690523:2327 ADR-028-228-migration #01

2026-05-23 23:27:52 +07:00
parent ff5cadc9f2
commit 5a17f969b8
23 changed files with 1169 additions and 252 deletions
@@ -6,8 +6,8 @@
 > # Speckit Agent Infrastructure (v1.9.0)
 >
 > - Version: 1.9.0
-> - Last Updated: 2026-05-13
-> - Core Principle: **Sync with AGENTS.md v1.9.0**
+> - Last Updated: 2026-05-22
+> - Core Principle: **Sync with AGENTS.md v1.9.6**

 ---

@@ -95,18 +95,18 @@ The toolkit is organized into modular components that provide both the logic (Sc
 │   └── util-speckit-*.md          # Utilities (checklist, diff, migrate, etc.)
 │
 ├── rules/                         # Project Context & Validation Rules
-│   ├── 00-project-context.md      # Role, Persona, Rule Tiers (v1.9.0)
+│   ├── 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)
@@ -265,9 +265,9 @@ If you change your mind mid-project:

 ---

-## 🏗️ LCBP3-DMS Project Notes (v1.9.0)
+## 🏗️ LCBP3-DMS Project Notes (v1.9.6)

-### 📊 Current Status: Production Ready (2026-04-14)
+### 📊 Current Status: Production Ready (2026-05-22)

 | Area          | Status                          |
 | ------------- | ------------------------------- |
@@ -306,7 +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

 ---
@@ -325,7 +325,7 @@ If you change your mind mid-project:
 # Run version validation
 ./scripts/bash/validate-versions.sh

-# Fix by updating all files to v1.9.0
+# Fix by updating all files to v1.9.6
 # Then re-run validation to confirm
 ```

@@ -1,56 +1,164 @@
-# NAP-DMS Project Context & Core Rules
+# NAP-DMS Project Context & Rules

- Version: 1.9.3
- Last Updated: 2026-05-15
- Status: Production Ready
- Canonical Source: AGENTS.md
+- For: Windsurf Cascade (and compatible: Codex CLI, opencode, Amp, Antigravity, AGENTS.md tools)
+- Version: 1.9.6 | Last synced from repo: 2026-05-22
+- 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
+## 🧠 Role & Persona

-Act as a **Senior Full Stack Developer** specialized in NestJS, Next.js, and TypeScript.
-Focus on **Data Integrity, Security, Maintainability, and Performance**.
-You are a **Document Intelligence Engine** — every response must be precise, spec-compliant, and production-ready.
+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**.

 ---

-## 🔴 Tier 1 — CRITICAL (CI BLOCKER)
+## 🧩 Thought & Planning Protocol (Powered by Everything-Claude-Code)

-1. **Identifier Strategy (ADR-019)**
-   - ห้ามใช้ `parseInt()` บน UUID
-   - ใช้ `publicId` (string) สำหรับการติดต่อภายนอก (API/URL) เท่านั้น
-2. **Database Management (ADR-009)**
-   - ห้ามใช้ TypeORM Migrations หรือ `synchronize: true`
-   - การแก้ Schema ต้องแก้ที่ SQL files ใน `specs/03-Data-and-Storage/` เท่านั้น
-3. **Security (ADR-016)**
-   - ทุก API ต้องมี `CASL Guard` และตรวจสอบสิทธิ์ผ่าน RBAC Matrix
-   - การอัปโหลดไฟล์ต้องเป็น Two-Phase (Temp → Commit) และต้องสแกน ClamAV
-4. **AI Boundary (ADR-018)**
-   - AI Agent ต้องทำงานผ่าน DMS API เท่านั้น ห้ามเขียนลง Database หรือ Storage โดยตรง
+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.

 ---

-## 📐 TypeScript Rules & Coding Standards (v1.9.0)
+## ⚙️ DMS Workflow Engine Protocol

- **File Header:** ทุกไฟล์ต้องขึ้นต้นด้วย `// File: path/filename`
- **Change Log:** ต้องมีส่วน `// Change Log` ที่หัวไฟล์
- **Language:** ตัวแปร/Logic เป็น English, Comment/JSDoc เป็น **Thai**
- **Explicit Typing:** กำหนด Type ให้ชัดเจนเสมอ ห้ามใช้ `any`
- **Cleanliness:** ห้ามมีบรรทัดว่างในฟังก์ชัน, Export ได้เพียง 1 symbol หลักต่อไฟล์
+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)

 ---

-## 📁 Specs Folder Organization (Hybrid Model)
+## 🛡️ Security & Integrity Audit Protocol

- **Core (00-06):** ข้อมูลอ้างอิงถาวร (Permanent Source of Truth)
- **Feature (100-300):** สำหรับงาน Implementation ใหม่
-  - `100-Infrastructures/`
-  - `200-fullstacks/`
-  - `300-others/`
+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)

 ---

-## 🔄 Workflow Engine (ADR-001/021)
+## 🧭 Rule Enforcement Tiers

- ใช้ DSL-based state machine
- การเปลี่ยนสถานะต้องตรวจสอบสถานะปัจจุบันจาก DB ก่อนเสมอ
- งานที่ใช้เวลานานต้องส่งไปที่ **BullMQ** เท่านั้น
+### 🔴 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                                     |
+| ----------------------------------------------- | ------------------------------------------------------- |
+| SQL Triggers for business logic                 | NestJS Service methods                                  |
+| `.env` files in production                      | `docker-compose.yml` environment section                |
+| TypeORM migration files                         | Edit schema SQL directly (ADR-009)                      |
+| Inventing table/column names                    | Verify against `lcbp3-v1.9.0-schema-02-tables.sql`      |
+| `any` TypeScript type                           | Proper types / generics                                 |
+| `console.log` in committed code                 | NestJS Logger (backend) / remove (frontend)             |
+| `req: any` in controllers                       | `RequestWithUser` typed interface                       |
+| `parseInt()` on UUID values                     | Use UUID string directly (ADR-019)                      |
+| Exposing INT PK in API responses                | UUIDv7 (ADR-019)                                        |
+| AI accessing DB/storage directly                | AI → DMS API → DB (ADR-023)                             |
+| Direct file operations bypassing StorageService | `StorageService` for all file moves                     |
+| Inline email/notification sending               | BullMQ queue job                                        |
+| Deploying without Release Gates                 | Complete `04-08-release-management-policy.md`           |
+| AI direct cloud API calls                       | On-premises Ollama only (ADR-023)                       |
+| AI outputs without human validation             | Human-in-the-loop validation required (ADR-023)         |
+| n8n calling Ollama/Qdrant directly              | n8n → DMS API → BullMQ → Ollama/Qdrant (ADR-023A)       |
+| Qdrant query without `projectPublicId` filter   | `QdrantService.search(projectPublicId, ...)` (ADR-023A) |
+
+---
+
+## 🚧 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  |
@@ -9,9 +9,9 @@
 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-018):** Ollama on Admin Desktop ONLY — NO direct DB/storage access
+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-020):** RFA-First approach with unified pipeline architecture
+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

@@ -26,7 +26,7 @@
 - [ ] No SQL injection vulnerabilities
 - [ ] File upload validation (whitelist + ClamAV)
 - [ ] Rate limiting applied to auth endpoints
- [ ] AI boundary enforcement (ADR-023) - no direct DB/storage access
+- [ ] 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
@@ -1,4 +1,4 @@
-# TypeScript Rules (v1.9.3)
+# TypeScript Rules

 ## Core Standards

@@ -22,14 +22,20 @@

 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             |
-| **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                  |
+| 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                    |
@@ -28,15 +28,82 @@
 - 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.md`                | RHF+Zod + TanStack Query + Thai comments            |
-| "เพิ่ม field ใหม่"   | `ADR-009`, `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" | `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                      |
+| 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.md`                | RHF+Zod + TanStack Query + Thai comments                                              |
+| "เพิ่ม field ใหม่"      | `ADR-009`, `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"    | `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                 |
@@ -4,13 +4,14 @@ Critical rules and guidelines for AI agents working on LCBP3-DMS.

