APIゲートウェイパターンとBFF設計：Kong・Envoy・GraphQL Federationの実践実装

                          API 게이트웨이 토폴로지

    ┌──────────┐  ┌──────────┐  ┌──────────┐  ┌──────────┐
    │  Web App │  │Mobile App│  │ Partner  │  │IoT Device│
    │ (React)  │  │ (Swift)  │  │  (B2B)   │  │ (MQTT)   │
    └────┬─────┘  └────┬─────┘  └────┬─────┘  └────┬─────┘
         │             │             │              │
         └──────┬──────┴──────┬──────┘              │
                │             │                     │
         ┌──────▼──────┐ ┌───▼──────────┐   ┌──────▼──────┐
         │   Edge LB   │ │  Edge LB     │   │  Edge LB    │
         │  (L4/L7)    │ │  (L4/L7)     │   │  (L4/L7)    │
         └──────┬──────┘ └──────┬───────┘   └──────┬──────┘
                │               │                  │
         ┌──────▼───────────────▼──────────────────▼──────┐
         │              API Gateway Cluster                │
         │  ┌──────────────────────────────────────────┐   │
         │  │  Auth │ Rate Limit │ Logging │ Transform │   │
         │  └──────────────────────────────────────────┘   │
         │  ┌─────────────────────────────────────────┐    │
         │  │        Route Matching & Dispatch         │    │
         │  └─────────────────────────────────────────┘    │
         └───────┬──────────┬──────────┬──────────┬───────┘
                 │          │          │          │
          ┌──────▼───┐┌────▼────┐┌────▼────┐┌───▼──────┐
          │ User Svc ││Order Svc││Pay Svc  ││Notify Svc│
          │ (gRPC)   ││ (REST)  ││ (REST)  ││(WebSocket│
          └──────────┘└─────────┘└─────────┘└──────────┘

    외부 트래픽
        │
    ┌───▼────────────────────────┐
    │   Edge Gateway (Kong)      │  ← TLS 종료, WAF, 레이트 리미팅
    │   - DDoS 방어              │
    │   - JWT 검증               │
    │   - 글로벌 레이트 리미팅    │
    └───────────┬────────────────┘
                │
    ┌───────────▼────────────────┐
    │  Internal Gateway (Envoy)  │  ← mTLS, 서비스 라우팅
    │   - mTLS 상호 인증         │
    │   - 서비스 디스커버리       │
    │   - 세밀한 RBAC            │
    └──┬────────┬────────┬───────┘
       │        │        │
    ┌──▼──┐  ┌──▼──┐  ┌──▼──┐
    │Svc A│  │Svc B│  │Svc C│
    └─────┘  └─────┘  └─────┘

    ┌──────────┐     ┌──────────┐     ┌──────────┐
    │  Web App │     │Mobile App│     │ Admin App│
    │ (React)  │     │ (Flutter)│     │ (Vue.js) │
    └────┬─────┘     └────┬─────┘     └────┬─────┘
         │                │                │
    ┌────▼─────┐     ┌────▼─────┐     ┌────▼─────┐
    │ Web BFF  │     │Mobile BFF│     │Admin BFF │
    │(Node.js) │     │  (Go)    │     │(Node.js) │
    │          │     │          │     │          │
    │- 풍부한  │     │- 경량    │     │- 대시보드│
    │  데이터  │     │  페이로드│     │  집계    │
    │- SSR 지원│     │- 오프라인│     │- 벌크    │
    │- SEO     │     │  캐싱    │     │  연산    │
    └──┬───┬───┘     └──┬───┬───┘     └──┬───┬───┘
       │   │            │   │            │   │
       │   └────────┬───┘   └────────┬───┘   │
       │            │                │       │
    ┌──▼──┐     ┌───▼──┐         ┌───▼──┐   │
    │User │     │Order │         │Admin │◄──┘
    │ Svc │     │ Svc  │         │ Svc  │
    └─────┘     └──────┘         └──────┘

// web-bff/src/server.ts
import express from 'express'
import axios from 'axios'

const app = express()

// Web BFF: 대시보드를 위한 데이터 집계 엔드포인트
app.get('/api/dashboard', async (req, res) => {
  const userId = req.headers['x-user-id'] as string

  try {
    // 여러 마이크로서비스에서 병렬로 데이터 수집
    const [userProfile, recentOrders, notifications, analytics] = await Promise.all([
      axios.get(`${process.env.USER_SERVICE_URL}/users/${userId}`),
      axios.get(`${process.env.ORDER_SERVICE_URL}/orders?userId=${userId}&limit=10`),
      axios.get(`${process.env.NOTIFICATION_SERVICE_URL}/notifications/${userId}?unread=true`),
      axios.get(`${process.env.ANALYTICS_SERVICE_URL}/users/${userId}/summary`),
    ])

