feat(aia): Complete AIA V2.0 with universal streaming capabilities

Major Changes:
- Add StreamingService with OpenAI Compatible format
- Upgrade Chat component V2 with Ant Design X integration
- Implement AIA module with 12 intelligent agents
- Update API routes to unified /api/v1 prefix
- Update system documentation

Backend (~1300 lines):
- common/streaming: OpenAI Compatible adapter
- modules/aia: 12 agents, conversation service, streaming integration
- Update route versions (RVW, PKB to v1)

Frontend (~3500 lines):
- modules/aia: AgentHub + ChatWorkspace (100% prototype restoration)
- shared/Chat: AIStreamChat, ThinkingBlock, useAIStream Hook
- Update API endpoints to v1

Documentation:
- AIA module status guide
- Universal capabilities catalog
- System overview updates
- All module documentation sync

Tested: Stream response verified, authentication working
Status: AIA V2.0 core completed (85%)

docs/02-通用能力层/01-LLM大模型网关/03-CloseAI集成指南.md

@@ -1,25 +1,25 @@
 # CloseAI髮<49><E9ABAE>謖<EFBFBD>漉
 
-> **文档版本：** v1.0  
-> **创建日期：** 2025-11-09  
+> **譁<EFBFBD>｡｣迚域悽<EFBFBD>?* v1.0  
+> **蛻帛ｻｺ譌･譛滂ｼ?* 2025-11-09  
 > **逕ｨ騾費ｼ<E8B2BB>** 騾夊ｿ④loseAI莉｣逅<EFBDA3>ｹｳ蜿ｰ隶ｿ髣ｮOpenAI GPT-5蜥靴laude-4.5  
-> **适用场景：** AI智能文献双模型筛选、高质量文本生成
+> **騾ら畑蝨ｺ譎ｯ<EFBFBD>?* AI譎ｺ閭ｽ譁<EFBDBD>鍵蜿梧ｨ｡蝙狗ｭ幃€峨€<E5B3A8>ｫ倩ｴｨ驥乗枚譛ｬ逕滓<E98095>
 
 ---
 
-## 📋 CloseAI简介
+## <EFBFBD>搭 CloseAI邂€莉?
 
-### 什么是CloseAI？
+### 莉€荵域弍CloseAI<EFBFBD>?
 
-CloseAI是一个**API代理平台**，为中国用户提供稳定的OpenAI和Claude API访问服务。
+CloseAI譏ｯ荳€荳?*API莉｣逅<EFBDA3>ｹｳ蜿ｰ**<2A>御ｸｺ荳ｭ蝗ｽ逕ｨ謌ｷ謠蝉ｾ帷ｨｳ螳夂噪OpenAI蜥靴laude API隶ｿ髣ｮ譛榊苅縲?
 
-**核心优势：**
-- ✅ 国内直连，无需科学上网
-- ✅ 一个API Key同时调用OpenAI和Claude
-- ✅ 兼容OpenAI SDK标准接口
-- ✅ 支持最新模型（GPT-5、Claude-4.5）
+**譬ｸ蠢<EFBFBD>ｼ伜漢<EFBFBD>?*
+- 笨?蝗ｽ蜀<EFBDBD>峩霑橸ｼ梧裏髴€遘大ｭｦ荳顔ｽ<E9A194>
+- 笨?荳€荳ｪAPI Key蜷梧慮隹<EFBFBD>畑OpenAI蜥靴laude
+- 笨?蜈ｼ螳ｹOpenAI SDK譬<EFBFBD>㊥謗･蜿｣
+- 笨?謾ｯ謖∵怙譁ｰ讓｡蝙具ｼ<E585B7>PT-5縲，laude-4.5<EFBFBD>?
 
