Phase 1+2 구현: Electron 뼈대 + STT/핫키/오케스트레이터

Phase 1:
- 프로젝트 초기화 (TypeScript strict, electron-vite, ESLint, Prettier)
- shared 타입 (ipc-channels 113채널, types, errors, constants)
- 메인 프로세스 뼈대 (bootstrap, lifecycle, 단일 인스턴스)
- LoggerService, ConfigService (electron-store ESM dynamic import)
- React 19 + MUI 7 Dashboard, 시스템 트레이

Phase 2:
- AudioCaptureService (node-record-lpcm16, PCM16 16kHz mono)
- HotkeyService (uiohook-napi, 더블프레스, holdMode/toggleMode)
- LocalSTTService (faster-whisper Python sidecar, 이중 조건 플러시)
- VoiceModeService 오케스트레이터 (이중 상태머신, Action Queue)
- Python sidecar (FastAPI: health/load/transcribe/shutdown)
- IPC 핸들러 (voice, stt, hotkey) + Preload API 확장
This commit is contained in:
Yun Chan 2026-04-05 02:01:37 +09:00
parent e24bb8378c
commit 1d152d01a1
46 changed files with 10828 additions and 4 deletions

658
src/shared/types.ts Normal file
View file

@ -0,0 +1,658 @@
// src/shared/types.ts
// 모든 IPC 파라미터/반환 타입 정의
// ============================================================
// Common
// ============================================================
export type ThemeMode = 'light' | 'dark' | 'auto'
export type VoiceMode = 'dictation' | 'hands-free'
export type PermissionStatus = 'granted' | 'denied' | 'unknown'
// ============================================================
// Voice (음성 오케스트레이션)
// ============================================================
export enum RecognitionState {
IDLE = 'idle',
PREPARING = 'preparing',
CONNECTING = 'connecting',
READY = 'ready',
RECOGNIZING = 'recognizing',
COMPLETED = 'completed',
CANCELLED = 'cancelled',
ERROR = 'error',
DESTROYED = 'destroyed'
}
export enum AudioState {
IDLE = 'idle',
INITIALIZING = 'initializing',
STREAMING = 'streaming',
STOPPED = 'stopped'
}
export interface VoiceState {
recognitionState: RecognitionState
audioState: AudioState
mode: VoiceMode
sessionId: string | null
recordingStartedAt: number | null
}
export interface StartRecordingParams {
sessionId?: string
deviceId?: string
}
export interface StartRecordingResult {
sessionId: string
}
export interface StopRecordingParams {
sessionId: string
}
export interface StopRecordingResult {
sessionId: string
text: string
durationMs: number
}
export interface CancelRecordingParams {
sessionId: string
}
export interface SetVoiceModeParams {
mode: VoiceMode
}
// Voice events (Main → Renderer)
export interface VoiceStateChangedEvent {
previousState: RecognitionState
currentState: RecognitionState
audioState: AudioState
sessionId: string | null
}
export interface TranscriptionDeltaEvent {
sessionId: string
text: string
delta: string
isFinal: boolean
}
export interface TranscriptionCompleteEvent {
sessionId: string
text: string
durationMs: number
language: string
}
export interface VoiceErrorEvent {
sessionId: string | null
errorCode: number
message: string
}
export interface AudioLevelEvent {
level: number
}
// ============================================================
// Audio (디바이스 & 캡처)
// ============================================================
export interface AudioDevice {
deviceId: string
label: string
isDefault: boolean
}
export interface SetDeviceParams {
deviceId: string
}
export interface TestDeviceParams {
deviceId: string
durationMs?: number
}
export interface TestDeviceResult {
averageLevel: number
peakLevel: number
hasAudio: boolean
}
export interface AudioDeviceChangedEvent {
devices: AudioDevice[]
type: 'added' | 'removed' | 'default-changed'
}
// ============================================================
// STT (로컬 Whisper)
// ============================================================
export enum STTEngineState {
NOT_INSTALLED = 'not-installed',
DOWNLOADING = 'downloading',
LOADING = 'loading',
READY = 'ready',
PROCESSING = 'processing',
ERROR = 'error'
}
export interface STTStatus {
engineState: STTEngineState
activeModel: string | null
engineVersion: string | null
gpuAccelerated: boolean
}
export interface STTModel {
id: string
name: string
sizeBytes: number
downloaded: boolean
languages: string[]
accuracy: number
speed: number
}
export interface SetSTTModelParams {
modelId: string
}
export interface DownloadModelParams {
modelId: string
}
export interface SetSTTLanguageParams {
language: string
}
export interface STTStatusChangedEvent {
status: STTStatus
}
export interface DownloadProgressEvent {
modelId: string
percent: number
downloadedBytes: number
totalBytes: number
bytesPerSecond: number
}
