d3ro-voice/apps/desktop/src/main/services/PremiumLLMService.ts

// src/main/services/PremiumLLMService.ts
// Phase 3.2: Anthropic Claude 프리미엄 LLM 서비스.
// 내부적으로는 온라인 API를 호출한다.
// Supabase Edge Function(`llm-proxy`)을 경유해 Claude Messages API를 호출.
//
// 특징:
// - 싱글톤 + EventEmitter (설계서 01 패턴)
// - processText(), chatStream() — 시그니처 동일
// - 네트워크 실패 / 401 / 429 / 5xx 감지 시 에러 throw → LLMRouterService가 local로 fallback
// - quota-warning / upgrade-required / fallback-triggered 이벤트 emit

import { EventEmitter } from 'events'
import { getLogger } from './LoggerService'
import { getCloudSyncService } from './CloudSyncService'
import { D3ROError, ErrorCode } from '@d3ro/core/errors'
import type { LLMAction } from '@d3ro/core/types'
import { resolveSystemPrompt } from './llm-prompts'
import { parseAnthropicSSE } from '../utils/sse-parser'

const logger = getLogger('PremiumLLMService')

// ============================================================
// 내부 타입
// ============================================================

/** Ollama-style 메시지 → Claude Messages 변환용 */
interface ChatMessage {
  role: 'user' | 'assistant'
  content: string
}

/** llm-proxy Edge Function 요청 body */
interface LlmProxyRequest {
  messages: ChatMessage[]
  system?: string
  max_tokens?: number
  model?: string
  stream?: boolean
}

/** Claude Messages API 비스트리밍 응답 */
interface ClaudeMessageResponse {
  id: string
  model: string
  role: 'assistant'
  content: Array<{ type: 'text'; text: string }>
  stop_reason: string
  usage: { input_tokens: number; output_tokens: number }
}

export interface QuotaUsageSnapshot {
  tier: 'free' | 'pro' | 'pro_plus'
  current: number
  limit: number
  overageCredits: number
}

interface PremiumLLMEvents {
  'quota-warning': (payload: { current: number; limit: number; overageCredits: number }) => void
  'upgrade-required': (payload: { reason: 'quota_exceeded' | 'model_not_allowed' | 'auth_required' }) => void
  'fallback-triggered': (payload: { reason: string }) => void
}

// ============================================================
// PremiumLLMService
// ============================================================

class PremiumLLMService extends EventEmitter {
  private _abortController: AbortController | null = null
  private _disposed = false
  private _lastQuota: QuotaUsageSnapshot | null = null

  /**
   * 사용 가능 여부 — Supabase URL + access token 모두 있어야 true.
   * (LLMRouter가 local/premium 분기 시 호출)
   */
  isAvailable(): boolean {
    const cloud = getCloudSyncService()
    return cloud.isEnabled() && cloud.isAuthenticated()
  }

  /**
   * 마지막 응답에서 서버가 알려준 쿼터 상태.
   * Settings UI에서 "오늘 X/250" 표시에 사용.
   */
  getLastQuota(): QuotaUsageSnapshot | null {
    return this._lastQuota
  }

  /**
   * disposed / 미인증 상태 공통 가드.
   * 문제 시 D3ROError throw, upgrade-required emit.
   */
  private _ensureAuth(): void {
    if (this._disposed) {
      throw new D3ROError(ErrorCode.LLMProcessingFailed, 'PremiumLLMService disposed')
    }
    const cloud = getCloudSyncService()
    if (!cloud.isEnabled() || !cloud.isAuthenticated()) {
      this.emit('upgrade-required', { reason: 'auth_required' })
      throw new D3ROError(
        ErrorCode.LLMServerUnreachable,
        'Premium LLM 사용 전 로그인 필요',
      )
    }
  }

  /**
   * 텍스트 액션 처리.
   * Phase 3.2 MVP는 비스트리밍 (stream=false).
   */
  async processText(
    text: string,
    action: LLMAction,
    targetLanguage?: string,
    customPrompt?: string,
  ): Promise<string> {
    this._ensureAuth()

    const systemPrompt = resolveSystemPrompt(action, targetLanguage, customPrompt)

    const body: LlmProxyRequest = {
      messages: [{ role: 'user', content: text }],
      system: systemPrompt,
      max_tokens: 2048,
      stream: false,
    }

    try {
      const response = await this._invokeProxy(body)
      // Claude 응답 → text 추출
      const firstBlock = response.content?.[0]
      if (!firstBlock || firstBlock.type !== 'text' || !firstBlock.text.trim()) {
        throw new D3ROError(ErrorCode.LLMProcessingFailed, 'Premium LLM returned empty content')
      }
      return firstBlock.text.trim()
    } catch (err) {
      // LLMRouter가 local fallback 처리. 여기서는 에러 전파.
      if (err instanceof D3ROError) throw err
      throw new D3ROError(
        ErrorCode.LLMProcessingFailed,
        `Premium LLM failed: ${err instanceof Error ? err.message : String(err)}`,
      )
    }
  }