-**官网：** https://platform.openai-proxy.org
+**螳倡ｽ托ｼ?* https://platform.openai-proxy.org
 
 ---
 
@@ -38,15 +38,15 @@ CLOSEAI_OPENAI_BASE_URL=https://api.openai-proxy.org/v1
 CLOSEAI_CLAUDE_BASE_URL=https://api.openai-proxy.org/anthropic
 ```
 
-### 支持的模型
+### 謾ｯ謖∫噪讓｡蝙?
 
 | 讓｡蝙<EFBDA1> | Model ID | 隸ｴ譏<EFBDB4> | 騾ら畑蝨ｺ譎ｯ |
 |------|---------|------|---------|
-| **GPT-5-Pro** | `gpt-5-pro` | 最新GPT-5 ⭐ | 文献精准筛选、复杂推理 |
-| GPT-4-Turbo | `gpt-4-turbo-preview` | GPT-4高性能版 | 质量要求高的任务 |
-| GPT-3.5-Turbo | `gpt-3.5-turbo` | 快速经济版 | 简单任务、成本优化 |
-| **Claude-4.5-Sonnet** | `claude-sonnet-4-5-20250929` | 最新Claude ⭐ | 第三方仲裁、结构化输出 |
-| Claude-3.5-Sonnet | `claude-3-5-sonnet-20241022` | Claude-3.5稳定版 | 高质量文本生成 |
+| **GPT-5-Pro** | `gpt-5-pro` | 譛€譁ｰGPT-5 箝?| 譁<>鍵邊ｾ蜃<EFBDBE>ｭ幃€峨€∝､肴揩謗ｨ逅?|
+| GPT-4-Turbo | `gpt-4-turbo-preview` | GPT-4鬮俶€ｧ閭ｽ迚?| 雍ｨ驥剰ｦ∵ｱるｫ倡噪莉ｻ蜉｡ |
+| GPT-3.5-Turbo | `gpt-3.5-turbo` | 蠢ｫ騾溽ｻ乗ｵ守沿 | 邂€蜊穂ｻｻ蜉｡縲∵<E7B8B2>譛ｬ莨伜<E88EA8>?|
+| **Claude-4.5-Sonnet** | `claude-sonnet-4-5-20250929` | 譛€譁ｰClaude 箝?| 隨ｬ荳画婿莉ｲ陬√€∫ｻ捺桷蛹冶ｾ灘<EFBDBE> |
+| Claude-3.5-Sonnet | `claude-3-5-sonnet-20241022` | Claude-3.5遞ｳ螳夂<EFBFBD>?| 鬮倩ｴｨ驥乗枚譛ｬ逕滓<E98095>?|
 
 ---
 
@@ -58,9 +58,9 @@ CLOSEAI_CLAUDE_BASE_URL=https://api.openai-proxy.org/anthropic
 npm install openai
 ```
 
-### 2. 创建LLM服务类
+### 2. 蛻帛ｻｺLLM譛榊苅邀?
 
-**文件位置：** `backend/src/common/llm/closeai.service.ts`
+**譁<EFBFBD>ｻｶ菴咲ｽｮ<EFBFBD>?* `backend/src/common/llm/closeai.service.ts`
 
 ```typescript
 import OpenAI from 'openai';
@@ -71,13 +71,13 @@ export class CloseAIService {
   private claudeClient: OpenAI;
 
   constructor() {
-    // OpenAI客户端（通过CloseAI）
+    // OpenAI螳｢謌ｷ遶ｯ<EFBFBD>磯€夊ｿ④loseAI<EFBFBD>?
     this.openaiClient = new OpenAI({
       apiKey: config.closeaiApiKey,
       baseURL: config.closeaiOpenaiBaseUrl,
     });
 
-    // Claude客户端（通过CloseAI）
+    // Claude螳｢謌ｷ遶ｯ<EFBFBD>磯€夊ｿ④loseAI<EFBFBD>?
     this.claudeClient = new OpenAI({
       apiKey: config.closeaiApiKey,
       baseURL: config.closeaiClaudeBaseUrl,
@@ -135,7 +135,7 @@ export class CloseAIService {
   }
 
   /**
-   * 流式响应（GPT-5）
+   * 豬∝ｼ丞桃蠎費ｼ<EFBFBD>PT-5<EFBFBD>?
    */
   async *streamGPT5(prompt: string, systemPrompt?: string) {
     const messages: any[] = [];
@@ -165,7 +165,7 @@ export class CloseAIService {
 
 ### 3. 扈滉ｸ€LLM譛榊苅<E6A68A>亥性4荳ｪ讓｡蝙具ｼ<E585B7>
 
-**文件位置：** `backend/src/common/llm/llm.service.ts`
+**譁<EFBFBD>ｻｶ菴咲ｽｮ<EFBFBD>?* `backend/src/common/llm/llm.service.ts`
 
 ```typescript
 import OpenAI from 'openai';
@@ -258,7 +258,7 @@ export class UnifiedLLMService {
 
