fix: Restructure to monorepo and update dependencies

- Reorganize project structure (packages/rules, apps/mcp-server)
- Create codingbuddy-rules package
- Update MCP SDK and zod dependencies
- Fix workspace configuration

resolve #77

Author: wishket-pjw

.antigravity/rules/instructions.md

@@ -2,11 +2,11 @@
 
 ## Common AI Rules Reference
 
-This project follows shared AI coding rules from `.ai-rules/` for consistency across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro).
+This project follows shared AI coding rules from `packages/rules/.ai-rules/` for consistency across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro).
 
 ### 📚 Core Workflow (PLAN/ACT/EVAL)
 
-**Source**: `.ai-rules/rules/core.md`
+**Source**: `packages/rules/.ai-rules/rules/core.md`
 
 #### Work Modes
 
@@ -27,11 +27,11 @@ You have three modes of operation:
 - Print `# Mode: ACT` in act mode
 - Print `# Mode: EVAL` in eval mode
 
-See full workflow details in [.ai-rules/rules/core.md](../../.ai-rules/rules/core.md)
+See full workflow details in [packages/rules/.ai-rules/rules/core.md](../../packages/rules/.ai-rules/rules/core.md)
 
 ### 🏗️ Project Context
 
-**Source**: `.ai-rules/rules/project.md`
+**Source**: `packages/rules/.ai-rules/rules/project.md`
 
