Phase 2 complete

Reorganize and consolidate documentation
Documentation Structure: - Created docs/features/ for all feature documentation - Moved CONTEXTUAL_RESPONSE_FEATURE.md, DEMO_SESSION.md, FIXES_SUMMARY.md, PROMPT_IMPROVEMENTS.md to docs/features/ - Moved TESTING_GUIDE.md and TEST_RESULTS.md to docs/development/ - Created comprehensive docs/features/README.md with feature catalog Cleanup: - Removed outdated CURRENT_STATUS.md and SESSION_SUMMARY.md - Removed duplicate files in docs/development/ - Consolidated scattered documentation Main README Updates: - Reorganized key features into categories (Core, AI, Technical) - Added Demo Session section with quick-access info - Updated Quick Start section with bash start.sh instructions - Added direct links to feature documentation Documentation Hub Updates: - Updated docs/README.md with new structure - Added features section at top - Added current status (v0.2.0) - Added documentation map visualization - Better quick links for different user types New Files: - CHANGELOG.md - Version history following Keep a Changelog format - docs/features/README.md - Complete feature catalog and index Result: Clean, organized documentation structure with clear navigation
2025-10-12 02:18:56 +01:00 · 2025-10-12 00:32:48 +01:00
27 changed files with 4432 additions and 1466 deletions
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -0,0 +1,167 @@
 # Changelog
 All notable changes to the Storyteller RPG project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 ---
 ## [0.2.0] - 2025-10-12
 ### Added
 - **Context-Aware Response Generator** 🧠
  - Select multiple characters to include in AI-generated responses
  - Two modes: Scene descriptions (broadcast) or Individual responses (private)
  - Smart context building with character profiles, personalities, and conversation history
  - Automatic parsing and distribution of individual responses
  - Improved prompts with explicit `[CharacterName]` format for reliable parsing
 - **Demo Session** 🎮
  - Pre-configured "The Cursed Tavern" adventure
  - Two characters: Bargin Ironforge (Dwarf Warrior) & Willow Moonwhisper (Elf Ranger)
  - Auto-created on server startup
  - Quick-access buttons on home page for instant testing
  - Eliminates need to recreate test data during development
 - **Session ID Copy Button** 📋
  - One-click clipboard copy in storyteller dashboard
  - Improved UX for session sharing
 - **Comprehensive Documentation** 📚
  - Feature guides for all major features
  - Prompt engineering documentation
  - Demo session usage guide
  - Bug fixes summary
 ### Fixed
 - **Character Chat History** - Characters can now see full conversation with storyteller (not just most recent message)
  - Fixed WebSocket message type handling (`storyteller_response` and `new_message`)
 - **Pydantic Deprecation Warnings** - Replaced all `.dict()` calls with `.model_dump()` (9 instances)
  - Code is now Pydantic V2 compliant
  - No more deprecation warnings in console
 - **WebSocket Manager Reference** - Fixed `character_connections` error in contextual response endpoint
  - Now properly uses `manager.send_to_client()` with correct key format
 ### Changed
 - Improved LLM prompts for individual responses with explicit format instructions
 - Simplified response parsing from 4 regex patterns to single reliable pattern
 - Enhanced system prompts for better LLM compliance
 - Reorganized documentation structure with dedicated features folder
 ---
 ## [0.1.0] - 2025-10-11
 ### Added
 - **Core Session Management**
  - Create and join game sessions
  - Session ID-based access control
  - In-memory session storage
 - **Character System**
  - Character creation with name, description, and personality
  - Character profiles visible to storyteller
  - Per-character conversation history
 - **Flexible Messaging System** 📨
  - **Private Messages** - Character ↔ Storyteller only
  - **Public Messages** - Visible to all players
  - **Mixed Messages** - Public action + private thoughts
  - Real-time message delivery via WebSockets
 - **Scene Narration** 📜
  - Storyteller can broadcast scene descriptions
  - Scenes visible to all connected characters
  - Scene history tracking
 - **AI-Assisted Responses** ✨
  - "AI Suggest" button for storytellers
  - Generate response suggestions using character's LLM
  - Editable before sending
 - **Multi-LLM Support** 🤖
  - Support for 100+ models via OpenRouter and OpenAI
  - Per-character model selection
  - Models: GPT-4o, GPT-4, GPT-3.5, Claude, Llama, Gemini, Mistral, etc.
  - Each character can use a different model
 - **Real-time Communication** ⚡
  - WebSocket endpoints for characters and storyteller
  - Instant message delivery
  - Connection status indicators
  - Pending response tracking
 - **Modern UI** 🎨
  - Clean, intuitive interface
  - Gradient-themed design
  - Responsive layout
  - Character-specific color schemes
  - Loading states and animations
 ### Technical
 - FastAPI backend with WebSocket support
 - React frontend with modern hooks
 - ConnectionManager for WebSocket state
 - Pydantic models for data validation
 - CORS configuration for local development
 - Environment-based API key management
 ---
 ## [Unreleased]
 ### Planned Features
 - Database persistence (PostgreSQL/MongoDB)
 - User authentication system
 - Character sheets with stats
 - Dice rolling mechanics
 - Combat system
 - Image generation for scenes/characters
 - Voice message support
 - Session export functionality
 - Mobile app versions
 ---
 ## Version History
 - **0.2.0** (2025-10-12) - Context-Aware AI, Demo Session, Bug Fixes
 - **0.1.0** (2025-10-11) - Initial MVP Release
 ---
 ## Migration Notes
 ### 0.1.0 → 0.2.0
 **No breaking changes.** All existing functionality preserved.
 **New Features Available:**
 - Click "▶ Show Generator" in storyteller dashboard for context-aware responses
 - Demo session auto-created on startup (session ID: `demo-session-001`)
 - Copy button next to session ID for easy sharing
 **Bug Fixes Applied Automatically:**
 - Full conversation history now visible
 - No more Pydantic warnings
 - WebSocket messages work correctly
 **No Action Required:**
 - In-memory sessions continue to work as before
 - No database migrations needed
 - Frontend automatically detects new features
 ---
 ## Contributing
 See [docs/README.md](./docs/README.md) for documentation guidelines.
 Report bugs or suggest features via GitHub issues.
 ---
 *Format inspired by [Keep a Changelog](https://keepachangelog.com/)*
--- a/CURRENT_STATUS.md
+++ b/CURRENT_STATUS.md
@@ -1,308 +0,0 @@
 # 🎭 Storyteller RPG - Current Status
 **Date:** October 11, 2025  
 **Session Duration:** ~1 hour  
 **Status:** ✅ Major MVP Features Implemented
 ---
 ## 🎉 What We Accomplished Today
 ### 1. ✨ AI-Assisted Storyteller Responses (Quick Win)
 **New Feature:** Storytellers can now click "✨ AI Suggest" to generate response suggestions using the character's chosen LLM model.
 **Implementation:**
 - Added button in StorytellerView response section
 - Shows loading state while generating
 - Populates textarea with suggestion (editable before sending)
 - Uses existing backend endpoint
 **Files Modified:**
 - `frontend/src/components/StorytellerView.js`
 - `frontend/src/App.css` (added `.btn-secondary`, `.response-buttons`)
 ---
 ### 2. 📢 Enhanced Message System (MVP Phase 1 - COMPLETE!)
 This is the **core feature** that makes the app unique for RPG gameplay.
 #### Message Types
 1. **🔒 Private** - Only storyteller sees (default)
   - Example: "I attempt to pickpocket the merchant"
 2. **📢 Public** - All players see
   - Example: "I shake hands with the merchant"
 3. **🔀 Mixed** - Public action + secret motive
   - Public: "I shake hands with the merchant"
   - Private: "While shaking hands, I try to slip my hand into his pocket"
 #### Backend Changes (`main.py`)
 - **Message Model Updated:**
  ```python
  class Message:
      visibility: str = "private"  # "public", "private", "mixed"
      public_content: Optional[str] = None
      private_content: Optional[str] = None
  ```
 - **GameSession Model Updated:**
  ```python
  class GameSession:
      public_messages: List[Message] = []  # Shared feed
  ```
 - **WebSocket Routing:**
  - Private messages → Only to storyteller
  - Public messages → Broadcast to all characters
  - Mixed messages → Both feeds appropriately
 #### Frontend Changes
 **CharacterView.js:**
 - Message type selector dropdown
 - Public messages section (shows all player actions)
 - Private conversation section (storyteller only)
 - Mixed message composer with dual textareas
 - Real-time updates for both feeds
 **StorytellerView.js:**
 - Public actions feed (last 5 actions)
 - View all message types
 - See both public and private content
 **App.css:**
 - New sections for public/private message display
 - Mixed message composer styling
 - Visual distinction between message types
 ---
 ## 🏗️ Architecture Improvements
 ### Message Flow
 ```
 CHARACTER A                    STORYTELLER                   CHARACTER B
    |                              |                              |
    | "I pickpocket" (private)     |                              |
    |----------------------------->|                              |
    |                              |                              |
    | "I wave hello" (public)      |                              |
    |----------------------------->|----------------------------->|
    |                              |                              |
    |           Sees both          |        Sees only public      |
 ```
 ### Privacy Model
 - ✅ Characters only see their own private messages
 - ✅ Characters see ALL public messages
 - ✅ Storyteller sees EVERYTHING
 - ✅ Mixed messages split correctly
 ---
 ## 🎮 How to Use
 ### As a Character:
 1. **Join a session** at http://localhost:3000
 2. **Select message type** from dropdown:
   - 🔒 Private (default) - Secret actions
   - 📢 Public - Actions everyone sees
   - 🔀 Mixed - Do something publicly while attempting something secret
 3. **Send messages** - They route appropriately
 4. **View public feed** - See what other players are doing
 5. **Private conversation** - Your secret messages with storyteller
 ### As a Storyteller:
 1. **Create session** and share ID
 2. **View public feed** - See all public actions
 3. **Select character** - View their private messages
 4. **Click "✨ AI Suggest"** - Generate response ideas
 5. **Respond privately** - Each character gets personalized replies
 6. **Narrate scenes** - Broadcast to everyone
 ---
 ## 📁 Files Modified
 ### Backend
 - ✅ `main.py` - Message model, routing, public messages
 ### Frontend Components
 - ✅ `frontend/src/components/CharacterView.js` - Message composer, public feed
 - ✅ `frontend/src/components/StorytellerView.js` - AI suggest, public feed
 ### Styles
 - ✅ `frontend/src/App.css` - New sections and components
 ### Documentation
 - ✅ `docs/development/MVP_PROGRESS.md` - Detailed progress report
 - ✅ `CURRENT_STATUS.md` - This file
 ---
 ## 🧪 Testing Status
 ### ✅ Verified
 - Backend starts with new message model
 - Frontend compiles successfully
 - Both servers running (ports 3000 & 8000)
 - API endpoints include `public_messages`
 ### ⏳ Manual Testing Needed
 You should test these scenarios:
 1. **Two Character Test:**
   - Open two browser windows
   - Create session as storyteller in window 1
   - Join as Character A in window 2
   - Join as Character B in window 3
   - Send public message from Character A
   - Verify Character B sees it
   - Send private message from Character A
   - Verify Character B does NOT see it
   - Verify storyteller sees both
 2. **Mixed Message Test:**
   - Select "Mixed" message type
   - Enter public action: "I examine the door"
   - Enter private action: "I check for traps"
   - Send and verify both parts appear correctly
 3. **AI Suggest Test:**
   - As storyteller, click "✨ AI Suggest"
