// tests/main/services/VoiceModeService.test.ts // 상태 머신 전이 + 이중 조건 플러시 + accidentalPress 테스트 import { describe, it, expect, beforeEach, vi } from 'vitest' import { EventEmitter } from 'events' import { RecognitionState, AudioState } from '@d3ro/core/types' import { TIMING } from '@d3ro/core/constants' // 모든 하위 서비스 모킹 vi.mock('../../../src/main/services/LoggerService', () => ({ getLogger: () => ({ info: vi.fn(), warn: vi.fn(), error: vi.fn(), debug: vi.fn() }) })) const mockSTT = { initialize: vi.fn(() => Promise.resolve()), transcribe: vi.fn(() => Promise.resolve({ text: '테스트 전사', segments: [], language: 'ko', duration: 2, processingTime: 500 }) ), getStatus: vi.fn(() => ({ state: 'ready', modelId: 'base', uptime: 0 })), // 프리플라이트 검증(모델 설치 여부)용 — 기본은 설치된 상태로 목킹 getModels: vi.fn(() => [ { id: 'base', name: 'Base', sizeBytes: 0, downloaded: true, languages: [], accuracy: 2, speed: 4 }, ]), on: vi.fn(), off: vi.fn() } vi.mock('../../../src/main/services/LocalSTTService', () => ({ getLocalSTTService: () => mockSTT, resetLocalSTTServiceForTests: () => undefined, })) const audioBus = new EventEmitter() const mockAudio = { start: vi.fn(() => Promise.resolve()), stop: vi.fn(() => Promise.resolve()), on: vi.fn((ev: string, fn: (...args: unknown[]) => void) => { audioBus.on(ev, fn) }), off: vi.fn((ev: string, fn: (...args: unknown[]) => void) => { audioBus.off(ev, fn) }), } vi.mock('../../../src/main/services/AudioCaptureService', () => ({ getAudioCaptureService: () => mockAudio })) const mockKeyBinding = { on: vi.fn(), off: vi.fn() } vi.mock('../../../src/main/services/KeyBindingService', () => ({ getKeyBindingService: () => mockKeyBinding })) const CONFIG_DEFAULTS: Record = { sttModelId: 'base', defaultLLMAction: 'refine', ollamaServerUrl: 'http://localhost:11434', llmModelId: 'gemma4:e4b' } const config = vi.hoisted(() => ({ values: {} as Record })) vi.mock('../../../src/main/services/ConfigService', () => ({ configGet: vi.fn((key: string) => config.values[key]) })) const instructionStore = vi.hoisted(() => ({ byId: {} as Record })) vi.mock('../../../src/main/services/CustomInstructionService', () => ({ getCustomInstructionService: () => ({ getById: (id: string) => instructionStore.byId[id] ?? null }) })) // 음성 단축키(두 번째 진입점) — 기본은 비활성 const voiceCommand = vi.hoisted(() => ({ enabled: false, instructionId: null as string | null, cleanedText: '' })) vi.mock('../../../src/main/services/VoiceCommandService', () => ({ getVoiceCommandService: () => ({ isEnabled: () => voiceCommand.enabled, match: (text: string) => voiceCommand.enabled && voiceCommand.instructionId ? { matched: true, ruleId: 'rule-1', instructionId: voiceCommand.instructionId, cleanedText: voiceCommand.cleanedText || text, matchedKeyword: '번역' } : { matched: false, ruleId: null, instructionId: null, cleanedText: text, matchedKeyword: null } }) })) const mockTextInsert = { insertText: vi.fn(() => Promise.resolve({ success: true, method: 'clipboard', textLength: 10, durationMs: 50 })) } vi.mock('../../../src/main/services/TextInsertService', () => ({ getTextInsertService: () => mockTextInsert })) const mockLLM = { isAvailable: vi.fn(() => false), processText: vi.fn(() => Promise.resolve('다듬어진 텍스트')), on: vi.fn(), off: vi.fn() } vi.mock('../../../src/main/services/LocalLLMService', () => ({ getLocalLLMService: () => mockLLM })) let getVoiceModeService: () => ReturnType beforeEach(async () => { vi.resetModules() vi.clearAllMocks() audioBus.removeAllListeners() config.values = { ...CONFIG_DEFAULTS } instructionStore.byId = {} voiceCommand.enabled = false voiceCommand.instructionId = null voiceCommand.cleanedText = '' mockSTT.initialize.mockResolvedValue(undefined as never) mockSTT.transcribe.mockResolvedValue({ text: '테스트 전사', segments: [], language: 'ko', duration: 2, processingTime: 500, } as never) mockLLM.processText.mockResolvedValue('다듬어진 텍스트' as never) const mod = await import('../../../src/main/services/VoiceModeService') mod.resetVoiceModeServiceForTests() getVoiceModeService = mod.getVoiceModeService }) describe('VoiceModeService', () => { describe('상태 머신', () => { it('초기 상태는 IDLE이다', () => { const svc = getVoiceModeService() const state = svc.getState() expect(state.recognitionState).toBe(RecognitionState.IDLE) expect(state.audioState).toBe(AudioState.IDLE) expect(state.sessionId).toBeNull() }) it('startSession 호출 시 PREPARING으로 전이한다', async () => { const svc = getVoiceModeService() const stateChanges: RecognitionState[] = [] svc.on('recognition-state-changed', (payload: { current: RecognitionState }) => { stateChanges.push(payload.current) }) await svc.startSession('dictation') // PREPARING → CONNECTING → READY 순서 expect(stateChanges[0]).toBe(RecognitionState.PREPARING) expect(stateChanges).toContain(RecognitionState.CONNECTING) }) it('isActive는 세션이 활성일 때 true이다', async () => { const svc = getVoiceModeService() expect(svc.isActive).toBe(false) // startSession은 완전 비동기이므로 await 후 세션 활성 확인 await svc.startSession('dictation') expect(svc.isActive).toBe(true) }) }) describe('accidentalPress', () => { it('700ms 미만 세션은 자동 취소된다', async () => { const svc = getVoiceModeService() let cancelReason: string | null = null svc.on('session-cancelled', (payload: { reason: string }) => { cancelReason = payload.reason }) // 세션 시작 즉시 종료 (700ms 미만) await svc.startSession('dictation') await svc.stopSession() expect(cancelReason).toBe('too-short') }) }) describe('STT 준비 대기', () => { it('전사가 시작된 뒤에는 readiness timeout 으로 세션을 취소하지 않는다', async () => { let resolveInit: (() => void) | undefined mockSTT.initialize.mockImplementation( () => new Promise((resolve) => { resolveInit = resolve }), ) mockSTT.transcribe.mockResolvedValue({ text: '안녕하세요', segments: [], language: 'ko', duration: 2, processingTime: 50, } as never) const svc = getVoiceModeService() let cancelReason: string | null = null let completed = false svc.on('session-cancelled', (payload: { reason: string }) => { cancelReason = payload.reason }) const completedPromise = new Promise((resolve) => { svc.once('session-completed', () => { completed = true resolve() }) }) await svc.startSession('dictation') audioBus.emit('audio-data', { buffer: Buffer.alloc(16000 * 2) }) await new Promise((r) => setTimeout(r, 850)) await svc.stopSession() resolveInit?.