 #### Tech Stack
 
@@ -47,11 +47,11 @@ src/
 └── shared/       # Common modules
 ```
 
-See full project setup in [.ai-rules/rules/project.md](../../.ai-rules/rules/project.md)
+See full project setup in [packages/rules/.ai-rules/rules/project.md](../../packages/rules/.ai-rules/rules/project.md)
 
 ### 🎯 Augmented Coding Principles
 
-**Source**: `.ai-rules/rules/augmented-coding.md`
+**Source**: `packages/rules/.ai-rules/rules/augmented-coding.md`
 
 #### TDD Cycle
 1. **Red**: Write a failing test
@@ -65,11 +65,11 @@ See full project setup in [.ai-rules/rules/project.md](../../.ai-rules/rules/pro
 - **90%+ test coverage** goal
 - **No mocking** - test real behavior
 
-See full augmented coding guide in [.ai-rules/rules/augmented-coding.md](../../.ai-rules/rules/augmented-coding.md)
+See full augmented coding guide in [packages/rules/.ai-rules/rules/augmented-coding.md](../../packages/rules/.ai-rules/rules/augmented-coding.md)
 
 ### 🤖 Specialist Agents
 
-**Source**: `.ai-rules/agents/`
+**Source**: `packages/rules/.ai-rules/agents/`
 
 Available specialist agents:
 - **Frontend Developer** - React/Next.js, TDD, design system
@@ -85,7 +85,7 @@ Available specialist agents:
 - **Code Quality Specialist** - SOLID, DRY, complexity
 - **DevOps Engineer** - Docker, Datadog, deployment
 
-See agent details in [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md)
+See agent details in [packages/rules/.ai-rules/agents/README.md](../../packages/rules/.ai-rules/agents/README.md)
 
 ## Antigravity-Specific Features
 
@@ -105,4 +105,4 @@ Use `task_boundary` tool for tracking progress in different modes:
 
 ---
 
-For full integration guide, see [.ai-rules/adapters/antigravity.md](../../.ai-rules/adapters/antigravity.md)
+For full integration guide, see [packages/rules/.ai-rules/adapters/antigravity.md](../../packages/rules/.ai-rules/adapters/antigravity.md)

.claude/rules/custom-instructions.md

@@ -2,11 +2,11 @@
 
 ## Project Rules
 
-Follow the common rules defined in `.ai-rules/` for consistency across all AI coding assistants.
+Follow the common rules defined in `packages/rules/.ai-rules/` for consistency across all AI coding assistants.
 
 ### 📚 Core Workflow
 
-**Source**: `.ai-rules/rules/core.md`
+**Source**: `packages/rules/.ai-rules/rules/core.md`
 
 **Work Modes**:
 - **PLAN mode**: Create implementation plans with TDD approach
@@ -19,7 +19,7 @@ Follow the common rules defined in `.ai-rules/` for consistency across all AI co
 
 ### 🏗️ Project Context
 
-**Source**: `.ai-rules/rules/project.md`
+**Source**: `packages/rules/.ai-rules/rules/project.md`
 
 **Tech Stack**: 프로젝트의 `package.json` 참조
 
@@ -30,7 +30,7 @@ Follow the common rules defined in `.ai-rules/` for consistency across all AI co
 
 ### 🎯 Code Quality
 
-**Source**: `.ai-rules/rules/augmented-coding.md`
+**Source**: `packages/rules/.ai-rules/rules/augmented-coding.md`
 
 **TDD Cycle**: Red (failing test) → Green (minimal code) → Refactor
 
@@ -43,15 +43,15 @@ Follow the common rules defined in `.ai-rules/` for consistency across all AI co
 
 ### 🤖 Specialist Agents
 
-**Source**: `.ai-rules/agents/`
+**Source**: `packages/rules/.ai-rules/agents/`
 
 **Available Specialists** (12 agents):
 - Frontend Developer, Code Reviewer
 - Architecture, Test Strategy, Performance, Security
 - Accessibility, SEO, Design System, Documentation
 - Code Quality, DevOps Engineer
 
-See [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md) for details.
+See [packages/rules/.ai-rules/agents/README.md](../../packages/rules/.ai-rules/agents/README.md) for details.
 
 ## Keyword Invocation
 
@@ -68,18 +68,18 @@ See [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md) for details.
 - Always respond in **Korean (한국어)**
 - Use structured markdown formatting
 - Provide clear, actionable feedback
-- Reference project context from `.ai-rules/rules/project.md`
+- Reference project context from `packages/rules/.ai-rules/rules/project.md`
 - Follow PLAN → ACT → EVAL workflow when appropriate
 
 ## Full Documentation
 
 For comprehensive guides:
-- **Core Rules**: [.ai-rules/rules/core.md](../../.ai-rules/rules/core.md)
-- **Project Setup**: [.ai-rules/rules/project.md](../../.ai-rules/rules/project.md)
-- **Augmented Coding**: [.ai-rules/rules/augmented-coding.md](../../.ai-rules/rules/augmented-coding.md)
-- **Agents System**: [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md)
