|
|
aadceb5cde
|
feat(ssa): Implement dual-channel architecture Phase 1-3 (QPER + LLM Agent pipeline)
Completed:
- Phase 1: DB schema (execution_mode + ssa_agent_executions), ModeToggle component, Session PATCH API
- Phase 2: AgentPlannerService + AgentCoderService (streaming) + CodeRunnerService + R Docker /execute-code endpoint
- Phase 3: AgentCodePanel (3-step confirmation UI), SSE event handling (7 agent events), streaming code display
- Three-step confirmation pipeline: plan -> user confirm -> stream code -> user confirm -> execute R code -> results
- R Docker sandbox /execute-code endpoint with 120s timeout + block_helpers preloaded
- E2E dual-channel test script (8 tests)
- Updated R engine architecture doc (v1.5) and SSA module status doc (v4.0)
Technical details:
- AgentCoderService uses LLM streaming (chatStream) for real-time code generation feedback
- ReviewerAgent temporarily disabled, prioritizing Plan -> Code -> Execute flow
- CodeRunnerService wraps user code with auto data loading (df variable injection)
- Frontend handles agent_planning, agent_plan_ready, code_generating, code_generated, code_executing, code_result events
- ask_user mechanism used for plan and code confirmation steps
Files: 24 files (4 new services, 2 new components, 1 migration, 1 E2E test, 16 modified)
Made-with: Cursor
|
2026-03-02 22:23:54 +08:00 |
|
|
|
71d32d11ee
|
feat(iit): V3.2 data consistency + project isolation + admin config redesign + Chinese labels
Summary:
- Refactor timeline API to read from qc_field_status (SSOT) instead of qc_logs
- Add field-issues paginated API with severity/dimension/recordId filters
- Add LEFT JOIN field_metadata + qc_event_status for Chinese display names
- Implement per-project ChatOrchestrator cache and SessionMemory isolation
- Redesign admin IIT config tabs (REDCap -> Fields -> KB -> Rules -> Members)
- Add AI-powered QC rule generation (D3 programmatic + D1/D5/D6 LLM-based)
- Add clickable warning/critical detail Modal in ReportsPage
- Auto-dispatch eQuery after batch QC via DailyQcOrchestrator
- Update module status documentation to v3.2
Backend changes:
- iitQcCockpitController: rewrite getTimeline from qc_field_status, add getFieldIssues
- iitQcCockpitRoutes: add field-issues route
- ChatOrchestrator: per-projectId cached instances
- SessionMemory: keyed by userId::projectId
- WechatCallbackController: resolve projectId from iitUserMapping
- iitRuleSuggestionService: dimension-based suggest + generateD3Rules
- iitBatchController: call DailyQcOrchestrator after batch QC
Frontend changes:
- AiStreamPage: adapt to new timeline structure with dimension tags
- ReportsPage: clickable stats cards with issue detail Modal
- IitProjectDetailPage: reorder tabs, add AI rule generation UI
- iitProjectApi: add TimelineIssue, FieldIssueItem types and APIs
Status: TypeScript compilation verified, no new lint errors
Made-with: Cursor
|
2026-03-02 14:29:59 +08:00 |
|
|
|
0b29fe88b5
|
feat(iit): QC deep fix + V3.1 architecture plan + project member management
QC System Deep Fix:
- HardRuleEngine: add null tolerance + field availability pre-check (skipped status)
- SkillRunner: baseline data merge for follow-up events + field availability check
- QcReportService: record-level pass rate calculation + accurate LLM XML report
- iitBatchController: legacy log cleanup (eventId=null) + upsert RecordSummary
- seed-iit-qc-rules: null/empty string tolerance + applicableEvents config
V3.1 Architecture Design (docs only, no code changes):
- QC engine V3.1 plan: 5-level data structure (CDISC ODM) + D1-D7 dimensions
- Three-batch implementation strategy (A: foundation, B: bubbling, C: new engines)
- Architecture team review: 4 whitepapers reviewed + feedback doc + 4 critical suggestions
- CRA Agent strategy roadmap + CRA 4-tool explanation doc for clinical experts
Project Member Management:
- Cross-tenant member search and assignment (remove tenant restriction)
- IIT project detail page enhancement with tabbed layout (KB + members)
- IitProjectContext for business-side project selection
- System-KB route access control adjustment for project operators
Frontend:
- AdminLayout sidebar menu restructure
- IitLayout with project context provider
- IitMemberManagePage new component
- Business-side pages adapt to project context
Prisma:
- 2 new migrations (user-project RBAC + is_demo flag)
- Schema updates for project member management
Made-with: Cursor
|
2026-03-01 15:27:05 +08:00 |
|
|
|
7c3cc12b2e
|
feat(iit): Complete CRA Agent V3.0 P1 - ChatOrchestrator with LLM Function Calling
P1 Architecture: Lightweight ReAct (Function Calling loop, max 3 rounds)
Core changes:
- Add ToolDefinition/ToolCall types to LLM adapters (DeepSeek + CloseAI + Claude)
- Replace 6 old tools with 4 semantic tools: read_report, look_up_data, check_quality, search_knowledge
- Create ChatOrchestrator (~160 lines) replacing ChatService (1,442 lines)
- Wire WechatCallbackController to ChatOrchestrator, deprecate ChatService
- Fix nullable content (string | null) across 12+ LLM consumer files
E2E test results: 8/8 scenarios passed (100%)
- QC report query, critical issues, patient data, trend, on-demand QC
- Knowledge base search, project overview, data modification refusal
Net code reduction: ~1,100 lines
Tested: E2E P1 chat test 8/8 passed with DeepSeek API
Made-with: Cursor
|
2026-02-26 14:27:09 +08:00 |
|
|
|
203846968c
|
feat(iit): Complete CRA Agent V3.0 P0 milestone - autonomous QC pipeline
P0-1: Variable list sync from REDCap metadata
P0-2: QC rule configuration with JSON Logic + AI suggestion
P0-3: Scheduled QC + report generation + eQuery closed loop
P0-4: Unified dashboard + AI stream timeline + critical events
Backend:
- Add IitEquery, IitCriticalEvent Prisma models + migration
- Add cronEnabled/cronExpression to IitProject
- Implement eQuery service/controller/routes (CRUD + respond/review/close)
- Implement DailyQcOrchestrator (report -> eQuery -> critical events -> notify)
- Add AI rule suggestion service
- Register daily QC cron worker and eQuery auto-review worker
- Extend QC cockpit with timeline, trend, critical events APIs
- Fix timeline issues field compat (object vs array format)
Frontend:
- Create IIT business module with 6 pages (Dashboard, AI Stream, eQuery,
Reports, Variable List + project config pages)
- Migrate IIT config from admin panel to business module
- Implement health score, risk heatmap, trend chart, critical event alerts
- Register IIT module in App router and top navigation
Testing:
- Add E2E API test script covering 7 modules (46 assertions, all passing)
Tested: E2E API tests 46/46 passed, backend and frontend verified
Made-with: Cursor
|
2026-02-26 13:28:08 +08:00 |
|
|
|
49b5c37cb1
|
feat(ssa): Complete T-test end-to-end testing with 9 bug fixes - Phase 1 core 85% complete. R service: missing value auto-filter. Backend: error handling, variable matching, dynamic filename. Frontend: module activation, session isolation, error propagation. Full flow verified.
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-02-19 20:57:00 +08:00 |
|
