feat(sidebar&conversation): 新增动态获取客户历史消息功能，完善参数传递

1. 为ScriptRecommend组件新增customerId参数，支持从父组件传入客户ID
2. 添加动态获取最后一条学员消息的逻辑，从后端API拉取会话历史
3. 为ArchiveMessageEvent类添加Jackson忽略未知属性注解
4. 新增部署文档和项目说明文档AGENTS.md、CLAUDE.md

AGENTS.md

@@ -0,0 +1,111 @@
+# Agent Instructions for 九艺AI坐席辅助系统
+
+## 部署规则（核心）
+
+### ⚠️ 任何代码修改后必须同步服务器部署
+
+**无论前端、后台还是后端，任何代码修改完成后，都必须立即同步到服务器并重新部署，绝对不能只做本地修改就结束。**
+
+---
+
+## 一、前端 Sidebar 部署
+
+**模块路径**: `frontend/sidebar/`
+**服务器部署路径**: `/www/wwwroot/deploy-package/frontend/sidebar/`
+**容器名称**: `ai-assistant-sidebar`
+**访问地址**: `https://ai.9artedu.com/sidebar/`
+
+### 部署流程
+```bash
+# 1. 本地构建
+cd frontend/sidebar && npm run build
+
+# 2. 同步到服务器
+scp -r -o StrictHostKeyChecking=no -i root.pem frontend/sidebar/dist/* root@8.133.162.25:/www/wwwroot/deploy-package/frontend/sidebar/dist/
+
+# 3. SSH 登录服务器，重新构建镜像并重启容器
+ssh -o StrictHostKeyChecking=no -i root.pem root@8.133.162.25 << 'EOF'
+cd /www/wwwroot/deploy-package/frontend/sidebar
+docker build -t deploy-package-sidebar .
+docker stop ai-assistant-sidebar
+docker rm ai-assistant-sidebar
+cd /www/wwwroot/deploy-package
+docker-compose up -d sidebar
+EOF
+```
+
+---
+
+## 二、后台 Admin 部署
+
+**模块路径**: `frontend/admin/`
+**服务器部署路径**: `/www/wwwroot/deploy-package/frontend/admin/`
+**容器名称**: `ai-assistant-admin`
+**访问地址**: `https://ai.9artedu.com/admin/`
+
+### 部署流程
+```bash
+# 1. 本地构建
+cd frontend/admin && npm run build
+
+# 2. 同步到服务器
+scp -r -o StrictHostKeyChecking=no -i root.pem frontend/admin/dist/* root@8.133.162.25:/www/wwwroot/deploy-package/frontend/admin/dist/
+
+# 3. SSH 登录服务器，重新构建镜像并重启容器
+ssh -o StrictHostKeyChecking=no -i root.pem root@8.133.162.25 << 'EOF'
+cd /www/wwwroot/deploy-package/frontend/admin
+docker build -t deploy-package-admin .
+docker stop ai-assistant-admin
+docker rm ai-assistant-admin
+cd /www/wwwroot/deploy-package
+docker-compose up -d admin
+EOF
+```
+
+---
+
+## 三、后端微服务部署
+
+**模块路径**: `backend/*-service/`
+**服务器部署路径**: `/www/wwwroot/deploy-package/backend/*-service/`
+**技术栈**: Spring Boot + Docker Compose
+
+### 微服务列表
+| 服务名 | 容器名 | 端口 | 部署路径 |
+|--------|--------|------|----------|
+| gateway | ai-assistant-gateway | 8080 | `backend/gateway/` |
+| auth-service | ai-assistant-auth | 8081 | `backend/auth-service/` |
+| archive-service | ai-assistant-archive | 8082 | `backend/archive-service/` |
+| conversation-service | ai-assistant-conversation | 8083 | `backend/conversation-service/` |
+| intent-service | ai-assistant-intent | 8084 | `backend/intent-service/` |
+| recommend-service | ai-assistant-recommend | 8085 | `backend/recommendation-service/` |
+| generation-service | ai-assistant-generation | 8086 | `backend/generation-service/` |
+| kb-admin-service | ai-assistant-kbadmin | 8087 | `backend/kb-admin-service/` |
+| analytics-service | ai-assistant-analytics | 8088 | `backend/analytics-service/` |
+
+### 部署流程（以某个服务为例）
+```bash
+# 1. 本地构建 JAR 包（通常在对应服务目录下）
+cd backend/auth-service && mvn clean package -DskipTests
+
+# 2. 将 JAR 包同步到服务器的 deploy-package 对应目录
+scp -o StrictHostKeyChecking=no -i root.pem target/*.jar root@8.133.162.25:/www/wwwroot/deploy-package/backend/auth-service/
+
+# 3. SSH 登录服务器，重启对应容器
+ssh -o StrictHostKeyChecking=no -i root.pem root@8.133.162.25 << 'EOF'
+cd /www/wwwroot/deploy-package
+docker-compose up -d --build auth-service
+EOF
+```
+
+---
+
+## 服务器信息
+
+- **IP**: `8.133.162.25`
+- **SSH 私钥**: `root.pem`（项目根目录）
+- **部署根目录**: `/www/wwwroot/deploy-package/`
+- **Docker Compose 文件**: `/www/wwwroot/deploy-package/docker-compose.yml`
+- **前端站点**: `https://ai.9artedu.com/sidebar/`
+- **后台站点**: `https://ai.9artedu.com/admin/`
+- **代理**: 宝塔 Nginx → Docker Nginx (8089) → 各容器

