CASAN/README.md

# CASAN AI-SDLC

CASAN là governance harness cho AI Software Development Life Cycle. Harness có
thể được cài một lần ở máy developer rồi adopt vào nhiều dự án hiện hữu mà không
copy toàn bộ CASAN hoặc dựng lại project shell.

> **Bắt đầu nhanh:** xem [CASAN Quick Start](#casan-quick-start). Tài liệu chi
> tiết: [cài đặt hybrid](docs/casan/CASAN_INSTALL_HYBRID.md),
> [dùng CASAN cho dự án thực tế](docs/guides/CASAN_USING_FOR_REAL_PROJECTS_VI.md)
> và [tạo project shell production](docs/guides/CASAN_PROJECT_SHELL_PRODUCTION.md).

## Table of Contents

- [CASAN Quick Start](#casan-quick-start)
- [Project Objectives](#project-objectives)
- [Dùng CASAN cho dự án thực tế](docs/guides/CASAN_USING_FOR_REAL_PROJECTS_VI.md)
- [CASAN Project Shell production](docs/guides/CASAN_PROJECT_SHELL_PRODUCTION.md)
- [Requirements](#requirements)
- [Input for Flow](#input-for-flow)
- [Output for Flow](#output-for-flow)
- [Full AI-SDLC Flow](#full-ai-sdlc-flow)
  - [Flow Steps](#flow-steps)
  - [Flow Diagram](#flow-diagram)
  - [Legend](#legend)
- [Agents](#agents)
  - [Spec-Kit Agents (Core Flow)](#spec-kit-agents-core-flow)
  - [FPT-Defined Agents (IPA Gen + Review + Orchestrator + Test)](#fpt-defined-agents-ipa-gen--review--orchestrator--test)
- [AI-SDLC Usage Guide](#ai-sdlc-usage-guide)
- [Directory Structure](#directory-structure)
  - [Directory Details](#directory-details)

## CASAN Quick Start

### 1. Cài CASAN một lần trên máy developer

Yêu cầu chung: Python 3. Trên macOS/Linux cần Bash; trên Windows cần PowerShell
và Git for Windows (Git Bash).

macOS/Linux, chạy từ checkout CASAN:

```bash
sh install.sh --level devkit
# Nếu installer báo launcher chưa nằm trên PATH:
export PATH="${CASAN_HOME:-$HOME/.casan}/bin:$PATH"
casan version
```

Windows PowerShell, chạy từ checkout CASAN:

```powershell
pwsh .\install.ps1
```

Sau lần cài đầu tiên trên Windows, mở PowerShell mới rồi kiểm tra:

```powershell
casan version
```

Mặc định harness được cài tại `~/.casan` trên macOS/Linux và
`%LOCALAPPDATA%\casan` trên Windows.

### 2. Adopt CASAN vào dự án

Chạy tại root của dự án cần bảo vệ:

```bash
cd <project-root>
casan init
```

Trong terminal tương tác, `casan init` hiển thị menu cho phép chọn một hoặc
nhiều integration:

1. Claude Code
2. Codex
3. GitHub Copilot trong VS Code

Có thể cấu hình không tương tác:

```bash
casan init --client claude
casan init --client claude,codex
casan init --client vscode-copilot --vscode-install yes
casan init --client all
```

Mặc định production là `--mode enforce`. Chỉ dùng `--mode observe` cho giai
đoạn pilot telemetry-only.

`casan init` an toàn với dự án đã có project shell, agents, skills hoặc hooks:

- Không sửa source code và không dựng lại vỏ dự án.
- Merge idempotent vào `.claude/settings.json`, `.codex/hooks.json` và
  `.vscode/extensions.json`.
- Giữ nguyên cấu hình/hook của dự án; chạy lại không tạo hook CASAN trùng lặp.
- Chỉ ghi bootstrap/config per-project; harness vẫn dùng bản global đã pin hash.

Nếu ứng dụng tự gọi LLM API qua backend riêng, ngoài Claude Code/Codex/Copilot,
luồng đó không tự động đi qua project hooks và cần adapter CASAN riêng.

Với project đã adopt CASAN theo mô hình cũ và đang chứa
`packages/casan-harness`, init nhận diện đây là vendored application thay vì
source hub:

- Không cần `--force`.
- Không xóa harness, scripts, workflow hoặc evidence cũ.
- Tự nâng cấp các block nằm giữa marker `CASAN_PROMPT_ENFORCEMENT_START/END`.
- Báo rõ file nào còn prose legacy ngoài marker cần review thủ công.