// ============================================================
// TTS (로컬 TTS)
// ============================================================
export enum TTSEngineState {
NOT_INSTALLED = 'not-installed',
LOADING = 'loading',
READY = 'ready',
SPEAKING = 'speaking',
ERROR = 'error'
}
export interface TTSStatus {
engineState: TTSEngineState
activeVoice: string | null
engineVersion: string | null
}
export interface TTSVoice {
id: string
name: string
language: string
gender: 'male' | 'female' | 'neutral'
downloaded: boolean
sizeBytes: number
}
export interface TTSSpeakParams {
text: string
voiceId?: string
speed?: number
}
export interface TTSSpeakResult {
durationMs: number
}
export interface SetTTSVoiceParams {
voiceId: string
}
export interface DownloadVoiceParams {
voiceId: string
}
export interface TTSStatusChangedEvent {
status: TTSStatus
}
export interface SpeakingStateChangedEvent {
isSpeaking: boolean
text: string
}
// ============================================================
// LLM (Ollama)
// ============================================================
export enum LLMConnectionState {
DISCONNECTED = 'disconnected',
CONNECTING = 'connecting',
CONNECTED = 'connected',
ERROR = 'error'
}
export interface LLMStatus {
connectionState: LLMConnectionState
serverUrl: string
activeModel: string | null
serverVersion: string | null
}
export interface LLMModel {
id: string
name: string
sizeBytes: number
parameterSize: string
quantization: string
modifiedAt: string
}
export type LLMAction = 'refine' | 'translate' | 'summarize' | 'expand' | 'grammar' | 'custom'
export interface LLMProcessParams {
text: string
action: LLMAction
targetLanguage?: string
customPrompt?: string
modelId?: string
}
export interface LLMProcessResult {
originalText: string
processedText: string
action: LLMAction
processingTimeMs: number
tokenCount: number
}
export interface SetLLMModelParams {
modelId: string
}
export interface SetServerUrlParams {
url: string
}
export interface PullModelParams {
modelName: string
}
export interface LLMStatusChangedEvent {
status: LLMStatus
}
export interface LLMProcessProgressEvent {
text: string
token: string
done: boolean
}
export interface LLMPullProgressEvent {
modelName: string
status: string
percent: number
downloadedBytes: number
totalBytes: number
}
// ============================================================
// Hotkey (핫키)
// ============================================================
export interface HotkeyBinding {
keyCode: number
ctrl: boolean
alt: boolean
shift: boolean
meta: boolean
displayLabel: string
}
export interface SetHotkeyParams {
binding: HotkeyBinding
}
export interface SetEnabledParams {
enabled: boolean
}
export type HotkeyAction = 'dictation' | 'hands-free' | 'command'
export interface HotkeyTriggeredEvent {
action: HotkeyAction
type: 'pressed' | 'released'
isDoublePress: boolean
}
export interface HotkeyRecordingResultEvent {
binding: HotkeyBinding | null
conflictReason: string | null
}
// ============================================================
// Config (설정)
// ============================================================
export interface AppConfig {
theme: ThemeMode
language: string
closeToTray: boolean
autoLaunch: boolean
soundEnabled: boolean
selectedDeviceId: string | null
sttModelId: string
sttLanguage: string
ttsVoiceId: string | null
ttsSpeed: number
ollamaServerUrl: string
llmModelId: string | null
defaultLLMAction: LLMAction
dictationShortcut: HotkeyBinding
handsFreeShortcut: HotkeyBinding
commandShortcut: HotkeyBinding
hotkeyEnabled: boolean
insertMethod: 'clipboard' | 'keyboard'
autoInsert: boolean
maxHistoryEntries: number
}
export interface ConfigGetParams {
key: keyof AppConfig
}
export interface ConfigSetParams {
key: keyof AppConfig
value: AppConfig[keyof AppConfig]
}
export interface ConfigResetParams {
key?: keyof AppConfig
}
export interface SetThemeParams {
theme: ThemeMode
}
export interface SetLanguageParams {
language: string
}
export interface SetAutoLaunchParams {
enabled: boolean
}
export interface SetCloseToTrayParams {
enabled: boolean
}
export interface ConfigChangedEvent {
key: keyof AppConfig
value: AppConfig[keyof AppConfig]
previousValue: AppConfig[keyof AppConfig]
}
// ============================================================
// History (히스토리)
// ============================================================
export interface HistoryEntry {
id: string
originalText: string
polishedText: string | null