-- **Claude Integration**: [.ai-rules/adapters/claude-code.md](../../.ai-rules/adapters/claude-code.md)
+- **Core Rules**: [packages/rules/.ai-rules/rules/core.md](../../packages/rules/.ai-rules/rules/core.md)
+- **Project Setup**: [packages/rules/.ai-rules/rules/project.md](../../packages/rules/.ai-rules/rules/project.md)
+- **Augmented Coding**: [packages/rules/.ai-rules/rules/augmented-coding.md](../../packages/rules/.ai-rules/rules/augmented-coding.md)
+- **Agents System**: [packages/rules/.ai-rules/agents/README.md](../../packages/rules/.ai-rules/agents/README.md)
+- **Claude Integration**: [packages/rules/.ai-rules/adapters/claude-code.md](../../packages/rules/.ai-rules/adapters/claude-code.md)
 
 ---
 
-**Note**: These instructions reference common AI rules from `.ai-rules/` directory shared across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro) for consistency.
+**Note**: These instructions reference common AI rules from `packages/rules/.ai-rules/` directory shared across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro) for consistency.

.codex/rules/system-prompt.md

@@ -1,10 +1,10 @@
 # Codex System Prompt
 
-This project uses shared AI coding rules from `.ai-rules/` directory for consistency across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro).
+This project uses shared AI coding rules from `packages/rules/.ai-rules/` directory for consistency across all AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro).
 
 ## 📚 Core Workflow Rules
 
-**Source**: [.ai-rules/rules/core.md](../../.ai-rules/rules/core.md)
+**Source**: [packages/rules/.ai-rules/rules/core.md](../../packages/rules/.ai-rules/rules/core.md)
 
 ### Work Modes
 
@@ -28,21 +28,21 @@ You have three modes of operation:
 ### Agent System
 
 **Auto-activated Agents**:
-- **Frontend Developer** (`.ai-rules/agents/frontend-developer.json`): PLAN/ACT modes
-- **Code Reviewer** (`.ai-rules/agents/code-reviewer.json`): EVAL mode
+- **Frontend Developer** (`packages/rules/.ai-rules/agents/frontend-developer.json`): PLAN/ACT modes
+- **Code Reviewer** (`packages/rules/.ai-rules/agents/code-reviewer.json`): EVAL mode
 
 **Specialist Agents** (12 available):
 - Architecture, Test Strategy, Performance, Security
 - Accessibility, SEO, Design System, Documentation
 - Code Quality, DevOps Engineer
 
-For complete workflow details, see [.ai-rules/rules/core.md](../../.ai-rules/rules/core.md)
+For complete workflow details, see [packages/rules/.ai-rules/rules/core.md](../../packages/rules/.ai-rules/rules/core.md)
 
 ---
 
 ## 🏗️ Project Setup
 
-**Source**: [.ai-rules/rules/project.md](../../.ai-rules/rules/project.md)
+**Source**: [packages/rules/.ai-rules/rules/project.md](../../packages/rules/.ai-rules/rules/project.md)
 
 ### Tech Stack
 
@@ -64,13 +64,13 @@ src/
 - **Server Components**: Default, Client Components only when necessary
 - **Test coverage**: 90%+ goal
 
-For complete project setup, see [.ai-rules/rules/project.md](../../.ai-rules/rules/project.md)
+For complete project setup, see [packages/rules/.ai-rules/rules/project.md](../../packages/rules/.ai-rules/rules/project.md)
 
 ---
 
 ## 🎯 Augmented Coding Principles
 
-**Source**: [.ai-rules/rules/augmented-coding.md](../../.ai-rules/rules/augmented-coding.md)
+**Source**: [packages/rules/.ai-rules/rules/augmented-coding.md](../../packages/rules/.ai-rules/rules/augmented-coding.md)
 
 ### TDD Cycle (Strict Adherence)
 
@@ -94,15 +94,15 @@ Follow the **Red → Green → Refactor** cycle:
 - Minimize state, prefer pure functions
 - Tidy First: Separate structural vs behavioral changes
 
-For complete augmented coding guide, see [.ai-rules/rules/augmented-coding.md](../../.ai-rules/rules/augmented-coding.md)
+For complete augmented coding guide, see [packages/rules/.ai-rules/rules/augmented-coding.md](../../packages/rules/.ai-rules/rules/augmented-coding.md)
 
 ---
 
 ## 🤖 Specialist Agents
 
-**Source**: [.ai-rules/agents/](../../.ai-rules/agents/)
+**Source**: [packages/rules/.ai-rules/agents/](../../packages/rules/.ai-rules/agents/)
 
-All specialist agents are defined in `.ai-rules/agents/` directory:
+All specialist agents are defined in `packages/rules/.ai-rules/agents/` directory:
 
 | Agent | Expertise | Use Cases |
 |-------|-----------|-----------|
@@ -113,7 +113,7 @@ All specialist agents are defined in `.ai-rules/agents/` directory:
 | Performance Specialist | Bundle size, Core Web Vitals | Performance tuning, optimization |
 | +7 more specialists | Various domains | See agents README |
 
-For complete agent documentation, see [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md)
+For complete agent documentation, see [packages/rules/.ai-rules/agents/README.md](../../packages/rules/.ai-rules/agents/README.md)
 
 ---
 
@@ -140,12 +140,12 @@ Example: `PLAN design auth feature` → call parse_mode → work in PLAN mode
 ## 📖 Full Documentation
 
 For comprehensive guides:
-- **Core Rules**: [.ai-rules/rules/core.md](../../.ai-rules/rules/core.md)
-- **Project Setup**: [.ai-rules/rules/project.md](../../.ai-rules/rules/project.md)
-- **Augmented Coding**: [.ai-rules/rules/augmented-coding.md](../../.ai-rules/rules/augmented-coding.md)
-- **Agents System**: [.ai-rules/agents/README.md](../../.ai-rules/agents/README.md)
-- **Integration Guide**: [.ai-rules/adapters/codex.md](../../.ai-rules/adapters/codex.md)
+- **Core Rules**: [packages/rules/.ai-rules/rules/core.md](../../packages/rules/.ai-rules/rules/core.md)
+- **Project Setup**: [packages/rules/.ai-rules/rules/project.md](../../packages/rules/.ai-rules/rules/project.md)
+- **Augmented Coding**: [packages/rules/.ai-rules/rules/augmented-coding.md](../../packages/rules/.ai-rules/rules/augmented-coding.md)
+- **Agents System**: [packages/rules/.ai-rules/agents/README.md](../../packages/rules/.ai-rules/agents/README.md)
+- **Integration Guide**: [packages/rules/.ai-rules/adapters/codex.md](../../packages/rules/.ai-rules/adapters/codex.md)
 
 ---
 
-**Note**: This file references common AI rules from `.ai-rules/` directory. All AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro) share the same rules for consistency.
+**Note**: This file references common AI rules from `packages/rules/.ai-rules/` directory. All AI assistants (Cursor, Claude Code, Antigravity, Codex, Q, Kiro) share the same rules for consistency.

.github/workflows/canary.yml

@@ -6,8 +6,8 @@ on:
       - master
       - stag-**
     paths:
-      - 'mcp-server/**'
-      - '.ai-rules/**'
+      - 'apps/mcp-server/**'
+      - 'packages/rules/**'
       - '.antigravity/**'
       - '.claude/**'
       - '.codex/**'
@@ -23,9 +23,6 @@ jobs:
   publish-canary:
     if: github.repository == 'JeremyDev87/codingbuddy'
     runs-on: ubuntu-latest
-    defaults:
-      run:
-        working-directory: mcp-server
     steps:
       - name: Checkout code
         uses: actions/checkout@v6
@@ -35,23 +32,14 @@ jobs:
         with:
           node-version: '24'
 
-      - name: Restore dependencies from cache
-        id: cache
-        uses: actions/cache@v5
-        with:
-          path: ./mcp-server/node_modules
-          key: ${{ runner.os }}-yarn-${{ hashFiles(format('{0}{1}', github.workspace, '/mcp-server/yarn.lock')) }}
-          restore-keys: |
-            ${{ runner.os }}-yarn-
-
       - name: Install dependencies
-        if: steps.cache.outputs.cache-hit != 'true'
         run: yarn install --immutable
 
-      - name: Build
-        run: yarn build
+      - name: Build mcp-server
+        run: yarn workspace codingbuddy build
 
-      - name: Publish canary
+      - name: Publish rules canary
+        working-directory: packages/rules
         run: |
           TIMESTAMP=$(date +%Y%m%d%H%M%S)
           COMMIT_SHA=${GITHUB_SHA::7}
@@ -62,7 +50,21 @@ jobs:
           YARN_NPM_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
           GITHUB_SHA: ${{ github.sha }}
 
+      - name: Publish mcp-server canary
+        working-directory: apps/mcp-server
+        run: |
+          TIMESTAMP=$(date +%Y%m%d%H%M%S)
+          COMMIT_SHA=${GITHUB_SHA::7}
+          VERSION="0.0.0-canary.${TIMESTAMP}.${COMMIT_SHA}"
+          # Update version and replace workspace dependency with canary version
+          cat <<< "$( jq --arg v "$VERSION" '.version = $v | .dependencies["codingbuddy-rules"] = $v' package.json )" > package.json
+          yarn npm publish --tag canary
+        env:
+          YARN_NPM_AUTH_TOKEN: ${{ secrets.NPM_TOKEN }}
+          GITHUB_SHA: ${{ github.sha }}
+
       - name: Output canary version number
+        working-directory: apps/mcp-server
         run: |
           name=$(jq -r .name package.json)
           version=$(jq -r .version package.json)