fix(rfa): add RfaWorkflow entity to RfaModule

TypeORM error: Entity metadata for RfaRevision#workflows was not found.
RfaWorkflow entity was missing from TypeOrmModule.forFeature() registration,
causing the application to fail to start.

.agents/README.md

@@ -2,7 +2,12 @@
 
 > **The Event Horizon of Software Quality.**
 > _Adapted for Google Antigravity IDE from [github/spec-kit](https://github.com/github/spec-kit)._
-> _Version: 1.8.6 — LCBP3-DMS Edition (v1.8.6 Production Ready)_
+>
+> # Speckit Agent Infrastructure (v1.9.0)
+>
+> - Version: 1.9.0
+> - Last Updated: 2026-05-22
+> - Core Principle: **Sync with AGENTS.md v1.9.6**
 
 ---
 
@@ -78,36 +83,37 @@ The toolkit is organized into modular components that provide both the logic (Sc
 │   ├── speckit-tester/            # Test Runner & Coverage
 │   └── speckit-validate/          # Implementation Validator
 │
+├── workflows/                     # / Slash Commands (Orchestration)
+│   ├── 00-speckit.all.md          # Full Pipeline (10 steps: Specify → Validate)
+│   ├── 01–11-speckit-*.md         # Individual phase workflows
+│   ├── speckit-prepare.md         # Prep Pipeline (5 steps: Specify → Analyze)
+│   ├── schema-change.md           # DB Schema Change (ADR-009)
+│   ├── create-backend-module.md   # NestJS Module Scaffolding
+│   ├── create-frontend-page.md    # Next.js Page Scaffolding
+│   ├── deploy.md                  # Deployment via Gitea CI/CD
+│   ├── review.md                  # Code Review Workflow
+│   └── util-speckit-*.md          # Utilities (checklist, diff, migrate, etc.)
+│
 ├── rules/                         # Project Context & Validation Rules
-│   ├── 00-project-context.md      # Role, Persona, Rule Tiers
+│   ├── 00-project-context.md      # Role, Persona, Rule Tiers (v1.9.6)
 │   ├── 01-adr-019-uuid.md         # UUID Strategy (Critical)
-│   ├── 02-security.md             # Security Requirements
+│   ├── 02-security.md             # Security Requirements (ADR-023/023A)
 │   ├── 03-typescript.md            # TypeScript Standards
 │   ├── 04-domain-terminology.md   # DMS Glossary Compliance
 │   ├── 05-forbidden-actions.md    # Critical Prohibited Patterns
 │   ├── 06-backend-patterns.md     # NestJS Architecture Rules
 │   ├── 07-frontend-patterns.md    # Next.js App Router Rules
-│   ├── 08-development-flow.md      # Development Workflow
+│   ├── 08-development-flow.md      # Development Workflow (Tier 3 SPECIALIZED WORK)
 │   ├── 09-commit-checklist.md      # Pre-commit Validation
 │   ├── 10-error-handling.md       # ADR-007 Compliance
-│   └── 11-ai-integration.md       # ADR-018/020 AI Boundaries
+│   └── 11-ai-integration.md       # ADR-023/023A AI Boundaries
 │
 └── scripts/
     ├── bash/                      # Bash Core (Kinetic logic)
-    ├── powershell/                 # PowerShell Equivalents (Windows-native)
+    ├── powershell/                # PowerShell Equivalents (Windows-native)
     ├── fix_links.py               # Spec link fixer
     ├── verify_links.py            # Spec link verifier
     └── start-mcp.js               # MCP server launcher
-
-.windsurf/workflows/               # / Slash Commands (Orchestration)
-├── 00-speckit.all.md              # Full Pipeline (10 steps: Specify → Validate)
-├── 01–11-speckit-*.md             # Individual phase workflows
-├── speckit-prepare.md             # Prep Pipeline (5 steps: Specify → Analyze)
-├── schema-change.md               # DB Schema Change (ADR-009)
-├── create-backend-module.md       # NestJS Module Scaffolding
-├── create-frontend-page.md        # Next.js Page Scaffolding
-├── deploy.md                      # Deployment via Gitea CI/CD
-├── review.md                      # Code Review Workflow
 └── util-speckit-*.md              # Utilities (checklist, diff, migrate, etc.)
 ```
 
@@ -259,9 +265,9 @@ If you change your mind mid-project:
 
 ---
 
-## 🏗️ LCBP3-DMS Project Notes (v1.8.6)
+## 🏗️ LCBP3-DMS Project Notes (v1.9.6)
 
-### 📊 Current Status: Production Ready (2026-04-14)
+### 📊 Current Status: Production Ready (2026-05-22)
 
 | Area          | Status                          |
 | ------------- | ------------------------------- |
@@ -277,7 +283,7 @@ If you change your mind mid-project:
 
 | เอกสาร          | Path                                                             | ใช้เมื่อ            |
 | --------------- | ---------------------------------------------------------------- | ------------------- |
-| Schema Tables   | `specs/03-Data-and-Storage/lcbp3-v1.8.0-schema-02-tables.sql`    | ก่อนเขียน Query     |
+| Schema Tables   | `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`    | ก่อนเขียน Query     |
 | Data Dictionary | `specs/03-Data-and-Storage/03-01-data-dictionary.md`             | ตรวจ Business Rules |
 | Edge Cases      | `specs/01-Requirements/01-06-edge-cases-and-rules.md`            | 37 Rules            |
 | Migration Scope | `specs/03-Data-and-Storage/03-06-migration-business-scope.md`    | Migration Bot       |
@@ -300,7 +306,7 @@ If you change your mind mid-project:
 - ❌ DO NOT bypass Release Gates before deploying — `04-08-release-management-policy.md`
 - ❌ DO NOT start Migration without Gate #1 approval — `03-06-migration-business-scope.md`
 - ❌ DO NOT use TypeORM Migrations — modify schema SQL directly (ADR-009)
-- ❌ DO NOT give Ollama direct DB access — all writes via DMS API (ADR-018)
+- ❌ DO NOT give Ollama direct DB access — all writes via DMS API (ADR-023/023A)
 - ❌ DO NOT use `any` TypeScript type anywhere
 
 ---
@@ -319,7 +325,7 @@ If you change your mind mid-project:
 # Run version validation
 ./scripts/bash/validate-versions.sh
 
-# Fix by updating all files to v1.8.6
+# Fix by updating all files to v1.9.6
 # Then re-run validation to confirm
 ```
 

.agents/archive/setup-matt-pocock-skills/SKILL.md

@@ -2,6 +2,7 @@
 name: setup-matt-pocock-skills
 description: Sets up an `## Agent skills` block in AGENTS.md/CLAUDE.md and `docs/agents/` so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc layout. Run before first use of `to-issues`, `to-prd`, `triage`, `diagnose`, `tdd`, `improve-codebase-architecture`, or `zoom-out` — or if those skills appear to be missing context about the issue tracker, triage labels, or domain docs.
 disable-model-invocation: true
+version: 1.9.0
 ---
 
 # Setup Matt Pocock's Skills

.agents/rules/00-project-context.md

@@ -0,0 +1,164 @@
+# NAP-DMS Project Context & Rules
+
+- For: Devin Cascade (and compatible: Codex CLI, opencode, Amp, Antigravity, AGENTS.md tools)
+- Version: 1.9.10 | Last synced from repo: 2026-06-06
+- Repo: [https://git.np-dms.work/np-dms/lcbp3](https://git.np-dms.work/np-dms/lcbp3)
+- Skill pack: `.agents/skills/` (v1.9.0, 21 skills) — see [`skills/README.md`](./.agents/skills/README.md) + [`skills/_LCBP3-CONTEXT.md`](./.agents/skills/_LCBP3-CONTEXT.md)
+
+## 🧠 Role & Persona
+
+Act as **Senior Full Stack Developer** specialized in NestJS, Next.js, TypeScript, DMS. Focus: Data Integrity, Security, Maintainability, Performance.
+
+You are a **Document Intelligence Engine** — not a general chatbot. Every response must be **precise**, **spec-compliant**, and **production-ready**.
+
+---
+
+## 🧩 Thought & Planning Protocol (Powered by Everything-Claude-Code)
+
+Before writing any code or taking any action in Tier 1 and Tier 2, the AI must demonstrate the following thinking process:
+
+### 1. Analysis Phase (Explore & Analyze)
+
+Problem Understanding: Restate what the user wants in clear, unambiguous terms.
+Context Search: Identify the relevant Spec files or ADRs from the "Key Spec Files" table that must be read before starting.
+Constraints Identification: Identify key constraints (e.g. Security rules, UUID patterns, or Domain terminology).
+
+### 2. Planning Phase (Plan)
+
+Alternative Exploration: Present at least 2 solution approaches (where possible) with pros/cons analysis.
+Step-by-Step Roadmap: Write a file-by-file plan of changes before executing.
+Verification Plan: Specify how to verify the work is complete (e.g. "which unit tests to write" or "which file to check the schema in").
+
+### 3. Execution & Refinement (Execute & Refine)
+
+Follow the plan step by step, and pause to ask if any uncertainty arises.
+If significant logic changes are made, summarize what was done for the user after completion.
+
+---
+
+## ⚙️ DMS Workflow Engine Protocol
+
+กฎนี้ใช้คุม Logic การไหลของเอกสาร (RFA, Transmittal, Correspondence) เพื่อป้องกัน Race Condition และรักษาความถูกต้องของสถานะ:
+
+- **State Management:** ตรวจสอบสถานะปัจจุบันจาก DB ก่อนเสมอ เพื่อป้องกันการอนุมัติซ้ำซ้อน (ดู `05-06-code-snippets.md` `[workflow-transition]`)
+- **Concurrency Control:** การจอนเลขที่เอกสารต้องใช้ **Redis Redlock** หรือ **TypeORM `@VersionColumn`** เท่านั้น (ADR-002)
+- **Background Jobs:** งานนานหรือการแจ้งเตือนต้องส่งไปทำที่ **BullMQ** ห้ามเขียนแบบ Inline (ADR-008)
+- **Term Consistency:** ห้ามใช้ "Approval Flow" ให้ใช้ **"Workflow Engine"** และห้ามใช้ "Letter" ให้ใช้ **"Correspondence"** (หมายเหตุ: "จดหมาย" ในคอมเมนต์ภาษาไทย = Correspondence ที่ครอบคลุมทุกประเภท)
+
+---
+
+## 🛡️ Security & Integrity Audit Protocol
+
+กฎนี้ให้ AI เป็น Gatekeeper ก่อน Commit โดยเน้น **Tier 1 — CRITICAL**:
+
+- **UUID Validation:** ตรวจสอบว่าเป็น **UUIDv7** และห้ามใช้ `parseInt()` บน UUID (ADR-019)
+- **RBAC Check:** API ใหม่ต้องมี **CASL Guard** และตรวจสอบ 4-Level RBAC Matrix (ADR-016)
+- **Data Isolation:** AI ต้องรันผ่าน **Ollama บน Admin Desktop** เท่านั้น ห้ามเข้าถึง DB/storage โดยตรง (ADR-023)
+- **Input Sanitization:** ไฟล์อัปโหลดต้องผ่าน **Two-Phase** (Temp → Commit) และสแกนด้วย **ClamAV** (ADR-016)
+
+---
+
+## 🧭 Rule Enforcement Tiers
+
+### 🔴 Tier 1 — CRITICAL (CI BLOCKER)
+
+Build fails หากละเมิด:
+
+- Security (Auth, RBAC, Validation)
+- UUID Strategy (ADR-019) — no `parseInt` / `Number` / `+` on UUID
+- Database correctness — verify schema before writing queries
+- File upload security (ClamAV + whitelist)
+- AI validation boundary (ADR-023)
+- Error handling strategy (ADR-007)
+- Forbidden patterns: `any`, `console.log`, UUID misuse, `id ?? ''` fallback
+
+### 🟡 Tier 2 — IMPORTANT (CODE REVIEW)
+
+Must fix ก่อน merge:
+
+- Architecture patterns (thin controller, business logic in service)
+- Test coverage (80%+ business logic, 70%+ backend overall)
+- Cache invalidation
+- Naming conventions
+- **TypeScript Standards:** Missing JSDoc, explicit types, or file headers
+
+### 🟢 Tier 3 — SPECIALIZED WORK
+
+Requires domain-specific knowledge:
+
+- **ADR-021 Integration:** Workflow Engine & Context implementation
+- **AI Infrastructure:** ADR-023/023A boundary enforcement and pipeline usage
+- **AI Runtime Layer:** ADR-024 Intent Classification, ADR-025 Tool Layer, ADR-026 Chat UI, ADR-027 Admin Console
+- **Migration Pipeline:** ADR-028 Staging Queue & post-migration cleanup
+- **Complex Business Logic:** Multi-step workflows with state management
+- **Performance Optimization:** Database queries, caching strategies, bulk operations
+
+### 🔵 Tier 4 — GUIDELINES
+
+Best practice — follow when possible:
+
+- Code style / formatting (Prettier handles)
+- Comment completeness
+- Minor optimizations
+
+---
+
+## 📐 TypeScript Rules & Coding Standards
+
+### 📝 Core Standards
+
+- **Strict Mode** — all strict checks enforced.
+- **ZERO `any` types** — use proper types or `unknown` + narrowing.
+- **ZERO `console.log`** — use NestJS `Logger` (backend) or remove (frontend).
+- **English for Code** — use English for all code identifiers, variables, and logic.
+- **Thai for Comments** — use Thai for comments, documentation, and JSDoc.
+- **Explicit Typing** — explicitly define types for all variables, parameters, and return values.
+- **JSDoc** — use JSDoc for all public classes and methods.
+
+### 🏗️ File & Function Structure
+
+- **File Headers** — every file MUST start with `// File: path/filename` on the first line.
+- **Change Log** — include `// Change Log` at the top of the file to track modifications.
+- **Single Export** — export **only one main symbol** per file.
+- **Function Style** — avoid unnecessary blank lines inside functions.
+
+---
+
+## 🚫 Forbidden Actions
+
+| ❌ Forbidden                                    | ✅ Correct Approach                                     | ⚠️ Why                                               |
+| ----------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------- |
+| SQL Triggers for business logic                 | NestJS Service methods                                  | Untestable; bypasses audit log                       |
+| `.env` files in production                      | `docker-compose.yml` environment section                | Secrets exposed in version control                   |
+| TypeORM migration files                         | Edit schema SQL directly (ADR-009)                      | Migration drift risk; schema managed via SQL delta   |
+| Inventing table/column names                    | Verify against `schema-02-tables.sql`                   | Schema mismatch causes silent runtime errors         |
+| `any` TypeScript type                           | Proper types / generics                                 | Defeats strict mode; hides runtime type errors       |
+| `console.log` in committed code                 | NestJS Logger (backend) / remove (frontend)             | Log flooding in production; risk of data leakage     |
+| `req: any` in controllers                       | `RequestWithUser` typed interface                       | Type safety lost; auth context unreachable           |
+| `parseInt()` on UUID values                     | Use UUID string directly (ADR-019)                      | `"0195…"` parsed to integer `19` — silently wrong    |
+| Exposing INT PK in API responses                | UUIDv7 `publicId` (ADR-019)                             | Leaks row count; enables DB enumeration attacks      |
+| AI accessing DB/storage directly                | AI → DMS API → DB (ADR-023/023A)                        | Bypasses RBAC, audit trail, and validation layer     |
+| Direct file operations bypassing StorageService | `StorageService` for all file moves                     | Orphaned files; broken ClamAV scan; no audit trail   |
+| Inline email/notification sending               | BullMQ queue job (ADR-008)                              | Blocks request thread; no retry on transient failure |
+| Deploying without Release Gates                 | Complete `04-08-release-management-policy.md`           | Unverified deploy risks data loss in production      |
+| AI direct cloud API calls                       | On-premises Ollama only (ADR-023/023A)                  | Data privacy violation; no audit control             |
+| AI outputs without human validation             | Human-in-the-loop validation required (ADR-023/023A)    | Unvalidated AI metadata corrupts document records    |
+| n8n calling Ollama/Qdrant directly              | n8n → DMS API → BullMQ → Ollama (ADR-023A)              | Bypasses audit log, RBAC, and error handling layer   |
+| Qdrant query without `projectPublicId` filter   | `QdrantService.search(projectPublicId, ...)` (ADR-023A) | Cross-project data leak via vector search            |
+
+---
+
+## 🚧 Out of Scope — Never Do Without Explicit Approval
+
+| ❌ Never Do Autonomously                                        | ⚠️ Why Approval Is Required                                      |
+| --------------------------------------------------------------- | ---------------------------------------------------------------- |
+| `DROP` or `RENAME` a column / table                             | Irreversible data loss — requires DBA + PM sign-off              |
+| Push directly to `main` / `master` branch                       | Bypasses CI, code review, and release gates                      |
+| Generate or insert seed data into production database           | May corrupt live data or violate business state invariants       |
+| Delete files from permanent storage                             | Files may be referenced in active documents or audit trails      |
+| Modify RBAC permission matrix without security team approval    | Defines access control for all users — security boundary change  |
+| Upgrade major library versions (NestJS, Next.js, TypeORM, etc.) | Breaking changes require full regression test cycle              |
+| Disable or modify authentication / authorization guards         | Creates unguarded endpoints — immediate security risk            |
+| Change Redis lock TTL or disable Redlock                        | Risk of document number race condition (ADR-002)                 |
+| Create or supersede an ADR unilaterally                         | Architecture decisions require team consensus and review process |
+| Add new columns to production tables without schema review      | Must update Data Dictionary + downstream queries simultaneously  |

.agents/rules/01-adr-019-uuid.md

@@ -0,0 +1,68 @@
+
+# ADR-019 UUID Strategy
+
+## CRITICAL RULES
+
+- **NEVER** use `parseInt()` on UUID values
+- **NEVER** use `Number()` on UUID values
+- **NEVER** use `+` operator on UUID values
+- **ALWAYS** use `publicId` (string UUID) for API responses
+- **NEVER** expose internal INT `id` in API responses (use `@Exclude()`)
+
+## Identifier Types
+
+| Context          | Type                      | Notes                                       |
+| ---------------- | ------------------------- | ------------------------------------------- |
+| Internal / DB FK | `INT AUTO_INCREMENT`      | Never exposed in API                        |
+| Public API / URL | `UUIDv7` (MariaDB native) | Stored as BINARY(16), no transformer needed |
+| Entity Property  | `publicId: string`        | Exposed directly in API (no transformation) |
+| API Response     | `publicId: string` (UUID) | INT `id` has `@Exclude()` — never appears   |
+
+## Backend Pattern (NestJS/TypeORM)
+
+```typescript
+// Entity
+@Entity()
+class Project extends UuidBaseEntity {
+  @Column({ type: 'uuid' })
+  publicId: string;  // UUID string, no transformation needed
+
+  @PrimaryKey()
+  @Exclude()
+  id: number;  // Internal INT, never exposed
+}
+
+// API Response → { id: "019505a1-7c3e-7000-8000-abc123def456" }
+// Uses publicId directly, no @Expose({ name: 'id' }) needed
+```
+
+## Frontend Pattern (Next.js)
+
+```typescript
+// ✅ CORRECT — Use publicId only
+type ProjectOption = {
+  publicId?: string; // No uuid, no id fallback
+  projectName?: string;
+};
+
+// ❌ WRONG — Multiple identifiers cause confusion
+type ProjectOption = {
+  publicId?: string;
+  uuid?: string; // Don't do this
+  id?: number; // Don't do this
+};
+
+// ❌ NEVER use parseInt on UUID
+parseInt(projectId); // "0195..." → 19 (WRONG!)
+
+// ❌ NEVER use id ?? '' fallback
+const value = c.publicId ?? c.id ?? ''; // Wrong!
+
+// ✅ CORRECT — Use publicId only
+const value = c.publicId; // "019505a1-7c3e-7000-8000-abc123def456"
+```
+
+## Related Documents
+
+- `specs/06-Decision-Records/ADR-019-hybrid-identifier-strategy.md`
+- `specs/05-Engineering-Guidelines/05-07-hybrid-uuid-implementation-plan.md`

.agents/rules/02-security.md

@@ -0,0 +1,34 @@
+# Security Rules (Non-Negotiable)
+
+## Mandatory Security Requirements
+
+1. **Idempotency:** All critical `POST`/`PUT`/`PATCH` MUST validate `Idempotency-Key` header
+2. **Two-Phase File Upload:** Upload → Temp → Commit → Permanent
+3. **Race Conditions:** Redis Redlock + TypeORM `@VersionColumn` for Document Numbering
+4. **Validation:** Zod (frontend) + class-validator (backend DTO)
+5. **Password:** bcrypt 12 salt rounds, min 8 chars, rotate every 90 days
+6. **Rate Limiting:** `ThrottlerGuard` on all auth endpoints
+7. **File Upload:** Whitelist PDF/DWG/DOCX/XLSX/ZIP, max 50MB, ClamAV scan
+8. **AI Isolation (ADR-023/023A):** Ollama on Admin Desktop ONLY — NO direct DB/storage access; 2-model stack `gemma4:e4b Q8_0` + `nomic-embed-text`; all inference via BullMQ (`ai-realtime` / `ai-batch`)
+9. **Error Handling (ADR-007):** Use layered error classification with user-friendly messages
+10. **AI Integration (ADR-023/023A):** RFA-First approach; n8n orchestrates Migration Phase only via DMS API — never calls Ollama directly; `QdrantService.search()` requires `projectPublicId` as mandatory param
+11. **AI Audit Trail:** Log all AI interactions and human validations
+12. **Rate Limiting:** Apply to AI endpoints to prevent abuse
+
+## Full Documentation
+
+`specs/06-Decision-Records/ADR-016-security-authentication.md`
+
+## Security Checklist (Before Every Commit)
+
+- [ ] Input validation implemented (Zod/class-validator)
+- [ ] RBAC/CASL permissions checked
+- [ ] No SQL injection vulnerabilities
+- [ ] File upload validation (whitelist + ClamAV)
+- [ ] Rate limiting applied to auth endpoints
+- [ ] AI boundary enforcement (ADR-023/023A) - no direct DB/storage access
+- [ ] AI audit logging implemented for AI interactions
+- [ ] AI outputs validated before use (human-in-the-loop)
+- [ ] Error handling follows ADR-007 layered classification
+- [ ] Cache invalidation when data modified
+- [ ] OWASP Top 10 review passed

.agents/rules/03-typescript.md

@@ -0,0 +1,44 @@
+# TypeScript Rules
+
+## Core Standards
+
+- **Strict Mode** — all strict checks enforced.
+- **ZERO `any` types** — use proper types or `unknown` + narrowing.
+- **ZERO `console.log`** — use NestJS `Logger` (backend) or remove before commit (frontend).
+- **English for Code** — use English for all code identifiers, variables, and logic.
+- **Thai for Comments** — use Thai for comments, documentation, and JSDoc.
+- **Explicit Typing** — explicitly define types for all variables, parameters, and return values.
+- **JSDoc** — use JSDoc for all public classes and methods (in **Thai**).
+
+## File & Function Structure
+
+- **File Headers** — every file MUST start with `// File: path/filename` on the first line.
+  - Use **absolute path** from project root (e.g., `// File: backend/src/modules/correspondence/correspondence.service.ts`)
+  - Do NOT use relative path (e.g., `// File: src/example.service.ts`)
+- **Change Log** — include `// Change Log` at the top of the file.
+- **Single Export** — export **only one main symbol** per file.
+- **Function Style** — avoid unnecessary blank lines inside functions.
+
+## i18n Guidelines
+
+- **No Hardcoded Text:** Use i18n keys for all user-facing text
+- **Reference:** `specs/05-Engineering-Guidelines/05-08-i18n-guidelines.md`
+- **Pattern:** Use `t('key.path')` from i18n hook instead of hardcoded strings
+
+## Patterns
+
+```typescript
+// ✅ CORRECT
+// File: src/example.service.ts
+// Change Log:
+// - 2026-05-13: Initial creation
+
+/**
+ * บริการตัวอย่างสำหรับ LCBP3
+ */
+export class ExampleService {
+  public doSomething(data: string): boolean {
+    return data.length > 0;
+  }
+}
+```

.agents/rules/04-domain-terminology.md

@@ -0,0 +1,41 @@
+# Domain Terminology
+
+## DMS Glossary
+
+| ✅ Use             | ❌ Don't Use                          | คำอธิบายเพิ่มเติม                                |
+| ------------------ | ------------------------------------- | ------------------------------------------------ |
+| Correspondence     | Letter, Communication, Document       | ครอบคลุมทุกประเภท: Letter, RFA, Memo, ฯลฯ        |
+| RFA                | Approval Request, Submit for Approval | เอกสารขออนุมัติ (ชนิดหนึ่งของ Correspondence)    |
+| Transmittal        | Delivery Note, Cover Letter           | เอกสารนำส่ง (ชนิดหนึ่งของ Correspondence)        |
+| Circulation        | Distribution, Routing                 | ใบเวียนเอกสารภายใน (ชนิดหนึ่งของ Correspondence) |
+| Shop Drawing       | Construction Drawing                  | แบบก่อสร้าง                                      |
+| Contract Drawing   | Design Drawing, Blueprint             | แบบคู่สัญญา                                      |
+| Workflow Engine    | Approval Flow, Process Engine         | เครื่องมือจัดการลำดับงาน                         |
+| Document Numbering | Document ID, Auto Number              | ระบบจัดการเลขที่เอกสาร                           |
+| RBAC               | Permission System (generic)           | การควบคุมสิทธิ์ตามบทบาท                          |
+
+## Full Glossary
+
+`specs/00-overview/00-02-glossary.md`
+
+## Key Spec Files Priority
+
+Spec priority: **`06-Decision-Records`** > **`05-Engineering-Guidelines`** > others
+
+| Document                       | Path                                                                        | Use When                          |
+| ------------------------------ | --------------------------------------------------------------------------- | --------------------------------- |
+| **Glossary**                   | `specs/00-overview/00-02-glossary.md`                                       | Verify domain terminology         |
+| **Schema Tables**              | `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`               | Before writing any query          |
+| **Data Dictionary**            | `specs/03-Data-and-Storage/03-01-data-dictionary.md`                        | Field meanings + business rules   |
+| **Edge Cases**                 | `specs/01-Requirements/01-06-edge-cases-and-rules.md`                       | Prevent bugs in flows             |
+| **ADR-019 UUID**               | `specs/06-Decision-Records/ADR-019-hybrid-identifier-strategy.md`           | UUID-related work                 |
+| **ADR-023 AI**                 | `specs/06-Decision-Records/ADR-023-unified-ai-architecture.md`              | AI integration work               |
+| **ADR-023A AI Model**          | `specs/06-Decision-Records/ADR-023A-unified-ai-architecture.md`             | 2-model stack, BullMQ 2-queue     |
+| **ADR-024 Intent Class.**      | `specs/06-Decision-Records/ADR-024-intent-classification-strategy.md`       | Pattern→LLM Fallback; Redis cache |
+| **ADR-025 AI Tool Layer**      | `specs/06-Decision-Records/ADR-025-ai-tool-layer-architecture.md`           | Tool Registry; CASL-guarded       |
+| **ADR-026 Chat UI**            | `specs/06-Decision-Records/ADR-026-document-chat-ui-pattern.md`             | Side-panel; streaming SSE         |
+| **ADR-027 AI Admin Console**   | `specs/06-Decision-Records/ADR-027-ai-admin-console-and-dynamic-control.md` | Dynamic control; admin-only       |
+| **ADR-028 Migration Refactor** | `specs/06-Decision-Records/ADR-028-migration-architecture-refactor.md`      | Staging Queue; cleanup            |
+| **Backend Guidelines**         | `specs/05-Engineering-Guidelines/05-02-backend-guidelines.md`               | NestJS patterns                   |
+| **Frontend Guidelines**        | `specs/05-Engineering-Guidelines/05-03-frontend-guidelines.md`              | Next.js patterns                  |
+| **Testing Strategy**           | `specs/05-Engineering-Guidelines/05-04-testing-strategy.md`                 | Coverage goals                    |

