[CLAUDE] Skill: Setup multi-agent infrastructure (Investigator + Implementer + Reviewer)
Session 20 turn 12: User paste self-contained template setup multi-agent từ NAMGROUP s41-s43 trial (empirical-grounded Anthropic Building Effective Agents + Cognition "writes single-threaded"). Pre-flight decision gate 6/6 pass → proceed setup. ### Phase 0 — Pre-flight ✅ 6/6 - Codebase > 10K LOC ✅ (59 tables · 27 mig · ~142 endpoints · 34 FE pages) - Project > 6 months ✅ (roadmap T1-T13) - Heavy multi-file features regular ✅ (per-chunk 5-6 commit/session) - User extend ngáo threshold ✅ (S20 đã 12+ turn, deep context) - 25+ gotchas/patterns ✅ (44 gotchas · 14 memory · 6 skills) - Critical changes adversarial review ✅ (UAT live 3 prod domain) ### Phase 1-4 setup .claude/ ├── agents/ │ ├── README.md (master coordination guide ~9.7KB) │ ├── investigator.md (READ — research + audit + WebFetch ~7.3KB) │ ├── implementer.md (WRITE conditional Case 1+2+3+5 ~8.4KB) │ └── reviewer.md (READ adversarial pre-commit + live curl ~9.6KB) └── agent-memory/ ├── investigator/MEMORY.md (seed ~5.9KB) ├── implementer/MEMORY.md (seed ~6.9KB) └── reviewer/MEMORY.md (seed ~6.5KB) ### Customizations per SOLUTION_ERP - Stack: .NET 10 Clean Arch + 2 React 19 FE + SQL Server + Gitea + IIS - Skills preload mỗi agent (reuse 6 skills hiện có): - Investigator: contract-workflow + permission-matrix + ef-core-migration - Implementer: ef-core-migration + permission-matrix + form-engine - Reviewer: dependency-audit-erp + iis-deploy-runbook + contract-workflow - DB: SolutionErp_Dev (LocalDB runtime) + _Design (ef tooling distinct) - Test bearer: admin@solutions.com.vn / Admin@123456 (full) + nv.test@solutions.com.vn / TestUser@123456 (Drafter UAT scope) - Prod UAT: api/admin/eoffice.solutions.com.vn ### Windows MAX_PATH pitfall handled Project path D:\Dropbox\CONG_VIEC\SOLUTION\SOLUTION_ERP\ = 51 chars + nested Dropbox-managed → `isolation: worktree` DROPPED khỏi implementer.md frontmatter per template Pitfall 1. Em main reviews diff before commit (compensate). ### Memory baseline seeded 3 MEMORY.md có: - Patterns proven cross-session (5-chunk discipline, 3-file Mig rule, audit-reuse, service hook derived, FE mirror 2 app, VND format helpers) - 44 gotcha cross-ref - Phase 9 UAT iteration mode (skip test per chunk theo memory feedback_uat_skip_verify) - 5-category Reviewer checklist tinh chỉnh theo SOLUTION_ERP gotcha cluster (#44 silent 403 + #43 Step.Order + #42 V1/V2 dual schema + Wire BE claim) - Tests baseline 81/81 PASS preserve ### Trial workflow Week 1 candidate: Contract V2 wire (Mig 28+29) mirror PE pattern S17-S19 — audit-reuse pattern proven 1×. ~600+ LOC, 2 mig + Service + Controller + FE × 2 app. Investigator pre-flight + Implementer A→E chunks + Reviewer pre-commit verify gotcha #42 dual schema. Em main spawn first time qua /agents command. Pattern tracking ROI 4 tuần trial (week 4 evaluate keep / tune / archive). ### Acceptance criteria 7/7 ✅ - 4 agent .md với valid YAML frontmatter (name/description/model/effort/tools/ skills/memory/color/maxTurns) - 3 MEMORY.md seeds populated SOLUTION_ERP context - All template placeholders {XXX} replaced - Skills 3 đầu agent point tồn tại .claude/skills/ (6 skills sẵn) - File structure đúng template - Implementer isolation worktree dropped (Windows MAX_PATH) - Trial 1 ready (em main /agents spawn dispatch) References: Anthropic Building Effective Agents + Cognition "writes single-threaded" + NAMGROUP s41-s43 empirical curve (+83% → +27% → ~0% overhead). Setup time ~3-5h estimate (đã làm trong S20 turn 12 ~30min do template self-contained + project context đã accumulate). Path filter CI sẽ skip (.claude/skills/** trong paths-ignore, mirror cho .claude/agents/** + .claude/agent-memory/** thực tế cũng docs-class). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
pqhuy1987
157
.claude/agent-memory/implementer/MEMORY.md
Normal file
157
.claude/agent-memory/implementer/MEMORY.md
Normal file
@ -0,0 +1,157 @@
|
||||
# Implementer Agent — Persistent Memory
|
||||
|
||||
> **Persistent diary cross-session.** Auto-injected first 200 lines / 25KB at spawn.
