feat(asl): Complete Deep Research V2.0 core development
Backend: - Add SSE streaming client (unifuncsSseClient) replacing async polling - Add paragraph-based reasoning parser with mergeConsecutiveThinking - Add requirement expansion service (DeepSeek-V3 PICOS+MeSH) - Add Word export service with Pandoc, inline hyperlinks, reference link expansion - Add deep research V2 worker with 2s log flush and Chinese source prompt - Add 5 curated data sources config (PubMed/ClinicalTrials/Cochrane/CNKI/MedJournals) - Add 4 API endpoints (generate-requirement/tasks/task-status/export-word) - Update Prisma schema with 6 new V2.0 fields on AslResearchTask - Add DB migration for V2.0 fields - Simplify ASL_DEEP_RESEARCH_EXPANSION prompt (remove strategy section) Frontend: - Add waterfall-flow DeepResearchPage (phase 0-4 progressive reveal) - Add LandingView, SetupPanel, StrategyConfirm, AgentTerminal, ResultsView - Add react-markdown + remark-gfm for report rendering - Add custom link component showing visible URLs after references - Add useDeepResearchTask polling hook - Add deep research TypeScript types Tests: - Add E2E test, smoke test, and Chinese data source test scripts Docs: - Update ASL module status (v2.0 - core features complete) - Update system status (v6.1 - ASL V2.0 milestone) - Update Unifuncs DeepSearch API guide (v2.0 - SSE mode + Chinese source results) - Update module auth specification (test script guidelines) - Update V2.0 development plan Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
@@ -0,0 +1,10 @@
|
||||
-- Deep Research V2.0: Add 6 new fields to research_tasks
|
||||
-- Backward compatible: all new columns are nullable
|
||||
|
||||
ALTER TABLE "asl_schema"."research_tasks"
|
||||
ADD COLUMN IF NOT EXISTS "target_sources" JSONB,
|
||||
ADD COLUMN IF NOT EXISTS "confirmed_requirement" TEXT,
|
||||
ADD COLUMN IF NOT EXISTS "ai_intent_summary" JSONB,
|
||||
ADD COLUMN IF NOT EXISTS "execution_logs" JSONB,
|
||||
ADD COLUMN IF NOT EXISTS "synthesis_report" TEXT,
|
||||
ADD COLUMN IF NOT EXISTS "result_list" JSONB;
|
||||
@@ -1,100 +0,0 @@
|
||||
-- =====================================================
|
||||
-- Phase 2A: SSA 智能化核心 - 数据库迁移脚本
|
||||
-- 日期: 2026-02-20
|
||||
-- 描述: 添加工作流表和数据画像字段
|
||||
-- 注意: ssa_sessions.id 是 TEXT 类型（存储 UUID 字符串）
|
||||
-- =====================================================
|
||||
|
||||
-- 1. 给 ssa_sessions 表添加 data_profile 字段（如果不存在）
|
||||
ALTER TABLE ssa_schema.ssa_sessions
|
||||
ADD COLUMN IF NOT EXISTS data_profile JSONB;
|
||||
|
||||
COMMENT ON COLUMN ssa_schema.ssa_sessions.data_profile IS 'Python Tool C 生成的数据画像 (Phase 2A)';
|
||||
|
||||
-- 2. 创建 ssa_workflows 表（多步骤分析流程）
|
||||
CREATE TABLE IF NOT EXISTS ssa_schema.ssa_workflows (
|
||||
id TEXT PRIMARY KEY DEFAULT gen_random_uuid()::TEXT,
|
||||
session_id TEXT NOT NULL,
|
||||
message_id TEXT,
|
||||
status VARCHAR(20) NOT NULL DEFAULT 'pending',
|
||||
total_steps INTEGER NOT NULL,
|
||||
completed_steps INTEGER NOT NULL DEFAULT 0,
|
||||
workflow_plan JSONB NOT NULL,