.agents/rules/05-forbidden-actions.md

@@ -0,0 +1,39 @@
+# Forbidden Actions
+
+## ❌ Never Do This
+
+| ❌ Forbidden                                    | ✅ Correct Approach                                     | ⚠️ Why                                               |
+| ----------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------- |
+| SQL Triggers for business logic                 | NestJS Service methods                                  | Untestable; bypasses audit log                       |
+| `.env` files in production                      | `docker-compose.yml` environment section                | Secrets exposed in version control                   |
+| TypeORM migration files                         | Edit schema SQL directly (ADR-009)                      | Migration drift risk; schema managed via SQL delta   |
+| Inventing table/column names                    | Verify against `schema-02-tables.sql`                   | Schema mismatch causes silent runtime errors         |
+| `any` TypeScript type                           | Proper types / generics                                 | Defeats strict mode; hides runtime type errors       |
+| `console.log` in committed code                 | NestJS Logger (backend) / remove (frontend)             | Log flooding in production; risk of data leakage     |
+| `req: any` in controllers                       | `RequestWithUser` typed interface                       | Type safety lost; auth context unreachable           |
+| `parseInt()` on UUID values                     | Use UUID string directly (ADR-019)                      | `"0195…"` parsed to integer `19` — silently wrong    |
+| Exposing INT PK in API responses                | UUIDv7 `publicId` (ADR-019)                             | Leaks row count; enables DB enumeration attacks      |
+| AI accessing DB/storage directly                | AI → DMS API → DB (ADR-023/023A)                        | Bypasses RBAC, audit trail, and validation layer     |
+| Direct file operations bypassing StorageService | `StorageService` for all file moves                     | Orphaned files; broken ClamAV scan; no audit trail   |
+| Inline email/notification sending               | BullMQ queue job (ADR-008)                              | Blocks request thread; no retry on transient failure |
+| Deploying without Release Gates                 | Complete `04-08-release-management-policy.md`           | Unverified deploy risks data loss in production      |
+| AI direct cloud API calls                       | On-premises Ollama only (ADR-023/023A)                  | Data privacy violation; no audit control             |
+| AI outputs without human validation             | Human-in-the-loop validation required (ADR-023/023A)    | Unvalidated AI metadata corrupts document records    |
+| n8n calling Ollama/Qdrant directly              | n8n → DMS API → BullMQ → Ollama (ADR-023A)              | Bypasses audit log, RBAC, and error handling layer   |
+| Qdrant query without `projectPublicId` filter   | `QdrantService.search(projectPublicId, ...)` (ADR-023A) | Cross-project data leak via vector search            |
+
+## Schema Changes (ADR-009)
+
+- **NO TypeORM migrations** — edit SQL schema directly
+- Always check `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql` before writing queries
+- Update Data Dictionary when changing fields
+
+## UUID Handling
+
+See `01-adr-019-uuid.md` for complete UUID rules.
+
+Quick reminder:
+
+- ❌ `parseInt(uuid)` → NEVER
+- ❌ `Number(uuid)` → NEVER
+- ✅ Use UUID string directly

.agents/rules/06-backend-patterns.md

@@ -0,0 +1,54 @@
+# Backend Patterns (NestJS)
+
+## Architecture
+
+- **Thin Controller** — business logic in Service layer
+- **DTO Validation** — class-validator + class-transformer
+- **RBAC** — CASL for authorization
+- **Error Handling** — Logger + HttpException
+
+## UUID Resolution Pattern
+
+```typescript
+// Controller - accept UUID in DTO
+@Post()
+async create(@Body() dto: CreateCorrespondenceDto) {
+  // Resolve UUID to internal ID
+  const contract = await this.contractService.findOneByUuid(dto.contractUuid);
+  const contractId = contract.id; // Internal INT for DB queries
+
+  return this.service.create(dto, contractId);
+}
+
+// Service - use internal ID for DB operations
+async create(dto: CreateCorrespondenceDto, contractId: number) {
+  // Use contractId (INT) for database queries
+  const correspondence = this.repo.create({
+    contractId,  // FK is INT
+    // ... other fields
+  });
+  return this.repo.save(correspondence);
+}
+```
+
+## API Response Pattern
+
+```typescript
+// Entity
+@Entity()
+class Contract extends UuidBaseEntity {
+  @Column({ type: 'uuid' })
+  publicId: string;
+
+  @PrimaryGeneratedColumn()
+  @Exclude()
+  id: number;
+}
+
+// Response automatically includes publicId as 'id'
+// { id: "019505a1-7c3e-7000-8000-abc123def456", ... }
+```
+
+## Full Guidelines
+
+`specs/05-Engineering-Guidelines/05-02-backend-guidelines.md`

.agents/rules/07-frontend-patterns.md

@@ -0,0 +1,46 @@
+# Frontend Patterns (Next.js)
+
+## Form Handling
+
+- **RHF** (React Hook Form) for form management
+- **Zod** for validation schema
+- **TanStack Query** for server state
+
+## UUID Handling
+
+```typescript
+// ✅ CORRECT - Use publicId only
+interface ProjectOption {
+  publicId?: string;
+  projectName?: string;
+}
+
+// Select options
+const options = contracts.map((c) => ({
+  label: `${c.contractName} (${c.contractCode})`,
+  value: c.publicId!, // Use publicId, no fallback to id
+}));
+
+// ❌ WRONG - Never use these patterns
+const value = c.publicId ?? c.id ?? ''; // Wrong!
+const id = parseInt(projectId); // Wrong - parseInt on UUID!
+```
+
+## API Client Pattern
+
+```typescript
+// Use publicId directly in API calls
+const contract = await contractService.getById(publicId);
+
+// Form submission with UUID
+const onSubmit = async (data: FormData) => {
+  await correspondenceService.create({
+    contractUuid: selectedContract.publicId!, // UUID string
+    // ... other fields
+  });
+};
+```
+
+## Full Guidelines
+
+`specs/05-Engineering-Guidelines/05-03-frontend-guidelines.md`

.agents/rules/08-development-flow.md

@@ -0,0 +1,210 @@
+# Development Flow
+
+## 🔴 Critical Work — DB / API / Security / Workflow Engine
+
+**MUST complete all steps:**
+
+1. **Glossary check** — verify domain terms in `00-02-glossary.md`
+2. **Read the spec** — select from Key Spec Files table
+3. **Check schema** — verify table/column in `lcbp3-v1.9.0-schema-02-tables.sql`
+4. **Check data dictionary** — confirm field meanings + business rules
+5. **Scan edge cases** — `01-06-edge-cases-and-rules.md`
+6. **Check ADRs** — verify decisions align (ADR-009, ADR-019, ADR-023)
+7. **Write code** — TypeScript strict, no `any`, no `console.log`
+
+## 🟡 Normal Work — UI / Feature / Integration
+
+- Follow existing patterns in codebase.
+- Check spec for relevant module only.
+- **Hybrid Specs Organization:**
+  - Place new Infrastructure tasks in `specs/100-Infrastructures/`
+  - Place new Feature/Workflow tasks in `specs/200-fullstacks/`
+  - Place Documentation/Research in `specs/300-others/`
+- Ensure no forbidden patterns (`any`, `console.log`, UUID misuse) are introduced.
+
+## 🟢 Quick Fix — Bug Fix / Typo / Style
+
+- Fix directly
+- Add minimal test if logic changed
+- Check forbidden patterns before commit
+
+### 🟢 Specialized Work — ADR-021, AI Runtime Layer, Complex Logic
+
+**MUST complete:**
+
+1. **Domain Knowledge Check** - Read relevant ADRs (ADR-021, ADR-023/023A, ADR-024~028)
+2. **Pattern Verification** - Check existing implementations in codebase
+3. **Specialized Requirements** - Follow domain-specific patterns
+4. **Complex Logic Testing** - Multi-scenario test coverage
+5. **Performance Validation** - Load testing if applicable
+
+**For ADR-021 Integration:**
+
+- Read ADR-021 - Integrated workflow & step attachments
+- Check ADR-001 - Unified workflow engine patterns
+- Verify WorkflowEngineService - Polymorphic instance handling
+- Add workflow fields - Expose workflowInstanceId, workflowState, availableActions
+- Include IntegratedBanner - Frontend workflow lifecycle display
+- Test workflow transitions - State changes and action validation
+
+**For AI Infrastructure (ADR-023/023A):**
+
+- Verify AI boundary enforcement - No direct DB/storage access
+- Check BullMQ 2-queue setup - ai-realtime + ai-batch
+- Validate Qdrant multi-tenancy - projectPublicId filter required
+- Test human-in-the-loop validation workflows
+- Audit AI interaction logging to ai_audit_logs
+
+**For AI Runtime Layer (ADR-024/025/026/027):**
+
+- ADR-024: Pattern Layer first (ai_intent_patterns DB + Redis cache 5 min) → LLM Fallback (gemma4:e4b, semaphore max=3)
+- ADR-025: Tool Registry dispatch — AI Gateway → Tool → Business Service; ToolResult DTO must use publicId only
+- ADR-026: useAiChat() hook + side-panel UI; streaming response via SSE; TanStack Query cache
+- ADR-027: Admin Console — dynamic model/prompt/intent control; CASL-guarded admin-only endpoints
+
+**For Migration Pipeline (ADR-028):**
+
+- Use Staging Queue pattern — never write directly to production tables
+- Post-migration cleanup process required after each batch
+- Migration Validation Gates must pass before promoting to production
+
+**Expected output:**
+
+- Backend services expose specialized context fields
+- Frontend components use domain-specific patterns
+- Complex state management with proper validation
+- Performance metrics within acceptable thresholds
+- Comprehensive test coverage for edge cases
+
+---
+
+## Context-Aware Triggers
+
+| Request                     | Files to Check                                                                        | Expected Response                                                       |
+| --------------------------- | ------------------------------------------------------------------------------------- | ----------------------------------------------------------------------- |
+| "สร้าง API ใหม่"            | `05-02-backend-guidelines.md`, `lcbp3-v1.9.0-schema-02-tables.sql`                    | NestJS Controller + Service + DTO + CASL Guard                          |
+| "แก้ฟอร์ม frontend"         | `05-03-frontend-guidelines.md`, `01-06-edge-cases-and-rules.md`                       | RHF+Zod + TanStack Query + Thai comments                                |
+| "เพิ่ม field ใหม่"          | `ADR-009`, `03-01-data-dictionary.md`, `lcbp3-v1.9.0-schema-02-tables.sql`            | Edit SQL directly + update Data Dictionary + Entity                     |
+| "ตรวจสอบ UUID"              | `ADR-019`, `05-07-hybrid-uuid-implementation-plan.md`                                 | UUIDv7 MariaDB native UUID + TransformInterceptor                       |
+| "สร้าง migration"           | `ADR-009`, `03-06-migration-business-scope.md`                                        | Edit SQL schema directly + n8n workflow                                 |
+| "ตรวจสอบ permission"        | `lcbp3-v1.9.0-seed-permissions.sql`, `ADR-016`                                        | CASL 4-Level RBAC matrix                                                |
+| "deploy production"         | `04-08-release-management-policy.md`, `ADR-015`                                       | Release Gates + Blue-Green strategy                                     |
+| "เพิ่ม test"                | `05-04-testing-strategy.md`                                                           | Coverage goals + test patterns                                          |
+| "AI integration"            | `ADR-023`, `ADR-023A`, `ADR-024`, `ADR-025`                                           | AI boundary + 2-model stack + BullMQ queue policy + Intent/Tool Layer   |
+| "Error handling"            | `ADR-007`                                                                             | Layered error classification + recovery                                 |
+| "File upload"               | `ADR-016`, `05-02-backend-guidelines.md`, `03-Data-and-Storage/03-03-file-storage.md` | Two-phase upload → temp → commit; ClamAV + whitelist                    |
+| "Notifications / Queue"     | `ADR-008`, `05-02-backend-guidelines.md`                                              | BullMQ job — never inline; check retry + dead-letter                    |
+| "Add i18n / translate"      | `05-08-i18n-guidelines.md`                                                            | i18n keys only — no hardcoded text                                      |
+| "Workflow / DSL"            | `ADR-001`, `01-03-modules/01-03-06-unified-workflow.md`                               | DSL state machine + WorkflowEngineService                               |
+| "Document numbering"        | `ADR-002`, `01-02-business-rules/01-02-02-doc-numbering-rules.md`                     | Redis Redlock + DB optimistic lock (double-lock)                        |
+| "ตรวจสอบ Workflow"          | `01-06-edge-cases-and-rules.md`, `05-02-backend-guidelines.md`, `ADR-001`, `ADR-002`  | เช็คการเปลี่ยน State, คิว BullMQ และการล็อกเลขที่เอกสาร                 |
+| "Transmittal submit"        | `ADR-021`, `specs/200-fullstacks/201-transmittals-circulation/`                       | submit() with EC-RFA-004 validation                                     |
+| "Circulation reassign"      | `ADR-021`, `specs/200-fullstacks/201-transmittals-circulation/`                       | reassignRouting() with EC-CIRC-001                                      |
+| "สร้าง workflow ใหม่"       | `ADR-001`, `ADR-021`, `specs/200-fullstacks/203-unified-workflow-engine/`             | DSL workflow definition + WorkflowEngineService setup                   |
+| "ตรวจสอบ AI boundary"       | `ADR-023`, `ADR-023A`                                                                 | Verify Ollama isolation + BullMQ queues + Qdrant projectPublicId filter |
+| "Intent classification"     | `ADR-024`, `specs/200-fullstacks/224-intent-classification/`                          | Pattern Layer → LLM Fallback; ai_intent_patterns; Redis cache 5 min     |
+| "AI Tool Layer"             | `ADR-025`, `specs/200-fullstacks/225-ai-tool-layer-architecture/`                     | Tool Registry; CASL-guarded dispatch; ToolResult publicId only          |
+| "Document Chat UI"          | `ADR-026`, `specs/200-fullstacks/226-document-chat-ui-pattern/`                       | Side-panel; useAiChat() hook; streaming SSE; TanStack Query cache       |
+| "AI Admin Console"          | `ADR-027`, `specs/200-fullstacks/227-ai-admin-console/`                               | Dynamic model/prompt/intent control; admin-only CASL endpoints          |
+| "Migration refactor"        | `ADR-028`, `specs/200-fullstacks/228-migration-arch-refactor/`                        | Staging Queue; post-migration cleanup; validation gates                 |
+| "จัดการ document numbering" | `ADR-002`, `specs/03-Data-and-Storage/03-04-document-numbering.md`                    | Redis Redlock + template system + preview/override workflows            |
+| "Audit ความปลอดภัย"         | `ADR-016`, `ADR-019`, `ADR-023`, `ADR-023A`                                           | ตรวจสอบ UUID pattern, CASL Guard, AI Boundary และ Qdrant multi-tenancy  |
+| "แก้ bug / bugfix"          | `.agents/workflows/bugfix.md`, `error-catalog.md`                                     | ใช้ bugfix workflow สำหรับเคสที่สาเหตุชัดเจน                            |
+| "ตรวจแอปจริง"               | `.windsurf/workflows/check-real-app.md`                                               | ตรวจ endpoint/UI/console หลัง build pass — No Fake Evidence             |
+| "งานค้าง / resume"          | `.windsurf/workflows/resume-pending-work.md`                                          | อ่าน checkpoint เดิม → ตรวจ build → วางแผนต่อโดยไม่ทำงานซ้ำ             |
+
+---
+
+## 🔌 MCP MariaDB Tools
+
+MCP MariaDB server ให้เครื่องมือสำหรับตรวจสอบและจัดการ database โดยตรง ใช้สำหรับ:
+
+- ตรวจสอบ schema กับ spec file `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`
+- Debug ปัญหา database โดยไม่ต้องเข้า MySQL client
+- ตรวจสอบ data ใน production/staging
+- Validate การเปลี่ยนแปลง schema ก่อน deploy
+
+### Available Tools
+
+| Tool | หน้าที่ | ตัวอย่างการใช้งาน |
+|------|----------|------------------|
+| `mcp1_mysql_test_connection` | ทดสอบ connection กับ database | ตรวจสอบว่า MCP server เชื่อมต่อได้ |
+| `mcp1_mysql_show_databases` | แสดง databases ทั้งหมด | ดูว่ามี database อะไรบ้าง |
+| `mcp1_mysql_show_tables` | แสดง tables ทั้งหมดใน database | ดูรายชื่อ tables ใน `lcbp3` |
+| `mcp1_mysql_describe_table` | ดู structure/columns ของ table | ตรวจสอบ columns, types, keys ของ `correspondences` |
+| `mcp1_mysql_query` | รัน SELECT query | ดู data ใน table หรือ join query |
+| `mcp1_mysql_insert` | INSERT data | เพิ่ม seed data หรือ test data |
+| `mcp1_mysql_update` | UPDATE data | แก้ไข data ใน table |
+| `mcp1_mysql_delete` | DELETE data | ลบ data ใน table |
+
+### การใช้งานร่วมกับ Development Flow
+
+**เมื่อเขียน query ใหม่:**
+1. ใช้ `mcp1_mysql_describe_table` เพื่อตรวจสอบ columns และ types
+2. เปรียบเทียบกับ `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`
+3. ใช้ `mcp1_mysql_query` เพื่อทดสอบ query ก่อน implement
+
+**เมื่อเปลี่ยน schema (ADR-009):**
+1. ใช้ `mcp1_mysql_describe_table` เพื่อดู structure ปัจจุบัน
+2. สร้าง SQL delta ใน `specs/03-Data-and-Storage/deltas/`
+3. ใช้ `mcp1_mysql_query` เพื่อตรวจสอบผลลัพธ์หลัง apply delta
+
+**เมื่อ debug ปัญหา database:**
+1. ใช้ `mcp1_mysql_query` เพื่อดู data จริง
+2. เปรียบเทียบกับ spec และ data dictionary
+3. ตรวจสอบ foreign keys และ constraints
+
+### ข้อควรระวัง
+
+- **❌ ห้ามใช้ MCP MariaDB สำหรับ DDL operations** (CREATE/ALTER/DROP) โดยตรง — ต้องใช้ SQL delta ตาม ADR-009
+- **✅ ใช้สำหรับ DQL/DML operations** (SELECT/INSERT/UPDATE/DELETE) เพื่อ debug และ test เท่านั้น
+- **⚠️ ระวัง DELETE operations** — อาจทำให้เสีย data ใน production
+- **✅ ตรวจสอบ schema กับ spec file เสมอ** ก่อนเขียน query
+
+---
+
+## 🧠 MCP Memory Tools
+
+MCP Memory server ให้เครื่องมือสำหรับจัดการ Knowledge Graph และ Long-term Memory ใช้สำหรับ:
+
+- จัดเก็บความรู้และ context ของโปรเจกต์ในรูปแบบ Graph (Entities + Relations + Observations)
+- ค้นหาและดึงข้อมูล context จาก memory ที่บันทึกไว้ใน session ก่อนหน้า
+- สร้าง/แก้ไข/ลบ entities, relations, และ observations ใน knowledge graph
+
+### Available Tools
+
+| Tool | หน้าที่ | ตัวอย่างการใช้งาน |
+|------|----------|------------------|
+| `mcp3_create_entities` | สร้าง entities ใหม่หลายตัวพร้อม observations | สร้าง entity ใหม่เช่น Project, User, Task |
+| `mcp3_create_relations` | สร้าง relations ระหว่าง entities | สร้าง relation: Project → has → User |
+| `mcp3_add_observations` | เพิ่ม observations ให้ entity ที่มีอยู่แล้ว | เพิ่ม context เพิ่มเติมให้ entity |
+| `mcp3_delete_entities` | ลบ entities และ relations ที่เกี่ยวข้อง | ลบ entity ที่ไม่ใช้แล้ว |
+| `mcp3_delete_relations` | ลบ relations ระหว่าง entities | ลบ relation ที่ผิดหรือไม่ใช้แล้ว |
+| `mcp3_delete_observations` | ลบ observations จาก entity | ลบ context ที่ผิดหรือล้าสุด |
+| `mcp3_open_nodes` | ดึงข้อมูล entities ตามชื่อ | ดึง entity ที่ระบุชื่อ |
+| `mcp3_read_graph` | อ่าน knowledge graph ทั้งหมด | ดูทั้ง graph structure |
+| `mcp3_search_nodes` | ค้นหา entities ตาม query | ค้นหา entity จากชื่อ, type, หรือ observation |
+
+### การใช้งานร่วมกับ Development Flow
+
+**เมื่อบันทึก context ใหม่:**
+1. ใช้ `mcp3_create_entities` เพื่อสร้าง entities ใหม่ (ถ้ายังไม่มี)
+2. ใช้ `mcp3_create_relations` เพื่อเชื่อมโยง entities
+3. ใช้ `mcp3_add_observations` เพื่อเพิ่ม context/observations
+
+**เมื่อค้นหา context:**
+1. ใช้ `mcp3_search_nodes` เพื่อค้นหา entities ที่เกี่ยวข้อง
+2. ใช้ `mcp3_open_nodes` เพื่อดึงข้อมูล entities ที่ต้องการ
+3. ใช้ `mcp3_read_graph` เพื่อดู relations ระหว่าง entities
+
+**เมื่อแก้ไข context:**
+1. ใช้ `mcp3_add_observations` เพื่อเพิ่ม observations ใหม่
+2. ใช้ `mcp3_delete_observations` เพื่อลบ observations ที่ผิด
+3. ใช้ `mcp3_create_relations` หรือ `mcp3_delete_relations` เพื่อปรับ relations
+
+### ข้อควรระวัง
+
+- **✅ ใช้สำหรับบันทึก context ที่ต้องใช้ร่วมกันหลาย session** — เช่น การตัดสินใจสำคัญ, architecture decisions, rollout history
+- **⚠️ ระวังการลบ entities** — อาจทำให้เสีย context ที่ยังใช้งานอยู่
+- **✅ ตรวจสอบว่า entity มีอยู่แล้วก่อนสร้าง** — ใช้ `mcp3_search_nodes` หรือ `mcp3_open_nodes` ก่อน
+- **✅ ใช้ชื่อ entity ที่ชัดเจนและไม่ซ้ำกัน** — เพื่อป้องกันความสับสน

.agents/rules/09-commit-checklist.md

@@ -0,0 +1,33 @@
+# Commit Checklist
+
+## Pre-Commit Verification
+
+- [ ] UUID pattern verified (no parseInt on UUID)
+- [ ] No `any` types in TypeScript
+- [ ] No `console.log` in committed code
+- [ ] Comments in Thai
+- [ ] Code identifiers in English
+- [ ] Schema changes via SQL directly (not migration)
+- [ ] Test coverage meets targets (Backend 70%+, Business Logic 80%+)
+- [ ] Relevant ADRs checked (ADR-009, ADR-018, ADR-019)
+- [ ] Glossary terms used correctly
+- [ ] Error handling complete (Logger + HttpException)
+- [ ] i18n keys used instead of hardcode text
+- [ ] Cache invalidation when data modified
+- [ ] Security checklist passed (OWASP Top 10)
+
+## Commit Message Format
+
+```
+type(scope): description
+
+[optional body]
+```
+
+Types: `feat`, `fix`, `docs`, `style`, `refactor`, `test`, `chore`
+
+Examples:
+
+- `feat(correspondence): add originator organization validation`
+- `fix(uuid): correct parseInt usage to string comparison`
+- `spec(agents): bump to v1.8.5 - refactor structure`

.agents/rules/10-error-handling.md

@@ -0,0 +1,69 @@
+# ADR-007 Error Handling Strategy
+
+## CRITICAL RULES
+
+- **ALWAYS** use layered error classification (Validation, Business, System)
+- **NEVER** expose technical details to end users
+- **ALWAYS** provide user-friendly error messages with recovery guidance
+- **ALWAYS** log technical details for debugging
+- **NEVER** use generic error messages without context
+
+## Error Classification
+
+| Error Type     | Description               | User Message             | Technical Log              |
+| -------------- | ------------------------- | ------------------------ | -------------------------- |
+| **Validation** | Input validation failures | Clear field-level errors | Full validation details    |
+| **Business**   | Business rule violations  | Actionable guidance      | Business context + user ID |
+| **System**     | Infrastructure failures   | Generic "try again"      | Full stack trace + metrics |
+
+## Backend Pattern (NestJS)
+
+```typescript
+// Custom Exception Hierarchy
+export class BusinessException extends HttpException {
+  constructor(message: string, userMessage: string, recoveryAction?: string, errorCode?: string) {
+    super({ message, userMessage, recoveryAction, errorCode }, 400);
+  }
+}
+
+// Global Exception Filter
+@Catch()
+export class GlobalExceptionFilter implements ExceptionFilter {
+  catch(exception: unknown, host: ArgumentsHost) {
+    // Classify error and provide appropriate response
+    // Log technical details
+    // Return user-friendly message
+  }
+}
+```
+
+## Frontend Pattern (Next.js)
+
+```typescript
+// Error Display Component
+const ErrorDisplay = ({ error, onRetry }) => {
+  const userMessage = error.userMessage || 'เกิดข้อผิดพลาด';
+  const recoveryAction = error.recoveryAction;
+
+  return (
+    <div>
+      <p>{userMessage}</p>
+      {recoveryAction && <p>{recoveryAction}</p>}
+      {onRetry && <button onClick={onRetry}>ลองใหม่</button>}
+    </div>
+  );
+};
+```
+
+## Required Implementation
+
+- [ ] Global Exception Filter with layered classification
+- [ ] Custom exception hierarchy (Validation, Business, System)
+- [ ] Standardized error response DTOs
+- [ ] Frontend error display components
+- [ ] Error recovery mechanisms where applicable
+
+## Related Documents
+
+- `specs/06-Decision-Records/ADR-007-error-handling-strategy.md`
+- `specs/06-Decision-Records/ADR-010-logging-monitoring-strategy.md`