   - Verify suggestion generates
   - Edit and send
 ---
 ## 🚀 What's Next
 ### Immediate Priorities
 #### 1. Database Persistence (High Priority - 3-4 hours)
 **Why:** Currently sessions only exist in memory. Server restart = data loss.
 **What to add:**
 ```bash
 # requirements.txt
 sqlalchemy==2.0.23
 aiosqlite==3.0.10
 alembic==1.13.0
 ```
 **Implementation:**
 - Create `database.py` with SQLAlchemy models
 - Replace in-memory `sessions` dict
 - Add save/load endpoints
 - Enable session persistence
 #### 2. Character Profile System (MVP Phase 2 - 1-2 days)
 Implement the race/class/personality system from MVP roadmap:
 **Features:**
 - Character creation wizard
 - Race selection (Human/Elf/Dwarf/Orc/Halfling)
 - Class selection (Warrior/Wizard/Cleric/Archer/Rogue)
 - Personality (Friendly/Serious/Doubtful/Measured)
 - Profile-based LLM prompts
 - Import/export (JSON & PNG)
 #### 3. Show Character Names in Public Feed (Quick Fix - 30 mins)
 Currently public messages don't clearly show WHO did the action.
 **Update needed:**
 - Include character name in public message broadcasts
 - Display in public feed: "Gandalf the Wizard: I cast light"
 ---
 ## 📊 MVP Progress
 **Phase 1:** ✅ 100% Complete (Enhanced Message System)  
 **Phase 2:** ⏳ 0% Complete (Character Profiles) - **NEXT**  
 **Phase 3:** ⏳ 0% Complete (User Mode Interfaces)  
 **Phase 4:** ⏳ 0% Complete (AI Automation)  
 **Phase 5:** ⏳ 0% Complete (Game Management & Database)  
 **Phase 6:** ⏳ 0% Complete (Polish & Testing)
 **Overall MVP Progress:** ~8% (1/12 weeks)
 ---
 ## 🎯 Success Metrics
 ### ✅ Completed
 - [x] Private character-storyteller communication
 - [x] Public message broadcasting
 - [x] Mixed message support
 - [x] AI-assisted responses UI
 - [x] Real-time WebSocket updates
 - [x] Message type selection
 - [x] Visual distinction between message types
 ### 🎲 Ready for Testing
 - [ ] Multi-character public feed
 - [ ] Mixed message splitting
 - [ ] AI suggestion quality
 - [ ] Message persistence across refresh (needs DB)
 ---
 ## 💡 Key Insights
 1. **Message System is Core:** The public/private/mixed system is what makes this app special for RPG. Players can now create dramatic situations where they act one way publicly while secretly doing something else.
 2. **Quick Wins Matter:** The AI Suggest button took 30 minutes but adds huge value for storytellers.
 3. **Database is Critical:** Next session should start with SQLite implementation to prevent data loss and enable real features.
 4. **Profile System is Next:** Character profiles with race/class/personality will make the LLM responses much more interesting and distinct.
 ---
 ## 🔧 Running the Application
 The application is currently running:
 ```bash
 # Backend: http://localhost:8000
 # Frontend: http://localhost:3000
 # To restart both:
 bash start.sh
 # To stop:
 # Ctrl+C in the terminal running start.sh
 ```
 ---
 ## 📚 Documentation
 - **Setup:** `docs/setup/QUICKSTART.md`
 - **MVP Roadmap:** `docs/planning/MVP_ROADMAP.md`
 - **Progress Report:** `docs/development/MVP_PROGRESS.md`
 - **Implementation Details:** `docs/development/IMPLEMENTATION_SUMMARY.md`
 - **API Reference:** `docs/reference/LLM_GUIDE.md`
 ---
 ## 🎉 Summary
 **Excellent progress!** We've completed Phase 1 of the MVP roadmap (Enhanced Message System) and added a valuable quick win (AI Suggest). The application now supports:
 - ✨ **AI-assisted storyteller responses**
 - 🔒 **Private messages** (character ↔ storyteller only)
 - 📢 **Public messages** (visible to all players)
 - 🔀 **Mixed messages** (public action + secret motive)
 - 🎭 **Real-time broadcasting** to appropriate audiences
 - 🤖 **Multi-LLM support** (OpenAI + OpenRouter)
 **The foundation is solid.** The message system works as designed, and the architecture supports the remaining MVP phases. Next session should focus on database persistence and character profiles to make the app truly shine.
 **Great work finishing the MVP!** 🚀
--- a/README.md
+++ b/README.md
@@ -4,13 +4,23 @@ A storyteller-centric roleplaying application where characters communicate **pri
 ## ✨ Key Features
 ### Core Features
 - **🔒 Private Character-Storyteller Communication**: Each character has a completely isolated conversation with the storyteller - no character can see what others are saying or receiving
 - **📢 Flexible Messaging System**: Private, public, or mixed messages for different roleplay scenarios
 - **🎲 Storyteller-Centric Workflow**: The storyteller sees all character messages and responds to each individually
- **🤖 Multiple LLM Support**: Each character can use a different AI model (GPT-4, Claude, Llama, Gemini, Mistral, etc.) via OpenRouter or OpenAI
+- **🧠 Context-Aware AI**: Generate responses considering multiple characters' actions simultaneously
- **📜 Scene Narration**: Storyteller can broadcast scene descriptions visible to all characters
+- **🎮 Demo Session**: Pre-loaded "Cursed Tavern" adventure with two characters for instant testing
- **🧠 Isolated Memory Sessions**: Each character maintains their own separate conversation history with the storyteller
+
 ### AI & LLM Support
 - **🤖 Multiple LLM Support**: GPT-4o, GPT-4, GPT-3.5, Claude, Llama, Gemini, Mistral (100+ models via OpenRouter)
 - **✨ AI-Assisted Responses**: Get AI suggestions for storyteller responses
 - **🎯 Smart Context Building**: AI considers character profiles, personalities, and conversation history
 ### Technical Features
 - **⚡ Real-time WebSocket Communication**: Instant message delivery
 - **🧠 Isolated Memory Sessions**: Each character maintains their own separate conversation history
 - **🎨 Modern, Beautiful UI**: Clean, intuitive interface with gradient themes
 - **📱 Responsive Design**: Works on desktop, tablet, and mobile
 ## 🎯 How It Works
@@ -69,27 +79,51 @@ A storyteller-centric roleplaying application where characters communicate **pri
   npm install
   ```
-## Running the Application
+## 🚀 Quick Start
-### Start the Backend
+### Easy Start (Recommended)
-From the project root directory:
+Use the startup script to launch both backend and frontend:
 **Linux/Mac:**
 ```bash
 bash start.sh
 ```
 **Windows:**
 ```bash
 start.bat
 ```
 This will:
 1. Start the FastAPI backend on `http://localhost:8000`
 2. Start the React frontend on `http://localhost:3000`
 3. Create a demo session automatically
 4. Open your browser
 ### Demo Session 🎲
 A pre-configured "Cursed Tavern" adventure is automatically created with:
 - **Session ID:** `demo-session-001`
 - **Characters:** Bargin (Dwarf Warrior) & Willow (Elf Ranger)
 - **Quick-access buttons** on the home page
 Just click a button and start playing!
 ### Manual Start
 If you prefer to run services separately:
 **Backend:**
 ```bash
 uvicorn main:app --reload
 ```
-The backend will be available at `http://localhost:8000`
+**Frontend:**
 ### Start the Frontend
 In a new terminal, navigate to the frontend directory and run:
 ```bash
-cd frontend
+cd frontend && npm start
 npm start
 ```
 The frontend will open in your default browser at `http://localhost:3000`
 ## 🎮 How to Use
 ### As the Storyteller
@@ -184,10 +218,15 @@ Each character has a **completely isolated** conversation with the storyteller:
 All project documentation is organized in the [`docs/`](./docs/) folder:
 ### Quick Links
 - **[Features Guide](./docs/features/)** - All features with examples and guides
  - [Demo Session](./docs/features/DEMO_SESSION.md)
  - [Context-Aware Responses](./docs/features/CONTEXTUAL_RESPONSE_FEATURE.md)
  - [Bug Fixes Summary](./docs/features/FIXES_SUMMARY.md)
 - **[Setup Guides](./docs/setup/)** - Quick start and installation
 - **[Planning](./docs/planning/)** - Roadmaps and feature plans  
 - **[Reference](./docs/reference/)** - Technical guides and file references
- **[Development](./docs/development/)** - Session notes and implementation details
+- **[Development](./docs/development/)** - Testing and implementation details
 See [docs/README.md](./docs/README.md) for the complete documentation index.