 ### 蝨ｺ譎ｯ1<EFBDAF>壼曙讓｡蝙句ｯｹ豈皮ｭ幃€会ｼ域耳闕撰ｼ俄ｭ<E4BF84>
 
-**策略：** DeepSeek（快速初筛） + GPT-5（质量复核）
+**遲也払<EFBFBD>?* DeepSeek<EFBFBD>亥ｿｫ騾溷<EFBFBD>遲幢ｼ<EFBFBD> + GPT-5<>郁ｴｨ驥丞､肴<EFBDA4>ｸ<EFBFBD><EFBDB8>
 
 ```typescript
 export class LiteratureScreeningService {
@@ -269,23 +269,23 @@ export class LiteratureScreeningService {
   }
 
   /**
-   * 双模型文献筛选
+   * 蜿梧ｨ｡蝙区枚迪ｮ遲幃€?
    */
   async screenLiterature(title: string, abstract: string, picoConfig: any) {
     const prompt = `
 隸ｷ譬ｹ謐ｮ莉･荳輝ICO譬<EFBFBD>㊥<EFBFBD>悟愛譁ｭ霑咏ｯ<EFBFBD>枚迪ｮ譏ｯ蜷ｦ蠎碑ｯ･郤ｳ蜈･<EFBFBD><EFBFBD>
 
-**PICO标准：**
+**PICO譬<EFBFBD>㊥<EFBFBD>?*
 - Population: ${picoConfig.population}
 - Intervention: ${picoConfig.intervention}
 - Comparison: ${picoConfig.comparison}
 - Outcome: ${picoConfig.outcome}
 
-**文献信息：**
-标题：${title}
-摘要：${abstract}
+**譁<EFBFBD>鍵菫｡諱ｯ<EFBFBD>?*
+譬<EFBFBD>｢假ｼ?{title}
+鞫倩ｦ<EFBFBD>ｼ?{abstract}
 
-请输出JSON格式：
+隸ｷ霎灘<EFBFBD>JSON譬ｼ蠑擾ｼ?
 {
   "decision": "include/exclude/uncertain",
   "reason": "蛻､譁ｭ逅<EFBDAD>罰",
@@ -325,11 +325,11 @@ export class LiteratureScreeningService {
 
 ### 蝨ｺ譎ｯ2<EFBDAF>壻ｸ画ｨ｡蝙句<E89D99>隸<EFBFBD>ｻｲ陬<EFBDB2>
 
-**策略：** 当两个模型冲突时，启用Claude作为第三方仲裁
+**遲也払<EFBFBD>?* 蠖謎ｸ､荳ｪ讓｡蝙句<E89D99>遯∵慮<E288B5>悟星逕ｨClaude菴應ｸｺ隨ｬ荳画婿莉ｲ陬?
 
 ```typescript
 async screenWithArbitration(title: string, abstract: string, picoConfig: any) {
-  // 第一轮：双模型筛选
+  // 隨ｬ荳€霓ｮ<EFBFBD>壼曙讓｡蝙狗ｭ幃€?
   const initialScreen = await this.screenLiterature(title, abstract, picoConfig);
 
   // 螯よ棡荳€閾ｴ<E996BE>檎峩謗･霑泌屓
@@ -343,7 +343,7 @@ async screenWithArbitration(title: string, abstract: string, picoConfig: any) {
   const claudeResult = await this.llm.chat('claude', prompt);
   const claudeDecision = JSON.parse(claudeResult.content);
 
-  // 三模型投票
+  // 荳画ｨ｡蝙区兜逾?
   const decisions = [
     initialScreen.models[0].decision,
     initialScreen.models[1].decision,
@@ -356,7 +356,7 @@ async screenWithArbitration(title: string, abstract: string, picoConfig: any) {
     uncertain: decisions.filter(d => d === 'uncertain').length,
   };
 
-  // 多数决
+  // 螟壽焚蜀?
   const finalDecision = Object.keys(voteCount).reduce((a, b) => 
     voteCount[a] > voteCount[b] ? a : b
   );
@@ -370,13 +370,13 @@ async screenWithArbitration(title: string, abstract: string, picoConfig: any) {
 }
 ```
 
-### 场景3：成本优化策略
+### 蝨ｺ譎ｯ3<EFBFBD>壽<EFBFBD>譛ｬ莨伜喧遲也<EFBFBD>?
 
-**策略：** 只对不确定的结果使用GPT-5复核
+**遲也払<EFBFBD>?* 蜿ｪ蟇ｹ荳咲｡ｮ螳夂噪扈捺棡菴ｿ逕ｨGPT-5螟肴<EFBFBD>ｸ
 