.agents/rules/11-ai-integration.md

@@ -0,0 +1,145 @@
+# ADR-023/023A AI Integration Architecture
+
+## CRITICAL RULES
+
+- **ALWAYS** follow ADR-023 AI boundary policy (isolation on Admin Desktop)
+- **ALWAYS** use ADR-034 model stack (typhoon2.5-np-dms:latest + typhoon-np-dms-ocr:latest + nomic-embed-text)
+- **ALWAYS** use BullMQ 2-queue (ai-realtime + ai-batch) for GPU overload prevention
+- **NEVER** allow AI direct database/storage access
+- **ALWAYS** implement human-in-the-loop validation
+- **NEVER** send sensitive data to cloud AI services
+- **ALWAYS** enforce Qdrant projectPublicId filter (compile-time enforcement)
+- **NEVER** allow n8n to call Ollama/Qdrant directly (must go through DMS API → BullMQ)
+
+## AI Integration Patterns
+
+### Architecture Overview
+
+```
+Frontend → AI Gateway API → BullMQ → Admin Desktop (Ollama) → Backend Validation
+n8n (Migration) → DMS API → BullMQ → Admin Desktop (Ollama) → Backend Validation
+```
+
+### Key Components
+
+| Component         | Location                  | Purpose                                                                  |
+| ----------------- | ------------------------- | ------------------------------------------------------------------------ |
+| **AI Gateway**    | Backend (NestJS)          | API endpoints, validation, audit logging                                 |
+| **BullMQ Queues** | Backend (NestJS)          | ai-realtime (RAG/Suggest), ai-batch (OCR/Extract/Embed)                  |
+| **Ollama Engine** | Admin Desktop (Desk-5439) | typhoon2.5-np-dms:latest (Main LLM) + typhoon-np-dms-ocr:latest (OCR, keep_alive:0) + nomic-embed-text (Embedding) |
+| **OCR Engine**    | Admin Desktop (Desk-5439) | Tesseract OCR + Typhoon OCR (via Ollama) + PyThaiNLP (Thai/English text extraction) |
+| **Orchestrator**  | QNAP NAS (n8n)            | Migration Phase orchestrator only (calls DMS API, never Ollama directly) |
+
+## Backend Implementation (NestJS)
+
+```typescript
+// AI Module with boundary enforcement
+@Module({
+  controllers: [AiController],
+  providers: [AiService, AiGateway, QdrantService],
+  exports: [AiService],
+})
+export class AiModule {
+  constructor() {
+    // Enforce ADR-023 boundaries
+  }
+}
+
+// QdrantService with compile-time projectPublicId enforcement
+@Injectable()
+export class QdrantService {
+  async search(
+    projectPublicId: string,   // required — compile-time enforcement
+    vector: number[],
+    topK: number = 5,
+  ): Promise<QdrantSearchResult[]> {
+    return this.client.search('documents', {
+      vector,
+      limit: topK,
+      filter: {
+        must: [{ key: 'project_public_id', match: { value: projectPublicId } }],
+      },
+    });
+  }
+
+  async upsert(
+    projectPublicId: string,   // required
+    chunks: DocumentChunk[],
+  ): Promise<void> { ... }
+
+  // ❌ NEVER expose rawSearch() or method without projectPublicId filter
+}
+
+// AI Service with validation
+@Injectable()
+export class AiService {
+  async extractMetadata(documentId: string): Promise<AIMetadata> {
+    // 1. Validate permissions
+    // 2. Queue job to BullMQ (ai-batch or ai-realtime)
+    // 3. Worker sends to Admin Desktop AI (typhoon2.5-np-dms:latest)
+    // 4. Validate AI response
+    // 5. Log audit trail to ai_audit_logs
+    // 6. Return validated results
+  }
+}
+```
+
+## Frontend Pattern (Next.js)
+
+```typescript
+// Document Review Form (reusable component)
+const DocumentReviewForm = ({ document, aiSuggestions }) => {
+  return (
+    <form>
+      <Field label="Document Type" suggestions={aiSuggestions.documentType} />
+      <Field label="Project Code" suggestions={aiSuggestions.projectCode} />
+      <Field label="Discipline" suggestions={aiSuggestions.discipline} />
+
+      <ConfidenceScore score={aiSuggestions.confidence} />
+      <HumanValidationActions />
+    </form>
+  );
+};
+```
+
+## Security Requirements
+
+- **AI Isolation:** All AI processing on Admin Desktop only (Desk-5439)
+- **Data Privacy:** No cloud AI services, on-premises only
+- **Audit Trail:** Log all AI interactions and human validations to ai_audit_logs
+- **Rate Limiting:** Prevent AI abuse and resource exhaustion
+- **Validation:** All AI outputs must be validated before use
+- **Multi-tenant Isolation:** Qdrant queries MUST include projectPublicId filter (compile-time enforcement)
+- **n8n Boundary:** n8n MUST call DMS API → BullMQ, NEVER Ollama/Qdrant directly
+- **GPU Overload Prevention:** BullMQ 2-queue (ai-realtime + ai-batch) with concurrency=1
+
+## ADR-034 Model Stack (supersedes ADR-023A §2.1)
+
+- **3-Model Config:** typhoon2.5-np-dms:latest (Main) + typhoon-np-dms-ocr:latest (OCR, keep_alive:0) + nomic-embed-text (Embedding)
+- **PDF 3-Page Limit:** Classification/Tagging uses first 3 pages only (NOT RAG embedding)
+- **RAG Embedding:** Full document chunked at 512 tokens/64 tokens overlap
+- **OCR Auto-Detect:** PyMuPDF chars > 100 → Fast path, else Tesseract OCR (with Typhoon OCR option)
+- **Embed Auto-Trigger:** AUTO after commit (parallel), gap covered by DB search
+- **Threshold Recalibration:** After 100-500 docs, based on ai_audit_logs analysis
+
+## Required Implementation
+
+- [ ] AiModule with ADR-023 boundary enforcement
+- [ ] AI Gateway API endpoints with validation
+- [ ] BullMQ 2-queue setup (ai-realtime + ai-batch)
+- [ ] QdrantService with projectPublicId enforcement
+- [ ] DocumentReviewForm reusable component
+- [ ] Admin Desktop Ollama (typhoon2.5-np-dms:latest + typhoon-np-dms-ocr:latest + nomic-embed-text) setup
+- [ ] n8n workflow orchestration (Migration Phase only)
+- [ ] AI audit logging and monitoring (ai_audit_logs)
+- [ ] Human-in-the-loop validation workflows
+
+## Related Documents
+
+- `specs/06-Decision-Records/ADR-023-unified-ai-architecture.md` (Base architecture)
+- `specs/06-Decision-Records/ADR-023A-unified-ai-architecture.md` (Model revision - current)
+- `specs/06-Decision-Records/ADR-024-intent-classification-strategy.md` (Pattern→LLM Fallback)
+- `specs/06-Decision-Records/ADR-025-ai-tool-layer-architecture.md` (Tool Registry)
+- `specs/06-Decision-Records/ADR-026-document-chat-ui-pattern.md` (Chat UI)
+- `specs/06-Decision-Records/ADR-027-ai-admin-console-and-dynamic-control.md` (Admin Console)
+- `specs/06-Decision-Records/ADR-028-migration-architecture-refactor.md` (Migration Pipeline)

.agents/rules/README.md

@@ -0,0 +1,137 @@
+# LCBP3 Agent Rules
+
+Critical rules and guidelines for AI agents working on LCBP3-DMS.
+
+## Version
+
+- **Current:** v1.9.6
+- **Last Updated:** 2026-05-22
+- **Synced with:** `AGENTS.md` (v1.9.6)
+
+## Purpose
+
+This directory contains rule files that define:
+
+- Project context and role expectations
+- Critical Tier 1 rules (CI blockers)
+- Coding standards and patterns
+- Domain terminology and glossary
+- Development workflows
+- Security requirements
+- AI integration architecture (ADR-023/023A)
+
+## Rule Enforcement Tiers
+
+### 🔴 Tier 1 — CRITICAL (CI BLOCKER)
+
+Build fails immediately if violated:
+
+- Security (Auth, RBAC, Validation)
+- UUID Strategy (ADR-019) — no `parseInt` / `Number` / `+` on UUID
+- Database correctness — verify schema before writing queries
+- File upload security (ClamAV + whitelist)
+- AI validation boundary (ADR-023)
+- Error handling strategy (ADR-007)
+- Forbidden patterns: `any`, `console.log`, UUID misuse, `id ?? ''` fallback
+
+### 🟡 Tier 2 — IMPORTANT (CODE REVIEW)
+
+Must fix before merge:
+
+- Architecture patterns (thin controller, business logic in service)
+- Test coverage (80%+ business logic, 70%+ backend overall)
+- Cache invalidation
+- Naming conventions
+- TypeScript Standards: Missing JSDoc, explicit types, or file headers
+
+### 🟢 Tier 3 — SPECIALIZED WORK
+
+Requires domain-specific knowledge:
+
+- **ADR-021 Integration:** Workflow Engine & Context implementation
+- **AI Infrastructure:** ADR-023/023A boundary enforcement and pipeline usage
+- **AI Runtime Layer:** ADR-024 Intent Classification, ADR-025 Tool Layer, ADR-026 Chat UI, ADR-027 Admin Console
+- **Migration Pipeline:** ADR-028 Staging Queue & post-migration cleanup
+- **Complex Business Logic:** Multi-step workflows with state management
+- **Performance Optimization:** Database queries, caching strategies, bulk operations
+
+### 🔵 Tier 4 — GUIDELINES
+
+Best practice — follow when possible:
+
+- Code style / formatting (Prettier handles)
+- Comment completeness
+- Minor optimizations
+
+## Rule Files
+
+### Core Rules (Tier 1 - CRITICAL)
+
+| File                    | Purpose                                                                         |
+| ----------------------- | ------------------------------------------------------------------------------- |
+| `00-project-context.md` | Project context, role & persona, tier classification, specs folder organization |
+| `01-adr-019-uuid.md`    | UUID handling strategy — no parseInt, use publicId only                         |
+| `02-security.md`        | Security requirements, checklist, ADR-023/023A AI boundaries                    |
+
+### Coding Standards
+
+| File                      | Purpose                                                 |
+| ------------------------- | ------------------------------------------------------- |
+| `03-typescript.md`        | TypeScript rules, file headers, i18n guidelines         |
+| `06-backend-patterns.md`  | NestJS patterns, UUID resolution, API response patterns |
+| `07-frontend-patterns.md` | Next.js patterns, RHF+Zod+TanStack Query, UUID handling |
+
+### Domain & Workflow
+
+| File                       | Purpose                                                       |
+| -------------------------- | ------------------------------------------------------------- |
+| `04-domain-terminology.md` | DMS glossary, key spec files priority table                   |
+| `08-development-flow.md`   | Development workflow by work type (Critical/Normal/Quick Fix) |
+
+### Compliance & Architecture
+
+| File                      | Purpose                                                        |
+| ------------------------- | -------------------------------------------------------------- |
+| `05-forbidden-actions.md` | Actions that must never be done, schema changes, UUID handling |
+| `09-commit-checklist.md`  | Pre-commit verification, commit message format                 |
+| `10-error-handling.md`    | ADR-007 error handling strategy, layered classification        |
+| `11-ai-integration.md`    | ADR-023/023A AI architecture, 2-model stack, BullMQ 2-queue    |
+
+## Key Spec Files Priority
+
+Spec priority: **`06-Decision-Records`** > **`05-Engineering-Guidelines`** > others
+
+| Document                       | Path                                                                        | Use When                          |
+| ------------------------------ | --------------------------------------------------------------------------- | --------------------------------- |
+| **Glossary**                   | `specs/00-overview/00-02-glossary.md`                                       | Verify domain terminology         |
+| **Schema Tables**              | `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`               | Before writing any query          |
+| **Data Dictionary**            | `specs/03-Data-and-Storage/03-01-data-dictionary.md`                        | Field meanings + business rules   |
+| **Edge Cases**                 | `specs/01-Requirements/01-06-edge-cases-and-rules.md`                       | Prevent bugs in flows             |
+| **ADR-019 UUID**               | `specs/06-Decision-Records/ADR-019-hybrid-identifier-strategy.md`           | UUID-related work                 |
+| **ADR-023 AI**                 | `specs/06-Decision-Records/ADR-023-unified-ai-architecture.md`              | AI integration work               |
+| **ADR-023A AI Model**          | `specs/06-Decision-Records/ADR-023A-unified-ai-architecture.md`             | 2-model stack, BullMQ 2-queue     |
+| **ADR-024 Intent Class.**      | `specs/06-Decision-Records/ADR-024-intent-classification-strategy.md`       | Pattern→LLM Fallback; Redis cache |
+| **ADR-025 AI Tool Layer**      | `specs/06-Decision-Records/ADR-025-ai-tool-layer-architecture.md`           | Tool Registry; CASL-guarded       |
+| **ADR-026 Chat UI**            | `specs/06-Decision-Records/ADR-026-document-chat-ui-pattern.md`             | Side-panel; streaming SSE         |
+| **ADR-027 AI Admin Console**   | `specs/06-Decision-Records/ADR-027-ai-admin-console-and-dynamic-control.md` | Dynamic control; admin-only       |
+| **ADR-028 Migration Refactor** | `specs/06-Decision-Records/ADR-028-migration-architecture-refactor.md`      | Staging Queue; cleanup            |
+| **Backend Guidelines**         | `specs/05-Engineering-Guidelines/05-02-backend-guidelines.md`               | NestJS patterns                   |
+| **Frontend Guidelines**        | `specs/05-Engineering-Guidelines/05-03-frontend-guidelines.md`              | Next.js patterns                  |
+| **Testing Strategy**           | `specs/05-Engineering-Guidelines/05-04-testing-strategy.md`                 | Coverage goals                    |
+
+## Maintenance
+
+When updating rules:
+
+1. **Check AGENTS.md version** — Ensure rule files are synced
+2. **Update version numbers** — Bump version in `00-project-context.md` only (03-typescript.md no longer has version)
+3. **Review ADR references** — Ensure all ADR references are current (ADR-023, ADR-023A, ADR-024~028)
+4. **Add new forbidden actions** — When new patterns are identified as violations
+5. **Update key spec files table** — When new ADRs or guidelines are added
+6. **Update Tier 3 SPECIALIZED WORK** — When new domain-specific workflows are added
+
+## Related Documents
+
+- `AGENTS.md` — Master agent configuration and context
+- `specs/06-Decision-Records/` — All Architecture Decision Records
+- `specs/05-Engineering-Guidelines/` — Backend, frontend, and testing guidelines

.agents/scripts/bash/agent-registry.sh

@@ -42,7 +42,7 @@ init_agent_registry() {
         [qwen]="Qwen Code"
         [opencode]="opencode"
         [codex]="Codex CLI"
-        [windsurf]="Windsurf"
+        [devin]="Devin"
         [kilocode]="Kilo Code"
         [auggie]="Auggie CLI"
         [roo]="Roo Code"

.agents/scripts/bash/audit-skills.sh

@@ -20,6 +20,8 @@ SKILLS_DIR="$AGENTS_DIR/skills"
 
 echo "=== Skills Health Audit ==="
 echo "Base directory: $BASE_DIR"
+echo "Agents directory: $AGENTS_DIR"
+echo "Specs directory: $BASE_DIR/specs"
 echo
 
 # Function to check if skill has required files
@@ -178,8 +180,57 @@ fi
 
 echo
 
+# Specs Integrity Audit (New for v1.9.0)
+echo "=== Specs Integrity Audit ==="
+echo "---------------------------"
+
+SPECS_DIR="$BASE_DIR/specs"
+CATEGORIES=("100-Infrastructures" "200-fullstacks" "300-others")
+SPEC_ISSUES=0
+
+if [[ -d "$SPECS_DIR" ]]; then
+    # 1. Check for core categories
+    for cat in "${CATEGORIES[@]}"; do
+        if [[ -d "$SPECS_DIR/$cat" ]]; then
+            echo -e "${GREEN}  FOUND${NC}: category $cat"
+            
+            # Check features within category
+            features=$(find "$SPECS_DIR/$cat" -maxdepth 1 -type d -not -path "$SPECS_DIR/$cat" | wc -l)
+            echo "    -> Contains $features feature(s)"
+            
+            # Check each feature for spec.md
+            while IFS= read -r f_dir; do
+                if [[ -n "$f_dir" ]]; then
+                    f_name=$(basename "$f_dir")
+                    if [[ ! -f "$f_dir/spec.md" ]]; then
+                        echo -e "    ${RED}  MISSING${NC}: $f_name/spec.md"
+                        ((SPEC_ISSUES++))
+                    fi
+                fi
+            done < <(find "$SPECS_DIR/$cat" -maxdepth 1 -type d -not -path "$SPECS_DIR/$cat")
+        else
+            echo -e "${YELLOW}  MISSING${NC}: category $cat"
+            ((SPEC_ISSUES++))
+        fi
+    done
+
+    # 2. Check for misplaced files in specs root
+    misplaced=$(find "$SPECS_DIR" -maxdepth 1 -type f -name "*.md" | wc -l)
+    if [[ $misplaced -gt 1 ]]; then # Ignore README.md
+        echo -e "${YELLOW}  WARNING${NC}: Found $misplaced misplaced files in specs root (should be in 100/200/300)"
+        ((SPEC_ISSUES++))
+    fi
+else
+    echo -e "${RED}ERROR: Specs directory not found${NC}"
+    ((SPEC_ISSUES++))
+fi
+
+echo
+
 # Overall health
-if [[ $TOTAL_ISSUES -eq 0 ]]; then
+TOTAL_HEALTH_ISSUES=$((TOTAL_ISSUES + SPEC_ISSUES))
+
+if [[ $TOTAL_HEALTH_ISSUES -eq 0 ]]; then
     echo -e "${GREEN}=== SUCCESS: All skills healthy ===${NC}"
     echo "Total skills: ${#SKILL_DIRS[@]}"
     exit 0

.agents/scripts/bash/common.sh

@@ -99,14 +99,13 @@ find_feature_dir_by_prefix() {
 
     local prefix="${BASH_REMATCH[1]}"
 
-    # Search for directories in specs/ that start with this prefix
+    # Search for directories in specs/ that start with this prefix (supporting subdirectories)
     local matches=()
     if [[ -d "$specs_dir" ]]; then
-        for dir in "$specs_dir"/"$prefix"-*; do
+        # ค้นหาโฟลเดอร์ที่ตรงกับ prefix ในระบบย่อย
-            if [[ -d "$dir" ]]; then
+        while IFS= read -r -d '' dir; do
-                matches+=("$(basename "$dir")")
+            matches+=("$dir")
-            fi
+        done < <(find "$specs_dir" -maxdepth 3 -type d -name "${prefix}-*" -print0 2>/dev/null)
-        done
     fi
 
     # Handle results
@@ -115,12 +114,12 @@ find_feature_dir_by_prefix() {
         echo "$specs_dir/$branch_name"
     elif [[ ${#matches[@]} -eq 1 ]]; then
         # Exactly one match - perfect!
-        echo "$specs_dir/${matches[0]}"
+        echo "${matches[0]}"
     else
         # Multiple matches - this shouldn't happen with proper naming convention
         echo "ERROR: Multiple spec directories found with prefix '$prefix': ${matches[*]}" >&2
         echo "Please ensure only one spec directory exists per numeric prefix." >&2
-        echo "$specs_dir/$branch_name"  # Return something to avoid breaking the script
+        echo "${matches[0]}"  # Return first match to avoid breaking the script
     fi
 }
 

.agents/scripts/bash/update-agent-context.sh

@@ -30,12 +30,12 @@
 #
 # 5. Multi-Agent Support
 #    - Handles agent-specific file paths and naming conventions
-#    - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Windsurf, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, or Amazon Q Developer CLI
+#    - Supports: Claude, Gemini, Copilot, Cursor, Qwen, opencode, Codex, Devin, Kilo Code, Auggie CLI, Roo Code, CodeBuddy CLI, Qoder CLI, Amp, SHAI, or Amazon Q Developer CLI
 #    - Can update single agents or all existing agent files
 #    - Creates default Claude file if no agent files exist
 #
 # Usage: ./update-agent-context.sh [agent_type]
-# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|windsurf|kilocode|auggie|shai|q|bob|qoder
+# Agent types: claude|gemini|copilot|cursor-agent|qwen|opencode|codex|devin|kilocode|auggie|shai|q|bob|qoder
 # Leave empty to update all existing agent files
 
 set -e
@@ -609,8 +609,8 @@ update_specific_agent() {
         codex)
             update_agent_file "$AGENTS_FILE" "Codex CLI"
             ;;
-        windsurf)
+        devin)
-            update_agent_file "$WINDSURF_FILE" "Windsurf"
+            update_agent_file "$DEVIN_FILE" "Devin"
             ;;
         kilocode)
             update_agent_file "$KILOCODE_FILE" "Kilo Code"
@@ -681,8 +681,8 @@ update_all_existing_agents() {
         found_agent=true
     fi
 
-    if [[ -f "$WINDSURF_FILE" ]]; then
+    if [[ -f "$DEVIN_FILE" ]]; then
-        update_agent_file "$WINDSURF_FILE" "Windsurf"
+        update_agent_file "$DEVIN_FILE" "Devin"
         found_agent=true
     fi
 

.agents/skills/README.md

@@ -1,8 +1,8 @@
 # `.agents/skills/` — LCBP3 Agent Skill Pack
 
-**Version:** 1.8.9 | **Last Updated:** 2026-04-22 | **Total Skills:** 20
+**Version:** 1.9.0 | **Last Updated:** 2026-06-07 | **Total Skills:** 24
 
-Agent skills for AI-assisted development in **Windsurf IDE** (and compatible agents: Codex CLI, opencode, Amp, Antigravity, AGENTS.md-aware tools).
+Agent skills for AI-assisted development in **Devin IDE** (and compatible agents: Codex CLI, opencode, Amp, Antigravity, AGENTS.md-aware tools).
 
