Files
solution-erp/.claude/agent-memory/investigator/MEMORY.md
pqhuy1987 36e21c88d2 [CLAUDE] Docs: chốt Session 20 WRAP — 12 turn + 14 commit + 2 memory mới + 3 sub-agents setup
Session 20 wrap-up cuối ngày 2026-05-11 sau turn 12 multi-agent setup.

### Session log mới (turn 6 + 8-12)

`docs/changelog/sessions/2026-05-11-2200-pe-polish-responsive-multiagent.md`
- Turn 6 manual budget drop tên field
- Turn 8 NCC 5-màu palette + Winner 🏆 badge (initial)
- Turn 9 revert badge → icon ✓ đậm + hover
- Turn 10 AddSupplier auto-fill master
- Turn 11 responsive laptop nhỏ 4-tầng pattern
- Turn 12 multi-agent infrastructure setup 3 sub-agents

### MD updates

STATUS.md:
- Last updated S20 WRAP 22:00
- Recently Done row mới wrap turns 6+8-12 trên đầu (giữ S20 turn 7 + S20 t1-5 nguyên §6.5)

HANDOFF.md:
- Last updated S20 WRAP
- TL;DR Session 20 WRAP trên đầu (3 chủ đề + Stats + Multi-agent state + Memory mới + Pending S21+ + Audit cadence)
- Giữ TL;DR Session 20 turn 7 + S20 + S19 nguyên văn §6.5

migration-todos.md:
- Phase 9 WRAP S20 section trên cùng (stats final + memory mới + defer S21+ Trial Week 1)
- Giữ Session 20 turn 7 + S20 + S19 nguyên §6.5

### Multi-agent MEMORY.md sync

.claude/agent-memory/investigator/MEMORY.md:
- Count 14 → 16 memory entries
- +2 entry references (feedback_responsive_laptop_breakpoint + feedback_multi_agent_setup)

### Status agents chốt session

3 sub-agents seeds-only state — chưa spawn work. KHÔNG có findings cross-agent
flush ở session này (vừa setup turn 12). Trial Week 1 kick off Session 21
với Contract V2 wire Mig 28+29 candidate.

### Tests baseline preserve

dotnet test SolutionErp.slnx — 81/81 PASS (58 Domain + 23 Infra) — Phase 9
UAT iteration defer test increment per chunk (memory feedback_uat_skip_verify).

### Path filter CI sẽ skip (.gitea/workflows paths-ignore docs/** + .claude/**)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-11 21:29:32 +07:00

5.9 KiB

Investigator Agent — Persistent Memory

Persistent diary cross-session. Auto-injected first 200 lines / 25KB at spawn. Update BEFORE every stop. Curate when > 25KB.


🎯 Role baseline

Read-only research + audit for SOLUTION_ERP codebase. Tools: Read, Grep, Glob, Bash, WebFetch, WebSearch. Output: concise structured findings under 500 words.


📋 Patterns proven (cross-session)

Pattern: Smoke verify catalog SOLUTION_ERP

  • Bearer auth từ https://api.solutions.com.vn/api/auth/login (POST email + password)
  • Status code matrix expected vs actual + JSON output + MD audit
  • Test credentials: admin@solutions.com.vn / Admin@123456 (full) OR nv.test@solutions.com.vn / TestUser@123456 (Drafter UAT scope)

Pattern: Schema scan via sqlcmd

# LocalDB Dev (runtime — primary)
sqlcmd -S "(localdb)\MSSQLLocalDB" -d SolutionErp_Dev -Q "..."

# LocalDB Design (ef tooling)
sqlcmd -S "(localdb)\MSSQLLocalDB" -d SolutionErp_Design -Q "..."

# Production (qua SSH vietreport-vps)
ssh vietreport-vps "sqlcmd -S .\SQLEXPRESS -d SolutionErp -U vrapp -P '...' -Q '...'"

Common queries: sys.columns, sys.triggers, __EFMigrationsHistory, COUNT(*), sys.indexes.

Gotcha: 2 LocalDB distinct (memory feedback_designtime_runtime_db):

  • _Dev — runtime API (appsettings.Development.json ConnectionStrings:Default)
  • _Designdotnet ef migrations add/update default target
  • Use --connection "Server=(localdb)\MSSQLLocalDB;Database=SolutionErp_Dev;..." override khi cần Dev specifically.

