Cadence audit (2026-06-01), docs-only -> CI-skip. investigator-codebase drift scan (ground-truth from disk) -> em main patch. No code touched, 154 test unchanged. Drift fixes (42 count corrections): 40->42 mig, 84/59/55/47->91 tables, 130/111->154 test, 52/49->56 gotcha across CLAUDE.md, docs/CLAUDE.md, ef-core-migration + dependency-audit skills, schema-diagram, database-guide. schema-diagram migration table extended Mig 17-42; ef-core history Mig 27-42; detailed-section gap (Mig 27-42 modules) flagged explicit (deferred, not silent). AI_INFRA bundle 06-01 (federated, full scope): - A: RAG T1/T2 auto-ack - C: hygiene 7/7 agent-mem L1 <=16KB; "25KB"->"~30KB tiered" wording x7 - D: #4 self-sustaining adoption-report step -> /session-end Phase 6.3 - E/F: report + ledger -> docs/governance/ Carry-over .mcp.json + BROADCAST-05-29 left untouched (concurrency rule). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
3.0 KiB
3.0 KiB
Investigator-API Agent — Persistent Memory
Persistent diary cross-session. Auto-injected first ~200 lines at spawn (L1 HOT). Update BEFORE every stop. Tiered Memory v1: L1 HOT soft-cap ~30KB · L2
archive/on-demand · L3 RAGsearch_memoryjust-in-time. Keep entry ≤ 1.5K chars (gotcha #53). NEW agent S39 (2026-05-29) — split từ investigator (external research half). Internal audit history ởinvestigator-codebase.
🎯 Role baseline
Read-only EXTERNAL research specialist. WebFetch/WebSearch official docs + NuGet/npm CVE + FE lib eval + cross-project reference (NamGroup/DH_Y_DUOC/BVAAU). Tools: Read, Bash, WebFetch, WebSearch + 5 RAG MCP. Output: findings + source URLs ≤ 500 words. Skill: dependency-audit-erp.
🚫 Split boundary
- ✅ MINE: external docs, CVE scan, lib license+bundle eval, cross-project pattern port
- ❌ NOT: internal codebase audit / SQL schema / grep symbol →
investigator-codebase
🔑 Dependency pin constraints (flag violation)
- MediatR
12.4.1(gotcha #1) · Swashbuckle6.9.0(gotcha #2) · Node CI20.x· LibreOffice25.8.6· @microsoft/signalr8.0.7 - New dep eval: license MIT? bundle gzipped impact? (vd FullCalendar v6 React MIT verified S36 — daygrid/timegrid OK, Premium chỉ scheduler — SOL chọn custom HTML grid save ~80KB instead)
🌐 Trusted source URLs
anthropic.com/engineering/·cognition.ai/blog/·learn.microsoft.com/en-us/aspnet/core/+/ef/core/·tanstack.com/query/latest·ui.shadcn.com·philschmid.de·eugeneyan.com·hamel.dev
📂 Cross-project reference paths
- NamGroup
D:\Dropbox\CONG_VIEC\NAMGROUP\SOURCECODE_CÔNG_TY\NAMGROUP\(Phase 10 port — TblNhanVien/TblPhongHop/TblResource patterns) - DH_Y_DUOC
D:\Dropbox\CONG_VIEC\DAI_Y_DUOC\DH_Y_DUOC_SOURCECODE\DH_Y_DUOC\(clean arch + CQRS) - BVAAU
D:\Dropbox\CONG_VIEC\BENHVIEN_A_AU\SOURCE_CODDE\(multi-agent config — 7 agent split reference)
📅 Recent activity (last 10 FIFO)
- 2026-05-29 (S39 agent split setup): NEW agent created từ split investigator. Seeded external-research half. Prior cross-project audits (NamGroup Phase 10 port G-H1/G-O2 + FullCalendar eval S36 + BVAAU 7-agent config S39) absorbed into role baseline.
- 2026-05-29 (S40 FIRST SPAWN — smoke-verify + RAG fleet report): Agent load OK confirmed.
list_projects→ 7 project, total 39,798 chunks. Rerank pipeline LIVE verdict PASS (search_memory scope=self use_rerank=true → top rerank_score 0.8789, 3 results all carry rerank_score). Staleness >5d (vs 05-29): dh_y_duoc (05-23, 6d) / namgroup_main (05-22, 7d) / ashico_erp (05-22, 7d). solution_erp 05-28 fresh-ish but missing S37-S39 content.shared_global= 0 chunks (chưa promote pattern nào). MINOR drift: namgroup_main actual 11306 (brief said 11305). vipix_ai_infra (1652) = AI_INFRA hub rootD:\...\AI_INFRA. No re-ingest performed (report-only).
🔄 Curate trigger
- Size > ~30KB → archive to L2
archive/<period>.md. Stale > 3 months → remove.