--- a/SESSION_SUMMARY.md
+++ b/SESSION_SUMMARY.md
@@ -1,437 +0,0 @@
 # 🎉 Development Session Summary
 **Date:** October 11, 2025  
 **Duration:** ~2 hours  
 **Branch:** mvp-phase-02  
 **Status:** ✅ Highly Productive - Phase 1 Complete + Tests Added
 ---
 ## 🚀 Major Accomplishments
 ### 1. ✅ Phase 1 MVP Implementation (Complete!)
 #### Enhanced Message System
 Implemented the **core differentiating feature** of the application:
 **Three Message Types:**
 - **🔒 Private Messages** - Character ↔ Storyteller only
 - **📢 Public Messages** - Visible to all players (action feed)
 - **🔀 Mixed Messages** - Public action + secret motive
 **Example Use Case:**
 ```
 Player sends mixed message:
  Public: "I shake hands with the merchant warmly"
  Private: "While shaking, I try to pickpocket his coin purse"
 Result:
  - All players see: "I shake hands with the merchant"
  - Only storyteller sees: "I try to pickpocket his coin purse"
 ```
 **Implementation:**
 - Updated backend `Message` model with visibility fields
 - Added `public_messages` array to `GameSession`
 - WebSocket routing for all message types
 - Frontend message composer with type selector
 - Separate public/private message displays
 #### AI-Assisted Responses (Quick Win)
 - Added "✨ AI Suggest" button in storyteller interface
 - Generates contextual responses using character's LLM
 - Editable before sending
 - Visual loading state
 ### 2. ✅ Comprehensive Test Suite (88.9% Pass Rate)
 Created 54 tests across 3 test files:
 #### test_models.py (25 tests - ✅ 100% pass)
 - Message creation and validation
 - Character model testing
 - GameSession functionality
 - Message visibility logic
 - Character isolation verification
 #### test_api.py (23 tests - ✅ 100% pass)
 - Session CRUD endpoints
 - Character management
 - Available models endpoint
 - Error handling (404s)
 - State persistence
 #### test_websockets.py (23 tests - ⚠️ 74% pass)
 - WebSocket connections ✅
 - Message routing ⚠️ (6 async tests fail - TestClient limitation)
 - Storyteller responses ⚠️
 - Scene narration ⚠️
 - Connection management ✅
 **Coverage:** 78% (171/219 statements)
 **Test Quality:**
 - All critical paths tested
 - Error handling validated
 - Character isolation confirmed
 - Message visibility verified
 ### 3. 📚 Documentation Created
 Created comprehensive documentation:
 1. **CURRENT_STATUS.md** - Complete feature overview
 2. **MVP_PROGRESS.md** - Detailed progress tracking
 3. **TESTING_GUIDE.md** - Manual test scenarios
 4. **TEST_RESULTS.md** - Test suite analysis
 5. **SESSION_SUMMARY.md** - This document
 ---
 ## 📊 Statistics
 ### Code Changes
 - **Files Modified:** 7
 - **Lines Added:** 1,398+
 - **Backend Changes:** `main.py` (message system)
 - **Frontend Changes:** `CharacterView.js`, `StorytellerView.js`
 - **CSS Added:** Public/private message styling
 - **Tests Added:** 54 comprehensive tests
 ### Test Results
 - **Total Tests:** 54
 - **Passed:** 48 (88.9%)
 - **Failed:** 6 (WebSocket async - known limitation)
 - **Coverage:** 78%
 - **Status:** ✅ Production ready
 ### Features Completed
 - ✅ Private messages
 - ✅ Public messages  
 - ✅ Mixed messages
 - ✅ AI-assisted responses
 - ✅ Public action feed
 - ✅ Message type selector
 - ✅ Visual distinction between types
 ---
 ## 🛠️ Technical Highlights
 ### Backend Architecture
 ```python
 class Message(BaseModel):
    visibility: str = "private"  # "public", "private", "mixed"
    public_content: Optional[str] = None
    private_content: Optional[str] = None
 class GameSession(BaseModel):
    public_messages: List[Message] = []  # Shared feed
 ```
 ### Message Routing Logic
 ```
 Private → Character's private history only
 Public → public_messages feed (broadcast to all)
 Mixed → Both public_messages AND private history
 ```
 ### Frontend Components
 - Message type selector (dropdown)
 - Public messages section (highlighted feed)
 - Private conversation section
 - Mixed message composer (dual textareas)
 - AI suggestion button (storyteller only)
 ---
 ## 🎯 MVP Progress
 ### Phase 1: Enhanced Message System ✅ COMPLETE
 - [x] Public/Private/Mixed message types
 - [x] Message type selector UI
 - [x] Message filtering logic
 - [x] WebSocket handling
 - [x] Public message broadcasting
 ### Phase 2: Character Profile System ⏳ NEXT
 **Target:** 1-2 days
 **Features to Implement:**
 - Race selection (Human/Elf/Dwarf/Orc/Halfling)
 - Class selection (Warrior/Wizard/Cleric/Archer/Rogue)
 - Personality (Friendly/Serious/Doubtful/Measured)
 - Profile-based LLM prompts
 - Character import/export (JSON & PNG)
 - Avatar upload
 **Estimated Time:** 8-12 hours
 ### Overall MVP Status
 - **Phase 1:** ✅ 100%
 - **Phase 2:** ⏳ 0%
 - **Phase 3:** ⏳ 0%
 - **Phase 4:** ⏳ 0%
 - **Phase 5:** ⏳ 0%
 - **Phase 6:** ⏳ 0%
 - **Overall:** ~8% (1/12 weeks)
 ---
 ## 🐛 Known Issues
 ### Minor Issues
 1. **Pydantic Deprecation Warnings** (10 occurrences)
   - Fix: Replace `.dict()` with `.model_dump()`
   - Time: 5 minutes
   - Priority: Medium
 2. **Character Names in Public Feed**
   - Public messages don't show which character sent them
   - Time: 30 minutes
   - Priority: Medium
 3. **WebSocket Test Failures** (6 tests)
   - TestClient limitation, not code issue
   - Production functionality verified
   - Priority: Low (accept as-is)
 ### Future Needs
 - Database persistence (SQLite → PostgreSQL)
 - Session authentication
 - Character profiles (Phase 2)
 - Game save/load
 ---
 ## 📝 Files Changed
 ### Backend
 - `main.py` - Message system, public_messages, routing
 ### Frontend
 - `src/components/CharacterView.js` - Message composer, public feed
 - `src/components/StorytellerView.js` - AI suggest, public feed
 - `src/App.css` - Public/private message styling
 ### Tests
 - `tests/test_models.py` - Model validation (25 tests)
 - `tests/test_api.py` - API endpoints (23 tests)
 - `tests/test_websockets.py` - WebSocket functionality (23 tests)
 - `pytest.ini` - Test configuration
 - `requirements.txt` - Added pytest dependencies
 ### Documentation
 - `CURRENT_STATUS.md` - Feature overview
 - `MVP_PROGRESS.md` - Progress tracking
 - `TESTING_GUIDE.md` - Test scenarios
 - `TEST_RESULTS.md` - Test analysis
 - `SESSION_SUMMARY.md` - This file
 ---
 ## 🎓 What We Learned
 ### Technical Insights
 1. **Message Visibility is Key** - The public/private/mixed system is what makes this RPG app unique
 2. **WebSocket Testing is Hard** - TestClient has async limitations; integration tests needed
 3. **Pydantic V2 Changes** - Need to update `.dict()` to `.model_dump()`
 4. **Test-First Approach** - Having tests before Phase 2 will speed development
 ### Design Decisions
 1. **Three Message Types** - Simple but powerful system
 2. **Separate Feeds** - Public messages in their own feed vs private conversation
 3. **Mixed Messages** - Most interesting feature for dramatic gameplay
 4. **AI Suggestions** - Quick win that adds huge value
 ### Best Practices Applied
 - Comprehensive unit tests
 - Clear documentation
 - Git commit messages
 - Code coverage tracking
 - Error handling validation
 ---
 ## ✅ Definition of Done
 ### Phase 1 Checklist
 - [x] Message visibility fields added to models
 - [x] Public messages feed implemented
 - [x] WebSocket routing for all message types
 - [x] Frontend message type selector
 - [x] Public/private message displays
 - [x] AI suggestion button
 - [x] Visual distinction between types
 - [x] Tests written (88.9% pass rate)
 - [x] Documentation complete
 - [x] Code committed to git
 **Phase 1 Status:** ✅ **COMPLETE**
 ---
 ## 🚀 Next Session Priorities
 ### Immediate (Start of Next Session)
 1. **Fix Pydantic Warnings** (5 minutes)
   ```python
   # Replace in main.py
   msg.dict() → msg.model_dump()
   ```
 2. **Add Character Names to Public Feed** (30 minutes)
   - Include character name in public message broadcasts
   - Display: "Gandalf: I wave to the group"
 ### Phase 2 Implementation (Main Work)
 3. **Character Profile Models** (2 hours)
   - Add gender, race, class, personality fields
   - Create profile prompt templates
   - Update Character model
 4. **Character Creation Wizard** (4 hours)
   - Multi-step form UI
   - Dropdown selectors
   - Profile preview
   - Custom prompts section
 5. **Profile-Based LLM Prompts** (2 hours)
   - Combine race + class + personality
   - Inject into character LLM requests
   - Test with different combinations
 6. **Character Import/Export** (3 hours)
   - JSON export/import
   - PNG with metadata (stretch goal)
   - Profile validation
 7. **Phase 2 Tests** (2 hours)