    // Web 프론트엔드에 최적화된 응답 구조
    res.json({
      user: {
        name: userProfile.data.name,
        email: userProfile.data.email,
        avatar: userProfile.data.avatarUrl,
        memberSince: userProfile.data.createdAt,
      },
      orders: {
        recent: recentOrders.data.items.map((order: any) => ({
          id: order.id,
          status: order.status,
          total: order.totalAmount,
          date: order.createdAt,
          itemCount: order.items.length,
          // 웹에서만 필요한 상세 정보 포함
          trackingUrl: order.trackingUrl,
          invoice: order.invoiceUrl,
        })),
        totalCount: recentOrders.data.totalCount,
      },
      notifications: {
        unreadCount: notifications.data.count,
        items: notifications.data.items.slice(0, 5),
      },
      analytics: {
        totalSpent: analytics.data.totalSpent,
        orderFrequency: analytics.data.orderFrequency,
        favoriteCategories: analytics.data.topCategories,
      },
    })
  } catch (error) {
    // 부분 실패 시 가용한 데이터만 반환 (Graceful Degradation)
    res.status(207).json({
      partial: true,
      error: 'Some services are unavailable',
      available: {},
    })
  }
})

// Mobile BFF와의 차이점: 웹은 SSR을 위한 전체 데이터를 반환
// Mobile BFF는 동일 엔드포인트에서 경량 필드만 반환
app.listen(3001, () => {
  console.log('Web BFF running on port 3001')
})

# kong-values.yaml - Helm Chart 설정
# helm install kong kong/ingress -f kong-values.yaml -n kong-system

gateway:
  image:
    repository: kong/kong-gateway
    tag: '3.9'
  env:
    database: 'off' # DB-less 모드 (선언적 설정)
    proxy_access_log: /dev/stdout
    admin_access_log: /dev/stdout
    proxy_error_log: /dev/stderr
    admin_error_log: /dev/stderr
    plugins: bundled,oidc,prometheus
  proxy:
    type: LoadBalancer
    annotations:
      service.beta.kubernetes.io/aws-load-balancer-type: nlb
      service.beta.kubernetes.io/aws-load-balancer-scheme: internet-facing
    tls:
      enabled: true
  admin:
    enabled: true
    type: ClusterIP # 클러스터 내부에서만 접근
  resources:
    requests:
      cpu: 500m
      memory: 512Mi
    limits:
      cpu: 2000m
      memory: 2Gi

controller:
  image:
    repository: kong/kubernetes-ingress-controller
    tag: '3.4'
  ingressClass: kong
  resources:
    requests:
      cpu: 250m
      memory: 256Mi

# kong-gateway-api.yaml
# Kubernetes Gateway API를 사용한 선언적 라우팅 구성
apiVersion: gateway.networking.k8s.io/v1
kind: Gateway
metadata:
  name: kong-gateway
  namespace: kong-system
  annotations:
    konghq.com/gateway-operator: 'true'
spec:
  gatewayClassName: kong
  listeners:
    - name: http
      protocol: HTTP
      port: 80
    - name: https
      protocol: HTTPS
      port: 443
      tls:
        mode: Terminate
        certificateRefs:
          - name: api-tls-cert
            kind: Secret
---
# HTTPRoute로 서비스별 라우팅 정의
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  name: user-service-route
  namespace: default
  annotations:
    konghq.com/plugins: rate-limiting-global,jwt-auth,cors
spec:
  parentRefs:
    - name: kong-gateway
      namespace: kong-system
  hostnames:
    - 'api.example.com'
  rules:
    - matches:
        - path:
            type: PathPrefix
            value: /api/v1/users
      backendRefs:
        - name: user-service
          port: 8080
          weight: 100
    - matches:
        - path:
            type: PathPrefix
            value: /api/v1/orders
      backendRefs:
        - name: order-service
          port: 8080
          weight: 90
        - name: order-service-canary
          port: 8080
          weight: 10 # 카나리 배포: 10% 트래픽
---
# Kong 플러그인: JWT 인증
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: jwt-auth
  namespace: default
config:
  key_claim_name: iss
  claims_to_verify:
    - exp
  header_names:
    - Authorization
plugin: jwt
---
# Kong 플러그인: 레이트 리미팅
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: rate-limiting-global
  namespace: default
config:
  minute: 100
  hour: 5000
  policy: redis
  redis:
    host: redis-master.redis-system.svc.cluster.local
    port: 6379
    database: 0
    timeout: 2000
  fault_tolerant: true # Redis 장애 시에도 요청 통과
  hide_client_headers: false
plugin: rate-limiting
---
# Kong 플러그인: CORS
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: cors
  namespace: default
config:
  origins:
    - 'https://app.example.com'
    - 'https://admin.example.com'
  methods:
    - GET
    - POST
    - PUT
    - DELETE
    - OPTIONS
  headers:
    - Authorization
    - Content-Type
    - X-Request-ID
  exposed_headers:
    - X-RateLimit-Remaining
  max_age: 3600
  credentials: true
plugin: cors