() await Promise.race([completedPromise, new Promise((r) => setTimeout(r, 1000))]) expect(cancelReason).not.toBe('timeout') expect(completed).toBe(true) }) }) describe('cancelSession', () => { it('user 취소로 세션을 종료한다', async () => { const svc = getVoiceModeService() let cancelReason: string | null = null svc.on('session-cancelled', (payload: { reason: string }) => { cancelReason = payload.reason }) await svc.startSession('dictation') svc.cancelSession() expect(cancelReason).toBe('user') }) }) describe('LLM 후처리 인자 전달', () => { const TRANSCRIPT = '회의 끝나고 배포하자' /** 한 세션을 끝까지 돌린다. */ async function runSession(): Promise { mockSTT.transcribe.mockResolvedValue({ text: TRANSCRIPT, segments: [], language: 'ko', duration: 2, processingTime: 50, } as never) const svc = getVoiceModeService() const settled = new Promise((resolve) => { svc.once('session-completed', () => resolve()) svc.once('session-cancelled', () => resolve()) }) await svc.startSession('dictation') audioBus.emit('audio-data', { buffer: Buffer.alloc(16000 * 2) }) await new Promise((r) => setTimeout(r, 850)) await svc.stopSession() await Promise.race([settled, new Promise((r) => setTimeout(r, 2000))]) } function registerInstruction(inst: { id: string; name: string; prompt: string }): void { instructionStore.byId[inst.id] = inst } // ── 고친 경로: 커스텀 지시문 ─────────────────────────── describe('커스텀 지시문 경로 (고친 경로)', () => { it('{{text}} 없는 지시문은 시스템 프롬프트로, 전사 텍스트는 처리 대상으로 전달한다', async () => { registerInstruction({ id: 'builtin-summarize', name: '요약', prompt: '다음 텍스트의 핵심 내용을 3줄 이내로 요약해주세요.\n요약문만 출력하세요.', }) config.values.defaultLLMAction = 'custom' config.values.activeInstructionId = 'builtin-summarize' await runSession() expect(mockLLM.processText).toHaveBeenCalledTimes(1) const [text, action, targetLanguage, systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(action).toBe('custom') expect(targetLanguage).toBeUndefined() expect(systemPrompt).toBe( '다음 텍스트의 핵심 내용을 3줄 이내로 요약해주세요.\n요약문만 출력하세요.', ) }) it('builtin-translate의 {{targetLanguage}}를 치환해 시스템 프롬프트로 전달한다', async () => { registerInstruction({ id: 'builtin-translate', name: '번역', prompt: '다음 텍스트를 {{targetLanguage}}로 번역해주세요.\n자연스럽고 정확한 번역만 출력하세요.', }) config.values.defaultLLMAction = 'custom' config.values.activeInstructionId = 'builtin-translate' await runSession() const [text, , , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(systemPrompt).toContain('English로 번역') expect(systemPrompt).not.toContain('{{') }) it('builtin-free-prompt의 {{userPrompt}}를 전사 텍스트로 치환한다', async () => { registerInstruction({ id: 'builtin-free-prompt', name: '자유 프롬프트', prompt: '{{userPrompt}}', }) config.values.defaultLLMAction = 'custom' config.values.activeInstructionId = 'builtin-free-prompt' await runSession() const [text, , , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(systemPrompt).toBe(TRANSCRIPT) }) it('{{text}}를 쓰는 사용자 정의 지시문은 치환 결과를 처리 대상 텍스트로 넘긴다', async () => { registerInstruction({ id: 'user-bullets', name: '불릿 정리', prompt: '아래 내용을 불릿으로 정리해줘:\n{{text}}', }) config.values.defaultLLMAction = 'custom' config.values.activeInstructionId = 'user-bullets' await runSession() const [text, action, , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(`아래 내용을 불릿으로 정리해줘:\n${TRANSCRIPT}`) expect(action).toBe('custom') expect(systemPrompt).toBeUndefined() }) it('지시문을 찾지 못하면 전사 텍스트만 전달한다', async () => { config.values.defaultLLMAction = 'custom' config.values.activeInstructionId = 'does-not-exist' await runSession() const [text, action, , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(action).toBe('custom') expect(systemPrompt).toBeUndefined() }) }) // ── 두 번째 진입점: 음성 단축키 ──────────────────────── describe('음성 단축키 진입점 (overrideInstructionId)', () => { it('음성 명령으로 지목된 지시문도 시스템 