  /**
   * 스트리밍 대화 (Voice Conversation용).
   * SSE 스트리밍: llm-proxy에 stream=true로 요청, Anthropic SSE를 토큰 단위 yield.
   */
  async *chatStream(
    messages: Array<{ role: string; content: string }>,
    options?: { model?: string; temperature?: number },
  ): AsyncGenerator<string, string> {
    this._ensureAuth()

    const claudeMessages: ChatMessage[] = messages
      .filter((m) => m.role === 'user' || m.role === 'assistant')
      .map((m) => ({ role: m.role as 'user' | 'assistant', content: m.content }))

    const body: LlmProxyRequest = {
      messages: claudeMessages,
      model: options?.model,
      max_tokens: 2048,
      stream: true,
    }

    this._abortController = new AbortController()
    const cloud = getCloudSyncService()

    const { stream, error } = await cloud.invokeFunctionStream(
      'llm-proxy',
      body as unknown as Record<string, unknown>,
      this._abortController.signal,
    )

    if (error || !stream) {
      const msg = error?.message ?? 'Stream unavailable'
      logger.error(`SSE stream failed: ${msg}`)

      // SSE 실패 시 비스트리밍 fallback
      logger.info('Falling back to non-streaming Premium LLM')
      const fallbackBody = { ...body, stream: false }
      const response = await this._invokeProxy(fallbackBody)
      const firstBlock = response.content?.[0]
      const text = firstBlock?.type === 'text' ? firstBlock.text : ''
      if (text.length > 0) yield text
      return text
    }

    let accumulated = ''
    try {
      for await (const token of parseAnthropicSSE(stream)) {
        accumulated += token
        yield token
      }
    } catch (err) {
      if ((err as Error).name !== 'AbortError') {
        logger.warn(`SSE parse error: ${err instanceof Error ? err.message : String(err)}`)
      }
    } finally {
      this._abortController = null
    }

    return accumulated
  }

  /**
   * 제목/요약/액션 플랜 등 자유 생성. processText 와 같은 프록시 경로를 탄다.
   */
  async generate(
    text: string,
    options?: { systemPrompt?: string; temperature?: number; maxTokens?: number },
  ): Promise<{ text: string }> {
    this._ensureAuth()
    const response = await this._invokeProxy({
      messages: [{ role: 'user', content: text }],
      system: options?.systemPrompt,
      max_tokens: options?.maxTokens ?? 2048,
      stream: false,
    })
    const firstBlock = response.content?.[0]
    if (!firstBlock || firstBlock.type !== 'text' || !firstBlock.text.trim()) {
      throw new D3ROError(ErrorCode.LLMProcessingFailed, 'Premium LLM generate returned empty content')
    }
    return { text: firstBlock.text.trim() }
  }

  cancelGeneration(): void {
    if (this._abortController) {
      this._abortController.abort()
      this._abortController = null
      logger.info('Premium LLM generation cancelled')
    }
  }

  dispose(): void {
    this._disposed = true
    this.cancelGeneration()
    this.removeAllListeners()
    logger.info('PremiumLLMService disposed')
  }

  // ── 내부: Edge Function 호출 ─────────────────────────────

  private async _invokeProxy(body: LlmProxyRequest): Promise<ClaudeMessageResponse> {
    const cloud = getCloudSyncService()

    // Supabase JS 클라이언트의 functions.invoke() 사용 — auth 헤더를 올바르게 처리.
    // raw fetch + Authorization: Bearer 방식은 Supabase gateway가 401로 거부.
    const { data, error } = await cloud.invokeFunction('llm-proxy', body as unknown as Record<string, unknown>)

    if (error) {
      const msg = error.message ?? 'Edge Function error'
      logger.error(`llm-proxy error: ${msg}`)

      // 에러 메시지 기반 분류
      if (msg.includes('401') || msg.includes('Unauthorized') || msg.includes('auth')) {
        this.emit('upgrade-required', { reason: 'auth_required' })
        throw new D3ROError(ErrorCode.LLMServerUnreachable, `인증 실패: ${msg}`)
      }
      if (msg.includes('quota_exceeded') || msg.includes('429')) {
        this.emit('upgrade-required', { reason: 'quota_exceeded' })
        throw new D3ROError(ErrorCode.LLMProcessingFailed, `쿼터 초과: ${msg}`)
      }
      if (msg.includes('model_not_allowed') || msg.includes('403')) {
        this.emit('upgrade-required', { reason: 'model_not_allowed' })
        throw new D3ROError(ErrorCode.LLMInvalidAction, `모델 권한 없음: ${msg}`)
      }

      throw new D3ROError(ErrorCode.LLMProcessingFailed, `llm-proxy: ${msg}`)
    }

    // functions.invoke는 response body를 자동 파싱해서 data에 넣음
    const result = data as ClaudeMessageResponse
    if (!result?.content) {
      logger.warn('llm-proxy returned unexpected shape — falling back')
      throw new D3ROError(ErrorCode.LLMProcessingFailed, 'llm-proxy returned invalid response')
    }

    return result
  }

  // ── EventEmitter 타입 오버라이드 ───────────────────────

  on<K extends keyof PremiumLLMEvents>(event: K, listener: PremiumLLMEvents[K]): this {
    return super.on(event, listener)
  }

  emit<K extends keyof PremiumLLMEvents>(
    event: K,
    ...args: Parameters<PremiumLLMEvents[K]>
  ): boolean {
    return super.emit(event, ...args)
  }
}

// ── 싱글톤 ─────────────────────────────────────────────────

let _instance: PremiumLLMService | null = null

export function resetPremiumLLMServiceForTests(): void {
  if (_instance) _instance.removeAllListeners()
  _instance = null
}

export function getPremiumLLMService(): PremiumLLMService {
  if (!_instance) {
    _instance = new PremiumLLMService()
  }
  return _instance
}

export type { PremiumLLMService }