|
||||
> Update BEFORE every stop. Curate when > 25KB.
|
||||
|
||||
---
|
||||
|
||||
## 🎯 Role baseline
|
||||
|
||||
Code execution specialist for SOLUTION_ERP. Conditional WRITE (Case 1+2+3+5 ONLY). Tools: Read, Edit, Write, Bash, Skill, Grep, Glob. Output: commits + verification report.
|
||||
|
||||
## 🚨 STRICT scope auto-refuse criteria
|
||||
|
||||
REFUSE if ANY:
|
||||
1. Schema design decisions needed (FK strategy / nullable / discriminator)
|
||||
2. UX flow decisions needed (drawer vs tab vs modal)
|
||||
3. Cross-stack > 2 layers tight coupling
|
||||
4. Bug fix involving reasoning chain
|
||||
5. Integration testing involving multiple components
|
||||
6. < 30 min trivial task
|
||||
7. First time pattern (no prior precedent)
|
||||
8. Spec ambiguity > 20%
|
||||
|
||||
---
|
||||
|
||||
## 📋 Patterns proven (cross-session) — apply confidently
|
||||
|
||||
### Pattern 1: Per-chunk discipline 5-chunk A-E (Anthropic Case 2 orchestrator-workers)
|
||||
|
||||
Memory `feedback_per_chunk_commit` chốt:
|
||||
- **Chunk A:** Domain entities + Migration (3-file rule)
|
||||
- **Chunk B:** Application handlers (CQRS Commands + Queries + Validators)
|
||||
- **Chunk C:** Service layer (workflow logic, business rules)
|
||||
- **Chunk D:** API controllers + endpoints
|
||||
- **Chunk E:** FE update (cả 2 app mirror) + Tests + Docs + commit final
|
||||
|
||||
Build + test pass mỗi chunk. Commit message format:
|
||||
```
|
||||
[CLAUDE] <scope>: Chunk <X> — <one-line summary>
|
||||
<body>
|
||||
Verify:
|
||||
- Build pass (X warning, 0 error)
|
||||
- N test pass (...)
|
||||
Pending Chunk <Y+1>: <next>
|
||||
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
||||
```
|
||||
|
||||
### Pattern 2: 3-file rule EF migration (BẮT BUỘC commit đủ)
|
||||
|
||||
Memory + gotcha #17:
|
||||
- `Migrations/{TS}_{Name}.cs` (Up + Down)
|
||||
- `Migrations/{TS}_{Name}.Designer.cs` (snapshot at migration time)
|
||||
- `Migrations/ApplicationDbContextModelSnapshot.cs` (current snapshot)
|
||||
|
||||
```bash
|
||||
dotnet ef migrations add <Name> \
|
||||
--project src/Backend/SolutionErp.Infrastructure \
|
||||
--startup-project src/Backend/SolutionErp.Api
|
||||
|
||||
# Apply lên DB Dev:
|
||||
dotnet ef database update --project src/Backend/SolutionErp.Infrastructure \
|
||||
--startup-project src/Backend/SolutionErp.Api \
|
||||
--connection "Server=(localdb)\MSSQLLocalDB;Database=SolutionErp_Dev;Trusted_Connection=True;TrustServerCertificate=true"
|
||||
|
||||
# Apply lên DB Design (catchup nếu thiếu):
|
||||
dotnet ef database update --project src/Backend/SolutionErp.Infrastructure \
|
||||
--startup-project src/Backend/SolutionErp.Api
|
||||
```
|
||||
|
||||
### Pattern 3: Audit reuse trước khi clone (memory `feedback_audit_reuse_before_clone`)
|
||||
|
||||
Khi user nói "clone X sang Y":
|
||||
1. **Grep discriminator field** (`ApplicableType`, `Type`, `Kind` enum)
|
||||
2. **Check Service / Handler / Controller** có hardcode type cụ thể không
|
||||
3. **Check FE pages** có route dynamic typeCode hay hardcode
|
||||
4. **Check menu key** (BE const + FE menuKeys.ts) — thường thiếu chính ở đây
|
||||
5. Default reuse 80%, chỉ thêm menu key + sample seed (3 file ~60 LOC)
|
||||
|
||||
Bài học S17+ Clone B: 1 commit `937eb24`, deploy 1 phát chạy.
|
||||
|
||||
### Pattern 4: Service hook vs CRUD endpoint cho derived state (memory `feedback_service_hook_vs_endpoint`)
|
||||
|
||||
State X = derived của action Y → UPSERT trong handler Y, KHÔNG endpoint /X riêng.
|
||||
|
||||
Bài học S19 Mig 26 PE LevelOpinions: Service `ApproveV2Async` UPSERT row qua match `ApproverUserId == actorUserId` (fallback first khi Admin override). 0 endpoint mới.