 ## Version

- **Current:** v1.9.3
- **Last Updated:** 2026-05-15
- **Synced with:** `AGENTS.md` (v1.9.3)
+- **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
@@ -24,6 +25,7 @@ This directory contains rule files that define:
 ### 🔴 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
@@ -35,15 +37,28 @@ Build fails immediately if violated:
 ### 🟡 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 — GUIDELINES
+### 🟢 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
@@ -52,61 +67,68 @@ Best practice — follow when possible:

 ### Core Rules (Tier 1 - CRITICAL)

-| File | Purpose |
-|------|---------|
+| 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 |
+| `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 |
+| 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) |
+| 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 |
-|------|---------|
+| 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 |
+| `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 |
-| **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 |
+| 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` and `03-typescript.md`
-3. **Review ADR references** — Ensure all ADR references are current (ADR-023, ADR-023A, etc.)
+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

@@ -2,58 +2,102 @@
 trigger: always_on
 ---

-# NAP-DMS Project Context
+# NAP-DMS Project Context & Rules

-## Role & Persona
+- For: Windsurf Cascade (and compatible: Codex CLI, opencode, Amp, Antigravity, AGENTS.md tools)
+- Version: 1.9.6 | Last synced from repo: 2026-05-22
+- 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)

-Act as a **Senior Full Stack Developer** specialized in:
+## 🧠 Role & Persona

- NestJS, Next.js, TypeScript
- Document Management Systems (DMS)
+Act as **Senior Full Stack Developer** specialized in NestJS, Next.js, TypeScript, DMS. Focus: Data Integrity, Security, Maintainability, Performance.

-Focus:
+You are a **Document Intelligence Engine** — not a general chatbot. Every response must be **precise**, **spec-compliant**, and **production-ready**.

- 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)

-## Project Information
+Before writing any code or taking any action in Tier 1 and Tier 2, the AI must demonstrate the following thinking process:

- **Project:** NAP-DMS (LCBP3)
- Version: 1.9.0
- Last Updated: 2026-05-13
- Canonical Source: AGENTS.md
- **Stack:** NestJS + Next.js + TypeScript + MariaDB + Ollama (AI)
- **Repo:** https://git.np-dms.work/np-dms/lcbp3
+### 1. Analysis Phase (Explore & Analyze)

-## Rule Enforcement Tiers
+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 immediately if violated:
+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-018)
+- AI validation boundary (ADR-023)
 - Error handling strategy (ADR-007)
- Forbidden patterns: `any`, `console.log`, UUID misuse
+- Forbidden patterns: `any`, `console.log`, UUID misuse, `id ?? ''` fallback

 ### 🟡 Tier 2 — IMPORTANT (CODE REVIEW)

-Must fix before merge:
+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 — GUIDELINES
+### 🟢 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:

@@ -63,13 +107,13 @@ Best practice — follow when possible:

 ---

-## 📐 TypeScript Rules & Coding Standards (v1.9.3)
+## 📐 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 before commit (frontend).
+- **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.
@@ -81,3 +125,44 @@ Best practice — follow when possible:
 - **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                                     |
+| ----------------------------------------------- | ------------------------------------------------------- |
+| SQL Triggers for business logic                 | NestJS Service methods                                  |
+| `.env` files in production                      | `docker-compose.yml` environment section                |
+| TypeORM migration files                         | Edit schema SQL directly (ADR-009)                      |
+| Inventing table/column names                    | Verify against `lcbp3-v1.9.0-schema-02-tables.sql`      |
+| `any` TypeScript type                           | Proper types / generics                                 |
+| `console.log` in committed code                 | NestJS Logger (backend) / remove (frontend)             |
+| `req: any` in controllers                       | `RequestWithUser` typed interface                       |
+| `parseInt()` on UUID values                     | Use UUID string directly (ADR-019)                      |
+| Exposing INT PK in API responses                | UUIDv7 (ADR-019)                                        |
+| AI accessing DB/storage directly                | AI → DMS API → DB (ADR-023)                             |
+| Direct file operations bypassing StorageService | `StorageService` for all file moves                     |
+| Inline email/notification sending               | BullMQ queue job                                        |
+| Deploying without Release Gates                 | Complete `04-08-release-management-policy.md`           |
+| AI direct cloud API calls                       | On-premises Ollama only (ADR-023)                       |
+| AI outputs without human validation             | Human-in-the-loop validation required (ADR-023)         |
+| n8n calling Ollama/Qdrant directly              | n8n → DMS API → BullMQ → Ollama/Qdrant (ADR-023A)       |
+| Qdrant query without `projectPublicId` filter   | `QdrantService.search(projectPublicId, ...)` (ADR-023A) |
+
+---
+
+## 🚧 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  |
@@ -13,9 +13,9 @@ trigger: always_on
 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-018):** Ollama on Admin Desktop ONLY — NO direct DB/storage access
+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-020):** RFA-First approach with unified pipeline architecture
+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

@@ -30,7 +30,7 @@ trigger: always_on
 - [ ] No SQL injection vulnerabilities
 - [ ] File upload validation (whitelist + ClamAV)
 - [ ] Rate limiting applied to auth endpoints
- [ ] AI boundary enforcement (ADR-023) - no direct DB/storage access
+- [ ] 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
@@ -1,4 +1,8 @@
-# TypeScript Rules (v1.9.3)
+---
+trigger: always_on
+---
+
+# TypeScript Rules

 ## Core Standards

@@ -26,14 +26,20 @@ trigger: always_on

 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             |
-| **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                  |
+| 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                    |
@@ -32,15 +32,82 @@ trigger: always_on
 - 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.md`                | RHF+Zod + TanStack Query + Thai comments            |
-| "เพิ่ม field ใหม่"   | `ADR-009`, `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" | `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                      |
+| 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.md`                | RHF+Zod + TanStack Query + Thai comments                                              |
+| "เพิ่ม field ใหม่"      | `ADR-009`, `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"    | `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                 |
@@ -1,16 +1,21 @@
+---
+trigger: always_on
+---
+
 # LCBP3 Agent Rules

 Critical rules and guidelines for AI agents working on LCBP3-DMS.

 ## Version

- **Current:** v1.9.3
- **Last Updated:** 2026-05-15
- **Synced with:** `AGENTS.md` (v1.9.3)
+- **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
@@ -24,6 +29,7 @@ This directory contains rule files that define:
 ### 🔴 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
@@ -35,15 +41,28 @@ Build fails immediately if violated:
 ### 🟡 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 — GUIDELINES
+### 🟢 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
@@ -52,61 +71,68 @@ Best practice — follow when possible:

 ### Core Rules (Tier 1 - CRITICAL)

-| File | Purpose |
-|------|---------|
+| 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 |
+| `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 |
+| 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) |
+| 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 |
-|------|---------|
+| 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 |
+| `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 |
-| **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 |
+| 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` and `03-typescript.md`
-3. **Review ADR references** — Ensure all ADR references are current (ADR-023, ADR-023A, etc.)
