AIclinicalresearch

Develop/AIclinicalresearch

Fork 0

Commit Graph

Author	SHA1	Message	Date
HaHafeng	dfc472810b	feat(iit-manager): Integrate Dify knowledge base for hybrid retrieval Completed features: - Created Dify dataset (Dify_test0102) with 2 processed documents - Linked test0102 project with Dify dataset ID - Extended intent detection to recognize query_protocol intent - Implemented queryDifyKnowledge method (semantic search Top 5) - Integrated hybrid retrieval (REDCap data + Dify documents) - Fixed AI hallucination bugs (intent detection + API field path) - Developed debugging scripts - Completed end-to-end testing (5 scenarios passed) - Generated comprehensive documentation (600+ lines) - Updated development plans and module status Technical highlights: - Single project single knowledge base architecture - Smart routing based on user intent - Prevent AI hallucination by injecting real data/documents - Session memory for multi-turn conversations - Reused LLMFactory for DeepSeek-V3 integration Bug fixes: - Fixed intent detection missing keywords - Fixed Dify API response field path error Testing: All scenarios verified in WeChat production environment Status: Fully tested and deployed	2026-01-04 15:44:11 +08:00
HaHafeng	6a567f028f	feat(iit-manager): 完成MVP闭环 - 企业微信集成与端到端测试核心交付物: - WechatService (314行): Access Token缓存 + 消息推送 - WechatCallbackController (501行): URL验证 + 消息接收 - 质控Worker完善: 质控逻辑 + 企业微信推送 + 审计日志 - Worker注册修复: initIitManager() 在启动时调用 - 数据库字段修复: action -> action_type - 端到端测试通过: <2秒延迟, 100%成功率性能指标: - Webhook响应: 5.8ms (目标<10ms) - Worker执行: ~50ms (目标<100ms) - 端到端延迟: <2秒 (目标<5秒) - 消息成功率: 100% (测试5次) 临时措施: - UserID从环境变量获取 (Phase 2改进) - 定时轮询暂时禁用 (Phase 2添加) - 质控逻辑简化 (Phase 1.5集成Dify) Closes #IIT-MVP-Day3	2026-01-03 14:19:08 +08:00
HaHafeng	36ce1bbcb2	feat(iit): Complete Day 3 - WeChat Work integration and URL verification Summary: - Implement WechatService (314 lines, push notifications) - Implement WechatCallbackController (501 lines, async reply mode) - Complete iit_quality_check Worker with WeChat notifications - Configure WeChat routes (GET + POST /wechat/callback) - Configure natapp tunnel for local development - WeChat URL verification test passed Technical Highlights: - Async reply mode to avoid 5-second timeout - Message encryption/decryption using @wecom/crypto - Signature verification using getSignature - natapp tunnel: https://iit.nat100.top - Environment variables configuration completed Technical Challenges Solved: - Fix environment variable naming (WECHAT_CORP_SECRET) - Fix @wecom/crypto import (createRequire for CommonJS) - Fix decrypt function parameters (2 params, not 4) - Fix Token character recognition (lowercase l vs digit 1) - Regenerate EncodingAESKey (43 chars, correct format) - Configure natapp for internal network penetration Test Results: - WeChat developer tool verification: PASSED - Return status: request success - HTTP 200, decrypted 23 characters correctly - Backend logs: URL verification successful Documentation: - Add Day3 WeChat integration development record - Update MVP development task list (Day 2-3 completed) - Update module status guide (v1.2 -> v1.3) - Overall completion: 35% -> 50% Progress: - Module completion: 35% -> 50% - Day 3 development: COMPLETED - Ready for end-to-end testing (REDCap -> WeChat)	2026-01-03 00:13:36 +08:00

Author

SHA1

Message

Date

HaHafeng

dfc472810b

feat(iit-manager): Integrate Dify knowledge base for hybrid retrieval

Completed features:
- Created Dify dataset (Dify_test0102) with 2 processed documents
- Linked test0102 project with Dify dataset ID
- Extended intent detection to recognize query_protocol intent
- Implemented queryDifyKnowledge method (semantic search Top 5)
- Integrated hybrid retrieval (REDCap data + Dify documents)
- Fixed AI hallucination bugs (intent detection + API field path)
- Developed debugging scripts
- Completed end-to-end testing (5 scenarios passed)
- Generated comprehensive documentation (600+ lines)
- Updated development plans and module status

Technical highlights:
- Single project single knowledge base architecture
- Smart routing based on user intent
- Prevent AI hallucination by injecting real data/documents
- Session memory for multi-turn conversations
- Reused LLMFactory for DeepSeek-V3 integration

Bug fixes:
- Fixed intent detection missing keywords
- Fixed Dify API response field path error

Testing: All scenarios verified in WeChat production environment

Status: Fully tested and deployed

2026-01-04 15:44:11 +08:00

HaHafeng

6a567f028f

feat(iit-manager): 完成MVP闭环 - 企业微信集成与端到端测试

核心交付物:
- WechatService (314行): Access Token缓存 + 消息推送
- WechatCallbackController (501行): URL验证 + 消息接收
- 质控Worker完善: 质控逻辑 + 企业微信推送 + 审计日志
- Worker注册修复: initIitManager() 在启动时调用
- 数据库字段修复: action -> action_type
- 端到端测试通过: <2秒延迟, 100%成功率

性能指标:
- Webhook响应: 5.8ms (目标<10ms)
- Worker执行: ~50ms (目标<100ms)
- 端到端延迟: <2秒 (目标<5秒)
- 消息成功率: 100% (测试5次)

临时措施:
- UserID从环境变量获取 (Phase 2改进)
- 定时轮询暂时禁用 (Phase 2添加)
- 质控逻辑简化 (Phase 1.5集成Dify)

Closes #IIT-MVP-Day3

2026-01-03 14:19:08 +08:00

HaHafeng

36ce1bbcb2

feat(iit): Complete Day 3 - WeChat Work integration and URL verification

Summary:
- Implement WechatService (314 lines, push notifications)
- Implement WechatCallbackController (501 lines, async reply mode)
- Complete iit_quality_check Worker with WeChat notifications
- Configure WeChat routes (GET + POST /wechat/callback)
- Configure natapp tunnel for local development
- WeChat URL verification test passed

Technical Highlights:
- Async reply mode to avoid 5-second timeout
- Message encryption/decryption using @wecom/crypto
- Signature verification using getSignature
- natapp tunnel: https://iit.nat100.top
- Environment variables configuration completed

Technical Challenges Solved:
- Fix environment variable naming (WECHAT_CORP_SECRET)
- Fix @wecom/crypto import (createRequire for CommonJS)
- Fix decrypt function parameters (2 params, not 4)
- Fix Token character recognition (lowercase l vs digit 1)
- Regenerate EncodingAESKey (43 chars, correct format)
- Configure natapp for internal network penetration

Test Results:
- WeChat developer tool verification: PASSED
- Return status: request success
- HTTP 200, decrypted 23 characters correctly
- Backend logs: URL verification successful

Documentation:
- Add Day3 WeChat integration development record
- Update MVP development task list (Day 2-3 completed)
- Update module status guide (v1.2 -> v1.3)
- Overall completion: 35% -> 50%

Progress:
- Module completion: 35% -> 50%
- Day 3 development: COMPLETED
- Ready for end-to-end testing (REDCap -> WeChat)

2026-01-03 00:13:36 +08:00

3 Commits