CLAUDE.md

@@ -0,0 +1,120 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+九艺AI坐席辅助系统 — A real-time script recommendation system for course consultants/sales reps at 9artedu.com. It captures WeCom (企业微信) conversations, analyzes intent, builds customer profiles, and recommends sales scripts to agents via a sidebar H5 interface.
+
+## Architecture
+
+The system uses a microservices architecture with 10 backend services, all sharing a `common` module. An API Gateway routes requests by path prefix to individual services.
+
+```
+nginx (port 80)
+  → gateway (port 8080) — Spring Cloud Gateway, routes by /api/v1/*
+    → auth-service         (8081) — WeCom OAuth, JWT, JS-SDK signing
+    → archive-service      (8082) — WeCom archive C SDK via JNA, RSA decrypt, callbacks
+    → conversation-service (8083) — Session management, context windows (Redis List)
+    → intent-service       (8084) — Intent recognition (40 scenarios), customer profiles
+    → recommendation-svc   (8085) — 3-layer recall, multi-factor ranking, MMR reranking
+    → generation-service   (8086) — Tongyi Qianwen (DashScope) API, prompt engine
+    → kb-admin-service     (8087) — Script CRUD, category management, import/export
+    → analytics-service    (8088) — Statistics, script effectiveness analysis
+  → admin frontend (port 5174) — React + Ant Design (script library management, dashboards)
+  → sidebar frontend (port 5173) — React + Ant Design Mobile (agent-facing H5 sidebar)
+```
+
+### Key Design Patterns
+
+- **Unified API response**: All services use `Result<T>` from `common` module (`code: 0` = success, `code: -1` = failure, with `message` and `timestamp`)
+- **Pagination**: `PageResult<T>` for list responses
+- **Database**: MyBatis-Plus with logical delete (`deleted` field: 0/1), auto-fill handler for timestamps
+- **Config**: All services use environment variables for infra hosts (`MYSQL_HOST`, `REDIS_HOST`, `RABBITMQ_HOST`), allowing local dev with `localhost` and containerized with service names
+- **Data pipeline**: WeCom callback → archive-service → RabbitMQ → conversation-service → intent-service → recommendation-service → WebSocket push to sidebar
+
+## Development Commands
+
+### Backend (Java 8 / Spring Boot 2.7.18)
+
+```bash
+# Build all services from backend/
+cd backend && mvn clean package -DskipTests
+
+# Run a single service locally (e.g., conversation-service)
+cd backend/conversation-service && mvn spring-boot:run
+
+# Run a specific test
+cd backend/conversation-service && mvn test -Dtest=ConversationControllerTest
+
+# Run all tests
+cd backend && mvn test
+```
+
+### Frontend
+
+```bash
+# Sidebar (agent-facing H5)
+cd frontend/sidebar && npm install && npm run dev
+
+# Admin dashboard
+cd frontend/admin && npm install && npm run dev
+
+# Build for production
+cd frontend/sidebar && npm run build
+cd frontend/admin && npm run build
+```
+
+### Docker (full stack)
+
+```bash
+# Start all services
+docker compose up -d
+
+# Start only infrastructure (MySQL, Redis, RabbitMQ)
+docker compose up -d mysql redis rabbitmq
+
+# View logs for a service
+docker compose logs -f conversation-service
+
+# Rebuild and restart a specific service
+docker compose up -d --build recommendation-service
+```
+
+### Database
+
+- `init.sql` — Full schema (15+ tables) + seed data. Loaded into MySQL on first `docker compose up`.
+- `backend/utterances_cg.sql` — CG training script seed data
+- `add_utterances.sql` — Additional utterance data
+
+## Service Ports Reference
+
+| Service | Port |
+|---------|------|
+| Gateway | 8080 |
+| Auth | 8081 |
+| Archive | 8082 |
+| Conversation | 8083 |
+| Intent | 8084 |
+| Recommendation | 8085 |
+| Generation | 8086 |
+| KB Admin | 8087 |
+| Analytics | 8088 |
+| Admin Frontend | 5174 |
+| Sidebar Frontend | 5173 |
+| Nginx (unified entry) | 80 |
+
+## Tech Stack
+
+- **Backend**: Spring Boot 2.7.18, Spring Cloud 2021.0.8, MyBatis-Plus 3.5.5, Java 8
+- **Infra**: MySQL 5.7, Redis 6.x, RabbitMQ 3.x
+- **Frontend**: React 18, TypeScript, Vite 5, Ant Design 5 / Ant Design Mobile 5
+- **LLM**: DashScope (Tongyi Qianwen qwen-turbo/qwen-plus)
+- **Auth**: JWT (jjwt 0.11.5), WeCom OAuth2
+- **Deployment**: Docker + Docker Compose, Nginx
+
+## Important Constraints
+
+- **MySQL 5.7**: No native JSON functions beyond basics, no vector types. Vectors are stored in Redis.
+- **Java 8**: All services compile to Java 1.8 (not the Dockerfile's Temurin 17 JRE, which is forward-compatible)
+- **No Spring Cloud Discovery**: Services use static gateway routing, not Eureka/Consul