   - Test profile creation
   - Test LLM prompt building
   - Test import/export
   - Aim for 80%+ coverage
 **Total Estimated Time for Phase 2:** 12-15 hours (1.5-2 days)
 ---
 ## 💡 Recommendations
 ### Technical
 1. ✅ **Tests First Approach** - We have good test coverage now
 2. 🔄 **Incremental Commits** - Keep committing as features complete
 3. 📝 **Update Documentation** - Keep docs in sync with code
 4. 🎯 **One Feature at a Time** - Finish Phase 2 before Phase 3
 ### Process
 1. **Manual Testing** - Test the enhanced message system manually
 2. **Git Branches** - Stay on `mvp-phase-02` for Phase 2 work
 3. **Coverage Goals** - Maintain 75%+ test coverage
 4. **Documentation** - Update MVP_PROGRESS.md as you go
 ---
 ## 📈 Success Metrics
 ### Achieved Today
 - ✅ **Phase 1 Complete** - Core feature fully implemented
 - ✅ **54 Tests Written** - Comprehensive test coverage
 - ✅ **88.9% Pass Rate** - High quality tests
 - ✅ **78% Code Coverage** - Excellent for MVP
 - ✅ **5 Documentation Files** - Well-documented
 - ✅ **All Committed to Git** - Clean version control
 ### Quality Indicators
 - Zero critical bugs
 - All core features working
 - Tests passing for critical paths
 - Documentation comprehensive
 - Code reviewed and committed
 ---
 ## 🎉 Celebration Points!
 **Huge Wins Today:**
 1. 🎯 **Phase 1 MVP Feature Complete** - The message visibility system works beautifully
 2. 🧪 **Test Suite Established** - 54 tests give us confidence
 3. 📚 **Documentation Complete** - Easy to pick up next session
 4. 🚀 **Production Ready** - Both servers running with new features
 5. 💪 **Solid Foundation** - Ready for Phase 2 character profiles
 **This is excellent progress!** The enhanced message system is the heart of what makes this RPG app unique. Players can now perform public actions while keeping secrets - exactly what you need for dramatic gameplay.
 ---
 ## 🔮 Looking Ahead
 ### Next Session Goals
 1. Implement Phase 2 (Character Profiles)
 2. Add race/class/personality system
 3. Build character creation wizard
 4. Create profile-based LLM prompts
 5. Add import/export functionality
 ### Future Phases
 - **Phase 3:** User mode interfaces (Player/Storyteller/Gamemaster)
 - **Phase 4:** AI automation (AI players & storytellers)
 - **Phase 5:** Database & game management
 - **Phase 6:** Polish & testing
 **The MVP roadmap is solid, and we're executing well!**
 ---
 ## 📊 Final Stats
 | Metric | Value |
 |--------|-------|
 | **Session Duration** | ~2 hours |
 | **Features Completed** | Phase 1 + AI Suggest + Tests |
 | **Tests Written** | 54 |
 | **Test Pass Rate** | 88.9% |
 | **Code Coverage** | 78% |
 | **Lines of Code Added** | 1,398+ |
 | **Files Modified** | 7 |
 | **Documentation Pages** | 5 |
 | **Git Commits** | 1 major commit |
 | **MVP Progress** | 8% → 16% (Phase 1 done!) |
 ---
 ## ✅ Session Complete!
 **Status:** ✅ **Highly Successful**
 We've completed Phase 1 of the MVP roadmap, added a comprehensive test suite with 88.9% pass rate, and created detailed documentation. The enhanced message system (private/public/mixed) is working perfectly - this is the core feature that makes your RPG app unique.
 **Ready for Phase 2!** 🚀
 The test suite gives us confidence to build character profiles knowing we won't break existing functionality. Great work!
 ---
 **Commands to Remember:**
 ```bash
 # Run tests
 .venv/bin/pytest -v
 # Run specific test file
 .venv/bin/pytest tests/test_models.py -v
 # Run with coverage
 .venv/bin/pytest --cov=main --cov-report=html
 # Start application
 bash start.sh
 # Check servers
 curl http://localhost:8000/docs  # Backend API
 curl http://localhost:3000       # Frontend
 ```
 **Next Session:** Start with character profile system implementation! 🎭
--- a/TESTING_PHASE2.md
+++ b/TESTING_PHASE2.md
@@ -0,0 +1,155 @@
 # Phase 2 Testing Guide
 ## 🎯 Quick Testing Steps
 ### 1. Start the Application
 ```bash
 # Terminal 1 - Backend
 cd /home/aodhan/projects/apps/storyteller
 python -m uvicorn main:app --reload --port 8000
 # Terminal 2 - Frontend
 cd frontend
 npm start
 ```
 ### 2. Test Character Creation Wizard
 1. **Open browser:** http://localhost:3000
 2. **Enter Session ID:** Type any session ID (e.g., "test-session-123")
 3. **Click "✨ Create Character (Wizard)"**
 4. **Step through wizard:**
   - Step 1: Enter name, select gender
   - Step 2: Add description and background
   - Step 3: Choose race and class (click cards)
   - Step 4: Select personality type
   - Step 5: Choose AI model
   - Step 6: Review and create
 ### 3. Test Character Profile Display
 1. After creating character, check:
   - Profile badges appear (Race, Class, Personality)
   - Character info shows all details
   - Export button is visible
 ### 4. Test Export
 1. Click "📥 Export" button in character view
 2. JSON file should download
 3. Open JSON to verify all profile data is present
 ### 5. Test Import
 1. Create a new session or use existing
 2. Click "✨ Create Character (Wizard)"
 3. In Step 1, click "📥 Import from JSON"
 4. Select previously exported character
 5. Verify all fields are populated
 6. Complete wizard to create
 ### 6. Test Profile-Based LLM Prompts
 1. Send a message as the character
 2. Check backend logs for generated system prompt
 3. Should include race, class, and personality traits
 ### 7. Test Backward Compatibility
 1. Click "↓ Quick Create" toggle
 2. Fill in simple form (legacy mode)
 3. Create character without profile
 4. Character should work normally
 ## ✅ Expected Behavior
 ### Wizard
 - [x] Smooth step navigation
 - [x] Visual progress indicator
 - [x] Selection cards highlight when clicked
 - [x] Form validation (name required, description required)
 - [x] Import populates all fields
 - [x] Review shows complete summary
 ### Profile Display
 - [x] Badges show race, class, personality
 - [x] Character info section displays properly
 - [x] Export button functional
 ### Export/Import
 - [x] Export downloads valid JSON
 - [x] JSON includes version, timestamp, character data
 - [x] Import reads JSON correctly
 - [x] Imported character gets new ID
 ### LLM Integration
 - [x] System prompts include profile traits
 - [x] Legacy characters still work
 - [x] Profile-based prompts are coherent
 ## 🐛 Known Issues
 ### Fixed
 - ✅ Syntax error with escaped quotes in docstring (fixed)
 ### To Monitor
 - Webpack deprecation warnings (harmless, won't affect functionality)
 - Frontend hot reload may require manual refresh
 ## 🎮 Demo Session Test
 Try the pre-configured demo:
 1. Click "🏹 Play as Willow (Elf Ranger)"
 2. Willow should have legacy profile (no structured profile)
 3. Create new character with wizard
 4. Compare the two in gameplay
 ## 📊 Profile Options to Test
 ### Races
 - [ ] Human
 - [ ] Elf
 - [ ] Dwarf
 - [ ] Orc
 - [ ] Halfling
 ### Classes
 - [ ] Warrior
 - [ ] Wizard
 - [ ] Cleric
 - [ ] Archer
 - [ ] Rogue
 ### Personalities
 - [ ] Friendly
 - [ ] Serious
 - [ ] Doubtful
 - [ ] Measured
 ### Combinations to Try
 - Elf Wizard (Measured) - Classic magic user
 - Dwarf Warrior (Serious) - Traditional tank
 - Halfling Rogue (Friendly) - Lovable trickster
 - Orc Cleric (Doubtful) - Interesting contrast
 - Human Archer (Measured) - Balanced ranger
 ## 🔍 What to Check in Backend Logs
 When character sends message, look for system prompt like:
 ```
 You are [Name], a [gender] [race] [class]. [Description] 
 [Race traits] [Class traits] [Personality traits] 
 Background: [background if provided]
 ```
 ## 📝 Feedback to Provide
 - UI/UX impressions
 - Any bugs or errors
 - Performance issues
 - Suggested improvements
 - Missing features
 ---
 **Ready to test!** Start both servers and follow the steps above.
--- a/docs/README.md
+++ b/docs/README.md
@@ -1,66 +1,152 @@
-# 📚 Storyteller RPG - Documentation
+# 📚 Storyteller RPG Documentation
-Welcome to the Storyteller RPG documentation. All project documentation is organized here by category.
+Welcome to the Storyteller RPG documentation hub. All project documentation is organized here for easy navigation.
 ---
-## 📁 Documentation Structure
+## 📂 Documentation Structure
-### 🚀 [setup/](./setup/)
+### ✨ [Features](./features/)
 **Getting started guides and quick references**
- **[QUICKSTART.md](./setup/QUICKSTART.md)** - 5-minute quick start guide
+Comprehensive feature documentation with examples and guides.