# envoy-config.yaml
# Envoy 프록시 정적 설정 (프로덕션에서는 xDS 동적 설정 사용 권장)
admin:
  address:
    socket_address:
      address: 0.0.0.0
      port_value: 9901

static_resources:
  listeners:
    - name: api_listener
      address:
        socket_address:
          address: 0.0.0.0
          port_value: 8443
      filter_chains:
        - filters:
            - name: envoy.filters.network.http_connection_manager
              typed_config:
                '@type': type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
                stat_prefix: ingress_http
                codec_type: AUTO
                # 액세스 로그 설정
                access_log:
                  - name: envoy.access_loggers.file
                    typed_config:
                      '@type': type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
                      path: /dev/stdout
                      log_format:
                        json_format:
                          timestamp: '%START_TIME%'
                          method: '%REQ(:METHOD)%'
                          path: '%REQ(X-ENVOY-ORIGINAL-PATH?:PATH)%'
                          protocol: '%PROTOCOL%'
                          response_code: '%RESPONSE_CODE%'
                          duration_ms: '%DURATION%'
                          upstream_host: '%UPSTREAM_HOST%'
                          request_id: '%REQ(X-REQUEST-ID)%'
                # HTTP 필터 체인
                http_filters:
                  # JWT 인증 필터
                  - name: envoy.filters.http.jwt_authn
                    typed_config:
                      '@type': type.googleapis.com/envoy.extensions.filters.http.jwt_authn.v3.JwtAuthentication
                      providers:
                        auth0_provider:
                          issuer: 'https://your-tenant.auth0.com/'
                          audiences:
                            - 'https://api.example.com'
                          remote_jwks:
                            http_uri:
                              uri: 'https://your-tenant.auth0.com/.well-known/jwks.json'
                              cluster: auth0_jwks
                              timeout: 5s
                            cache_duration: 600s
                          forward: true
                          payload_in_metadata: jwt_payload
                      rules:
                        - match:
                            prefix: /api/
                          requires:
                            provider_name: auth0_provider
                        - match:
                            prefix: /health
                  # 레이트 리미팅 필터
                  - name: envoy.filters.http.local_ratelimit
                    typed_config:
                      '@type': type.googleapis.com/envoy.extensions.filters.http.local_ratelimit.v3.LocalRateLimit
                      stat_prefix: http_local_rate_limiter
                      token_bucket:
                        max_tokens: 1000
                        tokens_per_fill: 100
                        fill_interval: 1s
                      filter_enabled:
                        runtime_key: local_rate_limit_enabled
                        default_value:
                          numerator: 100
                          denominator: HUNDRED
                      filter_enforced:
                        runtime_key: local_rate_limit_enforced
                        default_value:
                          numerator: 100
                          denominator: HUNDRED
                      response_headers_to_add:
                        - append_action: OVERWRITE_IF_EXISTS_OR_ADD
                          header:
                            key: x-local-rate-limit
                            value: 'true'
                  # 라우터 필터 (반드시 마지막)
                  - name: envoy.filters.http.router
                    typed_config:
                      '@type': type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
                # 라우트 설정
                route_config:
                  name: local_route
                  virtual_hosts:
                    - name: api_service
                      domains: ['api.example.com']
                      routes:
                        - match:
                            prefix: '/api/v1/users'
                          route:
                            cluster: user_service
                            timeout: 10s
                            retry_policy:
                              retry_on: '5xx,connect-failure,reset'
                              num_retries: 3
                              per_try_timeout: 3s
                              retry_back_off:
                                base_interval: 0.1s
                                max_interval: 1s
                        - match:
                            prefix: '/api/v1/orders'
                          route:
                            cluster: order_service
                            timeout: 15s
                            retry_policy:
                              retry_on: '5xx,connect-failure'
                              num_retries: 2
          transport_socket:
            name: envoy.transport_sockets.tls
            typed_config:
              '@type': type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.DownstreamTlsContext
              common_tls_context:
                tls_certificates:
                  - certificate_chain:
                      filename: /etc/envoy/certs/server.crt
                    private_key:
                      filename: /etc/envoy/certs/server.key

  clusters:
    - name: user_service
      type: STRICT_DNS
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: user_service
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: user-service.default.svc.cluster.local
                      port_value: 8080
      # 서킷 브레이커 설정
      circuit_breakers:
        thresholds:
          - priority: DEFAULT
            max_connections: 1024
            max_pending_requests: 1024
            max_requests: 1024
            max_retries: 3
      # 헬스 체크
      health_checks:
        - timeout: 5s
          interval: 10s
          unhealthy_threshold: 3
          healthy_threshold: 2
          http_health_check:
            path: /health
      # Outlier Detection (이상 탐지)
      outlier_detection:
        consecutive_5xx: 5
        interval: 10s
        base_ejection_time: 30s
        max_ejection_percent: 50

