MindSift/frontend/src/lib/__tests__/useVoiceInput.test.tsx

import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import { act, renderHook, waitFor } from '@testing-library/react';

const getAuthStatus = vi.fn();
const transcribe = vi.fn();
vi.mock('../api', () => ({ api: { getAuthStatus: (...a: any[]) => getAuthStatus(...a), transcribe: (...a: any[]) => transcribe(...a) } }));

import { useVoiceInput } from '../useVoiceInput';
import { resetVoiceConfig } from '../voice';

class FakeMediaRecorder {
  static isTypeSupported = (t: string) => t === 'audio/webm;codecs=opus';
  state: 'inactive' | 'recording' = 'inactive';
  mimeType = 'audio/webm;codecs=opus';
  ondataavailable: ((e: { data: Blob }) => void) | null = null;
  onstop: (() => void) | null = null;
  constructor(public stream: any) {}
  start() {
    this.state = 'recording';
  }
  stop() {
    this.state = 'inactive';
    this.ondataavailable?.({ data: new Blob(['audio'], { type: this.mimeType }) });
    this.onstop?.();
  }
}

const stopTrack = vi.fn();

beforeEach(() => {
  resetVoiceConfig();
  getAuthStatus.mockReset();
  transcribe.mockReset();
  stopTrack.mockReset();
  (window as any).MediaRecorder = FakeMediaRecorder;
  Object.defineProperty(navigator, 'mediaDevices', {
    configurable: true,
    value: { getUserMedia: vi.fn(async () => ({ getTracks: () => [{ stop: stopTrack }] })) },
  });
});

afterEach(() => {
  delete (window as any).MediaRecorder;
  delete (window as any).SpeechRecognition;
  vi.useRealTimers();
});

describe('useVoiceInput', () => {
  it('server mode: records, sends the audio to the own server and returns its text', async () => {
    getAuthStatus.mockResolvedValue({ voice: { mode: 'server', maxSeconds: 600 } });
    transcribe.mockResolvedValue('Milch kaufen');
    const onText = vi.fn();
    const { result } = renderHook(() => useVoiceInput({ onText }));
    await waitFor(() => expect(result.current.mode).toBe('server'));
    expect(result.current.available).toBe(true);

    await act(async () => {
      await result.current.start();
    });
    expect(result.current.state).toBe('listening');

    await act(async () => {
      await result.current.stop();
    });
    expect(transcribe).toHaveBeenCalledTimes(1);
    expect((transcribe.mock.calls[0][0] as Blob).type).toBe('audio/webm;codecs=opus');
    expect(onText).toHaveBeenCalledWith('Milch kaufen', true);
    expect(result.current.state).toBe('idle');
    expect(stopTrack).toHaveBeenCalled(); // microphone released
  });

  it('server mode: cancel throws the recording away', async () => {
    getAuthStatus.mockResolvedValue({ voice: { mode: 'server', maxSeconds: 600 } });
    const onText = vi.fn();
    const { result } = renderHook(() => useVoiceInput({ onText }));
    await waitFor(() => expect(result.current.mode).toBe('server'));
    await act(async () => {
      await result.current.start();
    });
    act(() => result.current.cancel());
    expect(transcribe).not.toHaveBeenCalled();
    expect(onText).not.toHaveBeenCalled();
    expect(result.current.state).toBe('idle');
  });

  it('server mode: a failing server reports an error instead of text', async () => {
    getAuthStatus.mockResolvedValue({ voice: { mode: 'server', maxSeconds: 600 } });
    transcribe.mockRejectedValue(new Error('Spracherkennung fehlgeschlagen'));
    const onText = vi.fn();
    const onError = vi.fn();
    const { result } = renderHook(() => useVoiceInput({ onText, onError }));
    await waitFor(() => expect(result.current.mode).toBe('server'));
    await act(async () => {
      await result.current.start();
    });
    await act(async () => {
      await result.current.stop();
    });
    expect(onError).toHaveBeenCalledWith('Spracherkennung fehlgeschlagen');
    expect(onText).not.toHaveBeenCalled();
    expect(result.current.state).toBe('idle');
  });

  it('server mode: stops by itself after the maximum length', async () => {
    getAuthStatus.mockResolvedValue({ voice: { mode: 'server', maxSeconds: 5 } });
    transcribe.mockResolvedValue('Zu lang');
    const onText = vi.fn();
    const { result } = renderHook(() => useVoiceInput({ onText }));
    await waitFor(() => expect(result.current.mode).toBe('server'));
    vi.useFakeTimers();
    await act(async () => {
      await result.current.start();
    });
    await act(async () => {
      vi.advanceTimersByTime(5000);
    });
    vi.useRealTimers();
    await waitFor(() => expect(onText).toHaveBeenCalledWith('Zu lang', true));
  });

  it('hides the microphone when switched off, and without browser recognition', async () => {
    getAuthStatus.mockResolvedValue({ voice: { mode: 'off', maxSeconds: 600 } });
    const off = renderHook(() => useVoiceInput({ onText: vi.fn() }));
    await waitFor(() => expect(off.result.current.mode).toBe('off'));
    expect(off.result.current.available).toBe(false);

    resetVoiceConfig();
    getAuthStatus.mockResolvedValue({ voice: { mode: 'browser', maxSeconds: 600 } });
    const none = renderHook(() => useVoiceInput({ onText: vi.fn() }));
    await waitFor(() => expect(none.result.current.mode).toBe('unsupported'));
    expect(none.result.current.available).toBe(false);
  });
});