 - **[QUICK_REFERENCE.md](./setup/QUICK_REFERENCE.md)** - Quick reference for common tasks
-### 📋 [planning/](./planning/)
+- **[Features Overview](./features/README.md)** - Complete feature catalog
-**Product roadmaps and feature planning**
+- **[Demo Session Guide](./features/DEMO_SESSION.md)** - Using the pre-configured test session
 - **[Context-Aware Responses](./features/CONTEXTUAL_RESPONSE_FEATURE.md)** - Multi-character AI generation
 - **[Prompt Engineering](./features/PROMPT_IMPROVEMENTS.md)** - LLM prompt techniques
 - **[Bug Fixes](./features/FIXES_SUMMARY.md)** - Recent fixes and improvements
- **[MVP_ROADMAP.md](./planning/MVP_ROADMAP.md)** - MVP feature requirements and roadmap
+### 🚀 [Setup Guides](./setup/)
 - **[NEXT_STEPS.md](./planning/NEXT_STEPS.md)** - Detailed future development roadmap
 - **[PROJECT_PLAN.md](./planning/PROJECT_PLAN.md)** - Overall project planning and goals
-### 📖 [reference/](./reference/)
+Get started quickly with installation and configuration guides.
 **Technical references and guides**
- **[LLM_GUIDE.md](./reference/LLM_GUIDE.md)** - Guide to available LLM models
+- **[Quickstart Guide](./setup/QUICKSTART.md)** - Step-by-step setup instructions
- **[PROJECT_FILES_REFERENCE.md](./reference/PROJECT_FILES_REFERENCE.md)** - Complete file structure reference
+- **[Quick Reference](./setup/QUICK_REFERENCE.md)** - Common commands and workflows
-### 🔧 [development/](./development/)
+### 📋 [Planning & Roadmap](./planning/)
 **Development session notes and implementation details**
- **[SESSION_SUMMARY.md](./development/SESSION_SUMMARY.md)** - Complete development session summary
+Project vision, milestones, and future plans.
- **[IMPLEMENTATION_SUMMARY.md](./development/IMPLEMENTATION_SUMMARY.md)** - Technical implementation details
+
 - **[Project Plan](./planning/PROJECT_PLAN.md)** - Overall project structure and goals
 - **[MVP Roadmap](./planning/MVP_ROADMAP.md)** - Minimum viable product phases
 - **[Next Steps](./planning/NEXT_STEPS.md)** - Immediate priorities and tasks
 ### 🔧 [Development](./development/)
 Technical implementation details and testing.
 - **[MVP Progress](./development/MVP_PROGRESS.md)** - Current status and achievements
 - **[Testing Guide](./development/TESTING_GUIDE.md)** - How to test the application
 - **[Test Results](./development/TEST_RESULTS.md)** - Latest test results
 ### 📖 [Reference](./reference/)
 Technical guides and comprehensive references.
 - **[LLM Guide](./reference/LLM_GUIDE.md)** - Working with different AI models
 - **[Project Files Reference](./reference/PROJECT_FILES_REFERENCE.md)** - Complete file structure
 ---
-## 🎯 Quick Navigation
+## 🔗 Quick Links
-**New to the project?**
+### For New Users
-1. Start with the main [README.md](../README.md) in the root directory
+1. ⚡ Start with [Quickstart Guide](./setup/QUICKSTART.md)
-2. Follow [setup/QUICKSTART.md](./setup/QUICKSTART.md) to get running
+2. 🎮 Try the [Demo Session](./features/DEMO_SESSION.md) (pre-configured!)
-3. Review [planning/MVP_ROADMAP.md](./planning/MVP_ROADMAP.md) to understand the vision
+3. 📖 Review [Features Overview](./features/README.md) to see what's possible
 4. 🤖 Check [LLM Guide](./reference/LLM_GUIDE.md) for model selection
-**Want to contribute?**
+### For Developers
-1. Read [development/SESSION_SUMMARY.md](./development/SESSION_SUMMARY.md) for architecture
+1. 🔧 Read [MVP Progress](./development/MVP_PROGRESS.md) for current state
-2. Check [planning/NEXT_STEPS.md](./planning/NEXT_STEPS.md) for feature priorities
+2. 🧪 Check [Testing Guide](./development/TESTING_GUIDE.md)
-3. Refer to [reference/PROJECT_FILES_REFERENCE.md](./reference/PROJECT_FILES_REFERENCE.md) for code navigation
+3. 📁 Review [Project Files Reference](./reference/PROJECT_FILES_REFERENCE.md)
 4. 🚀 Follow [Next Steps](./planning/NEXT_STEPS.md) for contribution areas
-**Looking for specific info?**
+### For Storytellers
- **Setup/Installation** → [setup/](./setup/)
+1. 🎭 See [Features Guide](./features/README.md) for all tools
- **Features & Roadmap** → [planning/](./planning/)
+2. 🧠 Learn about [Context-Aware Responses](./features/CONTEXTUAL_RESPONSE_FEATURE.md)
- **API/Models/Files** → [reference/](./reference/)
+3. 💡 Use [Quick Reference](./setup/QUICK_REFERENCE.md) for common tasks
- **Architecture** → [development/](./development/)
+4. 🎲 Start with [Demo Session](./features/DEMO_SESSION.md) for practice
 ---
-## 📊 Documentation Overview
+## 📊 Current Status (v0.2.0)
-| Category | Files | Purpose |
+### ✅ Completed Features
-|----------|-------|---------|
+- Private/public/mixed messaging system
-| **Setup** | 2 | Getting started and quick references |
+- Context-aware AI response generator
-| **Planning** | 3 | Roadmaps, feature plans, project goals |
+- Demo session with pre-configured characters
-| **Reference** | 2 | Technical guides and file references |
+- Real-time WebSocket communication
-| **Development** | 2 | Session notes and implementation details |
+- Multi-LLM support (GPT-4o, Claude, Llama, etc.)
 - AI-assisted storyteller suggestions
 - Session ID quick copy
 - Full conversation history
 ### 🚧 Coming Soon
 - Database persistence
 - Character sheets & stats
 - Dice rolling mechanics
 - Combat system
 - Image generation
 - Voice messages
 See [MVP Roadmap](./planning/MVP_ROADMAP.md) for the complete timeline.
 ---
 ## 📝 Documentation Principles
 This documentation follows these principles:
 - **Progressive Disclosure**: Start simple, dive deeper as needed
 - **Always Current**: Updated with each feature implementation
 - **Example-Driven**: Real code examples and use cases
 - **Clear Structure**: Logical organization for easy navigation
 - **Feature-Focused**: Detailed guides for every feature
 ---
 ## 🎯 Documentation Map
 ```
 docs/
 ├── features/           ← Feature guides & examples
 │   ├── README.md
 │   ├── DEMO_SESSION.md
 │   ├── CONTEXTUAL_RESPONSE_FEATURE.md
 │   ├── PROMPT_IMPROVEMENTS.md
 │   └── FIXES_SUMMARY.md
 ├── setup/              ← Installation & quick start
 │   ├── QUICKSTART.md
 │   └── QUICK_REFERENCE.md
 ├── planning/           ← Roadmap & future plans
 │   ├── PROJECT_PLAN.md
 │   ├── MVP_ROADMAP.md
 │   └── NEXT_STEPS.md
 ├── development/        ← Technical & testing docs
 │   ├── MVP_PROGRESS.md
 │   ├── TESTING_GUIDE.md
 │   └── TEST_RESULTS.md
 └── reference/          ← Technical references
    ├── LLM_GUIDE.md
    └── PROJECT_FILES_REFERENCE.md
 ```
 ---
 ## 🤝 Contributing to Documentation
 Found a typo or want to improve the docs? Contributions are welcome!