|
||||
reasoning TEXT,
|
||||
created_at TIMESTAMP WITHOUT TIME ZONE NOT NULL DEFAULT NOW(),
|
||||
started_at TIMESTAMP WITHOUT TIME ZONE,
|
||||
completed_at TIMESTAMP WITHOUT TIME ZONE,
|
||||
|
||||
CONSTRAINT fk_ssa_workflow_session
|
||||
FOREIGN KEY (session_id)
|
||||
REFERENCES ssa_schema.ssa_sessions(id)
|
||||
ON DELETE CASCADE
|
||||
);
|
||||
|
||||
-- ssa_workflows 索引
|
||||
CREATE INDEX IF NOT EXISTS idx_ssa_workflow_session
|
||||
ON ssa_schema.ssa_workflows(session_id);
|
||||
CREATE INDEX IF NOT EXISTS idx_ssa_workflow_status
|
||||
ON ssa_schema.ssa_workflows(status);
|
||||
|
||||
-- ssa_workflows 字段注释
|
||||
COMMENT ON TABLE ssa_schema.ssa_workflows IS 'SSA 多步骤分析工作流 (Phase 2A)';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflows.status IS 'pending | running | completed | partial | error';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflows.workflow_plan IS 'LLM 生成的原始工作流计划 JSON';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflows.reasoning IS 'LLM 规划理由说明';
|
||||
|
||||
-- 3. 创建 ssa_workflow_steps 表（流程中的每个步骤）
|
||||
CREATE TABLE IF NOT EXISTS ssa_schema.ssa_workflow_steps (
|
||||
id TEXT PRIMARY KEY DEFAULT gen_random_uuid()::TEXT,
|
||||
workflow_id TEXT NOT NULL,
|
||||
step_order INTEGER NOT NULL,
|
||||
tool_code VARCHAR(50) NOT NULL,
|
||||
tool_name VARCHAR(100) NOT NULL,
|
||||
status VARCHAR(20) NOT NULL DEFAULT 'pending',
|
||||
input_params JSONB,
|
||||
guardrail_checks JSONB,
|
||||
output_result JSONB,
|
||||
error_info JSONB,
|
||||
execution_ms INTEGER,
|
||||
started_at TIMESTAMP WITHOUT TIME ZONE,
|
||||
completed_at TIMESTAMP WITHOUT TIME ZONE,
|
||||
|
||||
CONSTRAINT fk_ssa_workflow_step_workflow
|
||||
FOREIGN KEY (workflow_id)
|
||||
REFERENCES ssa_schema.ssa_workflows(id)
|
||||
ON DELETE CASCADE
|
||||
);
|
||||
|
||||
-- ssa_workflow_steps 索引
|
||||
CREATE INDEX IF NOT EXISTS idx_ssa_workflow_step_workflow
|
||||
ON ssa_schema.ssa_workflow_steps(workflow_id);
|
||||
CREATE INDEX IF NOT EXISTS idx_ssa_workflow_step_status
|
||||
ON ssa_schema.ssa_workflow_steps(status);
|
||||
|
||||
-- ssa_workflow_steps 字段注释
|
||||
COMMENT ON TABLE ssa_schema.ssa_workflow_steps IS 'SSA 工作流单步执行记录 (Phase 2A)';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflow_steps.status IS 'pending | running | success | warning | error | skipped';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflow_steps.guardrail_checks IS 'R Service JIT 护栏检验结果 (正态性、方差齐性等)';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflow_steps.output_result IS '工具执行结果 (已裁剪，符合 LLM 上下文限制)';
|
||||
COMMENT ON COLUMN ssa_schema.ssa_workflow_steps.error_info IS '错误信息 (用于容错管道的部分成功场景)';
|
||||
|
||||
-- =====================================================
|
||||
-- 验证脚本
|
||||
-- =====================================================
|
||||
SELECT 'ssa_sessions.data_profile 字段' as item,
|
||||
CASE WHEN EXISTS (
|
||||
SELECT 1 FROM information_schema.columns
|
||||
WHERE table_schema = 'ssa_schema' AND table_name = 'ssa_sessions' AND column_name = 'data_profile'