프롬프트로 전달한다', async () => { registerInstruction({ id: 'builtin-translate', name: '번역', prompt: '다음 텍스트를 {{targetLanguage}}로 번역해주세요.', }) voiceCommand.enabled = true voiceCommand.instructionId = 'builtin-translate' voiceCommand.cleanedText = '회의 끝나고 배포하자' config.values.defaultLLMAction = 'refine' await runSession() const [text, action, , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(action).toBe('custom') expect(systemPrompt).toBe('다음 텍스트를 English로 번역해주세요.') }) it("defaultLLMAction이 'none'이어도 음성 명령은 스킵되지 않는다", async () => { registerInstruction({ id: 'builtin-summarize', name: '요약', prompt: '다음 텍스트의 핵심 내용을 3줄 이내로 요약해주세요.', }) voiceCommand.enabled = true voiceCommand.instructionId = 'builtin-summarize' config.values.defaultLLMAction = 'none' await runSession() expect(mockLLM.processText).toHaveBeenCalledTimes(1) const [text, action, , systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(action).toBe('custom') expect(systemPrompt).toBe('다음 텍스트의 핵심 내용을 3줄 이내로 요약해주세요.') }) it("음성 명령이 없으면 'none'은 기존대로 LLM을 건너뛴다", async () => { config.values.defaultLLMAction = 'none' await runSession() expect(mockLLM.processText).not.toHaveBeenCalled() }) }) // ── 안 고친 경로: 일반 액션이 원래 맞았고 계속 맞다 ──── describe('일반 액션 경로 (수정 대상 아님 — 계속 정상이어야 한다)', () => { it.each(['refine', 'summarize', 'grammar', 'expand'])( "'%s' 액션은 전사 텍스트를 text로 넘기고 customPrompt를 넘기지 않는다", async (action) => { config.values.defaultLLMAction = action // 활성 지시문이 있어도 일반 액션 경로는 지시문을 타지 않아야 한다. registerInstruction({ id: 'builtin-summarize', name: '요약', prompt: '요약해줘' }) config.values.activeInstructionId = 'builtin-summarize' await runSession() expect(mockLLM.processText).toHaveBeenCalledTimes(1) const [text, passedAction, targetLanguage, systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(passedAction).toBe(action) expect(targetLanguage).toBeUndefined() expect(systemPrompt).toBeUndefined() }, ) it("'translate' 액션은 대상 언어를 함께 넘긴다", async () => { config.values.defaultLLMAction = 'translate' await runSession() const [text, action, targetLanguage, systemPrompt] = mockLLM.processText.mock.calls[0] expect(text).toBe(TRANSCRIPT) expect(action).toBe('translate') expect(targetLanguage).toBe('English') expect(systemPrompt).toBeUndefined() }) }) }) describe('getState', () => { it('현재 상태를 VoiceState 형태로 반환한다', () => { const svc = getVoiceModeService() const state = svc.getState() expect(state).toHaveProperty('recognitionState') expect(state).toHaveProperty('audioState') expect(state).toHaveProperty('mode') expect(state).toHaveProperty('sessionId') expect(state).toHaveProperty('recordingStartedAt') }) }) describe('터미널 상태', () => { it('cancelSession 후 _resetToIdle의 200ms 딜레이 후 IDLE로 전이한다', async () => { vi.useFakeTimers() const svc = getVoiceModeService() await svc.startSession('dictation') svc.cancelSession() // 200ms 딜레이로 IDLE 전이 예약됨 vi.advanceTimersByTime(250) const state = svc.getState() expect(state.recognitionState).toBe(RecognitionState.IDLE) vi.useRealTimers() }) }) }) describe('TIMING 상수', () => { it('핵심 타이밍 값이 Speakly 패턴과 일치한다', () => { expect(TIMING.MIN_AUDIO_DURATION).toBe(700) expect(TIMING.DOUBLE_PRESS_DURATION).toBe(300) expect(TIMING.POST_RECORDING_WAIT).toBe(4000) expect(TIMING.POST_RECORDING_WAIT_BUFFERED).toBe(6000) expect(TIMING.ABSOLUTE_MAX_WAIT).toBe(120000) expect(TIMING.AUDIO_LEVEL_INTERVAL).toBe(100) }) })