    - name: order_service
      type: STRICT_DNS
      lb_policy: LEAST_REQUEST
      load_assignment:
        cluster_name: order_service
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: order-service.default.svc.cluster.local
                      port_value: 8080
      circuit_breakers:
        thresholds:
          - priority: DEFAULT
            max_connections: 512
            max_pending_requests: 512

    - name: auth0_jwks
      type: LOGICAL_DNS
      lb_policy: ROUND_ROBIN
      load_assignment:
        cluster_name: auth0_jwks
        endpoints:
          - lb_endpoints:
              - endpoint:
                  address:
                    socket_address:
                      address: your-tenant.auth0.com
                      port_value: 443
      transport_socket:
        name: envoy.transport_sockets.tls
        typed_config:
          '@type': type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
          sni: your-tenant.auth0.com

    ┌──────────────────────────────────────────────────┐
    │                  클라이언트                        │
    │              (Web / Mobile App)                   │
    └────────────────────┬─────────────────────────────┘
                         │ GraphQL 쿼리
    ┌────────────────────▼─────────────────────────────┐
    │              Apollo Router                        │
    │         (슈퍼그래프 실행 엔진)                     │
    │                                                  │
    │  ┌────────────────────────────────────────────┐   │
    │  │       Query Plan (쿼리 실행 계획)           │   │
    │  │  1. users 서브그래프에서 User 조회          │   │
    │  │  2. orders 서브그래프에서 Order 조회        │   │
    │  │  3. reviews 서브그래프에서 Review 조회      │   │
    │  │  4. 결과 병합 후 클라이언트에 반환          │   │
    │  └────────────────────────────────────────────┘   │
    └───────┬───────────────┬───────────────┬──────────┘
            │               │               │
    ┌───────▼──────┐ ┌──────▼──────┐ ┌──────▼──────┐
    │ Users        │ │ Orders      │ │ Reviews     │
    │ Subgraph     │ │ Subgraph    │ │ Subgraph    │
    │ (Team A)     │ │ (Team B)    │ │ (Team C)    │
    │              │ │             │ │             │
    │ - User       │ │ - Order     │ │ - Review    │
    │ - Profile    │ │ - LineItem  │ │ - Rating    │
    │              │ │ - extends   │ │ - extends   │
    │              │ │   User      │ │   User      │
    └──────────────┘ └─────────────┘ └─────────────┘

// subgraphs/users/src/index.ts
import { ApolloServer } from '@apollo/server'
import { startStandaloneServer } from '@apollo/server/standalone'
import { buildSubgraphSchema } from '@apollo/subgraph'
import { gql } from 'graphql-tag'

const typeDefs = gql`
  extend schema
    @link(
      url: "https://specs.apollo.dev/federation/v2.11"
      import: ["@key", "@shareable", "@external", "@provides"]
    )

  type Query {
    user(id: ID!): User
    users(limit: Int = 10, offset: Int = 0): UserConnection!
    me: User
  }

  type User @key(fields: "id") {
    id: ID!
    email: String!
    name: String!
    avatarUrl: String
    role: UserRole!
    createdAt: String!
    updatedAt: String!
  }

  type UserConnection {
    nodes: [User!]!
    totalCount: Int!
    pageInfo: PageInfo!
  }

  type PageInfo @shareable {
    hasNextPage: Boolean!
    hasPreviousPage: Boolean!
  }

  enum UserRole {
    ADMIN
    USER
    MODERATOR
  }
`

const resolvers = {
  Query: {
    user: async (_: any, { id }: { id: string }, context: any) => {
      return context.dataSources.usersAPI.getUser(id)
    },
    users: async (_: any, args: any, context: any) => {
      return context.dataSources.usersAPI.getUsers(args)
    },
    me: async (_: any, __: any, context: any) => {
      if (!context.userId) throw new Error('Not authenticated')
      return context.dataSources.usersAPI.getUser(context.userId)
    },
  },
  User: {
    __resolveReference: async (ref: { id: string }, context: any) => {
      // Federation이 다른 서브그래프에서 User를 참조할 때 호출
      return context.dataSources.usersAPI.getUser(ref.id)
    },
  },
}

const server = new ApolloServer({
  schema: buildSubgraphSchema({ typeDefs, resolvers }),
})

const { url } = await startStandaloneServer(server, {
  listen: { port: 4001 },
  context: async ({ req }) => ({
    userId: req.headers['x-user-id'],
    dataSources: {
      usersAPI: new UsersDataSource(),
    },
  }),
})

console.log(`Users subgraph ready at ${url}`)

