Sprint 1-3 Completed (Backend + Frontend): Backend (Sprint 1-2): - Implement 5-layer Agent framework (Query->Planner->Executor->Tools->Reflection) - Create agent_schema with 6 tables (agent_definitions, stages, prompts, sessions, traces, reflexion_rules) - Create protocol_schema with 2 tables (protocol_contexts, protocol_generations) - Implement Protocol Agent core services (Orchestrator, ContextService, PromptBuilder) - Integrate LLM service adapter (DeepSeek/Qwen/GPT-5/Claude) - 6 API endpoints with full authentication - 10/10 API tests passed Frontend (Sprint 3): - Add Protocol Agent entry in AgentHub (indigo theme card) - Implement ProtocolAgentPage with 3-column layout - Collapsible sidebar (Gemini style, 48px <-> 280px) - StatePanel with 5 stage cards (scientific_question, pico, study_design, sample_size, endpoints) - ChatArea with sync button and action cards integration - 100% prototype design restoration (608 lines CSS) - Detailed endpoints structure: baseline, exposure, outcomes, confounders Features: - 5-stage dialogue flow for research protocol design - Conversation-driven interaction with sync-to-protocol button - Real-time context state management - One-click protocol generation button (UI ready, backend pending) Database: - agent_schema: 6 tables for reusable Agent framework - protocol_schema: 2 tables for Protocol Agent - Seed data: 1 agent + 5 stages + 9 prompts + 4 reflexion rules Code Stats: - Backend: 13 files, 4338 lines - Frontend: 14 files, 2071 lines - Total: 27 files, 6409 lines Status: MVP core functionality completed, pending frontend-backend integration testing Next: Sprint 4 - One-click protocol generation + Word export
4.9 KiB
4.9 KiB
通用能力层 - 快速引用卡片
一页纸速查表,快速找到需要的通用能力
🎯 我需要...
💬 AI 对话功能
前端:
import { AIStreamChat } from '@/shared/components/Chat';
<AIStreamChat apiEndpoint="/api/v1/xxx/chat/stream" enableDeepThinking={true} />
后端:
import { createStreamingService } from '../../../common/streaming';
const service = createStreamingService(reply);
await service.streamGenerate(messages);
📚 详细文档
🤖 调用 LLM
import { LLMFactory } from '../../../common/llm/adapters/LLMFactory';
const llm = LLMFactory.getAdapter('deepseek-v3');
const response = await llm.chat(messages);
// 流式
for await (const chunk of llm.chatStream(messages)) {
console.log(chunk.content);
}
📚 详细文档
📁 文件存储
import { storage } from '../../../common/storage';
// 上传
const url = await storage.upload('path/file.pdf', buffer);
// 下载
const buffer = await storage.download('path/file.pdf');
📚 详细文档
⚡ 异步任务
import { JobFactory } from '../../../common/jobs';
const queue = JobFactory.getQueue();
// 创建任务
await queue.createJob('job-name', { taskId: 'xxx' });
// 注册Worker
queue.registerWorker('job-name', async (job) => {
// 处理逻辑
});
📚 详细文档
📄 文档处理
import { ExtractionClient } from '../../../common/document/ExtractionClient';
const client = new ExtractionClient();
const text = await client.extractText(buffer, 'pdf');
📚 详细文档
🔍 知识库检索(RAG)
import { DifyClient } from '../../../common/rag/DifyClient';
const dify = new DifyClient(apiKey, baseURL);
const results = await dify.retrievalSearch(query, options);
📚 详细文档
💾 缓存服务
import { cache } from '../../../common/cache';
await cache.set('key', value, 3600); // TTL: 3600秒
const value = await cache.get('key');
await cache.delete('key');
📚 详细文档
📝 日志记录
import { logger } from '../../../common/logging';
logger.info('[Module] 操作描述', { userId: 'xxx', detail: 'xxx' });
logger.error('[Module] 错误', { error, stack: error.stack });
📚 详细文档
🔐 认证授权
后端:
import { authenticate, getUserId } from '../../../common/auth';
// 路由
fastify.get('/api', { preHandler: [authenticate] }, handler);
// 控制器
const userId = getUserId(request);
前端:
import { getAccessToken } from '@/framework/auth/api';
const token = getAccessToken();
// 或使用 apiClient(自动携带token)
import apiClient from '@/common/api/axios';
await apiClient.get('/api/xxx');
📚 详细文档
📋 Prompt 管理
import { PromptService } from '../../../common/prompt/prompt.service';
const promptService = new PromptService();
const prompt = await promptService.getActivePrompt('template_code');
const rendered = promptService.renderPrompt(template, variables);
📚 详细文档
🏗️ 架构原则
✅ 正确做法
// 1. 使用通用能力,不要重复造轮子
import { createStreamingService } from '../../../common/streaming';
// 2. 遵循云原生规范
await storage.upload(); // 不要用 fs.writeFileSync()
// 3. 使用结构化日志
logger.info('[Module] 操作', { detail }); // 不要用 console.log()
// 4. 统一认证
fastify.get('/api', { preHandler: [authenticate] });
// 5. 标准化API格式
// OpenAI Compatible, not 自定义格式
❌ 错误做法
// 1. 自己实现已有的能力
reply.raw.write('data: ...'); // ❌ 应该用 StreamingService
// 2. 直接操作本地文件
fs.writeFileSync('/tmp/file'); // ❌ 应该用 storage
// 3. 使用 console.log
console.log('debug'); // ❌ 应该用 logger
// 4. 硬编码用户ID
const userId = 'test'; // ❌ 应该用 getUserId(request)
// 5. 自定义格式
{ type: 'delta', content: 'xxx' } // ❌ 应该用 OpenAI Compatible
📚 完整文档
更新时间: 2026-01-14