### 3. Hành vi chat theo client

| Client đã enable | Prompt đi qua CASAN | Onboarding bắt buộc |
|---|---|---|
| Claude Code CLI/extension | Tự động với chat bình thường | Mở project ở trusted workspace |
| Codex CLI/extension | Tự động với chat bình thường | Mở `/hooks`, review và trust đúng hook hash |
| GitHub Copilot Chat | Chỉ khi gửi `@casan <prompt>` | Cài CASAN VSIX; built-in Copilot chat không bị global-intercept |

Không cần chỉ định một “CASAN agent” khi chat bằng Claude Code hoặc Codex.
GitHub Copilot là ngoại lệ: VS Code không cung cấp API cho extension intercept
mọi built-in Copilot prompt, nên CASAN cung cấp route explicit `@casan`.

### 4. Kiểm tra sau khi init

```bash
casan doctor
casan verify-harness
```

Với Codex, `doctor` kiểm tra config/bootstrap/runtime nhưng bước trust vẫn phải
thực hiện trong `/hooks`. Với Copilot, nếu máy chưa có `code` CLI, init trả về
đường dẫn VSIX để cài bằng lệnh **Extensions: Install from VSIX...**.

Khi nâng cấp global CASAN, chạy lại `casan init` trong project để cập nhật
bootstrap và pin hash mới. Xem đầy đủ tùy chọn và troubleshooting tại
[CASAN_INSTALL_HYBRID.md](docs/casan/CASAN_INSTALL_HYBRID.md).

## Project Objectives

Apply AI to the SDLC process to automate and optimize the creation of software products from initial requirements to complete source code.

## Requirements
- **Flow + Prompt + Template**: **Spec-Kit**
- **AI Tool của flow demo/legacy**: **Claude Code** là assistant chính; CASAN
  harness và Control Panel có thể chạy độc lập bằng browser/CLI/CI hoặc dùng model
  local/OmniRoute.
- **AI-SDLC**: AI-integrated SDLC process **Spec-Kit Modified** (Add IPA Gen + Review Loop + Orchestrator)
- **IPA Template**: Following IPA (Information-technology Promotion Agency) template standards

---

## Input for Flow

- `apps/<project-id>/domain/input/requirement.md` — project requirements
- `apps/<project-id>/domain/input/architecture.md` — architecture and constraints
- Project-owned input, reference, agent, and skill directories remain untouched

## Output for Flow

| Output | Location | Description |
|--------|----------|-------------|
| **IPA Docs** (SRS, BD, DD, Test Cases, Test Reports) | `docs/output/ipa-docs/` | Design documents generated by IPA agents (organized in `srs/`, `bd/`, `dd/`, `testcase/`, `testreport/` subdirectories) |
| **AI Agent Logs** | `docs/output/output_logs/` | Execution logs from AI agents |
| **SRS-Systems** | `docs/output/srs-systems/` | System-wide SRS (generated once during input clarification phase, not part of the main flow steps) |
| **Spec-Kit Artifacts** | `specs/[FEATURE_NAME]/` | Feature artifacts generated by Spec-Kit agents (`spec.md`, `plan.md`, `tasks.md`, contracts, checklists) |
| **Source Code** | Project-defined locations | CASAN does not impose an application framework or source layout |

---

## Full AI-SDLC Flow

The entire flow is orchestrated by **`casan.pipeline`**, which executes all steps automatically from start to finish.

### Flow Steps

| Step | Agent | Output | Category |
|------|-------|--------|----------|
| **STEP 1** | `casan.srs` | SRS (ソフトウェア要件定義書) | 📄 IPA Doc Gen |
| **STEP 2** | `casan.bd` | BD — 外部設計 (Basic Design) | 📄 IPA Doc Gen |
| **STEP 3** | `speckit.specify` | `spec.md` | 📝 Spec-Kit |
| **STEP 4** | `speckit.clarify` | Resolve ambiguities (NO PAUSE) | 📝 Spec-Kit |
| **STEP 5** | `casan.reviewspec` 🔄 | Spec review (auto-retry) | 🔍 Agent Review |
| **STEP 6** | `speckit.plan` | `plan.md` + data-model + contracts | 📝 Spec-Kit |
| **STEP 7** | `casan.reviewplan` 🔄 | Plan review (auto-retry) | 🔍 Agent Review |
| **STEP 8** | `casan.dd` | DD — 内部設計 (Detail Design) | 📄 IPA Doc Gen |
| **STEP 8b** | `casan.testkit` | Test cases (`gen-testcases`) | 🧪 Test |
| **STEP 9** | `speckit.tasks` | `tasks.md` | 📝 Spec-Kit |
| **STEP 10** | `speckit.implement` 🔄 | Implementation + build & fix (auto-retry) | 📝 Spec-Kit |
| **STEP 11** | `casan.reviewcode` 🔄 | Code review + DB data check (auto-retry) | 🔍 Agent Review |
| **STEP 12** | `casan.testkit` 🔄 | Run tests (`run-tests`) — BACK-TO-PLAN on fail | 🧪 Test |
| **STEP 13** | Boss (direct) | Build BE + connect DB + Build FE + Launch UI → `open_browser_page` | 🚀 Deploy |