|
||||
) THEN '✅ 已创建' ELSE '❌ 未创建' END as status;
|
||||
|
||||
SELECT 'ssa_workflows 表' as item,
|
||||
CASE WHEN EXISTS (
|
||||
SELECT 1 FROM information_schema.tables
|
||||
WHERE table_schema = 'ssa_schema' AND table_name = 'ssa_workflows'
|
||||
) THEN '✅ 已创建' ELSE '❌ 未创建' END as status;
|
||||
|
||||
SELECT 'ssa_workflow_steps 表' as item,
|
||||
CASE WHEN EXISTS (
|
||||
SELECT 1 FROM information_schema.tables
|
||||
WHERE table_schema = 'ssa_schema' AND table_name = 'ssa_workflow_steps'
|
||||
) THEN '✅ 已创建' ELSE '❌ 未创建' END as status;
|
||||
@@ -477,7 +477,7 @@ model AslFulltextScreeningTask {
|
||||
@@schema("asl_schema")
|
||||
}
|
||||
|
||||
/// 智能文献检索任务（DeepSearch）
|
||||
/// 智能文献检索任务（DeepSearch V1.x + V2.0）
|
||||
model AslResearchTask {
|
||||
id String @id @default(uuid())
|
||||
|
||||
@@ -486,23 +486,23 @@ model AslResearchTask {
|
||||
userId String @map("user_id")
|
||||
|
||||
// 检索输入
|
||||
query String // 用户的自然语言查询
|
||||
filters Json? // 🔜 后续：高级筛选 { yearFrom, yearTo, articleTypes }
|
||||
query String // 用户的自然语言查询（V1.x 原始输入 / V2.0 Step 1 粗略想法）
|
||||
filters Json? // 高级筛选 { yearRange, targetCount, requireOpenAccess }
|
||||
|
||||
// unifuncs 任务
|
||||
externalTaskId String? @map("external_task_id")
|
||||
|
||||
// 状态
|
||||
status String @default("pending") // pending/processing/completed/failed
|
||||
// 状态: draft → pending → running → completed / failed
|
||||
status String @default("pending")
|
||||
errorMessage String? @map("error_message")
|
||||
|
||||
// 结果
|
||||
// V1.x 结果字段（保留向后兼容）
|
||||
resultCount Int? @map("result_count")
|
||||
rawResult String? @map("raw_result") @db.Text
|
||||
reasoningContent String? @map("reasoning_content") @db.Text // AI思考过程
|
||||
literatures Json? // 解析后的文献列表
|
||||
reasoningContent String? @map("reasoning_content") @db.Text
|
||||
literatures Json?
|
||||
|
||||
// 统计（🔜 后续展示）
|
||||
// 统计
|
||||
tokenUsage Json? @map("token_usage")
|
||||
searchCount Int? @map("search_count")
|
||||
readCount Int? @map("read_count")
|
||||
@@ -513,6 +513,15 @@ model AslResearchTask {
|
||||
updatedAt DateTime @updatedAt @map("updated_at")
|
||||
completedAt DateTime? @map("completed_at")
|
||||
|
||||
// ── V2.0 新增字段 ──────────────────────────────
|
||||
targetSources Json? @map("target_sources") // 选中的数据源 ["https://pubmed.ncbi.nlm.nih.gov/", ...]
|
||||
confirmedRequirement String? @map("confirmed_requirement") @db.Text // 用户核验后的自然语言检索指令书
|
||||
aiIntentSummary Json? @map("ai_intent_summary") // PICOS + MeSH 结构化摘要
|
||||
executionLogs Json? @map("execution_logs") // 终端日志数组 [{type, title, text, ts}]
|
||||
synthesisReport String? @map("synthesis_report") @db.Text // AI综合报告（Markdown）
|
||||
resultList Json? @map("result_list") // 结构化文献元数据列表
|
||||
|
||||
// ── 索引 ────────────────────────────
|
||||
@@index([projectId], map: "idx_research_tasks_project_id")
|
||||
@@index([userId], map: "idx_research_tasks_user_id")
|
||||
@@index([status], map: "idx_research_tasks_status")
|
||||
|
||||
Reference in New Issue
Block a user