|
||||
|
||||
### Pattern 5: FE mirror 2 app rule §3.9
|
||||
|
||||
Duplicate `fe-admin/` + `fe-user/` CÓ CHỦ ĐÍCH:
|
||||
- Sửa fe-admin xong → mirror fe-user (tay)
|
||||
- Khi breaking change rename prop → BẮT BUỘC `npm run build` × 2 app (memory `feedback_uat_skip_verify` exception)
|
||||
|
||||
### Pattern 6: VND format helpers + Phone/Email validate (S20 turn 4)
|
||||
|
||||
Inline mỗi file FE PE:
|
||||
```ts
|
||||
const parseVnd = (s: string): number => Number(s.replace(/[^\d]/g, '')) || 0
|
||||
const formatVndInput = (n: number): string => (n > 0 ? n.toLocaleString('vi-VN') : '')
|
||||
const PHONE_RE = /^0\d{9,10}$/
|
||||
const EMAIL_RE = /^[^\s@]+@[^\s@]+\.[^\s@]+$/
|
||||
const isValidPhone = (s: string) => !s || PHONE_RE.test(s.replace(/[\s\-.]/g, ''))
|
||||
const isValidEmail = (s: string) => !s || EMAIL_RE.test(s)
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## ⚠️ Anti-patterns observed (DO NOT)
|
||||
|
||||
1. ❌ Skip MEMORY.md update — knowledge tài sản
|
||||
2. ❌ Bypass pre-commit hooks `--no-verify` (forbidden absolute)
|
||||
3. ❌ `git add -A` hoặc `git add .` — specific files only
|
||||
4. ❌ Touch files outside spec scope — anti-fiddle rule
|
||||
5. ❌ Push remote autonomously cho heavy change — em main pushes (UAT iteration: confirm với em trước push)
|
||||
6. ❌ Modify `SolutionErp.slnx` autonomously — em main updates khi thêm `.cs/.csproj`
|
||||
7. ❌ Lower bar to match em main quality — Smart Friend Cognition anti-pattern
|
||||
8. ❌ Proceed when spec ambiguous > 20% — return REFUSE với reason
|
||||
|
||||
---
|
||||
|
||||
## 🧠 SOLUTION_ERP conventions (auto-load via skills)
|
||||
|
||||
- **BE .NET 10:** PascalCase tiếng Anh entities + DTO records + command names. CQRS + MediatR + FluentValidation + AutoMapper. Repository qua `IApplicationDbContext`. `GlobalExceptionMiddleware` map exception → ProblemDetails (NO try-catch trong controllers).
|
||||
- **FE React 19 + Vite 8 + TS 6:** Named export only (trừ App). TanStack Query. shadcn/ui copy-paste. TS6 `erasableSyntaxOnly` cấm `enum` → const-object pattern. UI 100% tiếng Việt. Mirror 2 app rule §3.9.
|
||||
- **Test:** baseline 81/81 PASS (58 Domain + 23 Infra). Phase 9 UAT skip per chunk theo memory `feedback_uat_skip_verify`. Stack xUnit + FluentAssertions 7.2 + EF SQLite 10 `TestApplicationDbContext` override `nvarchar(max) → TEXT`.
|
||||
- **Build:** `dotnet build SolutionErp.slnx` clean 0 err + `npm run build` × 2 app pass.
|
||||
- **Commit:** `[CLAUDE] <scope>: <message>` + Co-Authored-By Claude Opus 4.7 (1M context).
|
||||
|
||||
## Scopes (pick 1)
|
||||
|
||||
`Contract` · `PurchaseEvaluation` · `Budget` · `Form` · `Workflow` · `Supplier` · `Auth` · `Admin` · `Api` · `App` · `Domain` · `Infra` · `FE-Admin` · `FE-User` · `Tests` · `Docs` · `CICD` · `Scripts` · `Skill`
|
||||
|
||||
---
|
||||
|
||||
## 🔑 Pin versions (package pinning §2.8)
|
||||
|
||||
KHÔNG `*` / `latest`. Critical pins:
|
||||
- MediatR `12.4.1` (14 fail DI)
|
||||
- Swashbuckle `6.9.0` (10 conflict OpenApi 2)
|
||||
- Node engines `>= 20` + CI pin `20.x` (bài học NamGroup, memory `feedback_node_cicd`)
|
||||
- LibreOffice `25.8.6`
|
||||
- @microsoft/signalr `8.0.7`
|
||||
|
||||
---
|
||||
|
||||
## 📅 Recent activity (last 10 FIFO)
|
||||
|
||||
- **2026-05-11 (setup):** Implementer agent initialized. Baseline knowledge load complete (5 patterns proven cumulative S1-S20: per-chunk 5 chunk, 3-file rule Mig, audit-reuse clone, service hook derived state, FE mirror 2 app, VND format helpers). No implementations performed yet. Awaiting first SendMessage from em main. Strict scope auto-refuse criteria active.
|
||||
|
||||
---
|
||||
|
||||
## 🔄 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)
|
||||
Reference in New Issue
Block a user