### Flow Diagram

```
┌─────────────────────────────────────────────────────────────┐
│  INPUT                                                      │
│  [ Raw Requirement ]  [ Clear Requirement ]  [ Tech Stack ] │
└──────────────────────────────┬──────────────────────────────┘
                               │
          ┌────────────────────┴──── (one-time, pre-flow) ────┐
          │  casan.srs → docs/output/srs-systems/     │
          └────────────────────┬──────────────────────────────┘
                               │
  ╔════════════════════════════╧══════════════════════════════════╗
  ║  casan.pipeline  (Orchestrator)                       ║
  ║                                                              ║
  ║  ┌─── IPA Doc Gen ───────────────────────────────────────┐   ║
  ║  │  STEP 1   casan.srs        → SRS                  │   ║
  ║  │  STEP 2   casan.bd         → BD (外部設計)         │   ║
  ║  └───────────────────────────────────────────────────────┘   ║
  ║        │                                                     ║
  ║        ▼                                                     ║
  ║  ┌─── Spec-Kit + Review Loop ────────────────────────────┐   ║
  ║  │  STEP 3   speckit.specify      → spec.md              │   ║
  ║  │  STEP 4   speckit.clarify      → resolve ambiguities  │   ║
  ║  │  STEP 5   casan.reviewspec 🔄 auto-retry          │   ║
  ║  │        │                                               │   ║
  ║  │        ▼                                               │   ║
  ║  │  STEP 6   speckit.plan         → plan.md + data-model │   ║
  ║  │  STEP 7   casan.reviewplan 🔄 auto-retry          │   ║
  ║  └───────────────────────────────────────────────────────┘   ║
  ║        │                                                     ║
  ║        ▼                                                     ║
  ║  ┌─── IPA Doc Gen (Detail) ──────────────────────────────┐   ║
  ║  │  STEP 8   casan.dd         → DD (内部設計)         │   ║
  ║  │  STEP 8b  casan.testkit    → gen-testcases         │   ║
  ║  └───────────────────────────────────────────────────────┘   ║
  ║        │                                                     ║
  ║        ▼                                                     ║
  ║  ┌─── Implementation ───────────────────────────────────┐    ║
  ║  │  STEP 9   speckit.tasks        → tasks.md            │    ║
  ║  │  STEP 10  speckit.implement    🔄 build & fix        │    ║
  ║  │  STEP 11  casan.reviewcode 🔄 code review        │    ║
  ║  │  STEP 12  casan.testkit    🔄 run-tests          │    ║
  ║  │           (BACK-TO-PLAN on fail)                      │    ║
  ║  └──────────────────────────────────────────────────────┘    ║
  ║        │                                                     ║
  ║        ▼                                                     ║
  ║  ┌─── Deploy ───────────────────────────────────────────┐    ║
  ║  │  STEP 13  Boss → build BE + DB + FE → open_browser   │    ║
  ║  └──────────────────────────────────────────────────────┘    ║
  ║                                                              ║
  ╚══════════════════════════════════════════════════════════════╝
```

### Legend

| Symbol | Meaning |
|--------|---------|
| 🔄 | Auto-retry loop (agent retries until pass) |

---

## Agents

### Spec-Kit Agents (Core Flow)

| Agent | Description |
|-------|-------------|
| `speckit.constitution` | Define project principles and constraints |
| `speckit.specify` | Convert requirements into feature specification (`spec.md`) |
| `speckit.clarify` | Resolve ambiguous requirements (no pause) |
| `speckit.plan` | Create implementation plan (`plan.md` + data-model + contracts) |
| `speckit.tasks` | Generate task list (`tasks.md`) |
| `speckit.implement` | Implementation with auto build & fix |
| `speckit.analyze` | Cross-artifact consistency and quality analysis |
| `speckit.checklist` | Generate custom quality checklists |
| `speckit.taskstoissues` | Convert tasks to GitHub issues |