backend/conversation-service/src/main/java/com/artedu/conversation/service/ConversationManager.java

@@ -257,6 +257,7 @@ public class ConversationManager {
         return content.length() > maxLength ? content.substring(0, maxLength) + "..." : content;
     }
 
+    @com.fasterxml.jackson.annotation.JsonIgnoreProperties(ignoreUnknown = true)
     public static class ArchiveMessageEvent {
         private String msgid;
         private String corpId;

frontend/sidebar/src/App.tsx

@@ -215,7 +215,7 @@ function App() {
 
       <Tabs activeKey={activeTab} onChange={setActiveTab}>
         <Tabs.Tab title="话术推荐" key="recommend">
-          <ScriptRecommend userInfo={userInfo} />
+          <ScriptRecommend userInfo={userInfo} customerId={currentCustomerId} />
         </Tabs.Tab>
         <Tabs.Tab title="对话分析" key="analysis">
           <ConversationAnalysis userInfo={userInfo} />

frontend/sidebar/src/components/ScriptRecommend.tsx

@@ -4,25 +4,66 @@ import type { Recommendation } from '../types'
 
 interface Props {
   userInfo?: any
+  customerId?: string
 }
 
-export default function ScriptRecommend({ userInfo }: Props) {
+interface ConversationTurn {
+  turnNumber: number
+  studentContent: string
+  seatContent: string
+}
+
+export default function ScriptRecommend({ userInfo, customerId: propCustomerId }: Props) {
   const [scripts, setScripts] = useState<Recommendation[]>([])
   const [loading, setLoading] = useState(false)
   const [generating, setGenerating] = useState(false)
-  const [customerMsg, setCustomerMsg] = useState('我想学游戏美术，零基础可以吗？')
+  const [customerMsg, setCustomerMsg] = useState('')
   const [generated, setGenerated] = useState('')
 
   // 从 localStorage 或企微环境获取真实身份信息
   const sessionId = localStorage.getItem('current_session_id') || `session_${Date.now()}`
-  const customerId = localStorage.getItem('current_customer_id') || 'wx_001'
+  const customerId = propCustomerId || localStorage.getItem('current_customer_id') || 'wx_001'
   const staffId = userInfo?.userId || 'staff_001'
   const corpId = userInfo?.corpId || 'wwd483c2fba24ae30a'
 
+  // 动态获取最后一条学员消息
+  const fetchLastCustomerMessage = async () => {
+    if (!customerId || customerId === 'wx_001') return
+    try {
+      const res = await fetch(`/api/v1/conversations?customerId=${customerId}&corpId=${corpId}`)
+      const data = await res.json()
+      if (data.code === 0 && data.data && data.data.length > 0) {
+        // 取最新的会话
+        const sessions = data.data as Array<{ sessionId: string; startTime: string }>
+        const latestSession = sessions.sort(
+          (a, b) => new Date(b.startTime).getTime() - new Date(a.startTime).getTime()
+        )[0]
+        const turnsRes = await fetch(`/api/v1/conversations/${latestSession.sessionId}/turns`)
+        const turnsData = await turnsRes.json()
+        if (turnsData.code === 0 && turnsData.data && turnsData.data.length > 0) {
+          const turns = turnsData.data as ConversationTurn[]
+          // 取最后一条有内容的学员消息
+          for (let i = turns.length - 1; i >= 0; i--) {
+            if (turns[i].studentContent?.trim()) {
+              setCustomerMsg(turns[i].studentContent.trim())
+              break
+            }
+          }
+        }
+      }
+    } catch (e) {
+      console.error('获取最后一条学员消息失败:', e)
+    }
+  }
+
   useEffect(() => {
     loadRecommendations()
   }, [])
 
+  useEffect(() => {
+    fetchLastCustomerMessage()
+  }, [customerId])
+
   const loadRecommendations = async () => {
     setLoading(true)
     try {