 ---
 
@@ -14,25 +14,27 @@ Agent skills for AI-assisted development in **Windsurf IDE** (and compatible age
 ├── skills.md                    # Overview + dependency matrix + health monitoring
 ├── _LCBP3-CONTEXT.md            # Shared LCBP3 context injected into every speckit-* skill
 ├── README.md                    # (this file)
+├── save-memory/                 # Session log & project memory update
 ├── nestjs-best-practices/       # Backend rules (40 rules across 10 categories)
 ├── next-best-practices/         # Frontend rules (Next.js 15+)
+├── e2e-testing/                 # Playwright E2E testing patterns (POM, flaky tests, CI/CD)
+├── verification-loop/           # Comprehensive verification (build, typecheck, lint, test, security)
+├── security-review/             # OWASP Top 10 + ADR compliance checklist
 └── speckit-*/                   # 18 workflow skills (spec → plan → tasks → implement → …)
 ```
 
 Each skill directory contains:
 
-- `SKILL.md` — frontmatter (`name`, `description`, `version: 1.8.9`, `scope`, `depends-on`, `handoffs`) + instructions
+- `SKILL.md` — frontmatter (`name`, `description`, `version: 1.9.0`, `scope`, `depends-on`, `handoffs`) + instructions
 - `templates/` _(optional)_ — artifact templates (spec/plan/tasks/checklist)
 - `rules/` _(nestjs only)_ — individual rule files grouped by prefix (`arch-`, `security-`, `db-`, etc.)
 
 ---
 
-## 🚀 How Windsurf Invokes These Skills
+## 🚀 How Devin Invokes These Skills
 
-Windsurf exposes two entry points:
+1. **Skill tool** — Devin discovers skills by scanning `.agents/skills/*/SKILL.md` frontmatter. Skills marked `user-invocable: false` are used silently by Cascade.
-
+2. **Slash commands** — `.devin/workflows/*.md` wraps each skill as a slash command (e.g. `/04-speckit.plan`). The workflow file is short; the heavy lifting is delegated to the skill via `skill` tool.
-1. **Skill tool** — Windsurf discovers skills by scanning `.agents/skills/*/SKILL.md` frontmatter. Skills marked `user-invocable: false` are used silently by Cascade.
-2. **Slash commands** — `.windsurf/workflows/*.md` wraps each skill as a slash command (e.g. `/04-speckit.plan`). The workflow file is short; the heavy lifting is delegated to the skill via `skill` tool.
 
 Both paths end up executing the same `SKILL.md` instructions.
 
@@ -62,14 +64,14 @@ Use `/00-speckit.all` to run specify → clarify → plan → tasks → analyze
 
 From repo root:
 
-| Script | Purpose |
+| Script                                                 | Purpose                                                    |
-| --- | --- |
+| ------------------------------------------------------ | ---------------------------------------------------------- |
 | `./.agents/scripts/bash/check-prerequisites.sh --json` | Emit `FEATURE_DIR` + `AVAILABLE_DOCS` for a feature branch |
-| `./.agents/scripts/bash/setup-plan.sh --json` | Emit `FEATURE_SPEC`, `IMPL_PLAN`, `SPECS_DIR`, `BRANCH` |
+| `./.agents/scripts/bash/setup-plan.sh --json`          | Emit `FEATURE_SPEC`, `IMPL_PLAN`, `SPECS_DIR`, `BRANCH`    |
-| `./.agents/scripts/bash/update-agent-context.sh windsurf` | Append tech entries to `AGENTS.md` |
+| `./.agents/scripts/bash/update-agent-context.sh devin` | Append tech entries to `AGENTS.md`                         |
-| `./.agents/scripts/bash/audit-skills.sh` | Validate all `SKILL.md` frontmatter + presence |
+| `./.agents/scripts/bash/audit-skills.sh`               | Validate all `SKILL.md` frontmatter + presence             |
-| `./.agents/scripts/bash/validate-versions.sh` | Version consistency check |
+| `./.agents/scripts/bash/validate-versions.sh`          | Version consistency check                                  |
-| `./.agents/scripts/bash/sync-workflows.sh` | Verify every skill has a `.windsurf/workflows/*.md` wrapper |
+| `./.agents/scripts/bash/sync-workflows.sh`             | Verify every skill has a `.devin/workflows/*.md` wrapper   |
 
 All scripts mirror to `.agents/scripts/powershell/*.ps1` for Windows.
 
@@ -92,9 +94,9 @@ See [`_LCBP3-CONTEXT.md`](./_LCBP3-CONTEXT.md) for the complete list.
 
 To add a new skill:
 
-1. Create `NAME/SKILL.md` with frontmatter: `name`, `description`, `version: 1.8.9`, `scope`, `depends-on`.
+1. Create `NAME/SKILL.md` with frontmatter: `name`, `description`, `version: 1.9.0`, `scope`, `depends-on`.
 2. Append an LCBP3 context reference pointing to `_LCBP3-CONTEXT.md`.
-3. Wrap with `.windsurf/workflows/NAME.md` so it becomes a slash command.
+3. Wrap with `.devin/workflows/NAME.md` so it becomes a slash command.
 4. Update [`skills.md`](./skills.md) dependency matrix.
 5. Run `./.agents/scripts/bash/audit-skills.sh` → must pass.
 

.agents/skills/VERSION

@@ -1,33 +1 @@
-# Speckit Skills Version
+version: 1.9.0
-
-version: 1.8.9
-release_date: 2026-04-22
-
-## Changelog
-
-### 1.8.9 (2026-04-22)
-- Full LCBP3-native rebuild of `.agents/skills/`
-- Fixed ADR-019 drift (removed `@Expose({ name: 'id' })` and `id ?? ''` fallback patterns)
-- Replaced all dead references (`GEMINI.md` → `AGENTS.md`, v1.7.0 → v1.8.0 schema, `.specify/memory/` → `AGENTS.md`)
-- Added real helper scripts under `.agents/scripts/bash/` and `.agents/scripts/powershell/`
-- Added ADR-007/008/020/021 coverage
-- New rules: workflow-engine, file-two-phase-upload, ai-boundary, i18n, file-upload, workflow-banner
-- Standardized frontmatter across all 20 skills (`version: 1.8.9`)
-
-### 1.8.6 (2026-04-14)
-- Version alignment with LCBP3-DMS v1.8.6
-- Complete skill implementations for all 20 skills
-- Enhanced security and audit capabilities
-- Production-ready deployment status
-
-### 1.1.0 (2026-01-24)
-- New QA skills: tester, reviewer, checker
-- tester: Execute tests, measure coverage, report results
-- reviewer: Code review with severity levels and suggestions
-- checker: Static analysis aggregation (lint, types, security)
-
-### 1.0.0 (2026-01-24)
-- Initial versioned release
-- Core skills: specify, clarify, plan, tasks, implement, analyze, checklist, constitution, quizme, taskstoissues
-- New skills: diff, validate, migrate, status
-- All workflows enhanced with error handling and relative paths

.agents/skills/_LCBP3-CONTEXT.md

@@ -5,14 +5,14 @@
 
 **Project:** NAP-DMS (LCBP3) — Laem Chabang Port Phase 3 Document Management System
 **Stack:** NestJS 11 + Next.js 16 + TypeScript + MariaDB 11.8 + Redis + BullMQ + Elasticsearch + Ollama (on-prem AI)
-**Version:** 1.8.9 (2026-04-18)
+**Version:** 1.9.7 (2026-05-25)
 
 ---
 
 ## 📌 Canonical Rule Sources (read in this order)
 
 1. **`AGENTS.md`** (repo root) — primary rule file for AI agents; supersedes legacy `GEMINI.md`.
-2. **`specs/06-Decision-Records/`** — architectural decisions (22 ADRs); ADR priority > Engineering Guidelines.
+2. **`specs/06-Decision-Records/`** — architectural decisions (29 ADRs); ADR priority > Engineering Guidelines.
 3. **`specs/05-Engineering-Guidelines/`** — backend/frontend/testing/i18n/git patterns.
 4. **`specs/00-Overview/00-02-glossary.md`** — domain terminology (Correspondence / RFA / Transmittal / Circulation).
 5. **`specs/00-Overview/00-03-product-vision.md`** — project constitution (Vision, Strategic Pillars, Guardrails).
@@ -24,11 +24,12 @@
 ## 🔴 Tier 1 Non-Negotiables
 
 - **ADR-019 UUID:** `publicId: string` exposed directly — **no** `@Expose({ name: 'id' })` rename; **no** `parseInt`/`Number`/`+` on UUID; **no** `id ?? ''` fallback in frontend.
-- **ADR-009:** No TypeORM migrations — edit `specs/03-Data-and-Storage/lcbp3-v1.8.0-schema-02-tables.sql` or add a `deltas/*.sql` file.
+- **ADR-009:** No TypeORM migrations — edit `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql` or add a `deltas/*.sql` file.
 - **ADR-016 Security:** JWT + CASL 4-Level RBAC; `@UseGuards(JwtAuthGuard, CaslAbilityGuard)` on every mutation controller; `ThrottlerGuard` on auth; bcrypt 12 rounds; `Idempotency-Key` required on POST/PUT/PATCH.
 - **ADR-002 Document Numbering:** Redis Redlock + TypeORM `@VersionColumn` (double-lock). Never use application-side counter alone.
 - **ADR-008 Notifications:** BullMQ queue — never inline email/notification in a request thread.
-- **ADR-018 AI Boundary:** Ollama on Admin Desktop only; AI → DMS API → DB (never direct DB/storage). Human-in-the-loop validation required.
+- **ADR-023/023A AI Boundary:** Ollama on Admin Desktop only; AI → DMS API → DB (never direct DB/storage). 2-model stack: `gemma4:e4b Q8_0` + `nomic-embed-text`. BullMQ `ai-realtime` / `ai-batch` queues. Human-in-the-loop validation required. (ADR-018 superseded by ADR-023)
+- **ADR-029 Dynamic Prompt Management:** Prompt templates in DB (`ai_prompts`), never hardcoded in processor; Redis cache `ai:prompt:active:{type}` TTL 60s; `activate()` runs in DB transaction + Redis DEL after commit; `system.manage_all` guard on all mutations.
 - **ADR-007 Error Handling:** Layered (Validation / Business / System); `BusinessException` hierarchy; user-friendly `userMessage` + `recoveryAction`; technical stack only in logs.
 - **TypeScript Strict:** Zero `any`, zero `console.log` (use NestJS `Logger`).
 - **i18n:** No hardcoded Thai/English strings in components — use i18n keys (see `05-08-i18n-guidelines.md`).
@@ -38,30 +39,36 @@
 
 ## 🏷️ Domain Glossary (reject generic terms)
 
-| ✅ Use | ❌ Don't Use |
+| ✅ Use             | ❌ Don't Use                          |
-| --- | --- |
+| ------------------ | ------------------------------------- |
-| Correspondence | Letter, Communication, Document |
+| Correspondence     | Letter, Communication, Document       |
-| RFA | Approval Request, Submit for Approval |
+| RFA                | Approval Request, Submit for Approval |
-| Transmittal | Delivery Note, Cover Letter |
+| Transmittal        | Delivery Note, Cover Letter           |
-| Circulation | Distribution, Routing |
+| Circulation        | Distribution, Routing                 |
-| Shop Drawing | Construction Drawing |
+| Shop Drawing       | Construction Drawing                  |
-| Contract Drawing | Design Drawing, Blueprint |
+| Contract Drawing   | Design Drawing, Blueprint             |
-| Workflow Engine | Approval Flow, Process Engine |
+| Workflow Engine    | Approval Flow, Process Engine         |
-| Document Numbering | Document ID, Auto Number |
+| Document Numbering | Document ID, Auto Number              |
 
 ---
 
 ## 📁 Key Files for Generating / Validating Artifacts
 
-| When you need... | Read |
+| When you need...           | Read                                                                                                                |
-| --- | --- |
+| -------------------------- | ------------------------------------------------------------------------------------------------------------------- |
-| A new feature spec | `.agents/skills/speckit-specify/templates/spec-template.md` + `specs/01-Requirements/01-06-edge-cases-and-rules.md` |
+| A new feature spec         | `.agents/skills/speckit-specify/templates/spec-template.md` + `specs/01-Requirements/01-06-edge-cases-and-rules.md` |
-| A plan | `.agents/skills/speckit-plan/templates/plan-template.md` + relevant ADRs |
+| A plan                     | `.agents/skills/speckit-plan/templates/plan-template.md` + relevant ADRs                                            |
-| Task breakdown | `.agents/skills/speckit-tasks/templates/tasks-template.md` + existing patterns in `specs/08-Tasks/` |
+| Task breakdown             | `.agents/skills/speckit-tasks/templates/tasks-template.md` + existing patterns in `specs/08-Tasks/`                 |
-| Acceptance criteria / UAT | `specs/01-Requirements/01-05-acceptance-criteria.md` |
+| Acceptance criteria / UAT  | `specs/01-Requirements/01-05-acceptance-criteria.md`                                                                |
-| Schema / table definition | `specs/03-Data-and-Storage/lcbp3-v1.8.0-schema-02-tables.sql` + `03-01-data-dictionary.md` |
+| Schema / table definition  | `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql` + `03-01-data-dictionary.md`                          |
-| RBAC / permissions | `specs/03-Data-and-Storage/lcbp3-v1.8.0-seed-permissions.sql` + `01-02-01-rbac-matrix.md` |
+| RBAC / permissions         | `specs/03-Data-and-Storage/lcbp3-v1.8.0-seed-permissions.sql` + `01-02-01-rbac-matrix.md`                           |
-| Release / hotfix | `specs/04-Infrastructure-OPS/04-08-release-management-policy.md` |
+| Release / hotfix           | `specs/04-Infrastructure-OPS/04-08-release-management-policy.md`                                                    |
+| ADR-024 Intent Class.      | `specs/06-Decision-Records/ADR-024-intent-classification-strategy.md`                                               |
+| ADR-025 AI Tool Layer      | `specs/06-Decision-Records/ADR-025-ai-tool-layer-architecture.md`                                                   |
+| ADR-026 Chat UI            | `specs/06-Decision-Records/ADR-026-document-chat-ui-pattern.md`                                                     |
+| ADR-027 AI Admin Console   | `specs/06-Decision-Records/ADR-027-ai-admin-console-and-dynamic-control.md`                                         |
+| ADR-028 Migration Refactor | `specs/06-Decision-Records/ADR-028-migration-architecture-refactor.md`                                              |
+| ADR-029 Dynamic Prompts    | `specs/06-Decision-Records/ADR-029-dynamic-prompt-management.md`                                                    |
 
 ---
 
@@ -83,7 +90,7 @@
 - [ ] Business comments in Thai, code identifiers in English
 - [ ] Schema changes via SQL directly (not migration)
 - [ ] Test coverage meets targets (Backend 70%+, Business Logic 80%+)
-- [ ] Relevant ADRs referenced (007/008/009/016/018/019/020/021)
+- [ ] Relevant ADRs referenced (007/008/009/016/019/021/023/023A/024-029 for AI work)
 - [ ] Domain glossary terms used correctly
 - [ ] Error handling: `Logger` + `HttpException` / `BusinessException`
 - [ ] i18n keys used (no hardcode text)

.agents/skills/bugfix/SKILL.md

@@ -0,0 +1,40 @@
+---
+name: bugfix
+description: Quick bugfix workflow with minimal impact. Focused on surgical fixes without unrelated refactoring.
+version: 1.9.0
+---
+
+# Bugfix
+
+ใช้สำหรับแก้ไข Bug ที่ระบุสาเหตุได้ชัดเจน โดยเน้นที่การแก้ไขที่ตรงจุด (Surgical Fix) และมีผลกระทบน้อยที่สุด (Minimal Impact)
+
+## Phase 1 — Analysis (การวิเคราะห์)
+
+1. **Read Logs & Context**: อ่าน Error Logs หรือรายละเอียดที่ User แจ้งมาให้ครบถ้วน
+2. **Identify Root Cause**: ค้นหาสาเหตุที่แท้จริง (Root Cause) ไม่ใช่แค่การแก้ที่ปลายเหตุ
+3. **Check Error Catalog**: ตรวจสอบ `docs/error-catalog.md` เพื่อดูว่ามี Error Code หรือ Pattern ที่เกี่ยวข้องหรือไม่
+4. **Locate Code**: ระบุไฟล์และบรรทัดที่เกิดปัญหาให้ชัดเจน
+
+## Phase 2 — Planning (การวางแผน)
+
+1. **Create Fix Plan**: ร่างแผนการแก้ไขที่เน้น **Minimal Change**
+   - ห้าม Refactor โค้ดที่ไม่เกี่ยวข้อง
+   - หลีกเลี่ยงการเปลี่ยนแปลงที่จะส่งผลกระทบต่อส่วนอื่น (No Side Effects)
+2. **Verify Standards**: ตรวจสอบว่าแผนการแก้ไขไม่ขัดกับ Tier 1 (Security, UUID, DB) และ Tier 2 (Architecture) ใน `AGENTS.md`
+3. **Save to fix.md**: (Optional) บันทึกรายละเอียดการแก้ไขลงในไฟล์ `fix.md` เพื่อใช้ตรวจสอบก่อนลงมือจริง
+
+## Phase 3 — Execution (การดำเนินการ)
+
+1. **Apply Fix**: ลงมือแก้ไขโค้ดตามแผน
+2. **Verify Fix**:
+   - จำลองสถานการณ์เพื่อยืนยันว่า Bug หายไปจริง
+   - ตรวจสอบว่าไม่มี Forbidden Patterns (`any`, `console.log`, UUID misuse)
+3. **Regression Check**: ตรวจสอบส่วนที่เกี่ยวข้องว่ายังทำงานได้ปกติ
+
+## Phase 4 — Finalization (การสรุปผล)
+
+1. **Report**: สรุปผลการแก้ไขให้ User ทราบ
+   - Root cause (สาเหตุ)
+   - Fix detail (รายละเอียดการแก้)
+   - Affected files (ไฟล์ที่เกี่ยวข้อง)
+2. **Cleanup**: ลบไฟล์ `fix.md` หรือ Debug logs ที่สร้างขึ้น

.agents/skills/diagnose/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: diagnose
 description: Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
+version: 1.9.0
 ---
 
 # Diagnose

.agents/skills/e2e-testing/SKILL.md

@@ -0,0 +1,354 @@
+---
+name: e2e-testing
+description: Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies for LCBP3-DMS.
+version: 1.9.0
+scope: testing
+depends-on: []
+handoffs-to: [speckit-tester]
+user-invocable: true
+---
+
+# E2E Testing Skill
+
+Playwright E2E testing patterns adapted for LCBP3-DMS (NestJS + Next.js + MariaDB stack).
+
+## LCBP3 Context
+
+See [`_LCBP3-CONTEXT.md`](../_LCBP3-CONTEXT.md) for project-specific testing requirements:
+- Backend: Jest (Unit + Integration + E2E)
+- Frontend: Vitest (Unit) + Playwright (E2E)
+- E2E test location: `frontend/e2e/workflow-adr021.spec.ts`
+- Coverage goals: Backend 70%+, Business Logic 80%+
+
+## When to Use
+
+Invoke this skill when:
+- Creating new E2E tests for frontend features
+- Debugging flaky Playwright tests
+- Setting up CI/CD integration for E2E tests
+- Optimizing test performance and reliability
+- Implementing Page Object Model (POM) patterns
+
+## Test File Organization
+
+```
+frontend/
+├── e2e/
+│   ├── auth/
+│   │   ├── login.spec.ts
+│   │   └── logout.spec.ts
+│   ├── correspondence/
+│   │   ├── create.spec.ts
+│   │   └── workflow.spec.ts
+│   ├── transmittals/
+│   │   ├── create.spec.ts
+│   │   └── submit.spec.ts
+│   ├── circulation/
+│   │   ├── routing.spec.ts
+│   │   └── approval.spec.ts
+│   └── workflow-adr021.spec.ts  # Existing ADR-021 integration test
+├── playwright.config.ts
+└── tests/
+    └── fixtures/
+        ├── auth.ts
+        └── data.ts
+```
+
+## Page Object Model (POM)
+
+```typescript
+// frontend/e2e/pages/CorrespondencePage.ts
+import { Page, Locator } from '@playwright/test'
+
+export class CorrespondencePage {
+  readonly page: Page
+  readonly createButton: Locator
+  readonly subjectInput: Locator
+  readonly recipientSelect: Locator
+  readonly submitButton: Locator
+  readonly successMessage: Locator
+
+  constructor(page: Page) {
+    this.page = page
+    this.createButton = page.getByTestId('create-correspondence')
+    this.subjectInput = page.getByTestId('subject-input')
+    this.recipientSelect = page.getByTestId('recipient-select')
+    this.submitButton = page.getByTestId('submit-button')
+    this.successMessage = page.getByTestId('success-message')
+  }
+
+  async goto() {
+    await this.page.goto('/admin/doc-control/correspondences')
+    await this.page.waitForLoadState('networkidle')
+  }
+
+  async createCorrespondence(data: {
+    subject: string
+    recipientId: string
+  }) {
+    await this.createButton.click()
+    await this.subjectInput.fill(data.subject)
+    await this.recipientSelect.selectOption(data.recipientId)
+    await this.submitButton.click()
+  }
+
+  async verifySuccess() {
+    await expect(this.successMessage).toBeVisible()
+  }
+}
+```
+
+## Test Structure
+
+```typescript
+// frontend/e2e/correspondence/create.spec.ts
+import { test, expect } from '@playwright/test'
+import { CorrespondencePage } from '../pages/CorrespondencePage'
+
+test.describe('Correspondence Creation', () => {
+  let correspondencePage: CorrespondencePage
+
+  test.beforeEach(async ({ page }) => {
+    correspondencePage = new CorrespondencePage(page)
+    await correspondencePage.goto()
+  })
+
+  test('should create correspondence successfully', async ({ page }) => {
+    await correspondencePage.createCorrespondence({
+      subject: 'Test Correspondence',
+      recipientId: 'test-recipient-id'
+    })
+
+    await correspondencePage.verifySuccess()
+    await page.screenshot({ path: 'artifacts/correspondence-created.png' })
+  })
+
+  test('should validate required fields', async ({ page }) => {
+    await correspondencePage.createButton.click()
+    await correspondencePage.submitButton.click()
+
+    await expect(page.getByTestId('subject-error')).toBeVisible()
+    await expect(page.getByTestId('recipient-error')).toBeVisible()
+  })
+})
+```
+
+## Playwright Configuration
+
+```typescript
+// frontend/playwright.config.ts
+import { defineConfig, devices } from '@playwright/test'
+
+export default defineConfig({
+  testDir: './e2e',
+  fullyParallel: true,
+  forbidOnly: !!process.env.CI,
+  retries: process.env.CI ? 2 : 0,
+  workers: process.env.CI ? 1 : undefined,
+  reporter: [
+    ['html', { outputFolder: 'playwright-report' }],
+    ['junit', { outputFile: 'playwright-results.xml' }],
+    ['json', { outputFile: 'playwright-results.json' }]
+  ],
+  use: {
+    baseURL: process.env.BASE_URL || 'http://localhost:3000',
+    trace: 'on-first-retry',
+    screenshot: 'only-on-failure',
+    video: 'retain-on-failure',
+    actionTimeout: 10000,
+    navigationTimeout: 30000,
+  },
+  projects: [
+    { name: 'chromium', use: { ...devices['Desktop Chrome'] } },
+  ],
+  webServer: {
+    command: 'pnpm dev',
+    url: 'http://localhost:3000',
+    reuseExistingServer: !process.env.CI,
+    timeout: 120000,
+  },
+})
+```
+
+## Flaky Test Patterns
+
+### Quarantine
+
+```typescript
+test('flaky: complex workflow', async ({ page }) => {
+  test.fixme(true, 'Flaky - Issue #123')
+  // test code...
+})
+
+test('conditional skip', async ({ page }) => {
+  test.skip(process.env.CI, 'Flaky in CI - Issue #123')
+  // test code...
+})
+```
+
+### Identify Flakiness
+
+```bash
+cd frontend
+npx playwright test e2e/correspondence/create.spec.ts --repeat-each=10
+npx playwright test e2e/correspondence/create.spec.ts --retries=3
+```
+
+### Common Causes & Fixes
+
+**Race conditions:**
+```typescript
+// Bad: assumes element is ready
+await page.click('[data-testid="submit-button"]')
+
+// Good: auto-wait locator
+await page.locator('[data-testid="submit-button"]').click()
+```
+
+**Network timing:**
+```typescript
+// Bad: arbitrary timeout
+await page.waitForTimeout(5000)
+
+// Good: wait for specific condition
+await page.waitForResponse(resp => 
+  resp.url().includes('/api/correspondences') && resp.status() === 201
+)
+```
+
+**Animation timing:**
+```typescript
+// Bad: click during animation
+await page.click('[data-testid="menu-item"]')
+
+// Good: wait for stability
+await page.locator('[data-testid="menu-item"]').waitFor({ state: 'visible' })
+await page.waitForLoadState('networkidle')
+await page.locator('[data-testid="menu-item"]').click()
+```
+
+## Artifact Management
+
+### Screenshots
+
+```typescript
+await page.screenshot({ path: 'artifacts/after-login.png' })
+await page.screenshot({ path: 'artifacts/full-page.png', fullPage: true })
+await page.locator('[data-testid="workflow-banner"]').screenshot({ 
+  path: 'artifacts/workflow-banner.png' 
+})
+```
+
+### Traces
+
+```typescript
+// In playwright.config.ts
+use: {
+  trace: 'on-first-retry'
+}
+
+// View trace
+npx playwright show-trace trace.zip
+```
+
+### Video
+
+```typescript
+// In playwright.config.ts
+use: {
+  video: 'retain-on-failure',
+  videosPath: 'artifacts/videos/'
+}
+```
+
+## CI/CD Integration
+
+```yaml
+# .github/workflows/e2e.yml
+name: E2E Tests
+on: [push, pull_request]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-node@v4
+        with:
+          node-version: 20
+      - run: pnpm install
+      - run: cd frontend && npx playwright install --with-deps
+      - run: cd frontend && npx playwright test
+        env:
+          BASE_URL: ${{ vars.STAGING_URL }}
+      - uses: actions/upload-artifact@v4
+        if: always()
+        with:
+          name: playwright-report
+          path: frontend/playwright-report/
+          retention-days: 30
+```
+
+## Test Report Template
+
+```markdown
+# E2E Test Report
+
+**Date:** YYYY-MM-DD HH:MM
+**Duration:** Xm Ys
+**Status:** PASSING / FAILING
+
+## Summary
+- Total: X | Passed: Y (Z%) | Failed: A | Flaky: B | Skipped: C
+
+## Failed Tests
+
+### correspondence-create
+**File:** `frontend/e2e/correspondence/create.spec.ts:45`
+**Error:** Expected element to be visible
+**Screenshot:** artifacts/failed.png
+**Recommended Fix:** Add waitForLoadState after form submission
+
+## Artifacts
+- HTML Report: frontend/playwright-report/index.html
+- Screenshots: frontend/artifacts/*.png
+- Videos: frontend/artifacts/videos/*.webm
+- Traces: frontend/artifacts/*.zip
+```
+
+## Critical Flow Testing
+
+```typescript
+// frontend/e2e/workflow/adr021.spec.ts
+test('workflow: correspondence → rfa → approval', async ({ page }) => {
+  // Create correspondence
+  await createCorrespondence(page)
+  await expect(page.getByTestId('correspondence-created')).toBeVisible()
+
+  // Submit for RFA
+  await page.getByTestId('submit-rfa').click()
+  await expect(page.getByTestId('rfa-submitted')).toBeVisible()
+
+  // Approve RFA
+  await page.goto('/admin/doc-control/rfa/123')
+  await page.getByTestId('approve-button').click()
+  await expect(page.getByTestId('approval-success')).toBeVisible()
+
+  // Verify workflow state
+  await expect(page.getByTestId('workflow-state')).toContainText('APPROVED')
+})
+```
+
+## LCBP3-Specific Considerations
+
+- **UUID Handling:** Use `publicId` (string UUID) in E2E tests, never `parseInt()` (ADR-019)
+- **Authentication:** Mock auth tokens for E2E tests to avoid real auth flows
+- **Workflow States:** Test ADR-021 workflow transitions (DRAFT → PENDING → APPROVED)
+- **i18n:** Test with Thai language to verify i18n key resolution
+- **RBAC:** Test different user roles (admin, user, reviewer) for permission checks
+
+## References
+
+- LCBP3 Testing Strategy: `specs/05-Engineering-Guidelines/05-04-testing-strategy.md`
+- ADR-021 Workflow Context: `specs/06-Decision-Records/ADR-021-workflow-context.md`
+- Existing E2E test: `frontend/e2e/workflow-adr021.spec.ts`

.agents/skills/grill-with-docs/SKILL.md

@@ -1,6 +1,7 @@
 ---
 name: grill-with-docs
 description: Grilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.
+version: 1.9.0
 ---
 
 <what-to-do>

.agents/skills/nestjs-best-practices/AGENTS.md

@@ -6454,7 +6454,7 @@ CREATE TABLE ai_audit_log (
   user_id INT NOT NULL,
   action VARCHAR(64) NOT NULL,       -- 'ai.extract_metadata', 'ai.classify', etc.
   file_id INT,
-  model VARCHAR(64),                  -- 'gemma-4:7b', 'paddleocr-v3'
+  model VARCHAR(64),                  -- 'gemma-4:7b', 'typhoon-np-dms-ocr', 'tesseract-ocr'
   confidence DECIMAL(4,3),
   input_hash CHAR(64),                -- SHA-256 of input for replay detection
   output_summary JSON,

.agents/skills/nestjs-best-practices/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: nestjs-best-practices
 description: NestJS best practices and architecture patterns for building production-ready LCBP3-DMS backend code. Enforces ADR-009 (no TypeORM migrations), ADR-019 (hybrid UUID), ADR-016 (security), ADR-007 (error handling), ADR-008 (BullMQ), ADR-001/002 (workflow + numbering), ADR-018/020 (AI boundary), and ADR-021 (workflow context).
-version: 1.8.9
+version: 1.9.0
 scope: backend
 user-invocable: false
 license: MIT
@@ -126,7 +126,7 @@ These rules override general NestJS best practices for the NAP-DMS project:
 ### ADR-009: No TypeORM Migrations
 
 - **ห้ามสร้างไฟล์ migration ของ TypeORM**
-- แก้ไข schema โดยตรงที่: `specs/03-Data-and-Storage/lcbp3-v1.8.0-schema-02-tables.sql`
+- แก้ไข schema โดยตรงที่: `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`
 - ใช้ n8n workflow สำหรับ data migration ถ้าจำเป็น
 