focusedApp: string | null
focusedAppName: string | null
focusedAppWindowTitle: string | null
mode: 'dictation' | 'translate' | 'command'
status: 'completed' | 'cancelled' | 'error'
errorCode: string | null
audioLocalPath: string | null
duration: number
detectedLanguage: string | null
micDevice: string | null
wordCount: number
sttModel: string | null
llmModel: string | null
sttLatencyMs: number | null
llmLatencyMs: number | null
createdAt: number
updatedAt: number
appVersion: string
}
export interface HistoryQueryParams {
page: number
pageSize: number
sortBy?: 'createdAt' | 'durationMs' | 'wordCount'
sortOrder?: 'asc' | 'desc'
}
export interface HistoryPage {
entries: HistoryEntry[]
total: number
page: number
pageSize: number
totalPages: number
}
export interface HistoryGetByIdParams {
id: string
}
export interface HistoryDeleteParams {
id: string
}
export interface HistorySearchParams {
query: string
page: number
pageSize: number
}
export interface HistoryExportParams {
format: 'json' | 'csv'
from?: string
to?: string
}
// ============================================================
// Dictionary (사전)
// ============================================================
export interface DictionaryEntry {
id: string
word: string
pronunciation: string | null
category: 'user' | 'auto' | 'technical'
usageCount: number
lastUsedAt: number | null
createdAt: number
updatedAt: number
}
export interface DictionaryQueryParams {
page: number
pageSize: number
sortBy?: 'word' | 'category' | 'usageCount' | 'createdAt'
sortOrder?: 'asc' | 'desc'
}
export interface DictionaryPage {
entries: DictionaryEntry[]
total: number
page: number
pageSize: number
totalPages: number
}
export interface DictionaryAddParams {
word: string
pronunciation?: string
category?: 'user' | 'auto' | 'technical'
}
export interface DictionaryUpdateParams {
id: string
word?: string
pronunciation?: string
category?: 'user' | 'auto' | 'technical'
}
export interface DictionaryDeleteParams {
id: string
}
export interface DictionaryImportParams {
filePath: string
format: 'json' | 'csv'
}
export interface DictionaryImportResult {
imported: number
skipped: number
errors: number
}
export interface DictionaryExportParams {
format: 'json' | 'csv'
}
export interface DictionarySearchParams {
query: string
page: number
pageSize: number
}
// ============================================================
// Window (윈도우 제어)
// ============================================================
export type RecordingTipState = 'opening' | 'recording' | 'thinking' | 'result' | 'error'
export interface ShowRecordingTipParams {
state: RecordingTipState
text?: string
errorMessage?: string
}
export interface ShowResultPopupParams {
text: string
autoHideMs?: number
}
export interface TipMeasuredParams {
width: number
height: number
}
export interface TipStateChangedEvent {
state: RecordingTipState
text?: string
errorMessage?: string
}
export interface TipPrepareEvent {
state: RecordingTipState
text?: string
}
export interface TipShowEvent {
state: RecordingTipState
}
// ============================================================
// System (시스템)
// ============================================================
export interface ActiveAppInfo {
name: string
title: string
pid: number
}
export interface ShowNotificationParams {
title: string
body: string
type?: 'info' | 'warning' | 'error'
}
export interface OpenExternalParams {
url: string
}
export interface InsertTextParams {
text: string
method?: 'clipboard' | 'keyboard'
}
export interface InsertTextResult {
success: boolean
insertedLength: number
}
export type SoundEffect =
| 'recording-start'
| 'recording-stop'
| 'transcription-complete'
| 'error'
| 'notification'
export interface PlaySoundParams {
sound: SoundEffect
}
export interface SetSoundEnabledParams {
enabled: boolean
}
// ============================================================
// Stats (통계)
// ============================================================
export interface StatsSummary {
totalRecordingTimeMs: number
totalWordCount: number
totalSessionCount: number
todayRecordingTimeMs: number
todayWordCount: number
todaySessionCount: number
streakDays: number
}
export interface StatsQueryParams {
from: string
to: string
}
export interface DailyStats {
date: string
recordingTimeMs: number
wordCount: number
sessionCount: number
}
export interface WeeklyStats {
weekStart: string
recordingTimeMs: number
wordCount: number
sessionCount: number
}