+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

@@ -0,0 +1,145 @@
+// File: src/modules/ai/ai-migration-checkpoint.service.ts
+// Change Log:
+// - 2026-05-23: สร้าง service จัดการ Migration Checkpoint, Queue และ Error log ผ่าน API (ADR-023A)
+
+import { Injectable, Logger } from '@nestjs/common';
+import { InjectRepository } from '@nestjs/typeorm';
+import { DataSource, Repository } from 'typeorm';
+import {
+  MigrationProgress,
+  MigrationProgressStatus,
+} from './entities/migration-progress.entity';
+import {
+  MigrationReviewRecord,
+  MigrationReviewRecordStatus,
+} from './entities/migration-review.entity';
+import {
+  MigrationErrorLogDto,
+  MigrationQueueRecordDto,
+  SaveCheckpointDto,
+} from './dto/migration-checkpoint.dto';
+
+/** Response DTO สำหรับ Checkpoint */
+export interface CheckpointResponse {
+  batchId: string;
+  lastProcessedIndex: number;
+  status: MigrationProgressStatus;
+  updatedAt: Date | null;
+}
+
+@Injectable()
+export class AiMigrationCheckpointService {
+  private readonly logger = new Logger(AiMigrationCheckpointService.name);
+
+  constructor(
+    @InjectRepository(MigrationProgress)
+    private readonly progressRepo: Repository<MigrationProgress>,
+    @InjectRepository(MigrationReviewRecord)
+    private readonly reviewRepo: Repository<MigrationReviewRecord>,
+    private readonly dataSource: DataSource
+  ) {}
+
+  /**
+   * ดึง Checkpoint ปัจจุบันของ Batch — ถ้ายังไม่มีให้คืนค่า default
+   */
+  async getCheckpoint(batchId: string): Promise<CheckpointResponse> {
+    const record = await this.progressRepo.findOne({ where: { batchId } });
+    if (!record) {
+      return {
+        batchId,
+        lastProcessedIndex: 0,
+        status: MigrationProgressStatus.RUNNING,
+        updatedAt: null,
+      };
+    }
+    return {
+      batchId: record.batchId,
+      lastProcessedIndex: record.lastProcessedIndex,
+      status: record.status,
+      updatedAt: record.updatedAt,
+    };
+  }
+
+  /**
+   * บันทึกหรืออัพเดต Checkpoint ของ Batch (Upsert)
+   */
+  async saveCheckpoint(dto: SaveCheckpointDto): Promise<CheckpointResponse> {
+    const existing = await this.progressRepo.findOne({
+      where: { batchId: dto.batchId },
+    });
+
+    const record =
+      existing ?? this.progressRepo.create({ batchId: dto.batchId });
+    record.lastProcessedIndex = dto.lastProcessedIndex;
+    record.status = dto.status ?? MigrationProgressStatus.RUNNING;
+
+    const saved = await this.progressRepo.save(record);
+    this.logger.log(
+      `Checkpoint saved — batchId=${dto.batchId} index=${dto.lastProcessedIndex}`
+    );
+    return {
+      batchId: saved.batchId,
+      lastProcessedIndex: saved.lastProcessedIndex,
+      status: saved.status,
+      updatedAt: saved.updatedAt,
+    };
+  }
+
+  /**
+   * บันทึกรายการเข้า Review Queue (Upsert โดยใช้ idempotencyKey)
+   */
+  async upsertQueueRecord(
+    dto: MigrationQueueRecordDto
+  ): Promise<{ publicId: string }> {
+    const idempotencyKey =
+      dto.idempotencyKey ?? `${dto.batchId}:${dto.documentNumber}`;
+
+    const existing = await this.reviewRepo.findOne({
+      where: { idempotencyKey },
+    });
+
+    const record = existing ?? this.reviewRepo.create({ idempotencyKey });
+
+    record.batchId = dto.batchId;
+    record.originalFileName = dto.documentNumber;
+    record.tempAttachmentId = dto.tempAttachmentId ?? undefined;
+    record.confidenceScore = dto.confidence ?? undefined;
+    record.status =
+      dto.status === 'PENDING_REVIEW'
+        ? MigrationReviewRecordStatus.PENDING_REVIEW
+        : MigrationReviewRecordStatus.PENDING;
+    record.errorReason = dto.reviewReason ?? undefined;
+    record.extractedMetadata = {
+      documentNumber: dto.documentNumber,
+      subject: dto.subject,
+      originalSubject: dto.originalSubject,
+      ...(dto.aiResult ?? {}),
+    };
+
+    const saved = await this.reviewRepo.save(record);
+    this.logger.log(
+      `Queue record upserted — batchId=${dto.batchId} doc=${dto.documentNumber} status=${dto.status}`
+    );
+    return { publicId: saved.publicId };
+  }
+
+  /**
+   * บันทึก Error Log สำหรับเอกสารที่ประมวลผลไม่สำเร็จ
+   */
+  async logError(dto: MigrationErrorLogDto): Promise<{ id: number }> {
+    const result = await this.dataSource.query<{ insertId: number }[]>(
+      `INSERT INTO migration_errors (batch_id, document_number, error_type, error_message, created_at)
+       VALUES (?, ?, ?, ?, NOW())`,
+      [
+        dto.batchId,
+        dto.documentNumber,
+        dto.errorType ?? 'UNKNOWN',
+        dto.errorMessage ?? '',
+      ]
+    );
+    this.logger.warn(
+      `Error logged — batchId=${dto.batchId} doc=${dto.documentNumber} type=${dto.errorType}`
+    );
+    return { id: result[0]?.insertId ?? 0 };
+  }
+}
@@ -7,6 +7,7 @@
 // - 2026-05-21: เพิ่ม GET /ai/admin/health สำหรับดึงสถานะสุขภาพ AI Infrastructure (T028).
 // - 2026-05-21: เพิ่ม POST /ai/admin/sandbox/extract endpoint สำหรับ Superadmin OCR sandbox (T041 & T042)
 // - 2026-05-21: แก้ไขข้อห้ามใช้ parseInt โดยการใช้ Number แทนตามกฎ Tier 1
+// - 2026-05-23: เพิ่ม Migration Checkpoint API endpoints แทน MySQL direct access (ADR-023A)
 // Controller สำหรับ AI Gateway Endpoints (ADR-023)

 import {
@@ -79,6 +80,12 @@ import { AiEnabledGuard } from './guards/ai-enabled.guard';
 import { InjectRedis } from '@nestjs-modules/ioredis';
 import Redis from 'ioredis';
 import { FileStorageService } from '../../common/file-storage/file-storage.service';
+import { AiMigrationCheckpointService } from './ai-migration-checkpoint.service';
+import {
+  MigrationErrorLogDto,
+  MigrationQueueRecordDto,
+  SaveCheckpointDto,
+} from './dto/migration-checkpoint.dto';

@ApiTags('AI Gateway')
@Controller('ai')
@@ -91,6 +98,7 @@ export class AiController {
    private readonly aiSettingsService: AiSettingsService,
    private readonly aiToolRegistryService: AiToolRegistryService,
    private readonly fileStorageService: FileStorageService,
+    private readonly migrationCheckpointService: AiMigrationCheckpointService,
    @InjectRedis() private readonly redis: Redis
  ) {}

@@ -682,4 +690,47 @@ export class AiController {
      user.user_id
    );
  }
+
+  // ─── Migration Checkpoint API (ADR-023A) ──────────────────────────────────
+
+  @Get('migration/checkpoint/:batchId')
+  @UseGuards(JwtAuthGuard)
+  @ApiBearerAuth()
+  @ApiOperation({ summary: 'Migration: ดึง Checkpoint ของ Batch (ADR-023A)' })
+  @ApiParam({
+    name: 'batchId',
+    description: 'Batch ID ที่ต้องการดึง Checkpoint',
+  })
+  async getMigrationCheckpoint(@Param('batchId') batchId: string) {
+    return this.migrationCheckpointService.getCheckpoint(batchId);
+  }
+
+  @Post('migration/checkpoint')
+  @UseGuards(JwtAuthGuard)
+  @ApiBearerAuth()
+  @HttpCode(HttpStatus.OK)
+  @ApiOperation({ summary: 'Migration: บันทึก/อัพเดต Checkpoint (ADR-023A)' })
+  async saveMigrationCheckpoint(@Body() dto: SaveCheckpointDto) {
+    return this.migrationCheckpointService.saveCheckpoint(dto);
+  }
+
+  @Post('migration/queue/record')
+  @UseGuards(JwtAuthGuard)
+  @ApiBearerAuth()
+  @HttpCode(HttpStatus.OK)
+  @ApiOperation({
+    summary: 'Migration: บันทึกรายการเข้า Review Queue (ADR-023A)',
+  })
+  async upsertMigrationQueueRecord(@Body() dto: MigrationQueueRecordDto) {
+    return this.migrationCheckpointService.upsertQueueRecord(dto);
+  }
+
+  @Post('migration/errors')
+  @UseGuards(JwtAuthGuard)
+  @ApiBearerAuth()
+  @HttpCode(HttpStatus.OK)
+  @ApiOperation({ summary: 'Migration: บันทึก Error Log (ADR-023A)' })
+  async logMigrationError(@Body() dto: MigrationErrorLogDto) {
+    return this.migrationCheckpointService.logError(dto);
+  }
 }
@@ -6,6 +6,7 @@
 // - 2026-05-19: เพิ่ม AiToolModule (ADR-025 AI Tool Layer).