 ### ADR-019: Hybrid Identifier Strategy (CRITICAL — March 2026 Pattern)

.agents/skills/nestjs-best-practices/rules/lcbp3-ai-boundary.md

@@ -137,7 +137,7 @@ CREATE TABLE ai_audit_log (
   user_id INT NOT NULL,
   action VARCHAR(64) NOT NULL,       -- 'ai.extract_metadata', 'ai.classify', etc.
   file_id INT,
-  model VARCHAR(64),                  -- 'gemma-4:7b', 'paddleocr-v3'
+  model VARCHAR(64),                  -- 'gemma-4:7b', 'typhoon-np-dms-ocr', 'tesseract-ocr'
   confidence DECIMAL(4,3),
   input_hash CHAR(64),                -- SHA-256 of input for replay detection
   output_summary JSON,

.agents/skills/next-best-practices/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: next-best-practices
 description: Next.js best practices for LCBP3-DMS frontend. Enforces ADR-019 (publicId only, no parseInt/id fallback), TanStack Query + RHF + Zod, shadcn/ui, i18n, ADR-007 error UX, ADR-021 IntegratedBanner/WorkflowLifecycle, two-phase file upload.
-version: 1.8.9
+version: 1.9.0
 scope: frontend
 user-invocable: false
 ---

.agents/skills/save-memory/SKILL.md

@@ -0,0 +1,198 @@
+---
+name: save-memory
+description: บันทึก session log และอัปเดต project memory ตามโครงสร้างใหม่
+version: 1.9.0
+scope: project-management
+depends-on: []
+user-invocable: true
+---
+
+# บันทึก Memory (Save Memory)
+
+Skill นี้ใช้สำหรับบันทึก session log และอัปเดต project memory ตามโครงสร้างใหม่ที่ reorganization แล้ว
+
+## โครงสร้าง Memory ใหม่
+
+```
+memory/
+├── README.md (index + overview)
+├── mcp-tools.md (MCP MariaDB + Memory Tools)
+└── project-memory-override.md (OS rules, Current Decisions, Environment, Next Session Focus)
+
+specs/88-logs/
+├── rollouts.md (Recent rollouts table)
+└── session-YYYY-MM-DD-[topic].md (Session logs)
+```
+
+## ขั้นตอนการบันทึก Memory
+
+### 1. สร้าง Session Log (ถ้ามีงาน session ใหม่)
+
+เมื่อทำงาน session ใหม่ให้:
+
+1. **สร้างไฟล์ session log ใหม่** ใน `specs/88-logs/`
+   - ชื่อไฟล์: `session-YYYY-MM-DD-[topic].md`
+   - ตัวอย่าง: `session-2026-06-07-memory-reorganization.md`
+
+2. **บันทึกเนื้อหาใน session log**:
+
+   ```markdown
+   # Session [N] — YYYY-MM-DD ([Topic])
+
+   ## Summary
+
+   [สรุปสิ่งที่ทำใน session นี้]
+
+   ## ปัญหาที่พบ (Root Cause)
+
+   [อธิบายปัญหาและสาเหตุ]
+
+   ## การแก้ไข (Fix)
+
+   | ไฟล์           | การเปลี่ยนแปลง         |
+   | -------------- | ---------------------- |
+   | [path/to/file] | [อธิบายการเปลี่ยนแปลง] |
+
+   ## กฎที่ Lock แล้ว
+
+   [บันทึก pattern หรือ decision ที่ตกลง]
+
+   ## Verification
+
+   [วิธีตรวจสอบว่างานสำเร็จ]
+   ```
+
+3. **อัปเดต `specs/88-logs/rollouts.md`**
+   - เพิ่ม entry ใหม่ในตาราง Recent Rollouts
+   - รูปแบบ: `| วันที่ | Version | รายการ | สถานะ |`
+
+### 2. อัปเดต Project Memory (ถ้ามี decision ใหม่)
+
+เมื่อมีการตัดสินใจสำคัญใหม่ให้:
+
+1. **เปิดไฟล์ `memory/project-memory-override.md`**
+
+2. **อัปเดตตาราง "Current Decisions (Locked)"**
+   - เพิ่ม entry ใหม่ถ้ามี decision ใหม่
+   - รูปแบบ: `| ID | Decision | ADR |`
+
+3. **อัปเดต "Next Session Focus"**
+   - เพิ่มงานใหม่ถ้ามี
+   - ทำเครื่องหมาย `[ ]` สำหรับงานที่ยังไม่เสร็จ
+   - ทำเครื่องหมาย `[X]` สำหรับงานที่เสร็จแล้ว
+
+4. **อัปเดต "Environment & Services"** (ถ้ามีการเปลี่ยนแปลง)
+   - อัปเดต URL, port, หรือ notes ถ้ามีการเปลี่ยน infrastructure
+
+### 3. อัปเดต MCP Tools (ถ้ามี tools ใหม่)
+
+เมื่อมี MCP tools ใหม่ให้:
+
+1. **เปิดไฟล์ `memory/mcp-tools.md`**
+
+2. **เพิ่ม tool ใหม่ในตาราง "Available Tools"**
+   - รูปแบบ: `| Tool | Purpose | Example Usage |`
+
+3. **เพิ่ม usage example และ warnings** ถ้าจำเป็น
+
+### 4. อัปเดต Root Documentation (ถ้ามีการเปลี่ยนแปลง)
+
+เมื่อมีการเปลี่ยนแปลงที่ส่งผลต่อเอกสารระดับ root ให้:
+
+1. **ARCHITECTURE.md** — อัปเดตเมื่อ:
+   - เปลี่ยน architecture หลัก
+   - เพิ่ม/ลบ component สำคัญ
+   - เปลี่ยน data flow หรือ integration pattern
+
+2. **CHANGELOG.md** — อัปเดตเมื่อ:
+   - Deploy version ใหม่
+   - เพิ่ม feature หรือ breaking change สำคัญ
+   - รูปแบบ: `## [version] (YYYY-MM-DD)` → `### feat(scope): description`
+
+3. **CONTEXT.md** — อัปเดตเมื่อ:
+   - เปลี่ยน domain terminology หลัก
+   - เพิ่ม concept ใหม่ที่ใช้ทั่ว project
+   - อัปเดต glossary หรือ business rules
+
+4. **CONTRIBUTING.md** — อัปเดตเมื่อ:
+   - เปลี่ยน workflow การทำงาน
+   - เพิ่ม/เปลี่ยน coding standards
+   - อัปเดต CI/CD process
+
+5. **README.md** — อัปเดตเมื่อ:
+   - เปลี่ยน project structure
+   - เพิ่ม/เปลี่ยน installation steps
+   - อัปเดต feature overview หรือ tech stack
+
+## Template สำหรับ Session Log
+
+```markdown
+# Session [N] — YYYY-MM-DD ([Topic])
+
+## Summary
+
+[สรุปสิ่งที่ทำใน session นี้ใน 1-2 ประโยค]
+
+## ปัญหาที่พบ (Root Cause)
+
+[อธิบายปัญหาและสาเหตุหลัก]
+
+## การแก้ไข (Fix)
+
+| ไฟล์           | การเปลี่ยนแปลง         |
+| -------------- | ---------------------- |
+| `path/to/file` | [อธิบายการเปลี่ยนแปลง] |
+
+## กฎที่ Lock แล้ว
+
+[บันทึก pattern หรือ decision ที่ตกลงและไม่ควรเปลี่ยน]
+
+## Verification
+
+- [ ] [check 1]
+- [ ] [check 2]
+```
+
+## ข้อควรระวัง
+
+- **ห้าม** บันทึก rules ที่ซ้ำกับ specs/ (ADRs, glossary, guidelines)
+- **ห้าม** บันทึก commands ที่ซ้ำกับ specs/05-Engineering-Guidelines/
+- **ห้าม** บันทึก environment ที่ซ้ำกับ specs/04-Infrastructure-OPS/
+- **ใช้** `specs/88-logs/` สำหรับ session history และ rollouts
+- **ใช้** `memory/project-memory-override.md` สำหรับ OS rules, decisions, environment ที่ไม่มีใน specs
+- **ใช้** `memory/mcp-tools.md` สำหรับ MCP tools documentation
+- **อัปเดต Root Documentation** (ARCHITECTURE.md, CHANGELOG.md, CONTEXT.md, CONTRIBUTING.md, README.md) เฉพาะเมื่อมีการเปลี่ยนแปลงที่ส่งผลต่อ project architecture, version, terminology, workflow หรือ structure
+
+## ตัวอย่างการใช้งาน
+
+### กรณีที่ 1: ทำงาน session ใหม่
+
+```
+1. สร้างไฟล์ specs/88-logs/session-2026-06-07-bug-fix.md
+2. บันทึกปัญหา, การแก้ไข, verification
+3. อัปเดต specs/88-logs/rollouts.md
+```
+
+### กรณีที่ 2: มี decision ใหม่
+
+```
+1. เปิด memory/project-memory-override.md
+2. เพิ่ม entry ใหม่ในตาราง Current Decisions
+3. อัปเดต Next Session Focus
+```
+
+### กรณีที่ 3: เปลี่ยน infrastructure
+
+```
+1. เปิด memory/project-memory-override.md
+2. อัปเดตตาราง Environment & Services
+3. อัปเดต Key Environment Variables ถ้าจำเป็น
+```
+
+### กรณีที่ 4: อัปเดต Root Documentation
+
+```
+1. ตรวจสอบว่ามีการเปลี่ยนแปลงที่ส่งผลต่อ ARCHITECTURE.md, CHANGELOG.md, CONTEXT.md, CONTRIBUTING.md, หรือ README.md
+2. อัปเดตไฟล์ที่เกี่ยวข้องตามรูปแบบที่กำหนด
+3. ตรวจสอบว่าการเปลี่ยนแปลงสอดคล้องกับ specs/ และ ADRs
+```

.agents/skills/security-review/SKILL.md

@@ -0,0 +1,517 @@
+---
+name: security-review
+description: Comprehensive security review for LCBP3-DMS with OWASP Top 10 checklist, ADR compliance, and automated security testing patterns.
+version: 1.9.0
+scope: security
+depends-on: []
+handoffs-to: [speckit-reviewer, speckit-security-audit]
+user-invocable: true
+---
+
+# Security Review Skill
+
+Comprehensive security review for LCBP3-DMS ensuring all code follows security best practices and identifies potential vulnerabilities.
+
+## LCBP3 Context
+
+See [`_LCBP3-CONTEXT.md`](../_LCBP3-CONTEXT.md) for project-specific security requirements:
+- **ADR-016**: Security & Authentication (JWT, CASL, RBAC, file upload)
+- **ADR-018**: AI Boundary (Ollama on Admin Desktop only, no direct DB/storage access)
+- **ADR-019**: UUID Strategy (no parseInt/Number/+ on UUID)
+- **ADR-023**: Unified AI Architecture (AI via DMS API only)
+- **ADR-007**: Error Handling (layered error classification)
+
+## When to Activate
+
+Invoke this skill:
+- Implementing authentication or authorization
+- Handling user input or file uploads
+- Creating new API endpoints
+- Working with secrets or credentials
+- Integrating AI features (Ollama/Qdrant)
+- Storing or transmitting sensitive data
+- Integrating third-party APIs
+
+## Security Checklist
+
+### 1. Secrets Management
+
+#### FAIL: NEVER Do This
+```typescript
+const apiKey = "sk-proj-xxxxx"  // Hardcoded secret
+const dbPassword = "password123" // In source code
+```
+
+#### PASS: ALWAYS Do This
+```typescript
+const apiKey = process.env.OPENAI_API_KEY
+const dbUrl = process.env.DATABASE_URL
+
+// Verify secrets exist
+if (!apiKey) {
+  throw new Error('OPENAI_API_KEY not configured')
+}
+```
+
+#### Verification Steps
+- [ ] No hardcoded API keys, tokens, or passwords
+- [ ] All secrets in environment variables
+- [ ] `.env.local` in .gitignore
+- [ ] No secrets in git history
+- [ ] Production secrets in QNAP docker-compose environment section (not .env files)
+
+### 2. Input Validation
+
+#### Always Validate User Input
+```typescript
+import { z } from 'zod'
+
+// Define validation schema
+const CreateCorrespondenceSchema = z.object({
+  subject: z.string().min(1).max(500),
+  recipientId: z.string().uuid(),
+  typeCode: z.string().min(1).max(50)
+})
+
+// Validate before processing
+export async function createCorrespondence(input: unknown) {
+  try {
+    const validated = CreateCorrespondenceSchema.parse(input)
+    return await correspondenceService.create(validated)
+  } catch (error) {
+    if (error instanceof z.ZodError) {
+      throw new BadRequestException(error.errors)
+    }
+    throw error
+  }
+}
+```
+
+#### File Upload Validation (ADR-016)
+```typescript
+function validateFileUpload(file: Express.Multer.File) {
+  // Size check (50MB max per ADR-016)
+  const maxSize = 50 * 1024 * 1024
+  if (file.size > maxSize) {
+    throw new BadRequestException('File too large (max 50MB)')
+  }
+
+  // Type check (whitelist: PDF, DWG, DOCX, XLSX, ZIP)
+  const allowedTypes = [
+    'application/pdf',
+    'application/vnd.dwg',
+    'application/vnd.openxmlformats-officedocument.wordprocessingml.document',
+    'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet',
+    'application/zip'
+  ]
+  if (!allowedTypes.includes(file.mimetype)) {
+    throw new BadRequestException('Invalid file type')
+  }
+
+  // Extension check
+  const allowedExtensions = ['.pdf', '.dwg', '.docx', '.xlsx', '.zip']
+  const extension = path.extname(file.originalname).toLowerCase()
+  if (!allowedExtensions.includes(extension)) {
+    throw new BadRequestException('Invalid file extension')
+  }
+
+  return true
+}
+```
+
+#### Verification Steps
+- [ ] All user inputs validated with Zod (frontend) + class-validator (backend)
+- [ ] File uploads restricted (50MB max, whitelist types)
+- [ ] No direct use of user input in queries
+- [ ] Whitelist validation (not blacklist)
+- [ ] Error messages don't leak sensitive info
+
+### 3. SQL Injection Prevention
+
+#### FAIL: NEVER Concatenate SQL
+```typescript
+// DANGEROUS - SQL Injection vulnerability
+const query = `SELECT * FROM correspondences WHERE uuid = '${correspondenceUuid}'`
+await this.connection.query(query)
+```
+
+#### PASS: ALWAYS Use TypeORM Parameterized Queries
+```typescript
+// Safe - TypeORM parameterized query
+const correspondence = await this.correspondenceRepository.findOne({
+  where: { publicId: correspondenceUuid }
+})
+
+// Or with QueryBuilder
+const result = await this.correspondenceRepository
+  .createQueryBuilder('c')
+  .where('c.publicId = :uuid', { uuid: correspondenceUuid })
+  .getOne()
+```
+
+#### Verification Steps
+- [ ] All database queries use TypeORM parameterized queries
+- [ ] No string concatenation in SQL
+- [ ] TypeORM query builder used correctly
+- [ ] Schema verified before writing queries (ADR-009)
+
+### 4. Authentication & Authorization (ADR-016)
+
+#### JWT Token Handling
+```typescript
+// FAIL: WRONG: localStorage (vulnerable to XSS)
+localStorage.setItem('token', token)
+
+// PASS: CORRECT: httpOnly cookies
+response.setHeader('Set-Cookie',
+  `token=${token}; HttpOnly; Secure; SameSite=Strict; Max-Age=3600`
+)
+```
+
+#### Authorization Checks (CASL)
+```typescript
+// Controller with CASL guard
+@Post()
+@UseGuards(JwtAuthGuard, RolesGuard, AbilitiesGuard)
+@CheckAbilities({ action: 'create', subject: 'Correspondence' })
+async create(@Body() dto: CreateCorrespondenceDto, @Request() req) {
+  // Service logic
+}
+```
+
+#### RBAC Matrix (ADR-016)
+- [ ] 4-Level RBAC matrix implemented (Admin, Manager, User, Viewer)
+- [ ] CASL AbilityFactory configured with correct permissions
+- [ ] JwtAuthGuard on all protected routes
+- [ ] RolesGuard for role-based access
+- [ ] AuditLogInterceptor on all mutation endpoints
+
+#### Verification Steps
+- [ ] Tokens stored in httpOnly cookies (not localStorage)
+- [ ] Authorization checks before sensitive operations
+- [ ] CASL abilities configured correctly
+- [ ] Role-based access control implemented
+- [ ] Session management secure
+
+### 5. XSS Prevention
+
+#### Sanitize HTML
+```typescript
+import DOMPurify from 'isomorphic-dompurify'
+
+// ALWAYS sanitize user-provided HTML
+function renderUserContent(html: string) {
+  const clean = DOMPurify.sanitize(html, {
+    ALLOWED_TAGS: ['b', 'i', 'em', 'strong', 'p'],
+    ALLOWED_ATTR: []
+  })
+  return <div dangerouslySetInnerHTML={{ __html: clean }} />
+}
+```
+
+#### Content Security Policy (Next.js)
+```typescript
+// next.config.js
+const securityHeaders = [
+  {
+    key: 'Content-Security-Policy',
+    value: `
+      default-src 'self';
+      script-src 'self' 'unsafe-eval' 'unsafe-inline';
+      style-src 'self' 'unsafe-inline';
+      img-src 'self' data: https:;
+      font-src 'self';
+      connect-src 'self' http://localhost:3001 https://192.168.10.8;
+    `.replace(/\s{2,}/g, ' ').trim()
+  }
+]
+```
+
+#### Verification Steps
+- [ ] User-provided HTML sanitized
+- [ ] CSP headers configured
+- [ ] No unvalidated dynamic content rendering
+- [ ] React's built-in XSS protection used
+
+### 6. CSRF Protection
+
+#### CSRF Tokens
+```typescript
+import { csrf } from '@/lib/csrf'
+
+export async function POST(request: Request) {
+  const token = request.headers.get('X-CSRF-Token')
+
+  if (!csrf.verify(token)) {
+    return NextResponse.json(
+      { error: 'Invalid CSRF token' },
+      { status: 403 }
+    )
+  }
+
+  // Process request
+}
+```
+
+#### SameSite Cookies
+```typescript
+response.setHeader('Set-Cookie',
+  `session=${sessionId}; HttpOnly; Secure; SameSite=Strict`
+)
+```
+
+#### Verification Steps
+- [ ] CSRF tokens on state-changing operations
+- [ ] SameSite=Strict on all cookies
+- [ ] Double-submit cookie pattern implemented
+
+### 7. Rate Limiting (ADR-016)
+
+#### API Rate Limiting
+```typescript
+import { ThrottlerGuard } from '@nestjs/throttler'
+
+// Apply to auth endpoints
+@UseGuards(ThrottlerGuard)
+@Throttle({ default: { limit: 10, ttl: 60000 } })
+async login(@Body() dto: LoginDto) {
+  // Login logic
+}
+```
+
+#### Expensive Operations
+```typescript
+// Aggressive rate limiting for AI endpoints
+@Throttle({ default: { limit: 5, ttl: 60000 } })
+async extractMetadata(@Body() dto: ExtractMetadataDto) {
+  // AI extraction logic
+}
+```
+
+#### Verification Steps
+- [ ] Rate limiting on all auth endpoints (ADR-016)
+- [ ] Rate limiting on AI endpoints (ADR-018/023)
+- [ ] IP-based rate limiting
+- [ ] User-based rate limiting (authenticated)
+
+### 8. Sensitive Data Exposure
+
+#### Logging
+```typescript
+// FAIL: WRONG: Logging sensitive data
+this.logger.log('User login:', { email, password })
+this.logger.log('Payment:', { cardNumber, cvv })
+
+// PASS: CORRECT: Redact sensitive data
+this.logger.log('User login:', { email, userId })
+this.logger.log('Payment:', { last4: card.last4, userId })
+```
+
+#### Error Messages (ADR-007)
+```typescript
+// FAIL: WRONG: Exposing internal details
+catch (error) {
+  return { error: error.message, stack: error.stack }
+}
+
+// PASS: CORRECT: Generic error messages
+catch (error) {
+  this.logger.error('Internal error:', error)
+  throw new BadRequestException('An error occurred. Please try again.')
+}
+```
+
+#### Verification Steps
+- [ ] No passwords, tokens, or secrets in logs
+- [ ] Error messages generic for users
+- [ ] Detailed errors only in server logs
+- [ ] No stack traces exposed to users
+
+### 9. AI Boundary Enforcement (ADR-018/023)
+
+#### FAIL: NEVER Do This
+```typescript
+// Direct AI access - FORBIDDEN
+import ollama from 'ollama'
+const response = await ollama.chat({ model: 'gemma4', messages })
+
+// Direct Qdrant access - FORBIDDEN
+import { QdrantClient } from '@qdrant/js-client-rest'
+const client = new QdrantClient({ url: 'http://localhost:6333' })
+```
+
+#### PASS: ALWAYS Do This
+```typescript
+// AI via DMS API only
+const response = await fetch('http://localhost:3001/api/ai/extract-metadata', {
+  method: 'POST',
+  headers: { 'Content-Type': 'application/json' },
+  body: JSON.stringify({ documentId })
+})
+
+// Qdrant via DMS API only
+const response = await fetch('http://localhost:3001/api/ai/search', {
+  method: 'POST',
+  headers: { 'Content-Type': 'application/json' },
+  body: JSON.stringify({ query, projectPublicId })
+})
+```
+
+#### Verification Steps
+- [ ] AI processing on Admin Desktop only (Desk-5439)
+- [ ] No direct Ollama calls from backend/frontend
+- [ ] No direct Qdrant calls from backend/frontend
+- [ ] All AI interactions via DMS API endpoints
+- [ ] AI audit logging implemented (ADR-020)
+- [ ] Human-in-the-loop validation for AI outputs
+
+### 10. UUID Handling (ADR-019)
+
+#### FAIL: NEVER Do This
+```typescript
+// parseInt on UUID - FORBIDDEN
+const projectId = parseInt(projectUuid) // "0195..." → 19 (WRONG!)
+
+// Number on UUID - FORBIDDEN
+const projectId = Number(projectUuid)
+
+// + operator on UUID - FORBIDDEN
+const projectId = +projectUuid
+
+// id ?? '' fallback - FORBIDDEN
+const value = c.publicId ?? c.id ?? ''
+```
+
+#### PASS: ALWAYS Do This
+```typescript
+// Use UUID string directly
+const projectId = projectUuid // "019505a1-7c3e-7000-8000-abc123def456"
+
+// Backend: findOneByUuid returns entity with publicId
+const project = await this.projectService.findOneByUuid(projectUuid)
+const projectId = project.id // Internal INT for DB operations
+
+// Frontend: use publicId only
+interface ProjectOption {
+  publicId?: string; // No uuid fallback
+  projectName?: string;
+}
+const value = c.publicId // "019505a1-7c3e-7000-8000-abc123def456"
+```
+
+#### Verification Steps
+- [ ] No `parseInt()` on UUID values
+- [ ] No `Number()` on UUID values
+- [ ] No `+` operator on UUID values
+- [ ] No `id ?? ''` fallback patterns
+- [ ] Use `publicId` (string UUID) in API responses
+- [ ] Internal INT `id` marked with `@Exclude()` in entities
+
+### 11. Dependency Security
+
+#### Regular Updates
+```bash
+# Check for vulnerabilities
+pnpm audit
+
+# Fix automatically fixable issues
+pnpm audit fix
+
+# Update dependencies
+pnpm update
+
+# Check for outdated packages
+pnpm outdated
+```
+
+#### Lock Files
+```bash
+# ALWAYS commit lock files
+git add pnpm-lock.yaml
+
+# Use in CI/CD for reproducible builds
+pnpm install --frozen-lockfile
+```
+
+#### Verification Steps
+- [ ] Dependencies up to date
+- [ ] No known vulnerabilities (pnpm audit clean)
+- [ ] Lock files committed
+- [ ] Regular security updates
+
+## Security Testing
+
+### Automated Security Tests
+
+```typescript
+// Test authentication
+test('requires authentication', async () => {
+  const response = await fetch('/api/correspondences')
+  expect(response.status).toBe(401)
+})
+
+// Test authorization
+test('requires admin role', async () => {
+  const response = await fetch('/api/admin/users', {
+    headers: { Authorization: `Bearer ${userToken}` }
+  })
+  expect(response.status).toBe(403)
+})
+
+// Test input validation
+test('rejects invalid input', async () => {
+  const response = await fetch('/api/correspondences', {
+    method: 'POST',
+    body: JSON.stringify({ subject: '', recipientId: 'invalid' })
+  })
+  expect(response.status).toBe(400)
+})
+
+// Test rate limiting
+test('enforces rate limits', async () => {
+  const requests = Array(11).fill(null).map(() =>
+    fetch('/api/auth/login', { method: 'POST' })
+  )
+
+  const responses = await Promise.all(requests)
+  const tooManyRequests = responses.filter(r => r.status === 429)
+
+  expect(tooManyRequests.length).toBeGreaterThan(0)
+})
+```
+
+## Pre-Deployment Security Checklist
+
+Before ANY production deployment:
+
+- [ ] **Secrets**: No hardcoded secrets, all in env vars
+- [ ] **Input Validation**: All user inputs validated (Zod + class-validator)
+- [ ] **SQL Injection**: All queries parameterized (TypeORM)
+- [ ] **XSS**: User content sanitized
+- [ ] **CSRF**: Protection enabled
+- [ ] **Authentication**: Proper token handling (httpOnly cookies)
+- [ ] **Authorization**: RBAC + CASL checks in place
+- [ ] **Rate Limiting**: Enabled on auth and AI endpoints
+- [ ] **HTTPS**: Enforced in production
+- [ ] **Security Headers**: CSP, X-Frame-Options configured
+- [ ] **Error Handling**: No sensitive data in errors (ADR-007)
+- [ ] **Logging**: No sensitive data logged
+- [ ] **Dependencies**: Up to date, no vulnerabilities
+- [ ] **UUID Handling**: No parseInt/Number/+ on UUID (ADR-019)
+- [ ] **AI Boundary**: AI via DMS API only (ADR-018/023)
+- [ ] **File Uploads**: Validated (50MB max, whitelist types)
+- [ ] **AI Audit**: All AI interactions logged (ADR-020)
+
+## Resources
+
+- [OWASP Top 10](https://owasp.org/www-project-top-ten/)
+- [NestJS Security](https://docs.nestjs.com/security)
+- [Next.js Security](https://nextjs.org/docs/security)
+- [ADR-016 Security Authentication](../../specs/06-Decision-Records/ADR-016-security-authentication.md)
+- [ADR-018 AI Boundary](../../specs/06-Decision-Records/ADR-018-ai-boundary.md)
+- [ADR-019 UUID Strategy](../../specs/06-Decision-Records/ADR-019-hybrid-identifier-strategy.md)
+- [ADR-023 AI Architecture](../../specs/06-Decision-Records/ADR-023-unified-ai-architecture.md)
+
+---
+
+**Remember**: Security is not optional. One vulnerability can compromise the entire platform. When in doubt, err on the side of caution.

.agents/skills/skills.md

@@ -1,8 +1,8 @@
-# 🧠 NAP-DMS Agent Skills (v1.8.9)
+# 🧠 NAP-DMS Agent Skills (v1.9.0)
 
-ไฟล์นี้กำหนดทักษะและความสามารถเฉพาะทางของ Document Intelligence Engine สำหรับโครงการ LCBP3 v1.8.9 เพื่อรักษามาตรฐานสูงสุดด้าน Security และ Data Integrity
+ไฟล์นี้กำหนดทักษะและความสามารถเฉพาะทางของ Document Intelligence Engine สำหรับโครงการ LCBP3 v1.9.0 เพื่อรักษามาตรฐานสูงสุดด้าน Security และ Data Integrity
 
-**Status**: Production Ready | **Last Updated**: 2026-04-22 | **Total Skills**: 20
+**Status**: Production Ready | **Last Updated**: 2026-06-07 | **Total Skills**: 24
 
 > 📌 Shared context for all speckit-\* skills: see [`_LCBP3-CONTEXT.md`](./_LCBP3-CONTEXT.md).
 
@@ -57,28 +57,32 @@
 
 ## 🔄 Skill Dependency Matrix
 
-| Skill                      | Dependencies         | Handoffs To                      | Notes                         |
+| Skill                      | Dependencies         | Handoffs To                              | Notes                         |
-| -------------------------- | -------------------- | -------------------------------- | ----------------------------- |
+| -------------------------- | -------------------- | ---------------------------------------- | ----------------------------- |
-| **speckit-constitution**   | None                 | speckit-specify                  | Project governance foundation |
+| **speckit-constitution**   | None                 | speckit-specify                          | Project governance foundation |
-| **speckit-specify**        | speckit-constitution | speckit-clarify                  | Feature specification         |
+| **speckit-specify**        | speckit-constitution | speckit-clarify                          | Feature specification         |
-| **speckit-clarify**        | speckit-specify      | speckit-plan                     | Resolve ambiguities           |
+| **speckit-clarify**        | speckit-specify      | speckit-plan                             | Resolve ambiguities           |
-| **speckit-plan**           | speckit-clarify      | speckit-tasks, speckit-checklist | Technical design              |
+| **speckit-plan**           | speckit-clarify      | speckit-tasks, speckit-checklist         | Technical design              |
-| **speckit-tasks**          | speckit-plan         | speckit-implement                | Task breakdown                |
+| **speckit-tasks**          | speckit-plan         | speckit-implement                        | Task breakdown                |
-| **speckit-implement**      | speckit-tasks        | speckit-checker                  | Code implementation           |
+| **speckit-implement**      | speckit-tasks        | speckit-checker                          | Code implementation           |
-| **speckit-checker**        | speckit-implement    | speckit-tester                   | Static analysis               |
+| **speckit-checker**        | speckit-implement    | speckit-tester                           | Static analysis               |
-| **speckit-tester**         | speckit-checker      | speckit-reviewer                 | Test execution                |
+| **speckit-tester**         | speckit-checker      | speckit-reviewer                         | Test execution                |
-| **speckit-reviewer**       | speckit-tester       | speckit-validate                 | Code review                   |
+| **speckit-reviewer**       | speckit-tester       | speckit-validate                         | Code review                   |
-| **speckit-validate**       | speckit-reviewer     | None                             | Requirements validation       |
+| **speckit-validate**       | speckit-reviewer     | None                                     | Requirements validation       |
-| **speckit-analyze**        | speckit-tasks        | None                             | Cross-artifact consistency    |
+| **speckit-analyze**        | speckit-tasks        | None                                     | Cross-artifact consistency    |
-| **speckit-migrate**        | None                 | speckit-plan                     | Legacy code import            |
+| **speckit-migrate**        | None                 | speckit-plan                             | Legacy code import            |
-| **speckit-quizme**         | speckit-specify      | speckit-plan                     | Logic validation              |
+| **speckit-quizme**         | speckit-specify      | speckit-plan                             | Logic validation              |
-| **speckit-diff**           | None                 | speckit-plan                     | Version comparison            |
+| **speckit-diff**           | None                 | speckit-plan                             | Version comparison            |
-| **speckit-status**         | None                 | None                             | Progress tracking             |
+| **speckit-status**         | None                 | None                                     | Progress tracking             |
-| **speckit-taskstoissues**  | speckit-tasks        | None                             | Issue sync                    |
+| **speckit-taskstoissues**  | speckit-tasks        | None                                     | Issue sync                    |
-| **speckit-checklist**      | speckit-plan         | None                             | Requirements validation       |