// subgraphs/orders/src/index.ts
import { ApolloServer } from '@apollo/server'
import { buildSubgraphSchema } from '@apollo/subgraph'
import { gql } from 'graphql-tag'

const typeDefs = gql`
  extend schema
    @link(
      url: "https://specs.apollo.dev/federation/v2.11"
      import: ["@key", "@external", "@requires"]
    )

  type Query {
    order(id: ID!): Order
    ordersByUser(userId: ID!, status: OrderStatus): [Order!]!
  }

  # User 타입을 확장하여 orders 필드 추가
  type User @key(fields: "id") {
    id: ID! @external
    orders(status: OrderStatus, limit: Int = 10): [Order!]!
    totalSpent: Float! @requires(fields: "id")
  }

  type Order @key(fields: "id") {
    id: ID!
    userId: ID!
    user: User!
    items: [OrderItem!]!
    status: OrderStatus!
    totalAmount: Float!
    currency: String!
    createdAt: String!
    shippingAddress: Address
  }

  type OrderItem {
    productId: ID!
    productName: String!
    quantity: Int!
    unitPrice: Float!
  }

  type Address {
    street: String!
    city: String!
    country: String!
    zipCode: String!
  }

  enum OrderStatus {
    PENDING
    CONFIRMED
    SHIPPED
    DELIVERED
    CANCELLED
  }
`

const resolvers = {
  Query: {
    order: async (_: any, { id }: { id: string }, ctx: any) => {
      return ctx.dataSources.ordersAPI.getOrder(id)
    },
    ordersByUser: async (_: any, args: any, ctx: any) => {
      return ctx.dataSources.ordersAPI.getOrdersByUser(args.userId, args.status)
    },
  },
  User: {
    orders: async (user: { id: string }, args: any, ctx: any) => {
      return ctx.dataSources.ordersAPI.getOrdersByUser(user.id, args.status)
    },
    totalSpent: async (user: { id: string }, _: any, ctx: any) => {
      return ctx.dataSources.ordersAPI.getTotalSpent(user.id)
    },
  },
  Order: {
    user: (order: { userId: string }) => ({ __typename: 'User', id: order.userId }),
  },
}

# supergraph-config.yaml
# rover supergraph compose --config supergraph-config.yaml > supergraph.graphql
federation_version: =2.11.2
subgraphs:
  users:
    routing_url: http://users-subgraph:4001/graphql
    schema:
      subgraph_url: http://users-subgraph:4001/graphql
  orders:
    routing_url: http://orders-subgraph:4002/graphql
    schema:
      subgraph_url: http://orders-subgraph:4002/graphql
  reviews:
    routing_url: http://reviews-subgraph:4003/graphql
    schema:
      subgraph_url: http://reviews-subgraph:4003/graphql

# router-config.yaml (Apollo Router 설정)
supergraph:
  listen: 0.0.0.0:4000
  introspection: false # 프로덕션에서는 비활성화

# 헤더 전파
headers:
  all:
    request:
      - propagate:
          named: 'Authorization'
      - propagate:
          named: 'X-Request-ID'
      - propagate:
          named: 'X-User-ID'

# 서브그래프별 설정
traffic_shaping:
  all:
    timeout: 10s
  subgraphs:
    orders:
      timeout: 15s # 주문 서비스는 더 긴 타임아웃

# 쿼리 깊이 제한 (DoS 방지)
limits:
  max_depth: 15
  max_height: 200
  max_aliases: 30

# 텔레메트리
telemetry:
  exporters:
    tracing:
      otlp:
        enabled: true
        endpoint: http://otel-collector:4317
        protocol: grpc
    metrics:
      prometheus:
        enabled: true
        listen: 0.0.0.0:9090
        path: /metrics

# 응답 캐싱
preview_entity_cache:
  enabled: true
  subgraph:
    all:
      enabled: true
      ttl: 60s

// gateway/src/middleware/auth.ts
import jwt from 'jsonwebtoken'
import jwksClient from 'jwks-rsa'
import { Request, Response, NextFunction } from 'express'

// JWKS 클라이언트 (키 캐싱 포함)
const client = jwksClient({
  jwksUri: `${process.env.AUTH0_DOMAIN}/.well-known/jwks.json`,
  cache: true,
  cacheMaxEntries: 5,
  cacheMaxAge: 600000, // 10분
  rateLimit: true,
  jwksRequestsPerMinute: 10,
})

function getSigningKey(header: jwt.JwtHeader): Promise<string> {
  return new Promise((resolve, reject) => {
    client.getSigningKey(header.kid, (err, key) => {
      if (err) return reject(err)
      const signingKey = key?.getPublicKey()
      if (!signingKey) return reject(new Error('No signing key found'))
      resolve(signingKey)
    })
  })
}