 // - 2026-05-21: ลงทะเบียน SystemSetting, AiSettingsService และ AiEnabledGuard สำหรับ ADR-027.
 // - 2026-05-22: นำเข้าและลงทะเบียน CleanupTempFilesWorker (T016) เพื่อลบไฟล์แนบชั่วคราวหมดอายุ
+// - 2026-05-23: ลงทะเบียน MigrationProgress + AiMigrationCheckpointService (ADR-023A)
 // Module สำหรับ AI Gateway — ลงทะเบียน Services และ Controllers (ADR-023)

 import { Logger, Module, OnModuleInit } from '@nestjs/common';
@@ -33,7 +34,9 @@ import { EmbeddingService } from './services/embedding.service';
 import { MigrationLog } from './entities/migration-log.entity';
 import { AiAuditLog } from './entities/ai-audit-log.entity';
 import { MigrationReviewRecord } from './entities/migration-review.entity';
+import { MigrationProgress } from './entities/migration-progress.entity';
 import { SystemSetting } from './entities/system-setting.entity';
+import { AiMigrationCheckpointService } from './ai-migration-checkpoint.service';
 import { AiEnabledGuard } from './guards/ai-enabled.guard';
 import { UserModule } from '../user/user.module';
 import { MigrationModule } from '../migration/migration.module';
@@ -67,6 +70,7 @@ import {
      AiAuditLog,
      AuditLog,
      MigrationReviewRecord,
+      MigrationProgress,
      SystemSetting,
      Attachment,
      Project,
@@ -129,6 +133,7 @@ import {
    AiService,
    AiSettingsService,
    AiIngestService,
+    AiMigrationCheckpointService,
    AiQueueService,
    AiQdrantService,
    AiValidationService,
@@ -151,6 +156,7 @@ import {
    AiService,
    AiSettingsService,
    AiIngestService,
+    AiMigrationCheckpointService,
    AiQueueService,
    AiQdrantService,
    AiValidationService,
@@ -0,0 +1,97 @@
+// File: src/modules/ai/dto/migration-checkpoint.dto.ts
+// Change Log:
+// - 2026-05-23: สร้าง DTOs สำหรับ Migration Checkpoint API endpoints (ADR-023A)
+
+import {
+  IsEnum,
+  IsNotEmpty,
+  IsNumber,
+  IsObject,
+  IsOptional,
+  IsString,
+  Max,
+  Min,
+} from 'class-validator';
+import { MigrationProgressStatus } from '../entities/migration-progress.entity';
+
+/** DTO สำหรับบันทึก/อัพเดต Checkpoint */
+export class SaveCheckpointDto {
+  @IsString()
+  @IsNotEmpty()
+  batchId!: string;
+
+  @IsNumber()
+  @Min(0)
+  lastProcessedIndex!: number;
+
+  @IsEnum(MigrationProgressStatus)
+  @IsOptional()
+  status?: MigrationProgressStatus;
+}
+
+/** DTO สำหรับบันทึกรายการเข้า Review Queue */
+export class MigrationQueueRecordDto {
+  @IsString()
+  @IsNotEmpty()
+  batchId!: string;
+
+  @IsString()
+  @IsNotEmpty()
+  documentNumber!: string;
+
+  @IsString()
+  @IsOptional()
+  subject?: string;
+
+  @IsString()
+  @IsOptional()
+  originalSubject?: string;
+
+  @IsNumber()
+  @IsOptional()
+  tempAttachmentId?: number;
+
+  @IsNumber()
+  @Min(0)
+  @Max(1)
+  @IsOptional()
+  confidence?: number;
+
+  @IsString()
+  @IsOptional()
+  reviewReason?: string;
+
+  @IsEnum(['PENDING', 'PENDING_REVIEW'])
+  status!: 'PENDING' | 'PENDING_REVIEW';
+
+  @IsObject()
+  @IsOptional()
+  aiResult?: Record<string, unknown>;
+
+  @IsString()
+  @IsOptional()
+  idempotencyKey?: string;
+}
+
+/** DTO สำหรับบันทึก Error Log */
+export class MigrationErrorLogDto {
+  @IsString()
+  @IsNotEmpty()
+  batchId!: string;
+
+  @IsString()
+  @IsNotEmpty()
+  documentNumber!: string;
+
+  @IsString()
+  @IsOptional()
+  errorType?: string;
+
+  @IsString()
+  @IsOptional()
+  errorMessage?: string;
+
+  @IsString()
+  @IsOptional()
+  jobId?: string;
+}
@@ -0,0 +1,32 @@
+// File: src/modules/ai/entities/migration-progress.entity.ts
+// Change Log:
+// - 2026-05-23: สร้าง entity สำหรับ migration_progress table (Checkpoint management ADR-023A)
+
+import { Column, Entity, PrimaryColumn, UpdateDateColumn } from 'typeorm';
+
+export enum MigrationProgressStatus {
+  RUNNING = 'RUNNING',
+  COMPLETED = 'COMPLETED',
+  FAILED = 'FAILED',
+}
+
+/** ตารางติดตามความคืบหน้า Batch Migration — ใช้สำหรับ Resume กรณี n8n หยุดกลางทาง */
+@Entity('migration_progress')
+export class MigrationProgress {
+  @PrimaryColumn({ name: 'batch_id', type: 'varchar', length: 50 })
+  batchId!: string;
+
+  @Column({ name: 'last_processed_index', type: 'int', default: 0 })
+  lastProcessedIndex!: number;
+
+  @Column({
+    name: 'STATUS',
+    type: 'enum',
+    enum: MigrationProgressStatus,
+    default: MigrationProgressStatus.RUNNING,
+  })
+  status!: MigrationProgressStatus;
+
+  @UpdateDateColumn({ name: 'updated_at' })
+  updatedAt!: Date;
+}
@@ -15,6 +15,7 @@ import { UuidBaseEntity } from '../../../common/entities/uuid-base.entity';

 export enum MigrationReviewRecordStatus {
  PENDING = 'PENDING',
+  PENDING_REVIEW = 'PENDING_REVIEW',
  IMPORTED = 'IMPORTED',
  REJECTED = 'REJECTED',
 }
@@ -0,0 +1,144 @@
+<!-- File: memory/agent-memory.md -->
+<!-- Change Log
+- 2026-05-23: Initialized long-term memory system with core project rules, Windows environment settings, and constraints.
+- 2026-05-23 (Session 2): N8N Workflow Refactor — QuizMe session, decisions locked, สร้าง CONTEXT-N8N-Refactor.md, สร้าง n8n.workflow.v2.json (ADR-023A compliant), อัพเดต 03-05 และ 03-06.