+| **speckit-checklist**      | speckit-plan         | None                                     | Requirements validation       |
-| **nestjs-best-practices**  | None                 | speckit-implement                | Backend patterns              |
+| **save-memory**            | None                 | None                                     | Session log & memory update   |
-| **next-best-practices**    | None                 | speckit-implement                | Frontend patterns             |
+| **nestjs-best-practices**  | None                 | speckit-implement                        | Backend patterns              |
-| **speckit-security-audit** | None                 | speckit-reviewer                 | Security validation           |
+| **next-best-practices**    | None                 | speckit-implement                        | Frontend patterns             |
+| **speckit-security-audit** | None                 | speckit-reviewer                         | Security validation           |
+| **e2e-testing**            | None                 | speckit-tester                           | Playwright E2E patterns       |
+| **verification-loop**      | None                 | speckit-checker, speckit-tester          | Comprehensive verification    |
+| **security-review**        | None                 | speckit-reviewer, speckit-security-audit | OWASP Top 10 + ADR compliance |
 
 ---
 
@@ -96,8 +100,8 @@
 
 ### Health Metrics
 
-- **Total Skills**: 20 implemented
+- **Total Skills**: 24 implemented
-- **Version Alignment**: v1.8.9 across all skills
+- **Version Alignment**: v1.9.0 across all skills
 - **Template Coverage**: 100% for skills requiring templates
 - **Documentation**: Complete front matter + shared `_LCBP3-CONTEXT.md` appendix
 

.agents/skills/speckit-analyze/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-analyze
 description: Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-tasks
 ---

.agents/skills/speckit-checker/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-checker
 description: Run static analysis tools and aggregate results.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-checklist/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-checklist
 description: Generate a custom checklist for the current feature based on user requirements.
-version: 1.8.9
+version: 1.9.0
 ---
 
 ## Checklist Purpose: "Unit Tests for English"

.agents/skills/speckit-clarify/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-clarify
 description: Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-specify
 handoffs:

.agents/skills/speckit-constitution/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-constitution
 description: Create or update the project constitution from interactive or provided principle inputs, ensuring all dependent templates stay in sync.
-version: 1.8.9
+version: 1.9.0
 handoffs:
   - label: Build Specification
     agent: speckit-specify

.agents/skills/speckit-diff/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-diff
 description: Compare two versions of a spec or plan to highlight changes.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-implement/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-implement
 description: Execute the implementation plan by processing and executing all tasks defined in tasks.md (with Ironclad Anti-Regression Protocols)
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-tasks
 ---

.agents/skills/speckit-migrate/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-migrate
 description: Migrate existing projects into the speckit structure by generating spec.md, plan.md, and tasks.md from existing code.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-plan/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-plan
 description: Execute the implementation planning workflow using the plan template to generate design artifacts.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-specify
 handoffs:

.agents/skills/speckit-quizme/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-quizme
 description: Challenge the specification with Socratic questioning to identify logical gaps, unhandled edge cases, and robustness issues.
-version: 1.8.9
+version: 1.9.0
 handoffs:
   - label: Clarify Spec Requirements
     agent: speckit-clarify

.agents/skills/speckit-reviewer/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-reviewer
 description: Perform code review with actionable feedback and suggestions.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-security-audit/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-security-audit
 description: Perform a security-focused audit of the codebase against OWASP Top 10, CASL authorization, and LCBP3-DMS security requirements.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-checker
 ---

.agents/skills/speckit-specify/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-specify
 description: Create or update the feature specification from a natural language feature description.
-version: 1.8.9
+version: 1.9.0
 handoffs:
   - label: Build Technical Plan
     agent: speckit-plan

.agents/skills/speckit-status/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-status
 description: Display a dashboard showing feature status, completion percentage, and blockers.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-tasks/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-tasks
 description: Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-plan
 handoffs:

.agents/skills/speckit-taskstoissues/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-taskstoissues
 description: Convert existing tasks into actionable, dependency-ordered issues for the feature based on available design artifacts.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-tasks
 tools: ['github/github-mcp-server/issue_write']

.agents/skills/speckit-tester/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-tester
 description: Execute tests, measure coverage, and report results.
-version: 1.8.9
+version: 1.9.0
 depends-on: []
 ---
 

.agents/skills/speckit-validate/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: speckit-validate
 description: Validate that implementation matches specification requirements.
-version: 1.8.9
+version: 1.9.0
 depends-on:
   - speckit-implement
 ---

.agents/skills/verification-loop/SKILL.md

@@ -0,0 +1,224 @@
+---
+name: verification-loop
+description: A comprehensive verification system for LCBP3-DMS development sessions with build, type check, lint, test, security scan, and diff review phases.
+version: 1.9.0
+scope: verification
+depends-on: []
+handoffs-to: [speckit-checker, speckit-tester]
+user-invocable: true
+---
+
+# Verification Loop Skill
+
+A comprehensive verification system for LCBP3-DMS development sessions.
+
+## LCBP3 Context
+
+See [`_LCBP3-CONTEXT.md`](../_LCBP3-CONTEXT.md) for project-specific verification requirements:
+- Backend: NestJS with TypeScript strict mode
+- Frontend: Next.js with TypeScript strict mode
+- Package manager: pnpm
+- Coverage goals: Backend 70%+, Business Logic 80%+
+- Security: ADR-016, ADR-018, ADR-019, ADR-023 compliance
+
+## When to Use
+
+Invoke this skill:
+- After completing a feature or significant code change
+- Before creating a PR
+- When you want to ensure quality gates pass
+- After refactoring
+- Before deploying to staging/production
+
+## Verification Phases
+
+### Phase 1: Build Verification
+
+```bash
+# Backend build
+cd backend
+pnpm build 2>&1 | tail -20
+
+# Frontend build
+cd frontend
+pnpm build 2>&1 | tail -20
+```
+
+If build fails, STOP and fix before continuing.
+
+### Phase 2: Type Check
+
+```bash
+# Backend TypeScript
+cd backend
+pnpm typecheck 2>&1 | head -30
+
+# Frontend TypeScript
+cd frontend
+pnpm typecheck 2>&1 | head -30
+```
+
+Report all type errors. Fix critical ones before continuing.
+
+### Phase 3: Lint Check
+
+```bash
+# Backend lint
+cd backend
+pnpm lint 2>&1 | head -30
+
+# Frontend lint
+cd frontend
+pnpm lint 2>&1 | head -30
+```
+
+### Phase 4: Test Suite
+
+```bash
+# Backend tests with coverage
+cd backend
+pnpm test -- --coverage 2>&1 | tail -50
+
+# Frontend unit tests
+cd frontend
+pnpm test 2>&1 | tail -50
+
+# Frontend E2E tests (if applicable)
+cd frontend
+npx playwright test 2>&1 | tail -50
+```
+
+Report:
+- Total tests: X
+- Passed: X
+- Failed: X
+- Coverage: X%
+
+### Phase 5: Security Scan
+
+```bash
+# Check for hardcoded secrets
+grep -rn "sk-" --include="*.ts" --include="*.tsx" . 2>/dev/null | head -10
+grep -rn "api_key" --include="*.ts" --include="*.tsx" . 2>/dev/null | head -10
+grep -rn "password" --include="*.ts" --include="*.tsx" . 2>/dev/null | head -10
+
+# Check for console.log (forbidden in committed code)
+grep -rn "console.log" --include="*.ts" --include="*.tsx" backend/src/ frontend/src/ 2>/dev/null | head -10
+
+# Check for any types (forbidden)
+grep -rn ": any" --include="*.ts" --include="*.tsx" backend/src/ frontend/src/ 2>/dev/null | head -10
+
+# Check for parseInt on UUID (ADR-019 violation)
+grep -rn "parseInt(" --include="*.ts" --include="*.tsx" backend/src/ frontend/src/ 2>/dev/null | head -10
+```
+
+### Phase 6: ADR Compliance Check
+
+```bash
+# Check for id ?? '' fallback (ADR-019 violation)
+grep -rn "id ?? ''" --include="*.ts" --include="*.tsx" frontend/src/ 2>/dev/null | head -10
+
+# Check for Number() on UUID (ADR-019 violation)
+grep -rn "Number(" --include="*.ts" --include="*.tsx" frontend/src/ 2>/dev/null | head -10
+
+# Check for + operator on UUID (ADR-019 violation)
+grep -rn "+ publicId\|+ id" --include="*.ts" --include="*.tsx" frontend/src/ 2>/dev/null | head -10
+```
+
+### Phase 7: Diff Review
+
+```bash
+# Show what changed
+git diff --stat
+git diff HEAD~1 --name-only
+
+# Show detailed changes
+git diff
+```
+
+Review each changed file for:
+- Unintended changes
+- Missing error handling (ADR-007)
+- Potential edge cases
+- UUID handling (ADR-019)
+- Security vulnerabilities (ADR-016)
+- AI boundary violations (ADR-018/023)
+
+## Output Format
+
+After running all phases, produce a verification report:
+
+```
+VERIFICATION REPORT
+==================
+
+Build:     [PASS/FAIL]
+Types:     [PASS/FAIL] (X errors)
+Lint:      [PASS/FAIL] (X warnings)
+Tests:     [PASS/FAIL] (X/Y passed, Z% coverage)
+Security:  [PASS/FAIL] (X issues)
+ADR:       [PASS/FAIL] (X violations)
+Diff:      [X files changed]
+
+Overall:   [READY/NOT READY] for PR
+
+Issues to Fix:
+1. ...
+2. ...
+```
+
+## Continuous Mode
+
+For long sessions, run verification every 15 minutes or after major changes:
+
+```markdown
+Set a mental checkpoint:
+- After completing each function
+- After finishing a component
+- Before moving to next task
+
+Run: /verify
+```
+
+## Integration with LCBP3 Skills
+
+This skill complements:
+- **speckit-checker**: Runs static analysis (lint, typecheck)
+- **speckit-tester**: Runs tests with coverage verification
+- **speckit-security-audit**: Performs security review against OWASP Top 10
+
+This skill provides a unified verification loop that combines all checks into a single report.
+
+## LCBP3-Specific Checks
+
+### Tier 1 — CRITICAL (CI BLOCKER)
+
+- [ ] **Security**: Auth, RBAC, Validation implemented
+- [ ] **UUID Strategy (ADR-019)**: No `parseInt` / `Number` / `+` on UUID
+- [ ] **Database correctness**: Schema verified before writing queries
+- [ ] **File upload security**: ClamAV + whitelist implemented
+- [ ] **AI validation boundary (ADR-018/023)**: AI via DMS API only
+- [ ] **Error handling (ADR-007)**: Layered error classification
+- [ ] **Forbidden patterns**: Zero `any`, zero `console.log`, UUID misuse
+
+### Tier 2 — IMPORTANT (CODE REVIEW)
+
+- [ ] **Architecture patterns**: Thin controller, business logic in service
+- [ ] **Test coverage**: 80%+ business logic, 70%+ backend overall
+- [ ] **Cache invalidation**: Implemented when data modified
+- [ ] **Naming conventions**: Follow domain terminology
+
+### Tier 3 — GUIDELINES
+
+- [ ] **Code style**: Prettier formatting
+- [ ] **Comment completeness**: Thai comments, JSDoc on public methods
+- [ ] **Minor optimizations**: Performance improvements where applicable
+
+## References
+
+- LCBP3 AGENTS.md: `AGENTS.md` (repo root)
+- ADR-007 Error Handling: `specs/06-Decision-Records/ADR-007-error-handling-strategy.md`
+- ADR-016 Security: `specs/06-Decision-Records/ADR-016-security-authentication.md`
+- ADR-019 UUID: `specs/06-Decision-Records/ADR-019-hybrid-identifier-strategy.md`
+- ADR-018 AI Boundary: `specs/06-Decision-Records/ADR-018-ai-boundary.md`
+- ADR-023 AI Architecture: `specs/06-Decision-Records/ADR-023-unified-ai-architecture.md`

.agents/tests/skill-integration.test.js

@@ -15,220 +15,249 @@ const WORKFLOWS_DIR = path.join(BASE_DIR, '.windsurf', 'workflows');
 
 // Test utilities
 class SkillTestSuite {
-    constructor() {
+  constructor() {
-        this.results = {
+    this.results = {
-            passed: 0,
+      passed: 0,
-            failed: 0,
+      failed: 0,
-            errors: []
+      errors: [],
-        };
+    };
+  }
+
+  log(message, type = 'info') {
+    const colors = {
+      info: '\x1b[36m', // Cyan
+      pass: '\x1b[32m', // Green
+      fail: '\x1b[31m', // Red
+      warn: '\x1b[33m', // Yellow
+      reset: '\x1b[0m',
+    };
+
+    const color = colors[type] || colors.info;
+    console.log(`${color}${message}${colors.reset}`);
+  }
+
+  assert(condition, message) {
+    if (condition) {
+      this.log(`  PASS: ${message}`, 'pass');
+      this.results.passed++;
+      return true;
+    } else {
+      this.log(`  FAIL: ${message}`, 'fail');
+      this.results.failed++;
+      this.results.errors.push(message);
+      return false;
+    }
+  }
+
+  testDirectoryExists(dirPath, description) {
+    const exists = fs.existsSync(dirPath);
+    this.assert(exists, `${description} exists at ${dirPath}`);
+    return exists;
+  }
+
+  testFileExists(filePath, description) {
+    const exists = fs.existsSync(filePath);
+    this.assert(exists, `${description} exists at ${filePath}`);
+    return exists;
+  }
+
+  testFileContent(filePath, pattern, description) {
+    if (!fs.existsSync(filePath)) {
+      this.assert(false, `${description} - file not found: ${filePath}`);
+      return false;
     }
 
-    log(message, type = 'info') {
+    try {
-        const colors = {
+      const content = fs.readFileSync(filePath, 'utf8');
-            info: '\x1b[36m',    // Cyan
+      const matches = content.match(pattern);
-            pass: '\x1b[32m',    // Green
+      this.assert(matches !== null, `${description} - pattern found in ${filePath}`);
-            fail: '\x1b[31m',    // Red
+      return matches !== null;
-            warn: '\x1b[33m',    // Yellow
+    } catch (error) {
-            reset: '\x1b[0m'
+      this.assert(false, `${description} - error reading file: ${error.message}`);
-        };
+      return false;
-        
-        const color = colors[type] || colors.info;
-        console.log(`${color}${message}${colors.reset}`);
     }
+  }
 
-    assert(condition, message) {
+  runScript(scriptPath, description) {
-        if (condition) {
+    try {
-            this.log(`  PASS: ${message}`, 'pass');
+      const output = execSync(scriptPath, { encoding: 'utf8', cwd: BASE_DIR });
-            this.results.passed++;
+      this.log(`  SCRIPT: ${description} executed successfully`, 'pass');
-            return true;
+      return { success: true, output };
-        } else {
+    } catch (error) {
-            this.log(`  FAIL: ${message}`, 'fail');
+      this.log(`  SCRIPT: ${description} failed - ${error.message}`, 'fail');
-            this.results.failed++;
+      this.results.failed++;
-            this.results.errors.push(message);
+      this.results.errors.push(`${description}: ${error.message}`);
-            return false;
+      return { success: false, error: error.message };
-        }
-    }
-
-    testDirectoryExists(dirPath, description) {
-        const exists = fs.existsSync(dirPath);
-        this.assert(exists, `${description} exists at ${dirPath}`);
-        return exists;
-    }
-
-    testFileExists(filePath, description) {
-        const exists = fs.existsSync(filePath);
-        this.assert(exists, `${description} exists at ${filePath}`);
-        return exists;
-    }
-
-    testFileContent(filePath, pattern, description) {
-        if (!fs.existsSync(filePath)) {
-            this.assert(false, `${description} - file not found: ${filePath}`);
-            return false;
-        }
-        
-        try {
-            const content = fs.readFileSync(filePath, 'utf8');
-            const matches = content.match(pattern);
-            this.assert(matches !== null, `${description} - pattern found in ${filePath}`);
-            return matches !== null;
-        } catch (error) {
-            this.assert(false, `${description} - error reading file: ${error.message}`);
-            return false;
-        }
-    }
-
-    runScript(scriptPath, description) {
-        try {
-            const output = execSync(scriptPath, { encoding: 'utf8', cwd: BASE_DIR });
-            this.log(`  SCRIPT: ${description} executed successfully`, 'pass');
-            return { success: true, output };
-        } catch (error) {
-            this.log(`  SCRIPT: ${description} failed - ${error.message}`, 'fail');
-            this.results.failed++;
-            this.results.errors.push(`${description}: ${error.message}`);
-            return { success: false, error: error.message };
-        }
     }
+  }
 }
 
 // Test suite implementation
 const testSuite = new SkillTestSuite();
 
 function runAllTests() {
-    testSuite.log('=== .agents Integration Test Suite ===', 'info');
+  testSuite.log('=== .agents Integration Test Suite ===', 'info');
-    testSuite.log(`Base directory: ${BASE_DIR}`, 'info');
+  testSuite.log(`Base directory: ${BASE_DIR}`, 'info');
-    testSuite.log(`Started: ${new Date().toISOString()}`, 'info');
+  testSuite.log(`Started: ${new Date().toISOString()}`, 'info');
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 1: Directory Structure
+  // Test 1: Directory Structure
-    testSuite.log('Test 1: Directory Structure', 'info');
+  testSuite.log('Test 1: Directory Structure', 'info');
-    testSuite.testDirectoryExists(AGENTS_DIR, '.agents directory');
+  testSuite.testDirectoryExists(AGENTS_DIR, '.agents directory');
-    testSuite.testDirectoryExists(SKILLS_DIR, 'skills directory');
+  testSuite.testDirectoryExists(SKILLS_DIR, 'skills directory');
-    testSuite.testDirectoryExists(WORKFLOWS_DIR, 'workflows directory');
+  testSuite.testDirectoryExists(WORKFLOWS_DIR, 'workflows directory');
-    testSuite.testDirectoryExists(path.join(AGENTS_DIR, 'scripts'), 'scripts directory');
+  testSuite.testDirectoryExists(path.join(AGENTS_DIR, 'scripts'), 'scripts directory');
-    testSuite.testDirectoryExists(path.join(AGENTS_DIR, 'rules'), 'rules directory');
+  testSuite.testDirectoryExists(path.join(AGENTS_DIR, 'rules'), 'rules directory');
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 2: Core Files
+  // Test 2: Core Files
-    testSuite.log('Test 2: Core Files', 'info');
+  testSuite.log('Test 2: Core Files', 'info');
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'README.md'), 'README.md');
+  testSuite.testFileExists(path.join(AGENTS_DIR, 'README.md'), 'README.md');
-    testSuite.testFileExists(path.join(SKILLS_DIR, 'VERSION'), 'skills VERSION file');
+  testSuite.testFileExists(path.join(SKILLS_DIR, 'VERSION'), 'skills VERSION file');
-    testSuite.testFileExists(path.join(SKILLS_DIR, 'skills.md'), 'skills.md documentation');
+  testSuite.testFileExists(path.join(SKILLS_DIR, 'skills.md'), 'skills.md documentation');
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 3: Script Files
+  // Test 3: Script Files
-    testSuite.log('Test 3: Validation Scripts', 'info');
+  testSuite.log('Test 3: Validation Scripts', 'info');
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'bash', 'validate-versions.sh'), 'bash validate-versions.sh');
+  testSuite.testFileExists(
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'bash', 'audit-skills.sh'), 'bash audit-skills.sh');
+    path.join(AGENTS_DIR, 'scripts', 'bash', 'validate-versions.sh'),
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'bash', 'sync-workflows.sh'), 'bash sync-workflows.sh');
+    'bash validate-versions.sh'
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'powershell', 'validate-versions.ps1'), 'powershell validate-versions.ps1');
+  );
-    testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'powershell', 'audit-skills.ps1'), 'powershell audit-skills.ps1');
+  testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'bash', 'audit-skills.sh'), 'bash audit-skills.sh');
-    testSuite.log('');
+  testSuite.testFileExists(path.join(AGENTS_DIR, 'scripts', 'bash', 'sync-workflows.sh'), 'bash sync-workflows.sh');
+  testSuite.testFileExists(
+    path.join(AGENTS_DIR, 'scripts', 'powershell', 'validate-versions.ps1'),
+    'powershell validate-versions.ps1'
+  );
+  testSuite.testFileExists(
+    path.join(AGENTS_DIR, 'scripts', 'powershell', 'audit-skills.ps1'),
+    'powershell audit-skills.ps1'
+  );
+  testSuite.log('');
 
-    // Test 4: Version Consistency
+  // Test 4: Version Consistency
-    testSuite.log('Test 4: Version Consistency', 'info');
+  testSuite.log('Test 4: Version Consistency', 'info');
-    testSuite.testFileContent(path.join(AGENTS_DIR, 'README.md'), /v1\.8\.6/, 'README.md version');
+  testSuite.testFileContent(path.join(AGENTS_DIR, 'README.md'), /v1\.8\.6/, 'README.md version');
-    testSuite.testFileContent(path.join(SKILLS_DIR, 'VERSION'), /version: 1\.8\.6/, 'skills VERSION file');
+  testSuite.testFileContent(path.join(SKILLS_DIR, 'VERSION'), /version: 1\.8\.6/, 'skills VERSION file');
-    testSuite.testFileContent(path.join(SKILLS_DIR, 'skills.md'), /v1\.8\.6/, 'skills.md version');
+  testSuite.testFileContent(path.join(SKILLS_DIR, 'skills.md'), /v1\.8\.6/, 'skills.md version');
-    testSuite.testFileContent(path.join(AGENTS_DIR, 'rules', '00-project-context.md'), /v1\.8\.6/, 'project context version');
+  testSuite.testFileContent(
-    testSuite.log('');
+    path.join(AGENTS_DIR, 'rules', '00-project-context.md'),
+    /v1\.8\.6/,
+    'project context version'
+  );
+  testSuite.log('');
 
-    // Test 5: Skills Structure
+  // Test 5: Skills Structure
-    testSuite.log('Test 5: Skills Structure', 'info');
+  testSuite.log('Test 5: Skills Structure', 'info');
-    const skillDirs = fs.readdirSync(SKILLS_DIR).filter(item => {
+  const skillDirs = fs.readdirSync(SKILLS_DIR).filter((item) => {
-        const itemPath = path.join(SKILLS_DIR, item);
+    const itemPath = path.join(SKILLS_DIR, item);
-        return fs.statSync(itemPath).isDirectory() && item.startsWith('speckit-') || item === 'nestjs-best-practices' || item === 'next-best-practices';
+    return (
-    });
+      (fs.statSync(itemPath).isDirectory() && item.startsWith('speckit-')) ||
+      item === 'nestjs-best-practices' ||
+      item === 'next-best-practices'
+    );
+  });
 
-    testSuite.assert(skillDirs.length >= 20, `Found at least 20 skill directories (found ${skillDirs.length})`);
+  testSuite.assert(skillDirs.length >= 20, `Found at least 20 skill directories (found ${skillDirs.length})`);
 
-    // Test a few key skills
+  // Test a few key skills
-    const keySkills = ['speckit-plan', 'speckit-implement', 'speckit-specify', 'speckit-validate'];
+  const keySkills = ['speckit-plan', 'speckit-implement', 'speckit-specify', 'speckit-validate'];
-    keySkills.forEach(skill => {
+  keySkills.forEach((skill) => {
-        const skillPath = path.join(SKILLS_DIR, skill);
+    const skillPath = path.join(SKILLS_DIR, skill);
-        const skillMdPath = path.join(skillPath, 'SKILL.md');
+    const skillMdPath = path.join(skillPath, 'SKILL.md');
-        testSuite.testDirectoryExists(skillPath, `${skill} directory`);
+    testSuite.testDirectoryExists(skillPath, `${skill} directory`);
-        testSuite.testFileExists(skillMdPath, `${skill} SKILL.md`);
+    testSuite.testFileExists(skillMdPath, `${skill} SKILL.md`);
 
-        if (fs.existsSync(skillMdPath)) {
+    if (fs.existsSync(skillMdPath)) {
-            testSuite.testFileContent(skillMdPath, /^name:/, `${skill} has name field`);
+      testSuite.testFileContent(skillMdPath, /^name:/, `${skill} has name field`);
-            testSuite.testFileContent(skillMdPath, /^description:/, `${skill} has description field`);
+      testSuite.testFileContent(skillMdPath, /^description:/, `${skill} has description field`);
-            testSuite.testFileContent(skillMdPath, /^version:/, `${skill} has version field`);
+      testSuite.testFileContent(skillMdPath, /^version:/, `${skill} has version field`);
-            testSuite.testFileContent(skillMdPath, /^## Role$/, `${skill} has Role section`);
+      testSuite.testFileContent(skillMdPath, /^## Role$/, `${skill} has Role section`);
-            testSuite.testFileContent(skillMdPath, /^## Task$/, `${skill} has Task section`);
+      testSuite.testFileContent(skillMdPath, /^## Task$/, `${skill} has Task section`);
-        }
+    }
-    });
+  });
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 6: Workflows Structure
+  // Test 6: Workflows Structure
-    testSuite.log('Test 6: Workflows Structure', 'info');
+  testSuite.log('Test 6: Workflows Structure', 'info');
-    const workflowFiles = fs.readdirSync(WORKFLOWS_DIR).filter(item => item.endsWith('.md'));
+  const workflowFiles = fs.readdirSync(WORKFLOWS_DIR).filter((item) => item.endsWith('.md'));
-    testSuite.assert(workflowFiles.length >= 20, `Found at least 20 workflow files (found ${workflowFiles.length})`);
+  testSuite.assert(workflowFiles.length >= 20, `Found at least 20 workflow files (found ${workflowFiles.length})`);
 
-    // Test key workflows
+  // Test key workflows
-    const keyWorkflows = ['00-speckit.all.md', '02-speckit.specify.md', '04-speckit.plan.md', '07-speckit.implement.md'];
+  const keyWorkflows = ['00-speckit.all.md', '02-speckit.specify.md', '04-speckit.plan.md', '07-speckit.implement.md'];
-    keyWorkflows.forEach(workflow => {
+  keyWorkflows.forEach((workflow) => {
-        const workflowPath = path.join(WORKFLOWS_DIR, workflow);
+    const workflowPath = path.join(WORKFLOWS_DIR, workflow);
-        testSuite.testFileExists(workflowPath, `${workflow} file`);
+    testSuite.testFileExists(workflowPath, `${workflow} file`);
-    });
+  });
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 7: Rules Structure
+  // Test 7: Rules Structure
-    testSuite.log('Test 7: Rules Structure', 'info');
+  testSuite.log('Test 7: Rules Structure', 'info');
-    const rulesDir = path.join(AGENTS_DIR, 'rules');
+  const rulesDir = path.join(AGENTS_DIR, 'rules');
-    const ruleFiles = fs.readdirSync(rulesDir).filter(item => item.endsWith('.md'));
+  const ruleFiles = fs.readdirSync(rulesDir).filter((item) => item.endsWith('.md'));