 1. Documentation lives in the `docs/` folder
 2. Use clear, concise language
 3. Include examples where helpful
 4. Keep formatting consistent
 5. Update relevant indexes when adding new docs
 ---
 **Need help?** Start with the [Quickstart Guide](./setup/QUICKSTART.md) or check the main [README](../README.md).
 ---
--- a/docs/development/IMPLEMENTATION_SUMMARY.md
+++ b/docs/development/IMPLEMENTATION_SUMMARY.md
@@ -1,126 +0,0 @@
 # Implementation Summary
 ## ✅ Completed Features
 ### Backend (`main.py`)
 - **Isolated Character Sessions**: Each character has a separate conversation history that only they and the storyteller can see
 - **Private WebSocket Channels**: 
  - `/ws/character/{session_id}/{character_id}` - Character's private connection
  - `/ws/storyteller/{session_id}` - Storyteller's master connection
 - **Message Routing**: Messages flow privately between storyteller and individual characters
 - **Scene Broadcasting**: Storyteller can narrate scenes visible to all characters
 - **Real-time Updates**: WebSocket events for character joins, messages, and responses
 - **Pending Response Tracking**: System tracks which characters are waiting for storyteller responses
 - **AI Suggestions** (Optional): Endpoint for AI-assisted storyteller response generation
 ### Frontend Components
 #### 1. **SessionSetup.js**
 - Create new session (storyteller)
 - Join existing session (character)
 - Character creation with name, description, and personality
 - Beautiful gradient UI with modern styling
 #### 2. **CharacterView.js**
 - Private chat interface with storyteller
 - Real-time message delivery via WebSocket
 - Scene narration display
 - Conversation history preservation
 - Connection status indicator
 #### 3. **StorytellerView.js**
 - Dashboard showing all characters
 - Character list with pending response indicators
 - Click character to view their private conversation
 - Individual response system for each character
 - Scene narration broadcast to all characters
 - Visual indicators for pending messages
 ### Styling (`App.css`)
 - Modern gradient theme (purple/blue)
 - Responsive design
 - Smooth animations and transitions
 - Clear visual hierarchy
 - Mobile-friendly layout
 ### Documentation
 - **README.md**: Comprehensive guide with architecture, features, and API docs
 - **QUICKSTART.md**: Fast setup and testing guide
 - **.env.example**: Environment variable template
 ## 🔐 Privacy Implementation
 The core requirement - **isolated character sessions** - is implemented through:
 1. **Separate Data Structures**: Each character has `conversation_history: List[Message]` 
 2. **WebSocket Isolation**: Separate WebSocket connections per character
 3. **Message Routing**: Messages only sent to intended recipient
 4. **Storyteller View**: Only storyteller can see all conversations
 5. **Scene Broadcast**: Shared narrations go to all, but conversations stay private
 ## 🎯 Workflow
 ```
 Character A → Storyteller: "I search the room"
 Character B → Storyteller: "I attack the guard"
    ↓
 Storyteller sees both messages separately
    ↓
 Storyteller → Character A: "You find a hidden key"
 Storyteller → Character B: "You miss your swing"
    ↓
 Character A only sees their conversation
 Character B only sees their conversation
 ```
 ## 📁 File Structure
 ```
 windsurf-project/
 ├── main.py                      # FastAPI backend with WebSocket support
 ├── requirements.txt             # Python dependencies
 ├── .env.example                 # Environment template
 ├── README.md                    # Full documentation
 ├── QUICKSTART.md               # Quick start guide
 ├── IMPLEMENTATION_SUMMARY.md   # This file
 └── frontend/
    ├── package.json
    └── src/
        ├── App.js              # Main app router
        ├── App.css             # All styling
        └── components/
            ├── SessionSetup.js      # Session creation/join
            ├── CharacterView.js     # Character interface
            └── StorytellerView.js   # Storyteller dashboard
 ```
 ## 🚀 To Run
 **Backend:**
 ```bash
 python main.py
 ```
 **Frontend:**
 ```bash
 cd frontend && npm start
 ```
 ## 🎨 Design Decisions
 1. **WebSocket over REST**: Real-time bidirectional communication required for instant message delivery
 2. **In-Memory Storage**: Simple session management; can be replaced with database for production
 3. **Component-Based Frontend**: Separate views for different roles (setup, character, storyteller)
 4. **Message Model**: Includes sender, content, timestamp for rich conversation history
 5. **Pending Response Flag**: Helps storyteller track which characters need attention
 ## 🔮 Future Enhancements
 - Database persistence (PostgreSQL/MongoDB)
 - User authentication
 - Character sheets with stats
 - Dice rolling system
 - Voice/audio support
 - Mobile apps
 - Multi-storyteller support
 - Group chat rooms (for party discussions)
--- a/docs/development/MVP_PROGRESS.md
+++ b/docs/development/MVP_PROGRESS.md
@@ -1,7 +1,7 @@
 # 🎯 MVP Progress Report
-**Last Updated:** October 11, 2025  
+**Last Updated:** October 12, 2025  
-**Status:** Phase 1 Complete, Moving to Phase 2
+**Status:** Phase 2 Complete, Moving to Phase 3
 ---
@@ -70,32 +70,48 @@
 - Public/private message flow ✅
 - WebSocket handling for all types ✅
-### 🔄 Phase 2: Character Profile System (NEXT)
+### ✅ Phase 2: Character Profile System (COMPLETE)
-**Target:** Week 3-4
+**Completed:** October 12, 2025
-**Tasks:**
+**Implemented:**
-1. Extend `Character` model with profile fields
+1. ✅ Extended `Character` model with profile fields
   - Gender (Male/Female/Non-binary/Custom)
   - Race (Human/Elf/Dwarf/Orc/Halfling)
   - Class (Warrior/Wizard/Cleric/Archer/Rogue)
   - Personality (Friendly/Serious/Doubtful/Measured)
   - Custom background text
-   - Avatar upload/selection
+   - Avatar data field (base64)
-2. Profile-based LLM prompts
+2. ✅ Profile-based LLM prompts
-   - Combine race + class + personality traits
+   - Combined race + class + personality traits
-   - Inject into character's LLM requests
+   - Injected into character's LLM requests
-   - Create prompt template system
+   - Created comprehensive prompt template system
   - `build_character_system_prompt()` function
-3. Character creation wizard
+3. ✅ Character creation wizard
-   - Multi-step form with dropdowns
+   - 6-step form with visual selection cards
-   - Profile preview
+   - Profile preview and review step
-   - Character customization
+   - Character customization with all options
   - Import from JSON functionality
-4. Import/Export system
+4. ✅ Import/Export system
-   - Export to JSON
+   - Export to JSON (complete)
-   - Export to PNG with metadata
+   - Import from JSON (complete)
-   - Import from JSON/PNG
+   - Export button in CharacterView
   - PNG with metadata (deferred to Phase 4)
 **New Files:**
 - `CharacterCreationWizard.js` (419 lines)
 - `CharacterCreationWizard.css` (352 lines)
 - `PHASE2_IMPLEMENTATION.md` (documentation)
 **Modified Files:**
 - `main.py` (+186 lines)
 - `SessionSetup.js` (+25 lines)
 - `CharacterView.js` (+30 lines)
 - `App.css` (+45 lines)
 **Total:** ~1,057 lines of code
 ### ⏳ Phase 3: User Mode Interfaces (Weeks 5-7)
 - Player interface refinement
--- a/docs/development/PHASE2_IMPLEMENTATION.md
+++ b/docs/development/PHASE2_IMPLEMENTATION.md
@@ -0,0 +1,351 @@
 # Phase 2 Implementation Summary
 **Date:** October 12, 2025  
 **Status:** ✅ Complete  
 **Phase:** Character Profile System (MVP Phase 2)
 ---
 ## 🎯 Overview
 Successfully implemented the Character Profile System as outlined in the MVP Roadmap. This phase adds structured character creation with race, class, gender, and personality traits, along with profile-based LLM prompts and import/export functionality.
 ---
 ## ✅ Completed Features
 ### 1. Backend: Character Profile Model
 **File:** `main.py`
 Added `CharacterProfile` model with:
 - **Gender:** Male, Female, Non-binary, Custom
 - **Race:** Human, Elf, Dwarf, Orc, Halfling
 - **Class:** Warrior, Wizard, Cleric, Archer, Rogue
 - **Personality Type:** Friendly, Serious, Doubtful, Measured
 - **Background:** Custom background story
 - **Avatar Data:** Base64 encoded avatar (placeholder for future image support)
 Extended `Character` model to include optional `profile` field for backward compatibility with legacy characters.
 ### 2. Backend: Prompt Template System
 **File:** `main.py` (lines 76-129)
 Created comprehensive prompt templates:
 #### Race Templates
 - **Human:** Versatile and adaptable
 - **Elf:** Graceful, wise, with keen senses and magic affinity
 - **Dwarf:** Stout, loyal, master craftsmen
 - **Orc:** Powerful, direct, honorable warriors
 - **Halfling:** Small, brave, lucky
 #### Class Templates
 - **Warrior:** Physical combat, tactics, protection
 - **Wizard:** Arcane magic, knowledge, intellectual approach
 - **Cleric:** Divine power, healing, compassion
 - **Archer:** Ranged combat, precision, patience
 - **Rogue:** Stealth, cunning, unconventional solutions
 #### Personality Templates
 - **Friendly:** Optimistic, cooperative, trusting
 - **Serious:** Focused, pragmatic, efficient
 - **Doubtful:** Cautious, skeptical, analytical
 - **Measured:** Balanced, thoughtful, diplomatic
 **Function:** `build_character_system_prompt(character: Character) -> str`
 - Combines all profile traits into cohesive system prompt
 - Maintains backward compatibility with legacy characters
 - Injects profile context into LLM requests
 ### 3. Backend: API Endpoints
 **New Endpoints:**
 #### Character Creation (Updated)
 ```
 POST /sessions/{session_id}/characters/
 Body: CreateCharacterRequest (JSON with optional profile)
 ```
 #### Legacy Character Creation (Backward Compatible)
 ```
 POST /sessions/{session_id}/characters/legacy/
 Query params: name, description, personality, llm_model
 ```
 #### Export Character
 ```
 GET /sessions/{session_id}/characters/{character_id}/export
 Returns: JSON with character data, version, timestamp
 ```
 #### Import Character
 ```
 POST /sessions/{session_id}/characters/import
 Body: { character_data: {...} }
 ```
 #### Profile Options
 ```
 GET /profile/options
 Returns: Available genders, races, classes, personalities with descriptions
 ```
 ### 4. Frontend: Character Creation Wizard
 **File:** `frontend/src/components/CharacterCreationWizard.js`
 6-step wizard interface:
 1. **Basic Info:** Name, gender, import option
 2. **Description:** Character description and background
 3. **Race & Class:** Visual selection cards with descriptions
 4. **Personality:** Personality type selection
 5. **AI Model:** LLM model selection with descriptions
 6. **Review:** Complete character preview before creation
 **Features:**
 - Progressive disclosure design
 - Visual progress indicator
 - Selection cards with hover effects
 - Import from JSON
 - Form validation
 - Responsive design
 **File:** `frontend/src/components/CharacterCreationWizard.css`
 - Modern dark theme matching application style
 - Smooth animations and transitions
 - Mobile-responsive grid layouts
 - Visual feedback on selections
 ### 5. Frontend: SessionSetup Integration
 **File:** `frontend/src/components/SessionSetup.js`
 Updated to support both wizard and simple character creation:
 - **Wizard Mode:** Full character creation with profile
 - **Quick Create:** Toggle for simple legacy mode
 - Import character JSON during wizard
 - Session ID validation before opening wizard
 ### 6. Frontend: Character Export
 **File:** `frontend/src/components/CharacterView.js`
 Added export functionality:
 - Export button in character header
 - Downloads JSON file with character data
 - Filename includes character name and date
 - Profile badges display in character info
 ### 7. CSS Updates
 **File:** `frontend/src/App.css`
 Added styles for:
 - Character profile badges
 - Character actions container
 - Export button styling
 - Character creation options
 - Wizard button styling
 - Mobile responsive adjustments
 ---
 ## 🔧 Technical Implementation Details
 ### Profile-Based LLM Prompts
 The system now generates context-aware prompts by combining:
 1. Character name and basic identity
 2. Race traits (from RACE_PROMPTS)
 3. Class abilities (from CLASS_PROMPTS)
 4. Personality traits (from PERSONALITY_PROMPTS)
 5. Custom background (if provided)
 6. Legacy personality field (backward compatible)
 **Example Generated Prompt:**
 ```
 You are Thorin, a male Dwarf Warrior. A grizzled veteran seeking redemption. 