// 경로별 인증 정책
const AUTH_POLICIES: Record<string, { required: boolean; scopes?: string[] }> = {
  '/api/v1/users/me': { required: true, scopes: ['read:profile'] },
  '/api/v1/orders': { required: true, scopes: ['read:orders'] },
  '/api/v1/admin': { required: true, scopes: ['admin:all'] },
  '/health': { required: false },
  '/api/v1/products': { required: false }, // 공개 API
}

export async function authMiddleware(
  req: Request,
  res: Response,
  next: NextFunction
): Promise<void> {
  // 경로별 정책 조회
  const policy = Object.entries(AUTH_POLICIES).find(([path]) => req.path.startsWith(path))

  if (policy && !policy[1].required) {
    return next()
  }

  const authHeader = req.headers.authorization
  if (!authHeader?.startsWith('Bearer ')) {
    res.status(401).json({
      error: 'unauthorized',
      message: 'Missing or invalid Authorization header',
    })
    return
  }

  const token = authHeader.substring(7)

  try {
    // JWT 디코딩 (검증 전 헤더 확인)
    const decoded = jwt.decode(token, { complete: true })
    if (!decoded || typeof decoded === 'string') {
      throw new Error('Invalid token format')
    }

    // 알고리즘 화이트리스트 검증
    if (!['RS256', 'ES256'].includes(decoded.header.alg)) {
      throw new Error(`Unsupported algorithm: ${decoded.header.alg}`)
    }

    // JWKS에서 공개 키를 가져와 서명 검증
    const signingKey = await getSigningKey(decoded.header)
    const payload = jwt.verify(token, signingKey, {
      algorithms: ['RS256', 'ES256'],
      audience: process.env.API_AUDIENCE,
      issuer: `${process.env.AUTH0_DOMAIN}/`,
      clockTolerance: 30, // 30초 시계 오차 허용
    }) as jwt.JwtPayload

    // 스코프 검증
    if (policy?.[1]?.scopes) {
      const tokenScopes = (payload.scope || '').split(' ')
      const requiredScopes = policy[1].scopes
      const hasAllScopes = requiredScopes.every((s) => tokenScopes.includes(s))

      if (!hasAllScopes) {
        res.status(403).json({
          error: 'insufficient_scope',
          message: `Required scopes: ${requiredScopes.join(', ')}`,
        })
        return
      }
    }

    // 검증된 클레임을 헤더로 전파 (하위 서비스에서 사용)
    req.headers['x-user-id'] = payload.sub || ''
    req.headers['x-user-email'] = payload.email || ''
    req.headers['x-user-roles'] = JSON.stringify(payload['https://api.example.com/roles'] || [])
    req.headers['x-auth-time'] = String(payload.iat || 0)

    // 원본 Authorization 헤더는 제거 (하위 서비스에 토큰 노출 방지)
    delete req.headers.authorization

    next()
  } catch (error: any) {
    const errorMap: Record<string, { status: number; message: string }> = {
      TokenExpiredError: { status: 401, message: 'Token has expired' },
      JsonWebTokenError: { status: 401, message: 'Invalid token' },
      NotBeforeError: { status: 401, message: 'Token not yet valid' },
    }

    const mapped = errorMap[error.name] || { status: 401, message: 'Authentication failed' }
    res.status(mapped.status).json({ error: error.name, message: mapped.message })
  }
}

// gateway/src/middleware/rateLimiter.ts
import Redis from 'ioredis'

const redis = new Redis({
  host: process.env.REDIS_HOST || 'localhost',
  port: parseInt(process.env.REDIS_PORT || '6379'),
  maxRetriesPerRequest: 3,
  retryStrategy: (times) => Math.min(times * 100, 3000),
  enableReadyCheck: true,
})

interface RateLimitConfig {
  windowMs: number // 시간 창 (밀리초)
  maxRequests: number // 최대 요청 수
  keyPrefix: string // Redis 키 프리픽스
}

// 슬라이딩 윈도우 레이트 리미터 (Redis Sorted Set 활용)
async function slidingWindowRateLimit(
  identifier: string,
  config: RateLimitConfig
): Promise<{ allowed: boolean; remaining: number; retryAfter?: number }> {
  const key = `${config.keyPrefix}:${identifier}`
  const now = Date.now()
  const windowStart = now - config.windowMs