-    testSuite.assert(ruleFiles.length >= 10, `Found at least 10 rule files (found ${ruleFiles.length})`);
+  testSuite.assert(ruleFiles.length >= 10, `Found at least 10 rule files (found ${ruleFiles.length})`);
 
-    // Test key rules
+  // Test key rules
-    const keyRules = ['00-project-context.md', '01-adr-019-uuid.md', '02-security.md'];
+  const keyRules = ['00-project-context.md', '01-adr-019-uuid.md', '02-security.md'];
-    keyRules.forEach(rule => {
+  keyRules.forEach((rule) => {
-        const rulePath = path.join(rulesDir, rule);
+    const rulePath = path.join(rulesDir, rule);
-        testSuite.testFileExists(rulePath, `${rule} file`);
+    testSuite.testFileExists(rulePath, `${rule} file`);
-    });
+  });
-    testSuite.log('');
+  testSuite.log('');
 
-    // Test 8: Script Execution (if on Unix-like system)
+  // Test 8: Script Execution (if on Unix-like system)
-    if (process.platform !== 'win32') {
+  if (process.platform !== 'win32') {
-        testSuite.log('Test 8: Script Execution', 'info');
+    testSuite.log('Test 8: Script Execution', 'info');
 
-        // Test version validation script
+    // Test version validation script
-        const versionScript = path.join(AGENTS_DIR, 'scripts', 'bash', 'validate-versions.sh');
+    const versionScript = path.join(AGENTS_DIR, 'scripts', 'bash', 'validate-versions.sh');
-        if (fs.existsSync(versionScript)) {
+    if (fs.existsSync(versionScript)) {
-            try {
+      try {
-                // Make executable
+        // Make executable
-                fs.chmodSync(versionScript, '755');
+        fs.chmodSync(versionScript, '755');
-                testSuite.runScript(versionScript, 'Version validation script');
+        testSuite.runScript(versionScript, 'Version validation script');
-            } catch (error) {
+      } catch (error) {
-                testSuite.log(`  SKIP: Cannot execute version script - ${error.message}`, 'warn');
+        testSuite.log(`  SKIP: Cannot execute version script - ${error.message}`, 'warn');
-            }
+      }
-        }
-        
-        testSuite.log('');
     }
 
-    // Test 9: Documentation Quality
-    testSuite.log('Test 9: Documentation Quality', 'info');
-    testSuite.testFileContent(path.join(AGENTS_DIR, 'README.md'), /## Troubleshooting/, 'README.md has troubleshooting section');
-    testSuite.testFileContent(path.join(SKILLS_DIR, 'skills.md'), /## Skill Dependency Matrix/, 'skills.md has dependency matrix');
-    testSuite.testFileContent(path.join(AGENTS_DIR, 'README.md'), /## Architecture/, 'README.md has architecture section');
     testSuite.log('');
+  }
 
-    // Results Summary
+  // Test 9: Documentation Quality
-    testSuite.log('=== Test Results Summary ===', 'info');
+  testSuite.log('Test 9: Documentation Quality', 'info');
-    testSuite.log(`Passed: ${testSuite.results.passed}`, 'pass');
+  testSuite.testFileContent(
-    testSuite.log(`Failed: ${testSuite.results.failed}`, testSuite.results.failed > 0 ? 'fail' : 'pass');
+    path.join(AGENTS_DIR, 'README.md'),
+    /## Troubleshooting/,
+    'README.md has troubleshooting section'
+  );
+  testSuite.testFileContent(
+    path.join(SKILLS_DIR, 'skills.md'),
+    /## Skill Dependency Matrix/,
+    'skills.md has dependency matrix'
+  );
+  testSuite.testFileContent(
+    path.join(AGENTS_DIR, 'README.md'),
+    /## Architecture/,
+    'README.md has architecture section'
+  );
+  testSuite.log('');
 
-    if (testSuite.results.errors.length > 0) {
+  // Results Summary
-        testSuite.log('Errors:', 'fail');
+  testSuite.log('=== Test Results Summary ===', 'info');
-        testSuite.results.errors.forEach(error => {
+  testSuite.log(`Passed: ${testSuite.results.passed}`, 'pass');
-            testSuite.log(`  - ${error}`, 'fail');
+  testSuite.log(`Failed: ${testSuite.results.failed}`, testSuite.results.failed > 0 ? 'fail' : 'pass');
-        });
-    }
 
-    testSuite.log(`Completed: ${new Date().toISOString()}`, 'info');
+  if (testSuite.results.errors.length > 0) {
+    testSuite.log('Errors:', 'fail');
+    testSuite.results.errors.forEach((error) => {
+      testSuite.log(`  - ${error}`, 'fail');
+    });
+  }
 
-    return testSuite.results.failed === 0;
+  testSuite.log(`Completed: ${new Date().toISOString()}`, 'info');
+
+  return testSuite.results.failed === 0;
 }
 
 // Export for use in other modules
@@ -236,6 +265,6 @@ module.exports = { SkillTestSuite, runAllTests };
 
 // Run tests if called directly
 if (require.main === module) {
-    const success = runAllTests();
+  const success = runAllTests();
-    process.exit(success ? 0 : 1);
+  process.exit(success ? 0 : 1);
 }

.agents/tests/workflow-validation.test.js

@@ -13,216 +13,218 @@ const AGENTS_DIR = path.join(BASE_DIR, '.agents');
 
 // Test utilities
 class WorkflowTestSuite {
-    constructor() {
+  constructor() {
-        this.results = {
+    this.results = {
-            passed: 0,
+      passed: 0,
-            failed: 0,
+      failed: 0,
-            errors: []
+      errors: [],
-        };
+    };
+  }
+
+  log(message, type = 'info') {
+    const colors = {
+      info: '\x1b[36m', // Cyan
+      pass: '\x1b[32m', // Green
+      fail: '\x1b[31m', // Red
+      warn: '\x1b[33m', // Yellow
+      reset: '\x1b[0m',
+    };
+
+    const color = colors[type] || colors.info;
+    console.log(`${color}${message}${colors.reset}`);
+  }
+
+  assert(condition, message) {
+    if (condition) {
+      this.log(`  PASS: ${message}`, 'pass');
+      this.results.passed++;
+      return true;
+    } else {
+      this.log(`  FAIL: ${message}`, 'fail');
+      this.results.failed++;
+      this.results.errors.push(message);
+      return false;
+    }
+  }
+
+  testWorkflowFile(filePath, expectedName) {
+    if (!fs.existsSync(filePath)) {
+      this.assert(false, `Workflow file exists: ${expectedName}`);
+      return false;
     }
 
-    log(message, type = 'info') {
+    try {
-        const colors = {
+      const content = fs.readFileSync(filePath, 'utf8');
-            info: '\x1b[36m',    // Cyan
-            pass: '\x1b[32m',    // Green
-            fail: '\x1b[31m',    // Red
-            warn: '\x1b[33m',    // Yellow
-            reset: '\x1b[0m'
-        };
 
-        const color = colors[type] || colors.info;
+      // Basic structure checks
-        console.log(`${color}${message}${colors.reset}`);
+      this.assert(content.length > 0, `${expectedName} has content`);
+      this.assert(content.includes('#'), `${expectedName} has markdown headers`);
+
+      // Check for workflow-specific patterns
+      if (expectedName.includes('speckit-')) {
+        this.assert(content.includes('speckit-'), `${expectedName} contains speckit reference`);
+      }
+
+      // Check for proper markdown formatting
+      const lines = content.split('\n');
+      const nonEmptyLines = lines.filter((line) => line.trim().length > 0);
+      this.assert(nonEmptyLines.length >= 5, `${expectedName} has sufficient content`);
+
+      return true;
+    } catch (error) {
+      this.assert(false, `${expectedName} - error reading file: ${error.message}`);
+      return false;
+    }
+  }
+
+  validateWorkflowDependency(workflowName, workflowContent) {
+    // Check if workflow references existing skills
+    const skillReferences = workflowContent.match(/@speckit-\w+/g) || [];
+    const skillsDir = path.join(AGENTS_DIR, 'skills');
+
+    for (const skillRef of skillReferences) {
+      const skillName = skillRef.replace('@', '');
+      const skillPath = path.join(skillsDir, skillName);
+
+      if (!fs.existsSync(skillPath)) {
+        this.assert(false, `${workflowName} references non-existent skill: ${skillRef}`);
+        return false;
+      }
     }
 
-    assert(condition, message) {
+    return true;
-        if (condition) {
+  }
-            this.log(`  PASS: ${message}`, 'pass');
-            this.results.passed++;
-            return true;
-        } else {
-            this.log(`  FAIL: ${message}`, 'fail');
-            this.results.failed++;
-            this.results.errors.push(message);
-            return false;
-        }
-    }
-
-    testWorkflowFile(filePath, expectedName) {
-        if (!fs.existsSync(filePath)) {
-            this.assert(false, `Workflow file exists: ${expectedName}`);
-            return false;
-        }
-
-        try {
-            const content = fs.readFileSync(filePath, 'utf8');
-            
-            // Basic structure checks
-            this.assert(content.length > 0, `${expectedName} has content`);
-            this.assert(content.includes('#'), `${expectedName} has markdown headers`);
-            
-            // Check for workflow-specific patterns
-            if (expectedName.includes('speckit-')) {
-                this.assert(content.includes('speckit-'), `${expectedName} contains speckit reference`);
-            }
-            
-            // Check for proper markdown formatting
-            const lines = content.split('\n');
-            const nonEmptyLines = lines.filter(line => line.trim().length > 0);
-            this.assert(nonEmptyLines.length >= 5, `${expectedName} has sufficient content`);
-            
-            return true;
-        } catch (error) {
-            this.assert(false, `${expectedName} - error reading file: ${error.message}`);
-            return false;
-        }
-    }
-
-    validateWorkflowDependency(workflowName, workflowContent) {
-        // Check if workflow references existing skills
-        const skillReferences = workflowContent.match(/@speckit-\w+/g) || [];
-        const skillsDir = path.join(AGENTS_DIR, 'skills');
-        
-        for (const skillRef of skillReferences) {
-            const skillName = skillRef.replace('@', '');
-            const skillPath = path.join(skillsDir, skillName);
-            
-            if (!fs.existsSync(skillPath)) {
-                this.assert(false, `${workflowName} references non-existent skill: ${skillRef}`);
-                return false;
-            }
-        }
-        
-        return true;
-    }
 }
 
 // Expected workflows mapping
 const expectedWorkflows = {
-    '00-speckit.all.md': 'Full pipeline workflow',
+  '00-speckit.all.md': 'Full pipeline workflow',
-    '01-speckit.constitution.md': 'Constitution workflow',
+  '01-speckit.constitution.md': 'Constitution workflow',
-    '02-speckit.specify.md': 'Specification workflow',
+  '02-speckit.specify.md': 'Specification workflow',
-    '03-speckit.clarify.md': 'Clarification workflow',
+  '03-speckit.clarify.md': 'Clarification workflow',
-    '04-speckit.plan.md': 'Planning workflow',
+  '04-speckit.plan.md': 'Planning workflow',
-    '05-speckit.tasks.md': 'Task breakdown workflow',
+  '05-speckit.tasks.md': 'Task breakdown workflow',
-    '06-speckit.analyze.md': 'Analysis workflow',
+  '06-speckit.analyze.md': 'Analysis workflow',
-    '07-speckit.implement.md': 'Implementation workflow',
+  '07-speckit.implement.md': 'Implementation workflow',
-    '08-speckit.checker.md': 'Static analysis workflow',
+  '08-speckit.checker.md': 'Static analysis workflow',
-    '09-speckit.tester.md': 'Testing workflow',
+  '09-speckit.tester.md': 'Testing workflow',
-    '10-speckit.reviewer.md': 'Code review workflow',
+  '10-speckit.reviewer.md': 'Code review workflow',
-    '11-speckit.validate.md': 'Validation workflow',
+  '11-speckit.validate.md': 'Validation workflow',
-    'speckit.prepare.md': 'Preparation workflow',
+  'speckit.prepare.md': 'Preparation workflow',
-    'schema-change.md': 'Schema change workflow',
+  'schema-change.md': 'Schema change workflow',
-    'create-backend-module.md': 'Backend module creation',
+  'create-backend-module.md': 'Backend module creation',
-    'create-frontend-page.md': 'Frontend page creation',
+  'create-frontend-page.md': 'Frontend page creation',
-    'deploy.md': 'Deployment workflow',
+  'deploy.md': 'Deployment workflow',
-    'review.md': 'Code review workflow',
+  'review.md': 'Code review workflow',
-    'util-speckit.checklist.md': 'Checklist utility',
+  'util-speckit.checklist.md': 'Checklist utility',
-    'util-speckit.diff.md': 'Diff utility',
+  'util-speckit.diff.md': 'Diff utility',
-    'util-speckit.migrate.md': 'Migration utility',
+  'util-speckit.migrate.md': 'Migration utility',
-    'util-speckit.quizme.md': 'Quiz utility',
+  'util-speckit.quizme.md': 'Quiz utility',
-    'util-speckit.status.md': 'Status utility',
+  'util-speckit.status.md': 'Status utility',
-    'util-speckit.taskstoissues.md': 'Task to issues utility'
+  'util-speckit.taskstoissues.md': 'Task to issues utility',
 };
 
 // Test suite implementation
 const workflowTestSuite = new WorkflowTestSuite();
 
 function runWorkflowTests() {
-    workflowTestSuite.log('=== Workflow Validation Test Suite ===', 'info');
+  workflowTestSuite.log('=== Workflow Validation Test Suite ===', 'info');
-    workflowTestSuite.log(`Workflows directory: ${WORKFLOWS_DIR}`, 'info');
+  workflowTestSuite.log(`Workflows directory: ${WORKFLOWS_DIR}`, 'info');
-    workflowTestSuite.log(`Started: ${new Date().toISOString()}`, 'info');
+  workflowTestSuite.log(`Started: ${new Date().toISOString()}`, 'info');
-    workflowTestSuite.log('');
+  workflowTestSuite.log('');
 
-    // Test 1: Workflows directory exists
+  // Test 1: Workflows directory exists
-    workflowTestSuite.log('Test 1: Directory Structure', 'info');
+  workflowTestSuite.log('Test 1: Directory Structure', 'info');
-    workflowTestSuite.assert(fs.existsSync(WORKFLOWS_DIR), 'Workflows directory exists');
+  workflowTestSuite.assert(fs.existsSync(WORKFLOWS_DIR), 'Workflows directory exists');
-    workflowTestSuite.log('');
+  workflowTestSuite.log('');
 
-    // Test 2: Expected workflow files exist
+  // Test 2: Expected workflow files exist
-    workflowTestSuite.log('Test 2: Expected Workflow Files', 'info');
+  workflowTestSuite.log('Test 2: Expected Workflow Files', 'info');
-    let foundWorkflows = 0;
+  let foundWorkflows = 0;
 
-    for (const [filename, description] of Object.entries(expectedWorkflows)) {
+  for (const [filename, description] of Object.entries(expectedWorkflows)) {
-        const filePath = path.join(WORKFLOWS_DIR, filename);
+    const filePath = path.join(WORKFLOWS_DIR, filename);
-        workflowTestSuite.testWorkflowFile(filePath, description);
+    workflowTestSuite.testWorkflowFile(filePath, description);
-        if (fs.existsSync(filePath)) {
+    if (fs.existsSync(filePath)) {
-            foundWorkflows++;
+      foundWorkflows++;
-        }
     }
+  }
 
-    workflowTestSuite.assert(foundWorkflows >= 20, `Found at least 20 workflows (found ${foundWorkflows})`);
+  workflowTestSuite.assert(foundWorkflows >= 20, `Found at least 20 workflows (found ${foundWorkflows})`);
-    workflowTestSuite.log('');
+  workflowTestSuite.log('');
 
-    // Test 3: Workflow content validation
+  // Test 3: Workflow content validation
-    workflowTestSuite.log('Test 3: Content Validation', 'info');
+  workflowTestSuite.log('Test 3: Content Validation', 'info');
 
-    for (const [filename, description] of Object.entries(expectedWorkflows)) {
+  for (const [filename, description] of Object.entries(expectedWorkflows)) {
-        const filePath = path.join(WORKFLOWS_DIR, filename);
+    const filePath = path.join(WORKFLOWS_DIR, filename);
 
-        if (fs.existsSync(filePath)) {
+    if (fs.existsSync(filePath)) {
-            try {
+      try {
-                const content = fs.readFileSync(filePath, 'utf8');
+        const content = fs.readFileSync(filePath, 'utf8');
 
-                // Check for proper workflow structure
+        // Check for proper workflow structure
-                workflowTestSuite.assert(content.includes('#'), `${filename} has markdown headers`);
+        workflowTestSuite.assert(content.includes('#'), `${filename} has markdown headers`);
-                workflowTestSuite.assert(content.length > 100, `${filename} has substantial content`);
+        workflowTestSuite.assert(content.length > 100, `${filename} has substantial content`);
 
-                // Validate skill dependencies
+        // Validate skill dependencies
-                workflowTestSuite.validateWorkflowDependency(filename, content);
+        workflowTestSuite.validateWorkflowDependency(filename, content);
-                
+      } catch (error) {
-            } catch (error) {
+        workflowTestSuite.assert(false, `${filename} - content validation error: ${error.message}`);
-                workflowTestSuite.assert(false, `${filename} - content validation error: ${error.message}`);
+      }
-            }
-        }
     }
-    workflowTestSuite.log('');
+  }
+  workflowTestSuite.log('');
 
-    // Test 4: Workflow naming consistency
+  // Test 4: Workflow naming consistency
-    workflowTestSuite.log('Test 4: Naming Consistency', 'info');
+  workflowTestSuite.log('Test 4: Naming Consistency', 'info');
-    const actualFiles = fs.readdirSync(WORKFLOWS_DIR).filter(file => file.endsWith('.md'));
+  const actualFiles = fs.readdirSync(WORKFLOWS_DIR).filter((file) => file.endsWith('.md'));
 
-    for (const actualFile of actualFiles) {
+  for (const actualFile of actualFiles) {
-        if (!expectedWorkflows[actualFile]) {
+    if (!expectedWorkflows[actualFile]) {
-            workflowTestSuite.log(`  UNEXPECTED: ${actualFile} not in expected list`, 'warn');
+      workflowTestSuite.log(`  UNEXPECTED: ${actualFile} not in expected list`, 'warn');
-        }
     }
+  }
 
-    for (const expectedFile of Object.keys(expectedWorkflows)) {
+  for (const expectedFile of Object.keys(expectedWorkflows)) {
-        if (!actualFiles.includes(expectedFile)) {
+    if (!actualFiles.includes(expectedFile)) {
-            workflowTestSuite.assert(false, `Missing expected workflow: ${expectedFile}`);
+      workflowTestSuite.assert(false, `Missing expected workflow: ${expectedFile}`);
-        }
     }
-    workflowTestSuite.log('');
+  }
+  workflowTestSuite.log('');
 
-    // Test 5: Cross-reference validation
+  // Test 5: Cross-reference validation
-    workflowTestSuite.log('Test 5: Cross-Reference Validation', 'info');
+  workflowTestSuite.log('Test 5: Cross-Reference Validation', 'info');
 
-    // Check if README.md references workflows correctly
+  // Check if README.md references workflows correctly
-    const readmePath = path.join(AGENTS_DIR, 'README.md');
+  const readmePath = path.join(AGENTS_DIR, 'README.md');
-    if (fs.existsSync(readmePath)) {
+  if (fs.existsSync(readmePath)) {
-        const readmeContent = fs.readFileSync(readmePath, 'utf8');
+    const readmeContent = fs.readFileSync(readmePath, 'utf8');
-        workflowTestSuite.assert(
+    workflowTestSuite.assert(
-            readmeContent.includes('.windsurf/workflows'), 
+      readmeContent.includes('.windsurf/workflows'),
-            'README.md references correct workflows path'
+      'README.md references correct workflows path'
-        );
+    );
-    }
+  }
-    workflowTestSuite.log('');
+  workflowTestSuite.log('');
 
-    // Results Summary
+  // Results Summary
-    workflowTestSuite.log('=== Workflow Test Results Summary ===', 'info');
+  workflowTestSuite.log('=== Workflow Test Results Summary ===', 'info');
-    workflowTestSuite.log(`Passed: ${workflowTestSuite.results.passed}`, 'pass');
+  workflowTestSuite.log(`Passed: ${workflowTestSuite.results.passed}`, 'pass');
-    workflowTestSuite.log(`Failed: ${workflowTestSuite.results.failed}`, workflowTestSuite.results.failed > 0 ? 'fail' : 'pass');
+  workflowTestSuite.log(
+    `Failed: ${workflowTestSuite.results.failed}`,
+    workflowTestSuite.results.failed > 0 ? 'fail' : 'pass'
+  );
 
-    if (workflowTestSuite.results.errors.length > 0) {
+  if (workflowTestSuite.results.errors.length > 0) {
-        workflowTestSuite.log('Errors:', 'fail');
+    workflowTestSuite.log('Errors:', 'fail');
-        workflowTestSuite.results.errors.forEach(error => {
+    workflowTestSuite.results.errors.forEach((error) => {
-            workflowTestSuite.log(`  - ${error}`, 'fail');
+      workflowTestSuite.log(`  - ${error}`, 'fail');
-        });
+    });
-    }
+  }
 
-    workflowTestSuite.log(`Completed: ${new Date().toISOString()}`, 'info');
+  workflowTestSuite.log(`Completed: ${new Date().toISOString()}`, 'info');
 
-    return workflowTestSuite.results.failed === 0;
+  return workflowTestSuite.results.failed === 0;
 }
 
 // Export for use in other modules
@@ -230,6 +232,6 @@ module.exports = { WorkflowTestSuite, runWorkflowTests };
 
 // Run tests if called directly
 if (require.main === module) {
-    const success = runWorkflowTests();
+  const success = runWorkflowTests();
-    process.exit(success ? 0 : 1);
+  process.exit(success ? 0 : 1);
 }

.agents/workflows/00-speckit.all.md

@@ -10,27 +10,27 @@ This meta-workflow orchestrates the **complete development lifecycle**, from spe
 ## Preparation Phase (Steps 1-5)
 
 1. **Specify** (`/speckit.specify`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-specify/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-specify/SKILL.md`
    - Execute with user's feature description
    - Creates: `spec.md`
 
 2. **Clarify** (`/speckit.clarify`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-clarify/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-clarify/SKILL.md`
    - Execute to resolve ambiguities
    - Updates: `spec.md`
 
 3. **Plan** (`/speckit.plan`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-plan/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-plan/SKILL.md`
    - Execute to create technical design
    - Creates: `plan.md`
 
 4. **Tasks** (`/speckit.tasks`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-tasks/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-tasks/SKILL.md`
    - Execute to generate task breakdown
    - Creates: `tasks.md`
 
 5. **Analyze** (`/speckit.analyze`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-analyze/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-analyze/SKILL.md`
    - Execute to validate consistency across spec, plan, and tasks
    - Output: Analysis report
    - **Gate**: If critical issues found, stop and fix before proceeding
@@ -38,29 +38,29 @@ This meta-workflow orchestrates the **complete development lifecycle**, from spe
 ## Implementation Phase (Steps 6-7)
 
 6. **Implement** (`/speckit.implement`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-implement/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-implement/SKILL.md`
    - Execute all tasks from `tasks.md` with anti-regression protocols
    - Output: Working implementation
 
 7. **Check** (`/speckit.checker`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-checker/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-checker/SKILL.md`
    - Run static analysis (linters, type checkers, security scanners)
    - Output: Checker report
 
 ## Verification Phase (Steps 8-10)
 
 8. **Test** (`/speckit.tester`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-tester/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-tester/SKILL.md`
    - Run tests with coverage
    - Output: Test + coverage report
 
 9. **Review** (`/speckit.reviewer`):
-   - Use the `view_file` tool to read: `.windsurf/skills/speckit-reviewer/SKILL.md`
+   - Use the `view_file` tool to read: `.agents/skills/speckit-reviewer/SKILL.md`
    - Perform code review
    - Output: Review report with findings
 
 10. **Validate** (`/speckit.validate`):
-    - Use the `view_file` tool to read: `.windsurf/skills/speckit-validate/SKILL.md`
+    - Use the `view_file` tool to read: `.agents/skills/speckit-validate/SKILL.md`
     - Verify implementation matches spec requirements
     - Output: Validation report (pass/fail)
 

.agents/workflows/01-speckit.prepare.md

@@ -9,20 +9,20 @@ This workflow orchestrates the sequential execution of the Speckit preparation p
 
 1. **Step 1: Specify (Skill 02)**
    - Goal: Create or update the `spec.md` based on user input.
-   - Action: Read and execute `.windsurf/skills/speckit-specify/SKILL.md`.
+   - Action: Read and execute `.agents/skills/speckit-specify/SKILL.md`.
 
 2. **Step 2: Clarify (Skill 03)**
    - Goal: Refine the `spec.md` by identifying and resolving ambiguities.
-   - Action: Read and execute `.windsurf/skills/speckit-clarify/SKILL.md`.
+   - Action: Read and execute `.agents/skills/speckit-clarify/SKILL.md`.
 
 3. **Step 3: Plan (Skill 04)**
    - Goal: Generate `plan.md` from the finalized spec.
-   - Action: Read and execute `.windsurf/skills/speckit-plan/SKILL.md`.
+   - Action: Read and execute `.agents/skills/speckit-plan/SKILL.md`.
 
 4. **Step 4: Tasks (Skill 05)**
    - Goal: Generate actionable `tasks.md` from the plan.
-   - Action: Read and execute `.windsurf/skills/speckit-tasks/SKILL.md`.
+   - Action: Read and execute `.agents/skills/speckit-tasks/SKILL.md`.
 
 5. **Step 5: Analyze (Skill 06)**
    - Goal: Validate consistency across all design artifacts (spec, plan, tasks).
-   - Action: Read and execute `.windsurf/skills/speckit-analyze/SKILL.md`.
+   - Action: Read and execute `.agents/skills/speckit-analyze/SKILL.md`.

.agents/workflows/101-speckit.constitution.md

@@ -9,7 +9,7 @@ description: Create or update the project constitution from interactive or provi
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-constitution/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-constitution/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/102-speckit.specify.md

@@ -10,7 +10,7 @@ description: Create or update the feature specification from a natural language
    - This is typically the starting point of a new feature.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-specify/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-specify/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/103-speckit.clarify.md

@@ -9,7 +9,7 @@ description: Identify underspecified areas in the current feature spec by asking
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-clarify/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-clarify/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/104-speckit.plan.md

@@ -9,7 +9,7 @@ description: Execute the implementation planning workflow using the plan templat
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-plan/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-plan/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/105-speckit.tasks.md

@@ -9,7 +9,7 @@ description: Generate an actionable, dependency-ordered tasks.md for the feature
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-tasks/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-tasks/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/106-speckit.analyze.md

@@ -11,7 +11,7 @@ description: Perform a non-destructive cross-artifact consistency and quality an
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-analyze/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-analyze/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/107-speckit.implement.md