+-->
+
+# 🧠 Agent Long-term Project Memory
+
+> **Project:** NAP-DMS (LCBP3) — Laem Chabang Port Phase 3 Document Management System
+> **Version:** 1.9.6 (Last Synced: 2026-05-23)
+> **Stack:** NestJS 11 + Next.js 16 + TypeScript + MariaDB 11.8 + Redis + BullMQ + Elasticsearch + Ollama (on-prem AI)
+
+---
+
+## 🧭 1. กฎการรันคำสั่งและการทำงานบนระบบ (OS Rules & Sandbox Constraints)
+
+> [!IMPORTANT]
+> **ระบบรันอยู่บน Windows OS**
+>
+> - ห้ามใช้คำสั่ง `bash` หรือคำสั่งของ Linux โดยเด็ดขาด
+> - คำสั่งทุกประเภทที่จะส่งให้ผู้ใช้รันหรือรันผ่าน Terminal ต้องเป็น **PowerShell** หรือ **CMD** เท่านั้น
+> - ห้ามใช้คำสั่ง `cd` ในการสลับ Directory ให้ระบุพารามิเตอร์ `Cwd` ใน Tool ตรง ๆ
+
+---
+
+## 🔴 2. กฎเหล็กระดับ Tier 1 (CI Blocker - ห้ามละเมิดเด็ดขาด)
+
+### 🆔 2.1 กลยุทธ์ UUID (ADR-019)
+
+- คีย์หลักในฐานข้อมูล (Internal PK) เป็น `INT AUTO_INCREMENT` ส่วนคีย์สาธารณะใน API/URL (Public API) จะใช้ **UUIDv7** เท่านั้น
+- ฟิลด์คีย์สาธารณะชื่อ `publicId: string` จะถูกส่งออกไปใน API โดยตรง
+- ❌ **ห้ามใช้** `parseInt()`, `Number()`, หรือเครื่องหมายบวก `+` บน UUID (เช่น `parseInt(projectId)` จะคำนวณผิดพลาดทันที)
+- ❌ **ห้ามใช้** fallback ในลักษณะ `id ?? ''` ในฝั่ง Frontend ให้ใช้ `publicId` เท่านั้น
+
+### 🛡️ 2.2 สิทธิ์การใช้งานและความปลอดภัย (RBAC & Auth)
+
+- API ทุกตัวที่เป็นการปรับปรุงข้อมูล (Mutation: POST/PUT/PATCH) ต้องใช้ **CASL Guard** ตรวจสอบสิทธิ์ 4 ระดับ (RBAC Matrix) เสมอ
+- API สำหรับการแก้ไขข้อมูล (POST/PUT/PATCH) ต้องตรวจสอบและยืนยัน **`Idempotency-Key`** ใน HTTP Header ทุกครั้ง
+- การเข้ารหัสรหัสผ่านใช้ `bcrypt` ที่ระดับ 12 salt rounds เสมอ
+
+### 💾 2.3 การปรับแต่งและเปลี่ยนแปลง Schema (ADR-009)
+
+- ❌ **ห้ามใช้ TypeORM migrations ในการอัปเดต Schema** บนสภาพแวดล้อม Production
+- ให้ใช้วิธี **แก้ไขไฟล์ SQL โครงสร้างหลักตรง ๆ** ใน `specs/03-Data-and-Storage/lcbp3-v1.9.0-schema-02-tables.sql` หรือเพิ่มการทำงานในโฟลเดอร์ `deltas/*.sql` เท่านั้น
+
+### 🏎️ 2.4 ป้องกัน Race Conditions ในเลขเอกสาร (ADR-002)
+
+- การจัดสรรและจองเลขที่เอกสารใหม่ (Document Numbering) ต้องใช้ **Redis Redlock** ควบคู่กับ TypeORM `@VersionColumn` เสมอ ห้ามเขียนตัวนับ (Counter) ในฝั่ง Application เดี่ยว ๆ
+
+### 🤖 2.5 ขอบเขตและการแยกส่วน AI (ADR-023/023A)
+
+- **Ollama (AI Inference) ต้องทำงานบน Admin Desktop เท่านั้น** ห้ามรันบน Server หรือ Docker ใน Production
+- AI ห้ามเชื่อมต่อและเข้าถึง Database หรือ Storage โดยตรง (ต้องผ่าน DMS API เท่านั้น)
+- โมเดลที่ใช้: `gemma4:e4b Q8_0` (LLM) และ `nomic-embed-text` (Embeddings)
+- การทำงานแบบ Background Job หรือ Inference ที่ใช้เวลานานต้องสั่งงานผ่าน **BullMQ** (คิว `ai-realtime` และ `ai-batch`)
+- ข้อมูลผลลัพธ์จาก AI ทั้งหมดต้องผ่านการตรวจสอบความถูกต้องโดยมนุษย์ (Human-in-the-loop) เสมอ
+
+---
+
+## 🏷️ 3. Domain Terminology (คำศัพท์เฉพาะของระบบ DMS)
+
+ห้ามใช้คำศัพท์ทั่วไป ให้ใช้คำศัพท์ตามสารบัญหลักของโปรเจกต์เสมอ:
+
+| คำศัพท์ที่ถูกต้อง (✅ Use) | คำศัพท์ที่ห้ามใช้ (❌ Don't Use) | คำอธิบายภาษาไทย                                |
+| :------------------------- | :------------------------------- | :--------------------------------------------- |
+| **Correspondence**         | Letter, Communication            | จดหมาย/เอกสารติดต่อสื่อสาร (ครอบคลุมทุกประเภท) |
+| **RFA**                    | Approval Request                 | เอกสารขออนุมัติ (Request for Approval)         |
+| **Transmittal**            | Delivery Note, Cover Letter      | เอกสารนำส่งแบบและเอกสาร                        |
+| **Circulation**            | Distribution, Routing            | ใบเวียนเอกสารภายในหน่วยงาน                     |
+| **Shop Drawing**           | Construction Drawing             | แบบก่อสร้างจริง                                |
+| **Contract Drawing**       | Design Drawing, Blueprint        | แบบคู่สัญญา                                    |
+| **Workflow Engine**        | Approval Flow, Process Engine    | ระบบควบคุมและเปลี่ยนสถานะเอกสาร                |
+| **Document Numbering**     | Document ID, Auto Number         | ระบบออกเลขที่เอกสารอัตโนมัติ                   |
+
+---
+
+## 🔄 4. สถานะและประวัติการทำงาน (Latest Session Progress)
+
+### Session 1 — 2026-05-23 (Specs Reorganization)
+
+- Reorganize โครงสร้างโฟลเดอร์ `specs/` สำเร็จ (`100-Infrastructures`, `200-fullstacks`, `300-others`)
+- อัปเดตกฎ `AGENTS.md` และ `GEMINI.md` ให้ตรงกับมาตรฐานใหม่
+- ริเริ่มระบบ `memory/agent-memory.md`
+
+### Session 2 — 2026-05-23 (N8N Workflow Refactor) ← **ล่าสุด**
+
+#### Decisions ที่ Lock แล้ว (จาก QuizMe Session)
+
+| #       | Decision                                                                             |
+| ------- | ------------------------------------------------------------------------------------ |
+| S1      | **n8n = Migration only** — New Correspondence ใช้ Backend pipeline (BullMQ)          |
+| S2      | New Correspondence → BullMQ `ai-realtime` (ไม่ผ่าน n8n)                              |
+| S3      | n8n call `POST /api/ai/jobs` (Backend) แทน Ollama direct (ADR-023A)                  |
+| PA      | Excel metadata (`docNumber`, `title`, `sender`, etc.) ส่งไปพร้อม AI job เป็น context |
+| PB-Tags | Tag suggestion ทาง C — แนะนำ existing + สร้าง tag ใหม่ได้ถ้าไม่มี (`isNew` flag)     |
+| PB-UX   | Editable form pre-filled ด้วย AI suggestions — user approve/edit ก่อน submit         |
+
+#### Endpoint ที่ Verified แล้ว
+
+- `POST /api/ai/jobs` (`type: migrate-document`) — **พร้อมใช้งานแล้ว** (verified 2026-05-23)
+- `GET /api/ai/jobs/:jobId` — polling endpoint พร้อม
+- `POST /api/storage/upload` — two-phase upload พร้อม
+
+#### ไฟล์ที่สร้าง/แก้ไข
+
+| ไฟล์                                                           | การเปลี่ยนแปลง                                                 |
+| -------------------------------------------------------------- | -------------------------------------------------------------- |
+| `specs/03-Data-and-Storage/CONTEXT-N8N-Refactor.md`            | ✅ สร้างใหม่ — context doc สำหรับ implement                    |
+| `specs/03-Data-and-Storage/n8n.workflow.v2.json`               | ✅ สร้างใหม่ — ADR-023A compliant workflow                     |
+| `specs/03-Data-and-Storage/03-05-n8n-migration-setup-guide.md` | ✅ อัพเดต v1.9.0 — ลบ Ollama direct, เพิ่มขั้นตอน update token |
+| `specs/03-Data-and-Storage/03-06-migration-business-scope.md`  | ✅ อัพเดต — Gate #1 blocker → Verified 2026-05-23              |
+
+#### สาระสำคัญของ n8n.workflow.v2.json
+
+**Nodes ที่ลบ (ADR-023A violations):** `Ollama AI Analysis`, `Build AI Prompt`, `Extract PDF Text` (Tika), `Check/Update Fallback State`, `Import to Backend`, `Upsert Tags`, `Link Tags`
+
