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
7.6 KiB
研究方案制定 Agent 技术实现手册 V3.0
版本: v3.0
关联文档: Protocol_Agent_Architecture_Design_V3.md
核心内容: 数据库 Schema、核心服务代码、API 协议。
1. 数据库设计 (Prisma Schema)
1.1 记忆层 (Memory Layer)
存储“活的”方案数据,实现长程记忆。
// aia_schema.prisma
model ProtocolContext {
id String @id @default(uuid())
conversationId String @unique @map("conversation_id")
userId String @map("user_id")
// 状态机
currentStage String @default("SCIENTIFIC_QUESTION")
status String @default("IN_PROGRESS")
// 活的方案数据 (JSONB)
// 包含: scientific_question, pico, study_design, outcomes, sample_size 等
data Json @default("{}")
// V3 新增: 存储上一次的反思结果,避免重复报错
lastReflexion Json? @map("last_reflexion")
createdAt DateTime @default(now()) @map("created_at")
updatedAt DateTime @updatedAt @map("updated_at")
@@table("protocol_contexts")
@@schema("aia_schema")
}
1.2 配置层 (Configuration Layer)
这是 V3 的核心,支持后端配置 CoT。
// capability_schema.prisma
model PromptTemplate {
id String @id @default(uuid())
code String @unique // e.g., AIA_SAMPLE_SIZE
version Int @default(1)
// 基础人设
content String @db.Text
// V3 新增: 思维链配置 (JSONB)
// 存储 ChainStep[] 数组
chainConfig Json? @map("chain_config")
// V3 新增: 路由规则配置 (JSONB, 可选)
// 用于定义何时切出该阶段
routerConfig Json? @map("router_config")
isActive Boolean @default(true)
updatedAt DateTime @updatedAt
@@table("prompt_templates")
@@schema("capability_schema")
}
model AgentTrace {
id String @id @default(uuid())
conversationId String @map("conversation_id")
stage String
// 记录完整上下文
inputPayload Json @map("input_payload")
outputPayload Json @map("output_payload")
// 耗时与消耗
latencyMs Int @map("latency_ms")
tokens Int @default(0)
createdAt DateTime @default(now())
@@table("agent_traces")
@@schema("capability_schema")
}
2. 核心服务代码 (Orchestrator Engine)
2.1 动态 CoT 组装器 (promptBuilder.ts)
负责将 DB 中的 SOP 配置编译成 System Prompt。
import { prisma } from '@/common/db';
interface ChainStep {
key: string;
desc: string;
instruction: string;
}
export async function buildDynamicSystemPrompt(stage: string, contextData: any) {
// 1. 加载配置
const template = await prisma.promptTemplate.findUnique({ where: { code: stage } });
if (!template) throw new Error(`Prompt not found: ${stage}`);
const chainSteps = template.chainConfig as ChainStep[] || [];
// 2. 组装基础 Prompt (Persona)
let systemPrompt = `${template.content}\n\n`;
// 3. 注入当前上下文 (Memory)
systemPrompt += `=== 当前方案状态 (Context) ===\n${JSON.stringify(contextData, null, 2)}\n\n`;
// 4. 注入思维链 SOP (V3 核心)
if (chainSteps.length > 0) {
systemPrompt += `=== 思考步骤 (SOP) ===\n`;
systemPrompt += `请严格按照以下步骤进行思考,并使用 XML 标签包裹每一步的内容:\n`;
chainSteps.forEach((step, idx) => {
systemPrompt += `${idx + 1}. <${step.key}>: ${step.instruction}\n`;
});
systemPrompt += `最后,在 <response> 标签中输出给用户的回复。\n`;
}
return systemPrompt;
}
2.2 编排器主逻辑 (ProtocolOrchestrator.ts)
协调 Brain, Memory, Knowledge 和 Hands。
export class ProtocolOrchestrator {
async handleMessage(userId: string, conversationId: string, content: string) {
// 1. 获取上下文 (Memory)
let ctx = await prisma.protocolContext.findUnique({ where: { conversationId } });
// 2\. \[Reflexion Guard\] 检查数据变更
// 如果之前状态是 WAITING\_USER 且数据变了,说明工具执行回来了 (Hands 回调)
if (ctx.status \=== 'WAITING\_USER\_ACTION' && await this.checkDataChanged(ctx)) {
const validation \= await this.runReflexionCheck(ctx);
if (\!validation.pass) {
return this.streamResponse(\`⚠️ \*\*校验未通过\*\*: ${validation.reason}\`);
}
// 校验通过,重置状态
await this.updateStatus(ctx.id, 'IN\_PROGRESS');
}
// 3\. \[Knowledge RAG\] 混合检索 (自建 EKB)
// 仅在需要知识的阶段调用
const ragContext \= await knowledgeService.search(content, ctx.currentStage);
// 4\. \[Prompt Build\] 动态组装 (Brain)
const systemPrompt \= await buildDynamicSystemPrompt(ctx.currentStage, ctx.data);
// 5\. \[Execution\] 流式生成
const traceId \= await traceService.startTrace(conversationId, 'GENERATE');
return streamingService.streamGenerate({
systemPrompt,
userMessage: content \+ (ragContext ? \`\\n\\n参考资料:\\n${ragContext}\` : ''),
onFinish: async (output) \=\> {
await traceService.endTrace(traceId, output);
// 异步触发:结构化提取任务 (更新 Memory)
await pgBoss.send('extract-protocol-data', { conversationId, text: output });
}
});
}
}
3. 交互协议 (Deep Link Protocol)
3.1 Action Card Payload (Backend -> Frontend)
Orchestrator 决定需要用户操作时,发送此 JSON。
{
"type": "action_card",
"data": {
"title": "建议:样本量计算",
"tool_code": "SAMPLE_SIZE_CALC",
"path": "/tools/st/sample-size",
"params": {
"ctx_id": "uuid-1234", // 关键:传递上下文ID,让工具知道往哪里回写
"alpha": 0.05,
"power": 0.8
}
}
}
3.2 同步回写 API (Tool -> Backend)
工具端(如样本量计算器)计算完成后,调用此接口回写结果。
POST /api/v1/aia/protocol/:ctxId/sync
{
"stage": "SAMPLE_SIZE",
"data": {
"n_total": 386,
"method": "t-test",
"params": { "alpha": 0.05, "power": 0.8 }
}
}
4. 提取与反思 (Extraction & Reflexion)
4.1 异步提取 Worker
负责从非结构化对话中“提纯”信息存入 Memory。
// workers/extractionWorker.ts
export async function extractProtocolData(job) {
const { conversationId, text } = job.data;
// 调用廉价模型 (DeepSeek-Flash) 进行 JSON 提取
const extracted = await llm.extractJson(text, EXTRACT_PROMPT);
if (extracted) {
// 智能合并策略 (Deep Merge)
await prisma.protocolContext.update({
where: { conversationId },
data: { data: deepMerge(currentData, extracted) }
});
}
}
4.2 反思校验规则 (Reflexion Rules)
Brain 对 Hands 操作结果的质检逻辑。
function runReflexionCheck(ctx: ProtocolContext) {
const { sample_size } = ctx.data;
if (!sample_size) return { pass: true };
// 规则 1: 伦理红线
if (sample_size.n_total < 10)
return { pass: false, reason: "样本量过小 (<10),无法通过伦理审查" };
// 规则 2: 可行性预警
if (sample_size.n_total > 10000)
return { pass: false, reason: "样本量过大,请确认经费和周期是否支持" };
return { pass: true };
}