@@ -9,7 +9,7 @@ description: Execute the implementation plan by processing and executing all tas
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-implement/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-implement/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/108-speckit.checker.md

@@ -11,7 +11,7 @@ description: Run static analysis tools and aggregate results.
    - The user may specify paths to check or run on entire project.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-checker/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-checker/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/109-speckit.tester.md

@@ -11,7 +11,7 @@ description: Execute tests, measure coverage, and report results.
    - The user may specify test paths, options, or just run all tests.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-tester/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-tester/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/110-speckit.reviewer.md

@@ -9,7 +9,7 @@ description: Perform code review with actionable feedback and suggestions.
    - The user may specify files to review, "staged" for git staged changes, or "branch" for branch diff.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-reviewer/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-reviewer/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/111-speckit.validate.md

@@ -9,7 +9,7 @@ description: Validate that implementation matches specification requirements.
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-validate/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-validate/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/112-speckit.security-audit.md

@@ -9,7 +9,7 @@ description: Perform a security-focused audit of the codebase against OWASP Top
    - The user may pass a scope hint: `backend`, `frontend`, `both`, or specific module paths (defaults to `both`).
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-security-audit/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-security-audit/SKILL.md`
    - Also load `.agents/skills/_LCBP3-CONTEXT.md` for project-specific rules.
 
 3. **Execute**:

.agents/workflows/bugfix.md

@@ -0,0 +1,20 @@
+---
+auto_execution_mode: 0
+description: Quick bugfix workflow with minimal impact. Focused on surgical fixes without unrelated refactoring.
+---
+
+# Workflow: bugfix
+
+1. **Context Analysis**:
+   - The user has reported a bug. Treat the bug description or logs as the primary input.
+
+2. **Load Skill**:
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/bugfix/SKILL.md`
+
+3. **Execute**:
+   - Follow the instructions in the `SKILL.md` exactly.
+   - Phases: Analysis → Planning → Execution → Finalization
+
+4. **Safety Check**:
+   - Always ensure Tier 1 rules (Security, UUID v7, DB Schema) are NOT violated.
+   - Refer to `AGENTS.md` for the full list of forbidden patterns.

.agents/workflows/check-real-app.md

@@ -0,0 +1,83 @@
+---
+auto_execution_mode: 0
+description: Manual real-app verification — ตรวจแอปจริงหลัง build pass เพื่อยืนยันว่าทำงานถูกต้องใน environment จริง (ไม่ใช่แค่ unit test)
+---
+
+# Workflow: check-real-app
+
+ใช้เมื่อ build/lint/test ผ่านแล้ว แต่ต้องการยืนยันว่าแอปจริงทำงานถูกต้อง
+เน้นการตรวจที่ unit test ตรวจไม่ได้: UI flow, API response จริง, console errors, network requests
+
+## ขั้นตอน
+
+### 1. เริ่ม Dev Server (ถ้ายังไม่รัน)
+
+ตรวจก่อนว่ามี dev server รันอยู่แล้วหรือไม่ เพื่อป้องกันรันซ้ำ:
+
+```bash
+# Backend
+pnpm --filter backend run start:dev
+
+# Frontend
+pnpm --filter frontend run dev
+```
+
+### 2. ตรวจ Endpoint / หน้าที่เปลี่ยน
+
+- เปิด URL ที่เกี่ยวข้องกับงานที่เพิ่ง implement
+- ตรวจ API endpoint ด้วย curl หรือ browser dev tools
+- ดู network tab ว่า request/response ถูกต้อง
+
+```bash
+# ตัวอย่างตรวจ API จริง
+curl -X GET http://localhost:3001/api/[endpoint] \
+  -H "Authorization: Bearer <token>" | jq .
+```
+
+### 3. ตรวจ Console / Log
+
+- **Frontend**: เปิด browser DevTools → Console tab — ต้องไม่มี error หรือ warning ที่ไม่คาดเดา
+- **Backend**: ดู terminal log — ตรวจว่าไม่มี unhandled exception หรือ SQL error
+
+### 4. ตรวจ Happy Path + Edge Case หลัก
+
+ตรวจ flow ที่เกี่ยวข้องอย่างน้อย:
+- [ ] Happy path ทำงานถูกต้อง
+- [ ] Input ผิดรูปแบบ → แสดง error message ที่เหมาะสม
+- [ ] Unauthorized access → redirect/403 ถูกต้อง
+- [ ] หน้าที่ไม่ได้แก้ยังทำงานปกติ (regression check)
+
+### 5. ตรวจ NAP-DMS Specific
+
+- [ ] UUID ใน URL และ response เป็น string format ถูกต้อง (ไม่ใช่ integer)
+- [ ] ไม่มี `NaN` หรือ `undefined` ใน form values หรือ API payload
+- [ ] Thai/English text แสดงผลถูกต้อง (i18n)
+- [ ] RBAC: role ที่ไม่มีสิทธิ์ไม่เห็น/เข้าถึงไม่ได้
+
+## 🚫 No Fake Evidence Rule
+
+> **ห้ามรายงานว่าตรวจแอปจริงแล้ว ถ้าไม่ได้เปิดแอปและตรวจจริง**
+> ถ้าตรวจไม่ได้ (เช่น ไม่มี DB, ไม่มี token) ให้ระบุเหตุผลชัดเจน
+
+## ✅ Mandatory Output
+
+รายงานท้ายงานต้องมีครบ:
+
+### Commands run
+```
+✅ curl GET /api/correspondences   → 200 OK, returned 3 records
+✅ curl POST /api/correspondences  → 201 Created, uuid: "019..."
+❌ ไม่ได้ตรวจ: file upload flow   → เหตุผล: ต้องการ ClamAV service ที่ไม่มีใน local
+```
+
+### Evidence
+- URL ที่ตรวจ + HTTP status code
+- Screenshot หรือ response body (ถ้า sensitive ให้ mask)
+- Console log ที่พบ (ถ้ามี error ต้องระบุ)
+
+### Limitations / Risks
+- flow หรือ endpoint ที่ยังไม่ได้ตรวจ + เหตุผล
+- ความเสี่ยงที่ควรตรวจใน staging ก่อน deploy
+
+### Next steps
+- งานที่ต้องทำต่อ หรือ flag สำหรับ QA

.agents/workflows/diagnose.md

@@ -9,7 +9,7 @@ description: Disciplined diagnosis loop for hard bugs and performance regression
    - The user has provided a bug report or performance regression. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/diagnose/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/diagnose/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/e2e-testing.md

@@ -0,0 +1,13 @@
+---
+auto_execution_mode: 0
+description: Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, and flaky test strategies for LCBP3-DMS
+---
+
+This workflow invokes the e2e-testing skill to help with Playwright E2E testing patterns for LCBP3-DMS.
+
+Invoke the e2e-testing skill when:
+- Creating new E2E tests for frontend features
+- Debugging flaky Playwright tests
+- Setting up CI/CD integration for E2E tests
+- Optimizing test performance and reliability
+- Implementing Page Object Model (POM) patterns

.agents/workflows/grill-with-docs.md

@@ -9,7 +9,7 @@ description: Grilling session that challenges your plan against the existing dom
    - The user has provided a plan to stress-test. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/grill-with-docs/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/grill-with-docs/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/resume-pending-work.md

@@ -0,0 +1,100 @@
+---
+auto_execution_mode: 0
+description: Resume pending multi-session work — อ่าน context เดิม, หา last checkpoint, สรุปสถานะปัจจุบัน และวางแผนต่อ โดยไม่ทำงานซ้ำ
+---
+
+# Workflow: resume-pending-work
+
+ใช้เมื่อกลับมาทำงานที่ค้างไว้ข้าม session — เช่น งานใหญ่ที่แบ่งเป็น phase, งาน migration, หรืองานที่หยุดกลางคัน
+
+## ขั้นตอน
+
+### 1. อ่าน Context เดิม
+
+ตรวจแหล่งข้อมูลเหล่านี้ตามลำดับ:
+
+```
+1. Memory system — ดู system-retrieved memories ที่เกี่ยวข้อง
+2. specs/200-fullstacks/<feature>/tasks.md — ดู task status ล่าสุด
+3. git log --oneline -20 — ดู commits ล่าสุด
+4. progress.txt หรือ PROGRESS.md (ถ้ามี) — ดู notes ที่ทิ้งไว้
+```
+
+### 2. หา Last Checkpoint
+
+ระบุให้ชัดว่า:
+- **ทำไปถึงไหนแล้ว** — phase/task/file ที่ complete แล้ว
+- **ค้างอยู่ที่ไหน** — step ที่กำลังทำอยู่ตอนหยุด
+- **ยังไม่ได้ทำอะไร** — tasks ที่เหลือ
+
+### 3. ตรวจสถานะ Build ปัจจุบัน
+
+ก่อนทำงานต่อ ต้องรู้ว่า codebase ปัจจุบัน clean หรือไม่:
+
+```bash
+# ตรวจ TypeScript errors
+pnpm --filter backend run build 2>&1 | tail -20
+pnpm --filter frontend run build 2>&1 | tail -20
+
+# ดู uncommitted changes
+git status --short
+git diff --stat HEAD
+```
+
+### 4. สรุปสถานะและวางแผนต่อ
+
+ก่อนลงมือ ให้สรุปให้ผู้ใช้เห็นก่อน:
+
+```
+✅ เสร็จแล้ว:
+  - Phase 1: Entity + Migration (commit abc1234)
+  - Phase 2: Service layer (commit def5678)
+
+🔄 ค้างอยู่:
+  - Phase 3: Controller — เขียนครึ่งนึง, ยังไม่มี tests
+
+⏳ ยังไม่ได้ทำ:
+  - Phase 4: Frontend integration
+  - Phase 5: E2E tests
+
+🚩 Issues ที่พบ:
+  - build error ที่ correspondence.service.ts:142
+```
+
+จากนั้นถามผู้ใช้ว่าต้องการ:
+- ทำงานต่อจาก checkpoint เดิม
+- Skip ขั้นตอนที่ค้าง (พร้อมระบุ risk)
+- Re-verify งานที่ทำไปแล้วก่อน
+
+### 5. ตรวจ NAP-DMS Specific
+
+ก่อน resume ให้ตรวจ:
+- [ ] ADR ที่เกี่ยวข้องยังไม่เปลี่ยนแปลง (ดู git log ที่ `specs/06-Decision-Records/`)
+- [ ] Schema ที่ใช้อยู่ตรงกับ `lcbp3-v1.9.0-schema-02-tables.sql`
+- [ ] ไม่มี merge conflict หรือ stash ค้าง
+
+## 🚫 No Fake Resume Rule
+
+> **ห้ามบอกว่า "ทำต่อจากตรงนี้" โดยไม่ได้อ่าน context เดิมจริง**
+> ต้องระบุหลักฐานที่ชัดเจนว่า checkpoint อยู่ที่ไหน
+
+## ✅ Mandatory Output
+
+### Last checkpoint summary
+```
+- เสร็จแล้ว: [phase/commit/task]
+- ค้างอยู่: [file:line หรือ task ที่หยุด]
+- ยังไม่ได้ทำ: [tasks ที่เหลือ]
+```
+
+### Build status
+```
+✅ backend build  → clean
+❌ frontend build → 2 errors (ระบุ errors)
+```
+
+### Plan ต่อ
+แผน 3-5 ข้อที่จะทำในส่วนที่เหลือ พร้อม verification method
+
+### Risks / Blockers
+สิ่งที่อาจ block งาน หรือต้องระวังก่อนทำต่อ

.agents/workflows/review.md

@@ -40,7 +40,7 @@ The following are **CI-blocking issues** that must be caught in code review. The
 
 - **❌ NO SQL Triggers for business logic** — use NestJS Service methods instead
 - **❌ NO `.env` files in production** — use Docker environment variables
-- **❌ NO direct table/column name invention** — verify against `specs/03-Data-and-Storage/lcbp3-v1.8.0-schema-02-tables.sql`
+- **❌ NO direct table/column name invention** — verify against `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql`
 
 ### Security (ADR-016)
 

.agents/workflows/save-memory.md

@@ -0,0 +1,11 @@
+---
+description: บันทึก session log และอัปเดต project memory
+---
+
+# บันทึก Memory
+
+ใช้ skill `save-memory` เพื่อบันทึก session log และอัปเดต project memory ตามโครงสร้างใหม่
+
+```bash
+skill save-memory
+```

.agents/workflows/security-review.md

@@ -0,0 +1,15 @@
+---
+auto_execution_mode: 0
+description: Comprehensive security review for LCBP3-DMS with OWASP Top 10 checklist, ADR compliance, and automated security testing patterns
+---
+
+This workflow invokes the security-review skill to perform comprehensive security review of LCBP3-DMS code changes.
+
+Invoke the security-review skill when:
+- Implementing authentication or authorization
+- Handling user input or file uploads
+- Creating new API endpoints
+- Working with secrets or credentials
+- Integrating AI features (Ollama/Qdrant)
+- Storing or transmitting sensitive data
+- Integrating third-party APIs

.agents/workflows/tdd.md

@@ -9,7 +9,7 @@ description: Test-driven development with red-green-refactor loop. Use when user
    - The user wants to build features or fix bugs using TDD. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/tdd/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/tdd/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/to-issues.md

@@ -9,7 +9,7 @@ description: Break a plan, spec, or PRD into independently-grabbable issues on t
    - The user wants to convert a plan into issues. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/to-issues/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/to-issues/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/to-prd.md

@@ -9,7 +9,7 @@ description: Turn the current conversation context into a PRD and publish it to
    - The user wants to create a PRD from the current context. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/to-prd/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/to-prd/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/triage.md

@@ -9,7 +9,7 @@ description: Triage issues through a state machine driven by triage roles. Use w
    - The user wants to triage issues. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/triage/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/triage/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.checklist.md

@@ -9,7 +9,7 @@ description: Generate a custom checklist for the current feature based on user r
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-checklist/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-checklist/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.diff.md

@@ -9,7 +9,7 @@ description: Compare two versions of a spec or plan to highlight changes.
    - The user has provided an input prompt (optional file paths or version references).
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-diff/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-diff/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.migrate.md

@@ -9,7 +9,7 @@ description: Migrate existing projects into the speckit structure by generating
    - The user has provided an input prompt (path to analyze, feature name).
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-migrate/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-migrate/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.quizme.md

@@ -11,7 +11,7 @@ description: Challenge the specification with Socratic questioning to identify l
    - The user has provided an input prompt. Treat this as the primary input for the skill.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-quizme/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-quizme/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.status.md

@@ -11,7 +11,7 @@ description: Display a dashboard showing feature status, completion percentage,
    - The user may optionally specify a feature to focus on.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-status/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-status/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.agents/workflows/util-speckit.taskstoissues.md

@@ -9,7 +9,7 @@ description: Convert existing tasks into actionable, dependency-ordered issues o
    - The user may pass filters (e.g., phase, priority). Default: convert all pending tasks.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/speckit-taskstoissues/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/speckit-taskstoissues/SKILL.md`
    - Also load `.agents/skills/_LCBP3-CONTEXT.md` for project conventions (labels, commit format).
 
 3. **Execute**:

.agents/workflows/verification-loop.md

@@ -0,0 +1,50 @@
+---
+auto_execution_mode: 0
+description: A comprehensive verification system for LCBP3-DMS development sessions with build, type check, lint, test, security scan, and diff review phases
+---
+
+This workflow invokes the verification-loop skill to perform comprehensive verification of LCBP3-DMS code changes.
+
+Invoke the verification-loop skill when:
+
+- After completing a feature or significant code change
+- Before creating a PR
+- When you want to ensure quality gates pass
+- After refactoring
+- Before deploying to staging/production
+
+## 🚫 No Fake Evidence Rule
+
+> **ห้ามรายงานว่า test ผ่าน / build สำเร็จ ถ้าไม่ได้รันจริง**
+> ถ้ารันไม่ได้ ให้ระบุเหตุผลอย่างชัดเจนแทน
+
+## ✅ Mandatory Output (ทุก verification ต้องมีครบ)
+
+รายงานท้ายงานต้องมี 5 หัวข้อนี้เสมอ:
+
+### 1. Pipeline trace
+
+ลำดับขั้นตอนที่ทำจริง: Understand → Plan → Execute → Verify → Handoff
+
+### 2. Commands run
+
+รายการคำสั่งที่รันจริงพร้อมผลสรุป:
+
+```
+✅ pnpm run build          → Pass (0 errors)
+✅ pnpm run lint           → Pass (0 warnings)
+✅ pnpm run test           → 42 passed, 0 failed
+❌ ไม่ได้รัน: e2e tests    → เหตุผล: ต้องการ DB จริง, ไม่มีใน CI environment
+```
+
+### 3. Verification / Evidence
+
+หลักฐานจริง เช่น build output, test result, diff, screenshot, link
+
+### 4. Limitations / Risks
+
+สิ่งที่ยังไม่ได้ตรวจ, ความเสี่ยง, ข้อจำกัดของ environment
+
+### 5. Next steps
+
+งานที่ต้องทำต่อหลัง verification

.agents/workflows/zoom-out.md

@@ -9,7 +9,7 @@ description: Tell the agent to zoom out and give broader context or a higher-lev
    - The user is unfamiliar with a section of code or needs broader context. Treat this as the primary input.
 
 2. **Load Skill**:
-   - Use the `view_file` tool to read the skill file at: `.windsurf/skills/zoom-out/SKILL.md`
+   - Use the `view_file` tool to read the skill file at: `.agents/skills/zoom-out/SKILL.md`
 
 3. **Execute**:
    - Follow the instructions in the `SKILL.md` exactly.

.devin/rules/00-project-context.md

@@ -0,0 +1,168 @@
+---
+trigger: always_on
+---
+
+# NAP-DMS Project Context & Rules
+
+- For: Devin Cascade (and compatible: Codex CLI, opencode, Amp, Antigravity, AGENTS.md tools)
+- Version: 1.9.10 | Last synced from repo: 2026-06-06
+- Repo: [https://git.np-dms.work/np-dms/lcbp3](https://git.np-dms.work/np-dms/lcbp3)
+- Skill pack: `.agents/skills/` (v1.9.0, 21 skills) — see [`skills/README.md`](./.agents/skills/README.md) + [`skills/_LCBP3-CONTEXT.md`](./.agents/skills/_LCBP3-CONTEXT.md)
+
+## 🧠 Role & Persona
+
+Act as **Senior Full Stack Developer** specialized in NestJS, Next.js, TypeScript, DMS. Focus: Data Integrity, Security, Maintainability, Performance.
+
+You are a **Document Intelligence Engine** — not a general chatbot. Every response must be **precise**, **spec-compliant**, and **production-ready**.
+
+---
+
+## 🧩 Thought & Planning Protocol (Powered by Everything-Claude-Code)
+
+Before writing any code or taking any action in Tier 1 and Tier 2, the AI must demonstrate the following thinking process:
+
+### 1. Analysis Phase (Explore & Analyze)
+
+Problem Understanding: Restate what the user wants in clear, unambiguous terms.
+Context Search: Identify the relevant Spec files or ADRs from the "Key Spec Files" table that must be read before starting.
+Constraints Identification: Identify key constraints (e.g. Security rules, UUID patterns, or Domain terminology).
+
+### 2. Planning Phase (Plan)
+
+Alternative Exploration: Present at least 2 solution approaches (where possible) with pros/cons analysis.
+Step-by-Step Roadmap: Write a file-by-file plan of changes before executing.
+Verification Plan: Specify how to verify the work is complete (e.g. "which unit tests to write" or "which file to check the schema in").
+
+### 3. Execution & Refinement (Execute & Refine)
+
+Follow the plan step by step, and pause to ask if any uncertainty arises.
+If significant logic changes are made, summarize what was done for the user after completion.
+
+---
+
+## ⚙️ DMS Workflow Engine Protocol
+
+กฎนี้ใช้คุม Logic การไหลของเอกสาร (RFA, Transmittal, Correspondence) เพื่อป้องกัน Race Condition และรักษาความถูกต้องของสถานะ:
+
+- **State Management:** ตรวจสอบสถานะปัจจุบันจาก DB ก่อนเสมอ เพื่อป้องกันการอนุมัติซ้ำซ้อน (ดู `05-06-code-snippets.md` `[workflow-transition]`)
+- **Concurrency Control:** การจอนเลขที่เอกสารต้องใช้ **Redis Redlock** หรือ **TypeORM `@VersionColumn`** เท่านั้น (ADR-002)
+- **Background Jobs:** งานนานหรือการแจ้งเตือนต้องส่งไปทำที่ **BullMQ** ห้ามเขียนแบบ Inline (ADR-008)
+- **Term Consistency:** ห้ามใช้ "Approval Flow" ให้ใช้ **"Workflow Engine"** และห้ามใช้ "Letter" ให้ใช้ **"Correspondence"** (หมายเหตุ: "จดหมาย" ในคอมเมนต์ภาษาไทย = Correspondence ที่ครอบคลุมทุกประเภท)
+
+---
+
+## 🛡️ Security & Integrity Audit Protocol
+
+กฎนี้ให้ AI เป็น Gatekeeper ก่อน Commit โดยเน้น **Tier 1 — CRITICAL**:
+
+- **UUID Validation:** ตรวจสอบว่าเป็น **UUIDv7** และห้ามใช้ `parseInt()` บน UUID (ADR-019)
+- **RBAC Check:** API ใหม่ต้องมี **CASL Guard** และตรวจสอบ 4-Level RBAC Matrix (ADR-016)
+- **Data Isolation:** AI ต้องรันผ่าน **Ollama บน Admin Desktop** เท่านั้น ห้ามเข้าถึง DB/storage โดยตรง (ADR-023)
+- **Input Sanitization:** ไฟล์อัปโหลดต้องผ่าน **Two-Phase** (Temp → Commit) และสแกนด้วย **ClamAV** (ADR-016)
+
+---
+
+## 🧭 Rule Enforcement Tiers
+
+### 🔴 Tier 1 — CRITICAL (CI BLOCKER)
+
+Build fails หากละเมิด:
+
+- Security (Auth, RBAC, Validation)
+- UUID Strategy (ADR-019) — no `parseInt` / `Number` / `+` on UUID
+- Database correctness — verify schema before writing queries
+- File upload security (ClamAV + whitelist)
+- AI validation boundary (ADR-023)
+- Error handling strategy (ADR-007)
+- Forbidden patterns: `any`, `console.log`, UUID misuse, `id ?? ''` fallback
+
+### 🟡 Tier 2 — IMPORTANT (CODE REVIEW)
+
+Must fix ก่อน merge:
+
+- Architecture patterns (thin controller, business logic in service)
+- Test coverage (80%+ business logic, 70%+ backend overall)
+- Cache invalidation
+- Naming conventions
+- **TypeScript Standards:** Missing JSDoc, explicit types, or file headers
+
+### 🟢 Tier 3 — SPECIALIZED WORK
+
+Requires domain-specific knowledge:
+
+- **ADR-021 Integration:** Workflow Engine & Context implementation
+- **AI Infrastructure:** ADR-023/023A boundary enforcement and pipeline usage
+- **AI Runtime Layer:** ADR-024 Intent Classification, ADR-025 Tool Layer, ADR-026 Chat UI, ADR-027 Admin Console
+- **Migration Pipeline:** ADR-028 Staging Queue & post-migration cleanup
+- **Complex Business Logic:** Multi-step workflows with state management
+- **Performance Optimization:** Database queries, caching strategies, bulk operations
+
+### 🔵 Tier 4 — GUIDELINES
+
+Best practice — follow when possible:
+
+- Code style / formatting (Prettier handles)
+- Comment completeness
+- Minor optimizations
+
+---
+
+## 📐 TypeScript Rules & Coding Standards
+
+### 📝 Core Standards
+
+- **Strict Mode** — all strict checks enforced.
+- **ZERO `any` types** — use proper types or `unknown` + narrowing.
+- **ZERO `console.log`** — use NestJS `Logger` (backend) or remove (frontend).
+- **English for Code** — use English for all code identifiers, variables, and logic.
+- **Thai for Comments** — use Thai for comments, documentation, and JSDoc.
+- **Explicit Typing** — explicitly define types for all variables, parameters, and return values.
+- **JSDoc** — use JSDoc for all public classes and methods.
+
+### 🏗️ File & Function Structure
+
+- **File Headers** — every file MUST start with `// File: path/filename` on the first line.
+- **Change Log** — include `// Change Log` at the top of the file to track modifications.
+- **Single Export** — export **only one main symbol** per file.
+- **Function Style** — avoid unnecessary blank lines inside functions.
+
+---
+
+## 🚫 Forbidden Actions
+
+| ❌ Forbidden                                    | ✅ Correct Approach                                     | ⚠️ Why                                               |
+| ----------------------------------------------- | ------------------------------------------------------- | ---------------------------------------------------- |
+| SQL Triggers for business logic                 | NestJS Service methods                                  | Untestable; bypasses audit log                       |
+| `.env` files in production                      | `docker-compose.yml` environment section                | Secrets exposed in version control                   |
+| TypeORM migration files                         | Edit schema SQL directly (ADR-009)                      | Migration drift risk; schema managed via SQL delta   |
+| Inventing table/column names                    | Verify against `schema-02-tables.sql`                   | Schema mismatch causes silent runtime errors         |
+| `any` TypeScript type                           | Proper types / generics                                 | Defeats strict mode; hides runtime type errors       |
+| `console.log` in committed code                 | NestJS Logger (backend) / remove (frontend)             | Log flooding in production; risk of data leakage     |
+| `req: any` in controllers                       | `RequestWithUser` typed interface                       | Type safety lost; auth context unreachable           |
+| `parseInt()` on UUID values                     | Use UUID string directly (ADR-019)                      | `"0195…"` parsed to integer `19` — silently wrong    |
+| Exposing INT PK in API responses                | UUIDv7 `publicId` (ADR-019)                             | Leaks row count; enables DB enumeration attacks      |
+| AI accessing DB/storage directly                | AI → DMS API → DB (ADR-023/023A)                        | Bypasses RBAC, audit trail, and validation layer     |
+| Direct file operations bypassing StorageService | `StorageService` for all file moves                     | Orphaned files; broken ClamAV scan; no audit trail   |
+| Inline email/notification sending               | BullMQ queue job (ADR-008)                              | Blocks request thread; no retry on transient failure |
+| Deploying without Release Gates                 | Complete `04-08-release-management-policy.md`           | Unverified deploy risks data loss in production      |
+| AI direct cloud API calls                       | On-premises Ollama only (ADR-023/023A)                  | Data privacy violation; no audit control             |
+| AI outputs without human validation             | Human-in-the-loop validation required (ADR-023/023A)    | Unvalidated AI metadata corrupts document records    |
+| n8n calling Ollama/Qdrant directly              | n8n → DMS API → BullMQ → Ollama (ADR-023A)              | Bypasses audit log, RBAC, and error handling layer   |
+| Qdrant query without `projectPublicId` filter   | `QdrantService.search(projectPublicId, ...)` (ADR-023A) | Cross-project data leak via vector search            |
+
+---
+
+## 🚧 Out of Scope — Never Do Without Explicit Approval
+
+| ❌ Never Do Autonomously                                        | ⚠️ Why Approval Is Required                                      |
+| --------------------------------------------------------------- | ---------------------------------------------------------------- |
+| `DROP` or `RENAME` a column / table                             | Irreversible data loss — requires DBA + PM sign-off              |
+| Push directly to `main` / `master` branch                       | Bypasses CI, code review, and release gates                      |
+| Generate or insert seed data into production database           | May corrupt live data or violate business state invariants       |
+| Delete files from permanent storage                             | Files may be referenced in active documents or audit trails      |
+| Modify RBAC permission matrix without security team approval    | Defines access control for all users — security boundary change  |
+| Upgrade major library versions (NestJS, Next.js, TypeORM, etc.) | Breaking changes require full regression test cycle              |
+| Disable or modify authentication / authorization guards         | Creates unguarded endpoints — immediate security risk            |
+| Change Redis lock TTL or disable Redlock                        | Risk of document number race condition (ADR-002)                 |
+| Create or supersede an ADR unilaterally                         | Architecture decisions require team consensus and review process |
+| Add new columns to production tables without schema review      | Must update Data Dictionary + downstream queries simultaneously  |