+**Nodes ใหม่:** `Validate Token` → `Upload PDF to Backend` → `Build AI Job Payload` → `Submit AI Job` → `Poll AI Job Status`
+
+**Flow สรุป:**
+
+```
+Form Trigger → Set Config → Health/Token Check → Fetch Master Data
+→ File Mount Check → Read Excel → Read Checkpoint
+→ [Per Record: File Validate → Upload PDF → Submit AI Job → Poll → Parse/Route]
+    → Auto/Flagged → migration_review_queue
+    → Rejected → CSV Log
+    → Error → CSV + DB Log
+→ Save Checkpoint → Delay → Loop
+```
+
+---
+
+## 🎯 5. แผนงานขั้นต่อไป (Next Session Focus)
+
+### N8N Migration (งานหลักที่เหลือ)
+
+- [ ] **Import `n8n.workflow.v2.json`** เข้า n8n UI และทดสอบ End-to-End
+- [ ] **ตรวจสอบ `ai-realtime` processor** ว่า return `suggestedTags[]` พร้อม `isNew` flag
+- [ ] **Frontend Editable Review Form** (Pipeline B) — pre-fill AI suggestions + tag suggestion UI
+- [ ] **Dry Run** กับ Excel จริงก่อน Production Migration
+
+### งานทั่วไป
+
+- [ ] รักษาความเป็นระเบียบและอัปเดต `memory/agent-memory.md` ทุกครั้งที่ Task สำคัญเสร็จ
@@ -0,0 +1,15 @@
+-- File: specs/03-Data-and-Storage/deltas/2026-05-23-alter-migration-review-queue-enum.sql
+-- Change Log:
+-- - 2026-05-23: เพิ่ม PENDING_REVIEW เข้า status ENUM ของ migration_review_queue (TypeORM-managed)
+--              n8n workflow ไม่ใช้ MySQL direct access แล้ว — ใช้ POST /api/ai/migration/queue/record แทน (ADR-023A)
+-- Delta: เพิ่ม PENDING_REVIEW ใน status column ของ migration_review_queue
+-- Date: 2026-05-23
+-- Related: ADR-028, ADR-023A
+-- รันก่อน deploy backend ที่มี PENDING_REVIEW ใน MigrationReviewRecordStatus enum
+ALTER TABLE migration_review_queue
+MODIFY COLUMN STATUS ENUM(
+    'PENDING',
+    'PENDING_REVIEW',
+    'IMPORTED',
+    'REJECTED'
+  ) DEFAULT 'PENDING';
@@ -39,7 +39,12 @@ CREATE TABLE IF NOT EXISTS migration_review_queue (
  extracted_tags JSON COMMENT 'Tag ที่ AI นำเสนอหรือจับคู่ได้',
  temp_attachment_id INT NULL COMMENT 'ID ของไฟล์ชั่วคราวจาก Two-Phase Storage',
  review_reason VARCHAR(255),
-  STATUS ENUM('PENDING', 'APPROVED', 'REJECTED') DEFAULT 'PENDING',
+  STATUS ENUM(
+    'PENDING',
+    'PENDING_REVIEW',
+    'APPROVED',
+    'REJECTED'
+  ) DEFAULT 'PENDING',
  reviewed_by VARCHAR(100),
  reviewed_at TIMESTAMP NULL,
  created_at TIMESTAMP DEFAULT CURRENT_TIMESTAMP,
@@ -30,7 +30,7 @@
    },
    {
      "parameters": {
-        "jsCode": "// ============================================\n// CONFIGURATION v2.0 — ADR-023A Compliant\n// n8n เรียกแค่ DMS Backend API เท่านั้น — ห้ามเรียก Ollama โดยตรง\n// ============================================\nconst formData = $('Form Trigger').first()?.json || {};\nconst batchSizeInput = parseInt(String(formData['Batch Size'] || '0'));\nconst excelFileInput = String(formData['Excel File Path'] || '').trim();\n\nconst BATCH_ID = (() => {\n  const d = new Date(Date.now() + 7 * 3600000);\n  const s = d.toISOString();\n  return s.substring(0,10).replace(/-/g,'') + ':' + s.substring(11,16).replace(/:/g,'');\n})();\n\nconst CONFIG = {\n  // Backend Settings\n  BACKEND_URL: 'https://backend.np-dms.work',\n  MIGRATION_TOKEN: 'Bearer YOUR_MIGRATION_TOKEN_HERE', // 🔴 เปลี่ยน\n\n  // Batch Settings\n  BATCH_SIZE: batchSizeInput > 0 ? batchSizeInput : 10,\n  BATCH_ID: BATCH_ID,\n  DELAY_MS: 2000,\n\n  // AI Job Settings (ADR-023A)\n  AI_JOB_POLL_INTERVAL_MS: 5000,\n  AI_JOB_TIMEOUT_MS: 120000,\n\n  // Confidence Thresholds\n  CONFIDENCE_HIGH: 0.85,\n  CONFIDENCE_LOW: 0.60,\n\n  // Paths (Container paths — ต้องตรงกับ volume mount ใน docker-compose)\n  EXCEL_FILE: excelFileInput || '/home/node/.n8n-files/staging_ai/C22024.xlsx',\n  SOURCE_PDF_DIR: '/home/node/.n8n-files/staging_ai',\n  LOG_PATH: '/home/node/.n8n-files/migration_logs',\n};\n\nreturn [{ json: { config: CONFIG } }];"
+        "jsCode": "// ============================================\n// CONFIGURATION v2.0 — ADR-023A Compliant\n// n8n เรียกแค่ DMS Backend API เท่านั้น — ห้ามเรียก Ollama โดยตรง\n// ============================================\nconst formData = $('Form Trigger').first()?.json || {};\nconst batchSizeInput = parseInt(String(formData['Batch Size'] || '0'));\nconst excelFileInput = String(formData['Excel File Path'] || '').trim();\n\nconst BATCH_ID = (() => {\n  const d = new Date(Date.now() + 7 * 3600000);\n  const s = d.toISOString();\n  return s.substring(0,10).replace(/-/g,'') + ':' + s.substring(11,16).replace(/:/g,'');\n})();\n\nconst CONFIG = {\n  // Backend Settings\n  BACKEND_URL: 'https://backend.np-dms.work',\n  MIGRATION_TOKEN: 'Bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJ1c2VybmFtZSI6Im1pZ3JhdGlvbl9ib3QiLCJzdWIiOjUsInNjb3BlIjoiR2xvYmFsIiwiaWF0IjoxNzc5NTQwNDk4LCJleHAiOjQ5MzUzMDA0OTh9.TZVzG8u4Cyz8hi0cU3eGaeXinKWKHN3HtYnDcS5p_5I', // 🔴 เปลี่ยน\n\n  // Batch Settings\n  BATCH_SIZE: batchSizeInput > 0 ? batchSizeInput : 10,\n  BATCH_ID: BATCH_ID,\n  DELAY_MS: 2000,\n\n  // AI Job Settings (ADR-023A)\n  AI_JOB_POLL_INTERVAL_MS: 5000,\n  AI_JOB_TIMEOUT_MS: 120000,\n\n  // Confidence Thresholds\n  CONFIDENCE_HIGH: 0.85,\n  CONFIDENCE_LOW: 0.60,\n\n  // Paths (Container paths — ต้องตรงกับ volume mount ใน docker-compose)\n  EXCEL_FILE: excelFileInput || '/home/node/.n8n-files/staging_ai/C22024.xlsx',\n  SOURCE_PDF_DIR: '/home/node/.n8n-files/staging_ai',\n  LOG_PATH: '/home/node/.n8n-files/migration_logs',\n};\n\nreturn [{ json: { config: CONFIG } }];"
      },
      "id": "8f1d3378-cca6-48b6-99db-693e46ac81ef",
      "name": "Set Configuration",
@@ -56,7 +56,7 @@
    },
    {
      "parameters": {
-        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/auth/me",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/auth/profile",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
@@ -160,28 +160,30 @@
    },
    {
      "parameters": {
-        "operation": "executeQuery",
-        "query": "SELECT last_processed_index, status FROM migration_progress WHERE batch_id = '{{$('Set Configuration').first().json.config.BATCH_ID}}' LIMIT 1",
+        "url": "={{ $('Set Configuration').first().json.config.BACKEND_URL + '/api/ai/migration/checkpoint/' + $('Set Configuration').first().json.config.BATCH_ID }}",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "={{$('Set Configuration').first().json.config.MIGRATION_TOKEN}}"
+            }
+          ]
+        },
        "options": {}
      },
      "id": "a83f8598-72fd-4cc8-9d98-1ea3cb3b42df",
      "name": "Read Checkpoint",
-      "type": "n8n-nodes-base.mySql",
-      "typeVersion": 2.4,
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.1,
      "position": [32096, 13504],
      "alwaysOutputData": true,