  // Redis 트랜잭션으로 원자적 처리
  const pipeline = redis.pipeline()
  pipeline.zremrangebyscore(key, 0, windowStart) // 만료된 항목 제거
  pipeline.zadd(key, now.toString(), `${now}:${Math.random()}`) // 현재 요청 추가
  pipeline.zcard(key) // 현재 윈도우 내 요청 수
  pipeline.expire(key, Math.ceil(config.windowMs / 1000)) // TTL 설정

  const results = await pipeline.exec()
  if (!results) throw new Error('Redis pipeline failed')

  const currentCount = results[2]?.[1] as number
  const allowed = currentCount <= config.maxRequests
  const remaining = Math.max(0, config.maxRequests - currentCount)

  if (!allowed) {
    // 가장 오래된 요청이 만료되는 시점 계산
    const oldestInWindow = await redis.zrange(key, 0, 0, 'WITHSCORES')
    const retryAfter =
      oldestInWindow.length >= 2
        ? Math.ceil((parseInt(oldestInWindow[1]) + config.windowMs - now) / 1000)
        : Math.ceil(config.windowMs / 1000)

    return { allowed: false, remaining: 0, retryAfter }
  }

  return { allowed: true, remaining }
}

// 티어별 레이트 리미팅 정책
const RATE_LIMIT_TIERS: Record<string, RateLimitConfig> = {
  free: { windowMs: 60_000, maxRequests: 60, keyPrefix: 'rl:free' },
  pro: { windowMs: 60_000, maxRequests: 600, keyPrefix: 'rl:pro' },
  enterprise: { windowMs: 60_000, maxRequests: 6000, keyPrefix: 'rl:enterprise' },
  // IP 기반 글로벌 제한 (DDoS 방어)
  global_ip: { windowMs: 1_000, maxRequests: 50, keyPrefix: 'rl:ip' },
}

export async function rateLimitMiddleware(req: any, res: any, next: any) {
  const clientIp = req.headers['x-forwarded-for']?.split(',')[0]?.trim() || req.ip
  const userId = req.headers['x-user-id']
  const tier = req.headers['x-user-tier'] || 'free'

  try {
    // 1단계: IP 기반 글로벌 레이트 리미팅
    const ipResult = await slidingWindowRateLimit(clientIp, RATE_LIMIT_TIERS.global_ip)
    if (!ipResult.allowed) {
      res.set('Retry-After', String(ipResult.retryAfter))
      return res.status(429).json({ error: 'Too many requests (IP limit)' })
    }

    // 2단계: 사용자/티어 기반 레이트 리미팅
    if (userId) {
      const config = RATE_LIMIT_TIERS[tier] || RATE_LIMIT_TIERS.free
      const userResult = await slidingWindowRateLimit(userId, config)

      res.set('X-RateLimit-Limit', String(config.maxRequests))
      res.set('X-RateLimit-Remaining', String(userResult.remaining))

      if (!userResult.allowed) {
        res.set('Retry-After', String(userResult.retryAfter))
        return res.status(429).json({ error: 'Rate limit exceeded', tier })
      }
    }

    next()
  } catch (error) {
    // Redis 장애 시 요청을 통과시킴 (fault-tolerant)
    console.error('Rate limiter error:', error)
    next()
  }
}

// gateway/src/middleware/circuitBreaker.ts
enum CircuitState {
  CLOSED = 'CLOSED', // 정상 - 요청 통과
  OPEN = 'OPEN', // 차단 - 즉시 실패 반환
  HALF_OPEN = 'HALF_OPEN', // 테스트 - 제한적 요청 허용
}

interface CircuitBreakerConfig {
  failureThreshold: number // 실패 임계치 (예: 5)
  successThreshold: number // 복구 판정 성공 횟수 (예: 3)
  timeout: number // Open 상태 유지 시간 (ms)
  monitorWindow: number // 모니터링 윈도우 (ms)
  halfOpenMaxRequests: number // Half-Open에서 허용할 최대 요청
}

class CircuitBreaker {
  private state: CircuitState = CircuitState.CLOSED
  private failureCount = 0
  private successCount = 0
  private lastFailureTime = 0
  private halfOpenRequests = 0

  constructor(
    private name: string,
    private config: CircuitBreakerConfig
  ) {}

  async execute<T>(fn: () => Promise<T>, fallback?: () => T): Promise<T> {
    if (this.state === CircuitState.OPEN) {
      if (Date.now() - this.lastFailureTime >= this.config.timeout) {
        this.transitionTo(CircuitState.HALF_OPEN)
      } else {
        console.warn(`[CircuitBreaker:${this.name}] OPEN - rejecting request`)
        if (fallback) return fallback()
        throw new Error(`Service ${this.name} is unavailable (circuit open)`)
      }
    }

    if (this.state === CircuitState.HALF_OPEN) {
      if (this.halfOpenRequests >= this.config.halfOpenMaxRequests) {
        if (fallback) return fallback()
        throw new Error(`Service ${this.name} is testing recovery`)
      }
      this.halfOpenRequests++
    }

    try {
      const result = await fn()
      this.onSuccess()
      return result
    } catch (error) {
      this.onFailure()
      if (fallback && this.state === CircuitState.OPEN) return fallback()
      throw error
    }
  }

