d3ro-voice/server/supabase/functions/llm-proxy/index.ts

// server/supabase/functions/llm-proxy/index.ts
// Anthropic Claude Messages API 프록시.
// Phase 3.2: 모델별 쿼터 (Haiku/Sonnet/Opus × Free/Pro/Pro+)
// 요청: application/json { messages, system?, max_tokens?, model? }
// 응답: JSON (non-stream) 또는 SSE (stream=true)

import { corsHeaders, handleCorsPreflightRequest } from '../_shared/cors.ts'
import { requireUser, authErrorResponse, type AuthError } from '../_shared/auth.ts'
import {
  checkQuota,
  consumeQuota,
  createServiceRoleClient,
  modelToQuotaKey,
  getQuotaPolicy,
  type Tier,
} from '../_shared/quota.ts'

interface LlmRequest {
  messages: Array<{ role: 'user' | 'assistant'; content: string }>
  system?: string
  max_tokens?: number
  model?: string
  stream?: boolean
}

/** 티어별 허용 모델 — free는 Haiku만, pro는 +Sonnet, pro_plus는 +Opus, team/enterprise는 전 모델 */
const TIER_MODELS: Record<Tier, string[]> = {
  free: ['claude-haiku-4-5-20251001'],
  pro: ['claude-haiku-4-5-20251001', 'claude-sonnet-4-6', 'claude-opus-4-6'],
  pro_plus: ['claude-haiku-4-5-20251001', 'claude-sonnet-4-6', 'claude-opus-4-6'],
  team: ['claude-haiku-4-5-20251001', 'claude-sonnet-4-6', 'claude-opus-4-6'],
  enterprise: ['claude-haiku-4-5-20251001', 'claude-sonnet-4-6', 'claude-opus-4-6'],
}

const DEFAULT_MODEL: Record<Tier, string> = {
  free: 'claude-haiku-4-5-20251001',
  pro: 'claude-sonnet-4-6',
  pro_plus: 'claude-sonnet-4-6',
  team: 'claude-sonnet-4-6',
  enterprise: 'claude-sonnet-4-6',
}

// @ts-expect-error — Deno 런타임 전역
Deno.serve(async (req: Request) => {
  const preflight = handleCorsPreflightRequest(req)
  if (preflight) return preflight

  if (req.method !== 'POST') {
    return new Response(JSON.stringify({ error: 'Method not allowed' }), {
      status: 405,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' },
    })
  }

  try {
    const user = await requireUser(req)
    const serviceClient = createServiceRoleClient()

    const body = (await req.json()) as LlmRequest

    // 1단계: 티어 조회 (어떤 모델이든 한 번만 읽으면 됨 — haiku로 대리 조회)
    const tierCheck = await checkQuota(user.id, 'llm_haiku', serviceClient)
    const tier = tierCheck.tier

    // 모델 선택 + 티어 검증
    const requestedModel = body.model ?? DEFAULT_MODEL[tier]
    if (!TIER_MODELS[tier].includes(requestedModel)) {
      return new Response(
        JSON.stringify({
          error: 'model_not_allowed',
          tier,
          requested: requestedModel,
          allowed: TIER_MODELS[tier],
        }),
        {
          status: 403,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' },
        },
      )
    }

    // 2단계: 해당 모델의 쿼터 확인 (모델별 일간/주간)
    const quotaKey = modelToQuotaKey(requestedModel)
    const modelQuota = await checkQuota(user.id, quotaKey, serviceClient)
    if (!modelQuota.allowed) {
      return new Response(
        JSON.stringify({
          error: 'quota_exceeded',
          model: requestedModel,
          current: modelQuota.current,
          limit: modelQuota.limit,
          period: modelQuota.period,
          tier,
          overage_credits: modelQuota.overageCredits,
        }),
        {
          status: 429,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' },
        },
      )
    }

    // 3단계: 쿼터 소비 (원자적 base → overage fallback)
    const policy = getQuotaPolicy(tier, quotaKey)
    const consume = await consumeQuota(user.id, quotaKey, serviceClient, policy.limit)
    if (!consume.allowed) {
      return new Response(
        JSON.stringify({
          error: 'quota_exceeded',
          model: requestedModel,
          current: consume.current,
          limit: consume.limit,
          tier,
          overage_credits: consume.overageCredits,
        }),
        {
          status: 429,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' },
        },
      )
    }

    // Anthropic API 호출
    // @ts-expect-error — Deno.env
    const anthropicKey = Deno.env.get('ANTHROPIC_API_KEY') ?? ''

    if (!anthropicKey) {
      // Placeholder 응답 (키 미설정 시)
      if (body.stream) {
        const encoder = new TextEncoder()
        const stream = new ReadableStream({
          start(controller) {
            const msg = '[llm-proxy placeholder — ANTHROPIC_API_KEY 미설정]'
            for (const ch of msg) {
              controller.enqueue(
                encoder.encode(
                  `data: ${JSON.stringify({ type: 'content_block_delta', delta: { type: 'text_delta', text: ch } })}\n\n`,
                ),
              )
            }
            controller.enqueue(encoder.encode('data: [DONE]\n\n'))
            controller.close()
          },
        })
        return new Response(stream, {
          status: 200,
          headers: {
            ...corsHeaders,
            'Content-Type': 'text/event-stream',
            'Cache-Control': 'no-cache',
            Connection: 'keep-alive',
          },
        })
      }

      return new Response(
        JSON.stringify({
          id: `msg_placeholder_${Date.now()}`,
          model: requestedModel,
          role: 'assistant',
          content: [
            {
              type: 'text',
              text: '[llm-proxy placeholder — ANTHROPIC_API_KEY 미설정]',
            },
          ],
          stop_reason: 'end_turn',
          usage: { input_tokens: 0, output_tokens: 0 },
        }),
        {
          status: 200,
          headers: { ...corsHeaders, 'Content-Type': 'application/json' },
        },
      )
    }

    // 실제 Anthropic API 호출 (Prompt Caching 2024-07-31 활성화)
    const systemPayload = body.system
      ? [
          {
            type: 'text',
            text: body.system,
            cache_control: { type: 'ephemeral' },
          },
        ]
      : undefined

    const anthropicResp = await fetch('https://api.anthropic.com/v1/messages', {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'x-api-key': anthropicKey,
        'anthropic-version': '2023-06-01',
        'anthropic-beta': 'prompt-caching-2024-07-31',
      },
      body: JSON.stringify({
        model: requestedModel,
        max_tokens: body.max_tokens ?? 2048,
        system: systemPayload,
        messages: body.messages,
        stream: body.stream ?? false,
      }),
    })

    if (!anthropicResp.ok) {
      const errText = await anthropicResp.text()
      throw new Error(`Anthropic ${anthropicResp.status}: ${errText.slice(0, 500)}`)
    }

    if (body.stream && anthropicResp.body) {
      return new Response(anthropicResp.body, {
        status: 200,
        headers: {
          ...corsHeaders,
          'Content-Type': 'text/event-stream',
          'Cache-Control': 'no-cache',
          Connection: 'keep-alive',
        },
      })
    }

    const data = await anthropicResp.json()
    return new Response(JSON.stringify(data), {
      status: 200,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' },
    })
  } catch (err) {
    if (err && typeof err === 'object' && 'status' in err && 'message' in err) {
      return authErrorResponse(err as AuthError, corsHeaders)
    }
    const message = err instanceof Error ? err.message : 'Unknown error'
    return new Response(JSON.stringify({ error: message }), {
      status: 500,
      headers: { ...corsHeaders, 'Content-Type': 'application/json' },
    })
  }
})