### FPT-Defined Agents (IPA Gen + Review + Orchestrator + Test)

| Agent | Description |
|-------|-------------|
| `casan.pipeline` | **Orchestrator** — runs all 13 steps end-to-end automatically |
| `casan.srs` | Generate SRS (ソフトウェア要件定義書) per module → `docs/output/ipa-docs/` |
| `casan.bd` | Generate BD / 外部設計 (Basic Design) per module → `docs/output/ipa-docs/` |
| `casan.dd` | Generate DD / 内部設計 (Detail Design) per module → `docs/output/ipa-docs/` |
| `casan.srs` | Generate system-wide SRS (one-time, pre-flow) → `docs/output/srs-systems/` |
| `casan.reviewspec` | **Review** — validate `spec.md` quality and completeness |
| `casan.reviewplan` | **Review** — validate `plan.md` conformance to spec |
| `casan.reviewcode` | **Review** — code review + DB data check |
| `casan.testkit` | **Test** — generate test cases from SRS + BD + DD; run automated tests |
| `Flow-Agent` | General-purpose flow agent |

---

## AI-SDLC Usage Guide

1. **Adopt governance**: Run `casan init`, select the IDE clients, complete any trust/VSIX onboarding, then run `casan doctor`
2. **Prepare Input**: Place requirements and architecture under `apps/<project-id>/domain/input/`
3. **Configuration**: Set up the project constitution first, keep specifications focused on what and why, and only decide technical stack where the input explicitly requires it
4. **(One-time) Generate System SRS**: Run `casan.srs` to generate system-wide SRS → `docs/output/srs-systems/`
5. **Run AI Flow**: Invoke `casan.pipeline` to execute the full 13-step flow automatically, with strict TDD enforced across specification, planning, task generation, and implementation
6. **Output**:
   - `docs/output/ipa-docs/` — IPA design documents (SRS, BD, DD, Test Cases)
   - `docs/output/output_logs/` — AI agent execution logs
   - `docs/output/srs-systems/` — System-wide SRS (generated once)
   - `specs/[FEATURE_NAME]/` — Spec-Kit artifacts (`spec.md`, `plan.md`, `tasks.md`, etc.)
   - Source code remains in the locations defined by the adopted project

---

## Directory Structure

```
├── .claude/
│   ├── agents/                     # All agent definitions (subagents)
│   │   ├── casan.pipeline.md      #   Boss orchestrator agent
│   │   ├── speckit.*.md            #   Spec-Kit agents (specify, clarify, plan, tasks, implement, analyze, checklist, taskstoissues)
│   │   ├── casan.*.md              #   Reusable CASAN agents (srs, bd, dd, reviews, testkit, pipeline)
│   │   ├── protocols/              #   Shared protocols (auto-resolve, gate-retry, logging, pipeline-context, etc.)
│   │   ├── steps/                  #   Step definitions for orchestrator (steps-01-04, steps-05-07, etc.)
│   │   └── templates/              #   Agent output templates (pipeline-completion, report-templates)
│   └── commands/                   # Claude Code slash commands
│       ├── casan.pipeline.md      #   Run full pipeline (/casan.pipeline)
│       ├── speckit.*.md            #   Spec-Kit slash commands
│       └── casan.*.md              #   Reusable CASAN commands
│
├── CLAUDE.md                       # Global Claude Code project instructions
│
├── .specify/                       # SpecKit configuration and templates
│   ├── init-options.json           # Initialization options
│   ├── memory/
│   │   └── constitution.md         # Project-wide principles and constraints
│   ├── scripts/                    # Utility scripts
│   │   ├── bash/                   #   Bash scripts
│   │   └── powershell/             #   PowerShell scripts
│   └── templates/
│       ├── agent-file-template.md  # Agent definition template
│       ├── checklist-template.md   # Quality checklist template
│       ├── constitution-template.md
│       ├── spec-template.md        # Spec-Kit templates
│       ├── plan-template.md
│       ├── tasks-template.md
│       ├── srs-template.md         # IPA templates (SRS, BD, DD)
│       ├── bd-ipa-template.md
│       └── dd-ipa-template.md
│
├── apps/
│   └── <project-id>/domain/        # Per-project CASAN domain pack
│       ├── input/
│       │   ├── requirement.md      # Project requirements
│       │   └── architecture.md     # Architecture and constraints
│       ├── corpus/                 # Benign/red-team evaluation corpus
│       ├── golden-runs/            # Golden outputs for drift checks
│       └── traceability-map.json
│
├── docs/
│   └── output/                     # Output of the AI-SDLC process
│       ├── ipa-docs/               #   IPA documents
│       │   ├── srs/                #     SRS documents per module
│       │   ├── bd/                 #     BD documents per module
│       │   ├── dd/                 #     DD documents per module
│       │   ├── testcase/           #     Test case documents per module
│       │   └── testreport/         #     Test report documents per module
│       ├── output_logs/            #   AI agent execution logs (per feature)
│       └── srs-systems/            #   System-wide SRS (generated once, pre-flow)
│
├── specs/                          # Optional Spec-Kit feature artifacts
├── <existing-source-directories>/  # Project-owned; CASAN init preserves them
└── <existing-ci-and-tooling>/      # Project-owned; CASAN init preserves them
```