-      "credentials": {
-        "mySql": {
-          "id": "CHHfbKhMacNo03V4",
-          "name": "MySQL account"
-        }
-      },
      "onError": "continueErrorOutput",
-      "notes": "อ่านตำแหน่งล่าสุดที่ประมวลผล"
+      "notes": "GET /api/ai/migration/checkpoint/:batchId — ADR-023A (ไม่ใช้ MySQL โดยตรง)"
    },
    {
      "parameters": {
-        "jsCode": "const cpJson = $input.first()?.json || {};\nconst startIndex = cpJson.last_processed_index || 0;\nconst config = $('Set Configuration').first().json.config;\n\nconst allItems = $('Read Excel').all().map(i => i.json);\nconst remaining = allItems.slice(startIndex);\nconst currentBatch = remaining.slice(0, config.BATCH_SIZE);\n\n// Exit condition: ไม่มี records เหลือ\nif (currentBatch.length === 0) {\n  return [{ json: { batch_complete: true, total_processed: startIndex } }];\n}\n\nconst normalize = (str) => {\n  if (!str) return '';\n  return String(str).normalize('NFC').trim();\n};\n\nreturn currentBatch.map((item, i) => {\n  const getVal = (possibleKeys) => {\n    const exactMatch = possibleKeys.find(k => item[k] !== undefined);\n    if (exactMatch) return item[exactMatch];\n    const lowerTrimmedKeys = Object.keys(item).map(k => ({ original: k, parsed: k.toLowerCase().trim() }));\n    for (const pk of possibleKeys) {\n      const found = lowerTrimmedKeys.find(k => k.parsed === pk.toLowerCase().trim());\n      if (found) return item[found.original];\n    }\n    return '';\n  };\n\n  const docNum = getVal(['document_number', 'correspondence_number', 'Document Number', 'Corr. No.']);\n  const excelFileName = getVal(['File name', 'file_name', 'File Name', 'filename']);\n  \n  if (!excelFileName) {\n    throw new Error(`Missing 'File name' column for row ${i + startIndex + 1}, document: ${docNum}`);\n  }\n  \n  return {\n    json: {\n      batch_complete: false,\n      document_number: normalize(docNum),\n      title: normalize(getVal(['title', 'Title', 'Subject', 'subject'])),\n      legacy_number: normalize(getVal(['legacy_number', 'Legacy Number', 'Response Doc.'])),\n      excel_revision: getVal(['revision', 'Revision', 'rev']) || 1,\n      original_index: startIndex + i,\n      batch_id: config.BATCH_ID,\n      file_name: normalize(excelFileName),\n      issued_date: normalize(getVal(['issued_date', 'Issued_date', 'Issued Date', 'date', 'Date'])),\n      received_date: normalize(getVal(['received_date', 'Received_date', 'Received Date'])),\n      sender: normalize(getVal(['sender', 'Sender', 'From', 'from'])),\n      receiver: normalize(getVal(['receiver', 'Receiver', 'To', 'to'])),\n    }\n  };\n});"
+        "jsCode": "const cpJson = $input.first()?.json || {};\nconst startIndex = cpJson.data?.lastProcessedIndex ?? cpJson.lastProcessedIndex ?? cpJson.last_processed_index ?? 0;\nconst config = $('Set Configuration').first().json.config;\n\nconst allItems = $('Read Excel').all().map(i => i.json);\nconst remaining = allItems.slice(startIndex);\nconst currentBatch = remaining.slice(0, config.BATCH_SIZE);\n\n// Exit condition: ไม่มี records เหลือ\nif (currentBatch.length === 0) {\n  return [{ json: { batch_complete: true, total_processed: startIndex } }];\n}\n\nconst normalize = (str) => {\n  if (!str) return '';\n  return String(str).normalize('NFC').trim();\n};\n\nreturn currentBatch.map((item, i) => {\n  const getVal = (possibleKeys) => {\n    const exactMatch = possibleKeys.find(k => item[k] !== undefined);\n    if (exactMatch) return item[exactMatch];\n    const lowerTrimmedKeys = Object.keys(item).map(k => ({ original: k, parsed: k.toLowerCase().trim() }));\n    for (const pk of possibleKeys) {\n      const found = lowerTrimmedKeys.find(k => k.parsed === pk.toLowerCase().trim());\n      if (found) return item[found.original];\n    }\n    return '';\n  };\n\n  const docNum = getVal(['document_number', 'correspondence_number', 'Document Number', 'Corr. No.']);\n  const excelFileName = getVal(['File name', 'file_name', 'File Name', 'filename']);\n  \n  if (!excelFileName) {\n    throw new Error(`Missing 'File name' column for row ${i + startIndex + 1}, document: ${docNum}`);\n  }\n  \n  return {\n    json: {\n      batch_complete: false,\n      document_number: normalize(docNum),\n      title: normalize(getVal(['title', 'Title', 'Subject', 'subject'])),\n      legacy_number: normalize(getVal(['legacy_number', 'Legacy Number', 'Response Doc.'])),\n      excel_revision: getVal(['revision', 'Revision', 'rev']) || 1,\n      original_index: startIndex + i,\n      batch_id: config.BATCH_ID,\n      file_name: normalize(excelFileName),\n      issued_date: normalize(getVal(['issued_date', 'Issued_date', 'Issued Date', 'date', 'Date'])),\n      received_date: normalize(getVal(['received_date', 'Received_date', 'Received Date'])),\n      sender: normalize(getVal(['sender', 'Sender', 'From', 'from'])),\n      receiver: normalize(getVal(['receiver', 'Receiver', 'To', 'to'])),\n    }\n  };\n});"
      },
      "id": "80845e32-c283-4e9f-af73-6339d675fb38",
      "name": "Process Batch + Encoding",
@@ -218,7 +220,7 @@
    {
      "parameters": {
        "method": "POST",
-        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/storage/upload",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/files/upload",
        "sendHeaders": true,
        "headerParameters": {
          "parameters": [
@@ -368,41 +370,55 @@
    },
    {
      "parameters": {
-        "operation": "executeQuery",
-        "query": "INSERT INTO migration_review_queue (document_number, title, original_title, ai_suggested_category, ai_confidence, ai_issues, review_reason, status, created_at) VALUES ('{{$json.document_number}}', '{{$json.ai_result.subject || $json.title}}', '{{$json.title}}', '{{$json.ai_result.suggested_category}}', {{$json.ai_result.confidence}}, '{{JSON.stringify({ job_id: $json.job_id, temp_attachment_id: $json.temp_attachment_id, type_code: $json.ai_result.type_code, subject: $json.ai_result.subject, suggested_tags: $json.ai_result.suggested_tags, key_points: $json.ai_result.key_points || [], issued_date: $json.ai_result.issued_date, received_date: $json.ai_result.received_date })}}', '{{$json.review_reason || \"\"}}', 'PENDING', NOW()) ON DUPLICATE KEY UPDATE status = 'PENDING', review_reason = '{{$json.review_reason || \"\"}}', ai_issues = VALUES(ai_issues), created_at = NOW()",