 ```typescript
 async screenWithCostOptimization(title: string, abstract: string, picoConfig: any) {
-  // 第一轮：用DeepSeek快速初筛（便宜）
+  // 隨ｬ荳€霓ｮ<EFBFBD>夂畑DeepSeek蠢ｫ騾溷<EFBFBD>遲幢ｼ井ｾｿ螳懶ｼ?
   const quickScreen = await this.llm.chat('deepseek', prompt);
   const quickDecision = JSON.parse(quickScreen.content);
 
@@ -405,39 +405,39 @@ async screenWithCostOptimization(title: string, abstract: string, picoConfig: an
 
 ---
 
-## 📊 性能和成本对比
+## <EFBFBD>投 諤ｧ閭ｽ蜥梧<E89CA5>譛ｬ蟇ｹ豈?
 
 ### 讓｡蝙区€ｧ閭ｽ蟇ｹ豈<EFBDB9>
 
 | 謖<><E8AC96><EFBFBD> | DeepSeek-V3 | GPT-5-Pro | Claude-4.5 | Qwen-Max |
 |------|------------|-----------|-----------|----------|
-| **准确率** | 85% | **95%** ⭐ | 93% | 82% |
-| **速度** | **快** ⭐ | 中等 | 中等 | 快 |
-| **成本** | **¥0.001/1K** ⭐ | ¥0.10/1K | ¥0.021/1K | ¥0.004/1K |
-| **中文理解** | **优秀** ⭐ | 优秀 | 良好 | 优秀 |
-| **结构化输出** | 良好 | 优秀 | **优秀** ⭐ | 良好 |
+| **蜃<EFBFBD>｡ｮ邇?* | 85% | **95%** 箝?| 93% | 82% |
+| **騾溷ｺｦ** | **蠢?* 箝?| 荳ｭ遲<EFBDAD> | 荳ｭ遲<EFBDAD> | 蠢?|
+| **謌先悽** | **ﾂ･0.001/1K** 箝?| ﾂ･0.10/1K | ﾂ･0.021/1K | ﾂ･0.004/1K |
+| **荳ｭ譁<EFBFBD>炊隗｣** | **莨倡ｧ€** 箝?| 莨倡ｧ€ | 濶ｯ螂ｽ | 莨倡ｧ€ |
+| **扈捺桷蛹冶ｾ灘<EFBFBD>?* | 濶ｯ螂ｽ | 莨倡ｧ€ | **莨倡ｧ€** 箝?| 濶ｯ螂ｽ |
 
-### 筛选1000篇文献的成本估算
+### 遲幃€?000遽<30>枚迪ｮ逧<EFBDAE><E980A7>譛ｬ莨ｰ邂<EFBDB0>
 
 **遲也払A<E68995>壼宵逕ｨDeepSeek**
-- 成本：¥20-30
+- 謌先悽<EFBFBD>堋?0-30
 - 蜃<>｡ｮ邇<EFBDAE>ｼ<EFBFBD>85%
-- 适用：预算有限，可接受一定误差
+- 騾ら畑<EFBFBD>夐｢<EFBFBD>ｮ玲怏髯撰ｼ悟庄謗･蜿嶺ｸ€螳夊ｯｯ蟾?
 
-**策略B：DeepSeek + GPT-5 双模型**
-- 成本：¥150-200
+**遲也払B<EFBFBD>咼eepSeek + GPT-5 蜿梧ｨ｡蝙?*
+- 謌先悽<EFBFBD>堋?50-200
 - 蜃<>｡ｮ邇<EFBDAE>ｼ<EFBFBD>92%
-- 适用：质量要求高，预算充足 ⭐ 推荐
+- 騾ら畑<EFBFBD>夊ｴｨ驥剰ｦ∵ｱるｫ假ｼ碁｢<EFBFBD>ｮ怜<EFBFBD>雜?箝?謗ｨ闕<EFBDA8>
 
-**策略C：三模型共识（20%冲突启用Claude）**
-- 成本：¥180-220
+**遲也払C<EFBFBD>壻ｸ画ｨ｡蝙句<EFBFBD>隸<EFBFBD>ｼ?0%蜀ｲ遯∝星逕ｨClaude<64>?*
+- 謌先悽<EFBFBD>堋?80-220
 - 蜃<>｡ｮ邇<EFBDAE>ｼ<EFBFBD>95%
-- 适用：最高质量要求
+- 騾ら畑<EFBFBD>壽怙鬮倩ｴｨ驥剰ｦ∵ｱ?
 