Pattern: Controller audit

  • Grep \[Route\("api/[a-z]+"\)\] enumerate ~30+ controllers
  • Grep \[Authorize(Policy = "..." audit per-action policy (gotcha #44 silent 403 class-level quá strict)
  • Grep IActionResult vs ActionResult<T> — typed return preferred
  • Grep // Mock / alert( / setEditing(null) // close UI — wire claim bugs

Pattern: Memory cross-reference

16 memory entries tại C:\Users\pqhuy\.claude\projects\D--Dropbox-CONG-VIEC-SOLUTION\memory\ (S20 +2 turn 11/12):

  • MEMORY.md — index
  • project_solution_erp.md — cumulative narrative S1-S17
  • feedback_per_chunk_commit.md — 5-chunk A-E discipline
  • feedback_uat_skip_verify.md — Phase 9 skip test rule
  • feedback_drastic_refactor_scope.md — defer dedicated session
  • feedback_audit_reuse_before_clone.md — audit-first pattern (Investigator natural fit)
  • feedback_service_hook_vs_endpoint.md — derived state hook pattern
  • feedback_n_stage_workflow_pattern.md — DEPRECATED (Mig 21 flat workflow replaced)
  • feedback_designtime_runtime_db.md — 2 LocalDB distinct
  • feedback_md_compact_narrative.md — §6.5 KEEP narrative rule
  • feedback_unittest_timing.md — §7 test timing
  • feedback_cron_monthly_limitation.md — Cron SDK 7-day expire
  • feedback_user_manual_style.md — non-tech docs style
  • feedback_node_cicd.md — Node 20.x pin
  • feedback_responsive_laptop_breakpoint.md — 4-tầng responsive pattern (S20 t11)
  • feedback_multi_agent_setup.md — 3 sub-agents setup discipline (S20 t12)
  • reference_session_prompts.md — canonical session start template

Pattern: External research priority sources

  • anthropic.com/engineering/ (official patterns)
  • cognition.ai/blog/ (Devin lessons)
  • philschmid.de + eugeneyan.com + hamel.dev (senior engineers)
  • learn.microsoft.com/en-us/aspnet/core/ (.NET 10 official)
  • tanstack.com/query/latest (TanStack Query)

⚠️ Anti-patterns observed

  • Skip MEMORY.md update before stop — lose knowledge tài sản
  • Vague conclusion "seems like" / "probably" — em main rejects
  • Missing file:line refs — non-verifiable evidence
  • Exceed 500 words — em main reads too slow
  • Scope drift to architectural recommendations — em main decides, not me

🧠 SOLUTION_ERP context essentials (auto-load)

  • DB Dev: SolutionErp_Dev LocalDB (59 tables / 27 migrations / Mig 27 latest AddVisibilityAndDisplayLabelToMenuItems)
  • DB Design: SolutionErp_Design (ef tooling distinct)
  • DB Prod: .\SQLEXPRESS / SolutionErp / vrapp user via SSH vietreport-vps
  • Tech stack: .NET 10 Clean Arch (Api → Application ← Domain + Infra) + CQRS MediatR + EF Core 10 + 2 React 19 Vite 8 TS 6 (fe-admin :8082 + fe-user :8080) + SQL Server + Gitea Actions CI + IIS prod
  • Live deploys (Prod UAT): https://api.solutions.com.vn · https://admin.solutions.com.vn · https://eoffice.solutions.com.vn
  • Gitea remote: https://git.baocaogiaoduc.vn/vietreport-admin/solution-erp
  • SSH VPS: ssh vietreport-vps (config ~/.ssh/config user=Administrator key=id_ed25519)
  • Gotchas active: 44 (reference docs/gotchas.md)
  • Tests baseline: 81 PASS (58 Domain + 23 Infra) — Phase 9 UAT skip per chunk (memory feedback_uat_skip_verify)
  • Master HEAD reference: check via git log -1 --format='%H'
  • 6 skills: contract-workflow · permission-matrix · form-engine · ef-core-migration · dependency-audit-erp · iis-deploy-runbook

🔄 Active workflow schemas (V1 + V2 coexist post-Session 17)

  • V1 Mig 21 flat workflowWorkflowDefinition pin với PE/Contract cũ. Match Dept+PositionLevel.
  • V2 Mig 22-27ApprovalWorkflow pin với PE mới + match ApproverUserId 1-1 OR-of-N cùng Cấp. Steps (Phòng) > Levels (Cấp). PE đã wire V2. Contract V2 PENDING Session 21+.

State machine 5 trạng thái phiếu PE: Nháp / Đã gửi duyệt / Trả lại (TraLai=98) / Từ chối / Đã duyệt.


📅 Recent activity (last 10 FIFO)

  • 2026-05-11 (setup): Investigator agent initialized. Baseline knowledge load complete (44 gotchas + 14 memory entries + 6 skills + 27 mig + 81 test pass cumulative). No investigations performed yet. Awaiting first SendMessage from em main.

🔄 Curate trigger

  • Memory size > 25KB → archive recent entries to archive/<period>.md
  • Duplicate entries detected → merge
  • Stale > 3 months → remove

Last curate: 2026-05-11 (initial seed)