionSwitchOutcome.SwitchSessionToVL).toBe(
+        'switch_session_to_vl',
+      );
+      expect(VisionSwitchOutcome.DisallowWithGuidance).toBe(
+        'disallow_with_guidance',
+      );
+    });
+  });
+
+  it('should handle multiple onSelect calls correctly', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const onSelectCallback = mockRadioButtonSelect.mock.calls[0][0].onSelect;
+
+    // Call multiple times
+    onSelectCallback(VisionSwitchOutcome.SwitchOnce);
+    onSelectCallback(VisionSwitchOutcome.SwitchSessionToVL);
+    onSelectCallback(VisionSwitchOutcome.DisallowWithGuidance);
+
+    expect(mockOnSelect).toHaveBeenCalledTimes(3);
+    expect(mockOnSelect).toHaveBeenNthCalledWith(
+      1,
+      VisionSwitchOutcome.SwitchOnce,
+    );
+    expect(mockOnSelect).toHaveBeenNthCalledWith(
+      2,
+      VisionSwitchOutcome.SwitchSessionToVL,
+    );
+    expect(mockOnSelect).toHaveBeenNthCalledWith(
+      3,
+      VisionSwitchOutcome.DisallowWithGuidance,
+    );
+  });
+
+  it('should pass isFocused prop to RadioButtonSelect', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const callArgs = mockRadioButtonSelect.mock.calls[0][0];
+    expect(callArgs.isFocused).toBe(true);
+  });
+
+  it('should handle escape key multiple times', () => {
+    render(<ModelSwitchDialog onSelect={mockOnSelect} />);
+
+    const keypressHandler = mockUseKeypress.mock.calls[0][0];
+
+    // Call escape multiple times
+    keypressHandler({ name: 'escape' });
+    keypressHandler({ name: 'escape' });
+
+    expect(mockOnSelect).toHaveBeenCalledTimes(2);
+    expect(mockOnSelect).toHaveBeenCalledWith(
+      VisionSwitchOutcome.DisallowWithGuidance,
+    );
+  });
+});

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

@@ -0,0 +1,89 @@
+/**
+ * @license
+ * Copyright 2025 Qwen
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+import type React from 'react';
+import { Box, Text } from 'ink';
+import { Colors } from '../colors.js';
+import {
+  RadioButtonSelect,
+  type RadioSelectItem,
+} from './shared/RadioButtonSelect.js';
+import { useKeypress } from '../hooks/useKeypress.js';
+
+export enum VisionSwitchOutcome {
+  SwitchOnce = 'switch_once',
+  SwitchSessionToVL = 'switch_session_to_vl',
+  DisallowWithGuidance = 'disallow_with_guidance',
+}
+
+export interface ModelSwitchDialogProps {
+  onSelect: (outcome: VisionSwitchOutcome) => void;
+}
+
+export const ModelSwitchDialog: React.FC<ModelSwitchDialogProps> = ({
+  onSelect,
+}) => {
+  useKeypress(
+    (key) => {
+      if (key.name === 'escape') {
+        onSelect(VisionSwitchOutcome.DisallowWithGuidance);
+      }
+    },
+    { isActive: true },
+  );
+
+  const options: Array<RadioSelectItem<VisionSwitchOutcome>> = [
+    {
+      label: 'Switch for this request only',
+      value: VisionSwitchOutcome.SwitchOnce,
+    },
+    {
+      label: 'Switch session to vision model',
+      value: VisionSwitchOutcome.SwitchSessionToVL,
+    },
+    {
+      label: 'Do not switch, show guidance',
+      value: VisionSwitchOutcome.DisallowWithGuidance,
+    },
+  ];
+
+  const handleSelect = (outcome: VisionSwitchOutcome) => {
+    onSelect(outcome);
+  };
+
+  return (
+    <Box
+      flexDirection="column"
+      borderStyle="round"
+      borderColor={Colors.AccentYellow}
+      padding={1}
+      width="100%"
+      marginLeft={1}
+    >
+      <Box flexDirection="column" marginBottom={1}>
+        <Text bold>Vision Model Switch Required</Text>
+        <Text>
+          Your message contains an image, but the current model doesn&apos;t
+          support vision.
+        </Text>
+        <Text>How would you like to proceed?</Text>
+      </Box>
+
+      <Box marginBottom={1}>
+        <RadioButtonSelect
+          items={options}
+          initialIndex={0}
+          onSelect={handleSelect}
+          isFocused
+        />
+      </Box>
+
+      <Box>
+        <Text color={Colors.Gray}>Press Enter to select, Esc to cancel</Text>
+      </Box>
+    </Box>
+  );
+};