+        "method": "POST",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/ai/migration/queue/record",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "={{$('Set Configuration').first().json.config.MIGRATION_TOKEN}}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ batchId: $json.batch_id, documentNumber: $json.document_number, subject: ($json.ai_result?.subject || $json.title), originalSubject: $json.title, tempAttachmentId: $json.temp_attachment_id, confidence: $json.ai_result?.confidence, reviewReason: $json.review_reason || '', status: 'PENDING', aiResult: $json.ai_result, idempotencyKey: $json.batch_id + ':' + $json.document_number }) }}",
        "options": {}
      },
      "id": "c1bd4485-e58f-4270-892e-edda34c2e328",
      "name": "Insert Review Queue (Auto)",
-      "type": "n8n-nodes-base.mySql",
-      "typeVersion": 2.4,
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.1,
      "position": [33856, 13312],
-      "credentials": {
-        "mySql": {
-          "id": "CHHfbKhMacNo03V4",
-          "name": "MySQL account"
-        }
-      },
-      "notes": "Auto Ready (confidence ≥ 0.85) → migration_review_queue PENDING"
+      "onError": "continueErrorOutput",
+      "notes": "POST /api/ai/migration/queue/record (PENDING) — ADR-023A"
    },
    {
      "parameters": {
-        "operation": "executeQuery",
-        "query": "INSERT INTO migration_review_queue (document_number, title, original_title, ai_suggested_category, ai_confidence, ai_issues, review_reason, status, created_at) VALUES ('{{$json.document_number}}', '{{$json.ai_result.subject || $json.title}}', '{{$json.title}}', '{{$json.ai_result.suggested_category}}', {{$json.ai_result.confidence}}, '{{JSON.stringify({ job_id: $json.job_id, temp_attachment_id: $json.temp_attachment_id, type_code: $json.ai_result.type_code, subject: $json.ai_result.subject, suggested_tags: $json.ai_result.suggested_tags, key_points: $json.ai_result.key_points || [], issued_date: $json.ai_result.issued_date, received_date: $json.ai_result.received_date })}}', '{{$json.review_reason}}', 'PENDING_REVIEW', NOW()) ON DUPLICATE KEY UPDATE status = 'PENDING_REVIEW', review_reason = '{{$json.review_reason}}', ai_issues = VALUES(ai_issues), created_at = NOW()",
+        "method": "POST",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/ai/migration/queue/record",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "={{$('Set Configuration').first().json.config.MIGRATION_TOKEN}}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ batchId: $json.batch_id, documentNumber: $json.document_number, subject: ($json.ai_result?.subject || $json.title), originalSubject: $json.title, tempAttachmentId: $json.temp_attachment_id, confidence: $json.ai_result?.confidence, reviewReason: $json.review_reason || '', status: 'PENDING_REVIEW', aiResult: $json.ai_result, idempotencyKey: $json.batch_id + ':' + $json.document_number }) }}",
        "options": {}
      },
      "id": "f1a2b3c4-d5e6-7890-abcd-567890123456",
      "name": "Insert Review Queue (Flagged)",
-      "type": "n8n-nodes-base.mySql",
-      "typeVersion": 2.4,
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.1,
      "position": [33856, 13504],
-      "credentials": {
-        "mySql": {
-          "id": "CHHfbKhMacNo03V4",
-          "name": "MySQL account"
-        }
-      },
-      "notes": "Flagged (confidence 0.60–0.84) → migration_review_queue PENDING_REVIEW"
+      "onError": "continueErrorOutput",
+      "notes": "POST /api/ai/migration/queue/record (PENDING_REVIEW) — ADR-023A"
    },
    {
      "parameters": {
@@ -428,41 +444,55 @@
    },
    {
      "parameters": {
-        "operation": "executeQuery",
-        "query": "INSERT INTO migration_errors (batch_id, document_number, error_type, error_message, created_at) VALUES ('{{$('Set Configuration').first().json.config.BATCH_ID}}', '{{$json.document_number}}', '{{$json.error_type || \"UNKNOWN\"}}', '{{$json.error || $json.parse_error}}', NOW())",
+        "method": "POST",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/ai/migration/errors",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "={{$('Set Configuration').first().json.config.MIGRATION_TOKEN}}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ batchId: $('Set Configuration').first().json.config.BATCH_ID, documentNumber: $json.document_number, errorType: $json.error_type || 'UNKNOWN', errorMessage: $json.error || $json.parse_error || '', jobId: $json.job_id || '' }) }}",
        "options": {}
      },
      "id": "0f058ad0-3c09-4c9f-bdcf-503cd58ee395",
      "name": "Log Error to DB",
-      "type": "n8n-nodes-base.mySql",
-      "typeVersion": 2.4,
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.1,
      "position": [34032, 13888],
-      "credentials": {
-        "mySql": {
-          "id": "CHHfbKhMacNo03V4",
-          "name": "MySQL account"
-        }
-      },
-      "notes": "บันทึก Error ลง MariaDB"
+      "onError": "continueErrorOutput",
+      "notes": "POST /api/ai/migration/errors — ADR-023A"
    },
    {
      "parameters": {
-        "operation": "executeQuery",
-        "query": "INSERT INTO migration_progress (batch_id, last_processed_index, status) VALUES ('{{$('Set Configuration').first().json.config.BATCH_ID}}', {{$json.original_index || 0}}, 'RUNNING') ON DUPLICATE KEY UPDATE last_processed_index = {{$json.original_index || 0}}, updated_at = NOW()",
+        "method": "POST",
+        "url": "={{$('Set Configuration').first().json.config.BACKEND_URL}}/api/ai/migration/checkpoint",
+        "sendHeaders": true,
+        "headerParameters": {
+          "parameters": [
+            {
+              "name": "Authorization",
+              "value": "={{$('Set Configuration').first().json.config.MIGRATION_TOKEN}}"
+            }
+          ]
+        },
+        "sendBody": true,
+        "specifyBody": "json",
+        "jsonBody": "={{ JSON.stringify({ batchId: $('Set Configuration').first().json.config.BATCH_ID, lastProcessedIndex: $json.original_index || 0, status: 'RUNNING' }) }}",
        "options": {}
      },
      "id": "bb0e611b-db28-4266-ba40-3b5d534a16f7",
      "name": "Save Checkpoint",
-      "type": "n8n-nodes-base.mySql",
-      "typeVersion": 2.4,
+      "type": "n8n-nodes-base.httpRequest",
+      "typeVersion": 4.1,
      "position": [34032, 13312],
-      "credentials": {
-        "mySql": {
-          "id": "CHHfbKhMacNo03V4",
-          "name": "MySQL account"
-        }
-      },
-      "notes": "บันทึก Checkpoint ทุก record ที่ผ่าน Review Queue"
+      "onError": "continueErrorOutput",
+      "notes": "POST /api/ai/migration/checkpoint — ADR-023A"
    },
    {
      "parameters": {