 You are a dwarf, stout and honorable with deep knowledge of stone and metal. 
 You are loyal, practical, and value tradition. You excel in physical combat 
 and tactics, preferring direct action and protecting your allies. You are 
 brave and decisive in battle. You are serious and focused, prioritizing 
 efficiency and practical solutions. You are disciplined and value getting 
 things done. Background: Former guardian of the Mountain Keep, exiled after 
 a tragic failure.
 ```
 ### Import/Export Format
 **Export Structure:**
 ```json
 {
  "version": "1.0",
  "character": {
    "id": "...",
    "name": "Character Name",
    "description": "...",
    "profile": {
      "gender": "Male",
      "race": "Elf",
      "character_class": "Wizard",
      "personality_type": "Measured",
      "background": "...",
      "avatar_data": null
    },
    "llm_model": "gpt-4o",
    "conversation_history": [],
    "pending_response": false
  },
  "created_at": "2025-10-12T00:00:00",
  "export_type": "storyteller_rpg_character"
 }
 ```
 **Import Process:**
 1. Validates JSON structure
 2. Extracts character data
 3. Generates new ID to avoid conflicts
 4. Clears conversation history
 5. Adds to session
 6. Notifies storyteller via WebSocket
 ### Backward Compatibility
 The system maintains full backward compatibility:
 - Legacy characters without profiles still work
 - `build_character_system_prompt()` handles both types
 - Legacy endpoint available at `/characters/legacy/`
 - Simple creation mode in SessionSetup
 ---
 ## 📊 Files Changed
 ### Backend
 - `main.py`: +186 lines
  - CharacterProfile model
  - Prompt templates
  - Profile building function
  - Import/export endpoints
  - Profile options endpoint
  - Updated character creation
 ### Frontend
 - `CharacterCreationWizard.js`: +419 lines (new)
 - `CharacterCreationWizard.css`: +352 lines (new)
 - `SessionSetup.js`: +25 lines modified
 - `CharacterView.js`: +30 lines modified
 - `App.css`: +45 lines modified
 **Total:** ~1,057 lines added/modified
 ---
 ## 🧪 Testing Checklist
 - [ ] Create character with wizard (all steps)
 - [ ] Export character to JSON
 - [ ] Import character from JSON
 - [ ] Verify profile displays in CharacterView
 - [ ] Test legacy character creation (simple mode)
 - [ ] Verify LLM prompts include profile data
 - [ ] Test backward compatibility with existing characters
 - [ ] Mobile responsive testing
 - [ ] Profile options endpoint
 - [ ] All race/class/personality combinations
 ---
 ## 🚀 Next Steps (Phase 3)
 According to MVP Roadmap:
 ### Phase 3: User Mode Interfaces (Weeks 5-7)
 1. **Player Interface Refinement**
   - Enhanced character sheet display
   - Profile editing
   - Inventory/stats (if applicable)
 2. **Storyteller Dashboard**
   - View all character profiles
   - Profile-aware response generation
   - AI player profile management
 3. **Gamemaster Control Panel**
   - Game creation wizard
   - Player/role assignment
   - Profile-based AI configuration
 4. **Permission Enforcement**
   - Backend decorators
   - Frontend UI restrictions
   - WebSocket filtering
 ---
 ## 💡 Known Limitations & Future Improvements
 ### Current Limitations
 1. **Avatar Support:** Profile has `avatar_data` field but no UI for upload
 2. **PNG Export:** JSON export works, PNG with metadata not yet implemented
 3. **Profile Editing:** No UI to edit profile after creation
 4. **Pre-made Templates:** No quick-start character templates
 ### Future Enhancements
 1. **Avatar System:**
   - Upload images
   - AI-generated avatars (DALL-E/Stable Diffusion)
   - Avatar gallery
 2. **PNG Export/Import:**
   - Embed profile in PNG metadata
   - Visual character cards
 3. **Profile Templates:**
   - Pre-made character archetypes
   - Quick-start templates (Fighter, Mage, Rogue, etc.)
   - Community-shared templates
 4. **Advanced Profiles:**
   - Skills and abilities
   - Equipment/inventory
   - Stats (HP, MP, etc.)
   - Character progression/leveling
 5. **Profile Validation:**
   - Character name uniqueness
   - Profile completeness checks
   - Custom validation rules
 ---
 ## 📝 Documentation Updates Needed
 - [x] Phase 2 implementation summary (this document)
 - [ ] Update MVP_PROGRESS.md with Phase 2 completion
 - [ ] Update NEXT_STEPS.md with Phase 3 priorities
 - [ ] User guide for character creation wizard
 - [ ] API documentation for new endpoints
 - [ ] Update CHANGELOG.md
 ---
 ## 🎉 Achievements
 ✅ **Profile System:** Comprehensive character profiles with 5 races, 5 classes, 4 personalities  
 ✅ **Smart Prompts:** Context-aware LLM prompts based on character traits  
 ✅ **Beautiful UI:** 6-step wizard with modern design  
 ✅ **Import/Export:** Full character portability  
 ✅ **Backward Compatible:** Legacy characters still work  
 ✅ **Extensible:** Easy to add new races, classes, personalities  
 **Phase 2 Status:** ✅ COMPLETE
 ---
 *Last Updated: October 12, 2025*
 *Implementation Time: ~3 hours*
 *Lines of Code: ~1,057*
--- a/docs/development/SESSION_SUMMARY.md
+++ b/docs/development/SESSION_SUMMARY.md
@@ -1,502 +0,0 @@
 # 📝 Development Session Summary
 **Date:** October 11, 2025
 **Project:** Storyteller RPG Application
 **Status:** ✅ Fully Functional MVP Complete
 ---
 ## 🎯 Project Overview
 Built a **storyteller-centric roleplaying application** where multiple AI character bots or human players interact with a storyteller through **completely isolated, private conversations**.
 ### Core Concept
 - **Characters communicate ONLY with the storyteller** (never with each other by default)
 - **Each character has separate memory/LLM sessions** - their responses are isolated
 - **Storyteller sees all conversations** but responds to each character individually
 - **Characters cannot see other characters' messages or responses**
 - Characters can use **different AI models** (GPT-4, Claude, Llama, etc.) giving each unique personalities
 ---
 ## 🏗️ Architecture Built
 ### Backend: FastAPI + WebSockets
 **File:** `/home/aodhan/projects/apps/storyteller/main.py` (398 lines)
 **Key Components:**
 1. **Data Models:**
   - `GameSession` - Manages the game session and all characters
   - `Character` - Stores character info, LLM model, and private conversation history
   - `Message` - Individual message with sender, content, timestamp
   - `ConnectionManager` - Handles WebSocket connections
 2. **WebSocket Endpoints:**
   - `/ws/character/{session_id}/{character_id}` - Private character connection
   - `/ws/storyteller/{session_id}` - Storyteller dashboard connection
 3. **REST Endpoints:**
   - `POST /sessions/` - Create new game session
   - `GET /sessions/{session_id}` - Get session details
   - `POST /sessions/{session_id}/characters/` - Add character to session
   - `GET /sessions/{session_id}/characters/{character_id}/conversation` - Get conversation history
   - `POST /sessions/{session_id}/generate_suggestion` - AI-assisted storyteller responses
   - `GET /models` - List available LLM models
 4. **LLM Integration:**
   - **OpenAI**: GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo
   - **OpenRouter**: Claude 3.5, Llama 3.1, Gemini Pro, Mistral, Cohere, 100+ models
   - `call_llm()` function routes to appropriate provider based on model ID
   - Each character can use a different model
 5. **Message Flow:**
   ```
   Character sends message → WebSocket → Stored in Character.conversation_history
                          ↓
                    Forwarded to Storyteller
                          ↓
   Storyteller responds → WebSocket → Stored in Character.conversation_history
                          ↓
                    Sent ONLY to that Character
   ```
 ### Frontend: React
 **Files:** 
 - `frontend/src/App.js` - Main router component
 - `frontend/src/components/SessionSetup.js` (180 lines) - Session creation/joining
 - `frontend/src/components/CharacterView.js` (141 lines) - Character interface
 - `frontend/src/components/StorytellerView.js` (243 lines) - Storyteller dashboard
 - `frontend/src/App.css` (704 lines) - Complete styling
 **Key Features:**
 1. **SessionSetup Component:**
   - Create new session (becomes storyteller)
   - Join existing session (becomes character)
   - Select LLM model for character
   - Model selector fetches available models from backend
 2. **CharacterView Component:**
   - Private conversation with storyteller
   - WebSocket connection for real-time updates
   - See scene narrations from storyteller
   - Character info display (name, description, personality)
   - Connection status indicator
 3. **StorytellerView Component:**
   - Dashboard showing all characters
   - Click character to view their private conversation
   - Respond to characters individually
   - Narrate scenes visible to all characters
   - Pending response indicators (red badges)
   - Character cards showing:
     - Name, description, personality
     - LLM model being used
     - Message count
     - Pending status
 4. **UI/UX Design:**
   - Beautiful gradient purple theme
   - Responsive design
   - Real-time message updates
   - Auto-scroll to latest messages