  private onSuccess() {
    if (this.state === CircuitState.HALF_OPEN) {
      this.successCount++
      if (this.successCount >= this.config.successThreshold) {
        this.transitionTo(CircuitState.CLOSED)
      }
    }
    this.failureCount = 0
  }

  private onFailure() {
    this.failureCount++
    this.lastFailureTime = Date.now()
    if (this.failureCount >= this.config.failureThreshold) {
      this.transitionTo(CircuitState.OPEN)
    }
  }

  private transitionTo(newState: CircuitState) {
    console.log(`[CircuitBreaker:${this.name}] ${this.state} -> ${newState}`)
    this.state = newState
    if (newState === CircuitState.CLOSED) {
      this.failureCount = 0
      this.successCount = 0
    }
    if (newState === CircuitState.HALF_OPEN) {
      this.halfOpenRequests = 0
      this.successCount = 0
    }
  }

  getStatus() {
    return {
      name: this.name,
      state: this.state,
      failureCount: this.failureCount,
      lastFailureTime: this.lastFailureTime ? new Date(this.lastFailureTime).toISOString() : null,
    }
  }
}

// 서비스별 서킷 브레이커 인스턴스
export const circuitBreakers = {
  userService: new CircuitBreaker('user-service', {
    failureThreshold: 5,
    successThreshold: 3,
    timeout: 30_000, // 30초 후 Half-Open 전환
    monitorWindow: 60_000, // 1분 모니터링 윈도우
    halfOpenMaxRequests: 3,
  }),
  orderService: new CircuitBreaker('order-service', {
    failureThreshold: 3,
    successThreshold: 2,
    timeout: 60_000, // 결제 관련은 보수적으로 60초
    monitorWindow: 60_000,
    halfOpenMaxRequests: 1,
  }),
}

# otel-collector-config.yaml
# OpenTelemetry Collector 설정 - 게이트웨이 트래픽 수집
receivers:
  otlp:
    protocols:
      grpc:
        endpoint: 0.0.0.0:4317
      http:
        endpoint: 0.0.0.0:4318

processors:
  batch:
    timeout: 5s
    send_batch_size: 1024
  # 게이트웨이 메타데이터 추가
  attributes:
    actions:
      - key: deployment.environment
        value: production
        action: upsert
      - key: service.layer
        value: gateway
        action: upsert
  # 샘플링 (전체의 10%만 상세 트레이스)
  tail_sampling:
    decision_wait: 10s
    policies:
      - name: error-policy
        type: status_code
        status_code:
          status_codes: [ERROR]
      - name: latency-policy
        type: latency
        latency:
          threshold_ms: 1000
      - name: probabilistic-policy
        type: probabilistic
        probabilistic:
          sampling_percentage: 10

exporters:
  otlphttp/jaeger:
    endpoint: http://jaeger:4318
  prometheus:
    endpoint: 0.0.0.0:8889
  loki:
    endpoint: http://loki:3100/loki/api/v1/push
    labels:
      resource:
        service.name: 'service_name'
        service.layer: 'layer'

service:
  pipelines:
    traces:
      receivers: [otlp]
      processors: [batch, attributes, tail_sampling]
      exporters: [otlphttp/jaeger]
    metrics:
      receivers: [otlp]
      processors: [batch, attributes]
      exporters: [prometheus]
    logs:
      receivers: [otlp]
      processors: [batch, attributes]
      exporters: [loki]

# Kong: 요청/응답 본문 버퍼링 제한
apiVersion: configuration.konghq.com/v1
kind: KongPlugin
metadata:
  name: request-size-limiting
config:
  allowed_payload_size: 10 # MB
  size_unit: megabytes
  require_content_length: true
plugin: request-size-limiting

# Envoy: 버퍼 제한 설정
http_filters:
  - name: envoy.filters.http.buffer
    typed_config:
      '@type': type.googleapis.com/envoy.extensions.filters.http.buffer.v3.Buffer
      max_request_bytes: 10485760 # 10MB

# 인증서 만료일 확인 스크립트
#!/bin/bash
DOMAIN="api.example.com"
EXPIRY=$(echo | openssl s_client -servername $DOMAIN -connect $DOMAIN:443 2>/dev/null \
  | openssl x509 -noout -dates 2>/dev/null \
  | grep notAfter | cut -d= -f2)

EXPIRY_EPOCH=$(date -d "$EXPIRY" +%s 2>/dev/null || date -j -f "%b %d %T %Y %Z" "$EXPIRY" +%s)
NOW_EPOCH=$(date +%s)
DAYS_LEFT=$(( (EXPIRY_EPOCH - NOW_EPOCH) / 86400 ))

echo "Certificate expires: $EXPIRY ($DAYS_LEFT days remaining)"

if [ "$DAYS_LEFT" -lt 30 ]; then
  echo "WARNING: Certificate expiring soon!"
  # 슬랙/PagerDuty 알림 전송
fi