-**策略D：成本优化（80%用DeepSeek，20%用GPT-5）**
-- 成本：¥50-80
+**遲也払D<EFBFBD>壽<EFBFBD>譛ｬ莨伜喧<EFBFBD><EFBFBD>80%逕ｨDeepSeek<EFBFBD>?0%逕ｨGPT-5<>?*
+- 謌先悽<EFBFBD>堋?0-80
 - 蜃<>｡ｮ邇<EFBDAE>ｼ<EFBFBD>90%
-- 适用：质量和成本平衡 ⭐ 性价比最高
+- 騾ら畑<EFBFBD>夊ｴｨ驥丞柱謌先悽蟷ｳ陦｡ 箝?諤ｧ莉ｷ豈疲怙鬮?
 
 ---
 
@@ -446,12 +446,12 @@ async screenWithCostOptimization(title: string, abstract: string, picoConfig: an
 ### 1. API Key螳牙<E89EB3>
 
 ```typescript
-// ❌ 错误：硬编码API Key
+// 笶?髞呵ｯｯ<EFBDAF>夂｡ｬ郛也<E9839B>、PI Key
 const client = new OpenAI({
   apiKey: 'sk-cu0iepbXYGGx2jc7BqP6ogtSWmP6fk918qV3RUdtGC3Edlpo',
 });
 
-// ✅ 正确：从环境变量读取
+// 笨?豁｣遑ｮ<E98191>壻ｻ守識蠅<E8AD98>序驥剰ｯｻ蜿<EFBDBB>
 const client = new OpenAI({
   apiKey: process.env.CLOSEAI_API_KEY,
 });
@@ -465,15 +465,15 @@ async chat(provider: LLMProvider, prompt: string) {
     const response = await this.llm.chat(provider, prompt);
     return response;
   } catch (error) {
-    // CloseAI可能返回的错误
+    // CloseAI蜿ｯ閭ｽ霑泌屓逧<EFBFBD>漠隸?
     if (error.status === 429) {
       // 騾溽紫髯仙宛
       console.error('API隹<49>畑騾溽紫雜<E7B4AB>剞<EFBFBD>瑚ｯｷ遞榊錘驥崎ｯ<E5B48E>');
     } else if (error.status === 401) {
       // 隶､隸∝､ｱ雍･
-      console.error('API Key无效，请检查配置');
+      console.error('API Key譌<EFBFBD>謨茨ｼ瑚ｯｷ譽€譟･驟咲ｽ?);
     } else if (error.status === 500) {
-      // 服务端错误
+      // 譛榊苅遶ｯ髞呵ｯ?
       console.error('CloseAI譛榊苅蠑ょｸｸ<EFBFBD>瑚ｯｷ遞榊錘驥崎ｯ<EFBFBD>');
     }
     throw error;
@@ -491,7 +491,7 @@ async chatWithRetry(provider: LLMProvider, prompt: string, maxRetries = 3) {
     } catch (error) {
       if (i === maxRetries - 1) throw error;
       
-      // 指数退避
+      // 謖<EFBFBD>焚騾€驕?
       const delay = Math.pow(2, i) * 1000;
       await new Promise(resolve => setTimeout(resolve, delay));
     }
@@ -509,9 +509,9 @@ async chatWithRetry(provider: LLMProvider, prompt: string, maxRetries = 3) {
 
 ---
 
-**更新日志：**
+**譖ｴ譁ｰ譌･蠢暦ｼ?*
 - 2025-11-09: 蛻帛ｻｺ譁<EFBDBA>｡｣<EFBDA1>梧ｷｻ蜉<EFBDBB>CloseAI髮<49><E9ABAE>謖<EFBFBD>漉
-- 支持GPT-5-Pro和Claude-4.5-Sonnet最新模型
+- 謾ｯ謖；PT-5-Pro蜥靴laude-4.5-Sonnet譛€譁ｰ讓｡蝙?