### Directory Details

#### `.claude/agents/`
Contains all agent definition files used by Claude Code. This includes both **Spec-Kit agents** (core flow: `speckit.specify`, `speckit.clarify`, `speckit.plan`, `speckit.tasks`, `speckit.implement`, plus utility agents `speckit.analyze`, `speckit.checklist`, `speckit.taskstoissues`) and reusable **CASAN agents** (`casan.*`):
- **IPA Doc Gen agents** — `casan.srs`, `casan.bd`, `casan.dd`: generate IPA-standard design documents (SRS, BD, DD) per module, output to `docs/output/ipa-docs/`.
- **Review agents** — `casan.reviewspec`, `casan.reviewplan`, `casan.reviewcode`: validate the quality of Spec-Kit artifacts (`spec.md`, `plan.md`, source code) with auto-retry loops.
- **Orchestrator** — `casan.pipeline`: runs the full 13-step flow end-to-end automatically.
- **Test agent** — `casan.testkit`: generates test cases from SRS + BD + DD and executes automated tests (Jest / Playwright).
- **Subdirectories** — `protocols/` (shared protocols for auto-resolve, gate-retry, logging, etc.), `steps/` (orchestrator step definitions), `templates/` (output report templates).

#### `.claude/commands/`
Claude Code slash commands that invoke the corresponding agents. Type `/speckit.specify`, `/casan.pipeline`, etc. in Claude Code to trigger the pipeline.

#### `.specify/`
Spec-Kit configuration directory. Stores project-wide principles, scripts, and all templates:
- **`init-options.json`** — Initialization options for Spec-Kit setup.
- **`memory/constitution.md`** — The project constitution: shared principles, constraints, and conventions that apply to every feature across the entire project.
- **`scripts/`** — Utility scripts in `bash/` and `powershell/` for automation tasks.
- **`templates/`** — Format templates used by agents to generate artifacts. Includes Spec-Kit templates (`spec-template.md`, `plan-template.md`, `tasks-template.md`, `constitution-template.md`, `checklist-template.md`, `agent-file-template.md`) and IPA templates (`srs-template.md`, `bd-ipa-template.md`, `dd-ipa-template.md`).

#### `apps/<project-id>/domain/input/`
Per-project requirements and architecture used by CASAN gates and traceability.
The L2 initializer creates missing domain-pack files without overwriting existing
project content.

#### `docs/output/`
All artifacts produced by the AI-SDLC process:
- **`ipa-docs/`** — IPA design documents organized in subdirectories: `srs/`, `bd/`, `dd/`, `testcase/`, `testreport/`. Generated by `casan.srs`, `casan.bd`, `casan.dd`, and `casan.testkit`. Each subdirectory contains per-module documents.
- **`output_logs/`** — Execution logs from AI agents organized per feature (e.g., `000-system-srs/`, `001-access-authentication/`, etc.), useful for debugging and auditing the generation process.
- **`srs-systems/`** — System-wide SRS generated once at the beginning by `casan.srs`. Contains per-module SRS overviews (`mod01-access-authentication/`, `mod02-workspace-dashboard/`, etc.) plus `srs-overview-system.md`. Not part of the 13-step flow.

#### `specs/`

Each folder contains `spec.md`, `plan.md`, `tasks.md`, `checklists/`, and `contracts/`. This directory serves as the **knowledge base** for agents.

#### Source Code
CASAN does not prescribe NestJS, React, Java, .NET, or any other application
stack. Existing source, CI, `.claude`, `.github`, agents, skills, prompts, and
project instructions remain project-owned. Hybrid init only adds or merges the
CASAN integration files documented above.