   - Clear visual distinction between sent/received messages
   - Session ID prominently displayed for sharing
   - Empty states with helpful instructions
 ---
 ## 🔑 Key Technical Decisions
 ### 1. **Isolated Conversations (Privacy-First)**
 - Each `Character` object has its own `conversation_history: List[Message]`
 - Messages are never broadcast to all clients
 - WebSocket routing ensures messages only go to intended recipient
 - Storyteller has separate WebSocket endpoint to see all
 ### 2. **Multi-LLM Support**
 - Characters choose model at creation time
 - Stored in `Character.llm_model` field
 - Backend dynamically routes API calls based on model prefix:
  - `gpt-*` → OpenAI API
  - Everything else → OpenRouter API
 - Enables creative gameplay with different AI personalities
 ### 3. **In-Memory Storage (Current)**
 - `sessions: Dict[str, GameSession]` stores all active sessions
 - Fast and simple for MVP
 - **Limitation:** Data lost on server restart
 - **Next step:** Add database persistence (see NEXT_STEPS.md)
 ### 4. **WebSocket-First Architecture**
 - Real-time bidirectional communication
 - Native WebSocket API (not socket.io)
 - JSON message format with `type` field for routing
 - Separate connections for characters and storyteller
 ### 5. **Scene Narration System**
 - Storyteller can broadcast "scene" messages
 - Sent to all connected characters simultaneously
 - Stored in `GameSession.current_scene` and `scene_history`
 - Different from private character-storyteller messages
 ---
 ## 📁 Project Structure
 ```
 storyteller/
 ├── main.py                      # FastAPI backend (398 lines)
 ├── requirements.txt             # Python dependencies
 ├── .env.example                 # API key template
 ├── .env                        # Your API keys (gitignored)
 ├── README.md                   # Comprehensive documentation
 ├── QUICKSTART.md               # 5-minute setup guide
 ├── NEXT_STEPS.md               # Future development roadmap
 ├── SESSION_SUMMARY.md          # This file
 ├── start.sh                    # Auto-start script
 ├── dev.sh                      # Development mode script
 └── frontend/
    ├── package.json            # Node dependencies
    ├── public/
    │   └── index.html          # HTML template
    └── src/
        ├── App.js              # Main router
        ├── App.css             # All styles (704 lines)
        ├── index.js            # React entry point
        └── components/
            ├── SessionSetup.js     # Session creation/joining
            ├── CharacterView.js    # Character interface
            └── StorytellerView.js  # Storyteller dashboard
 ```
 ---
 ## 🚀 How to Run
 ### Quick Start (Automated)
 ```bash
 cd /home/aodhan/projects/apps/storyteller
 chmod +x start.sh
 ./start.sh
 ```
 ### Manual Start
 ```bash
 # Terminal 1 - Backend
 cd /home/aodhan/projects/apps/storyteller
 source .venv/bin/activate  # or: source venv/bin/activate
 python main.py
 # Terminal 2 - Frontend
 cd /home/aodhan/projects/apps/storyteller/frontend
 npm start
 ```
 ### Environment Setup
 ```bash
 # Copy example and add your API keys
 cp .env.example .env
 # Edit .env and add at least one:
 # OPENAI_API_KEY=sk-...          # For GPT models
 # OPENROUTER_API_KEY=sk-...      # For Claude, Llama, etc.
 ```
 ---
 ## 🔍 Important Implementation Details
 ### WebSocket Message Types
 **Character → Storyteller:**
 ```json
 {
  "type": "message",
  "content": "I search the room for clues"
 }
 ```
 **Storyteller → Character:**
 ```json
 {
  "type": "storyteller_response",
  "message": {
    "id": "...",
    "sender": "storyteller",
    "content": "You find a hidden letter",
    "timestamp": "2025-10-11T20:30:00"
  }
 }
 ```
 **Storyteller → All Characters:**
 ```json
 {
  "type": "narrate_scene",
  "content": "The room grows dark as thunder rumbles"
 }
 ```
 **Storyteller receives character message:**
 ```json
 {
  "type": "character_message",
  "character_id": "uuid",
  "character_name": "Aragorn",
  "message": { ... }
 }
 ```
 **Character joined notification:**
 ```json
 {
  "type": "character_joined",
  "character": {
    "id": "uuid",
    "name": "Legolas",
    "description": "...",
    "llm_model": "gpt-4"
  }
 }
 ```
 ### LLM Integration
 **Function:** `call_llm(model, messages, temperature, max_tokens)`
 **Routing Logic:**
 ```python
 if model.startswith("gpt-") or model.startswith("o1-"):
    # Use OpenAI client
    response = await client.chat.completions.create(...)
 else:
    # Use OpenRouter via httpx
    response = await http_client.post("https://openrouter.ai/api/v1/chat/completions", ...)
 ```
 **Available Models (as of this session):**
 - OpenAI: gpt-4o, gpt-4-turbo, gpt-4, gpt-3.5-turbo
 - Anthropic (via OpenRouter): claude-3.5-sonnet, claude-3-opus, claude-3-haiku
 - Meta: llama-3.1-70b, llama-3.1-8b
 - Google: gemini-pro-1.5
 - Mistral: mistral-large
 - Cohere: command-r-plus
 ---
 ## 🎨 UI/UX Highlights
 ### Color Scheme
 - Primary gradient: Purple (`#667eea` → `#764ba2`)
 - Background: White cards on gradient
 - Messages: Blue (sent) / Gray (received)
 - Pending indicators: Red badges
 - Status: Green (connected) / Gray (disconnected)
 ### Key UX Features
 1. **Session ID prominently displayed** for easy sharing
 2. **Pending response badges** show storyteller which characters are waiting
 3. **Character cards** with all relevant info at a glance
 4. **Empty states** guide users on what to do next
 5. **Connection status** always visible
 6. **Auto-scroll** to latest message
 7. **Keyboard shortcuts** (Enter to send)
 8. **Model selector** with descriptions helping users choose
 ---
 ## 🐛 Known Limitations & TODO
 ### Current Limitations
 1. **No persistence** - Sessions lost on server restart
 2. **No authentication** - Anyone with session ID can join
 3. **No message editing/deletion** - Messages are permanent
 4. **No character limit** on messages (could be abused)
 5. **No rate limiting** - API calls not throttled
 6. **No offline support** - Requires active connection
 7. **No mobile optimization** - Works but could be better
 8. **No sound notifications** - Easy to miss new messages
 ### Security Considerations
 - **CORS is wide open** (`allow_origins=["*"]`) - Restrict in production
 - **No input validation** on message content - Add sanitization
 - **API keys in environment** - Good, but consider secrets manager
 - **No session expiration** - Sessions live forever in memory
 - **WebSocket not authenticated** - Anyone with session ID can connect
 ### Performance Considerations
 - **In-memory storage** - Won't scale to many sessions
 - **No message pagination** - All history loaded at once
 - **No connection pooling** - Each character = new WebSocket
 - **No caching** - LLM calls always go to API
 ---
 ## 💡 What Makes This Special
 ### Unique Features
 1. **Each character uses a different AI model** - Creates emergent gameplay
 2. **Completely private conversations** - True secret communication
 3. **Storyteller-centric design** - Built for tabletop RPG flow
 4. **Real-time updates** - Feels like a chat app
 5. **Model flexibility** - 100+ LLMs via OpenRouter
 6. **Zero configuration** - Works out of the box
 ### Design Philosophy
 - **Storyteller is the hub** - All communication flows through them
 - **Privacy first** - Characters truly can't see each other's messages
 - **Flexibility** - Support for any LLM model
 - **Simplicity** - Clean, intuitive interface
 - **Real-time** - No page refreshes needed
 ---
 ## 🔄 Context for Continuing Development
 ### If Starting a New Chat Session
 **What works:**
 - ✅ Backend fully functional with all endpoints
 - ✅ Frontend complete with all views
 - ✅ WebSocket communication working
 - ✅ Multi-LLM support implemented
 - ✅ Scene narration working
 - ✅ Private conversations isolated correctly
 **Quick test to verify everything:**
 ```bash
 # 1. Start servers
 ./start.sh
 # 2. Create session as storyteller
 # 3. Join session as character (new browser/incognito)
 # 4. Send message from character
 # 5. Verify storyteller sees it
 # 6. Respond from storyteller
 # 7. Verify character receives it
 # 8. Test scene narration
 ```
 **Common issues:**
 - **Port 8000/3000 already in use** - `start.sh` kills existing processes
 - **WebSocket won't connect** - Check backend is running, check browser console
 - **LLM not responding** - Verify API keys in `.env`
 - **npm/pip dependencies missing** - Run install commands
 ### Files to Modify for Common Tasks
 **Add new WebSocket message type:**
 1. Update message handler in `main.py` (character or storyteller endpoint)
 2. Update frontend component to send/receive new type
 **Add new REST endpoint:**
 1. Add `@app.post()` or `@app.get()` in `main.py`
 2. Add fetch call in appropriate frontend component
 **Modify UI:**
 1. Edit component in `frontend/src/components/`
 2. Edit styles in `frontend/src/App.css`
 **Add new LLM provider:**
 1. Update `call_llm()` function in `main.py`
 2. Update `get_available_models()` endpoint
 3. Add model options in `SessionSetup.js`
 ---
 ## 📊 Project Statistics
 - **Total Lines of Code:** ~1,700
 - **Backend:** ~400 lines (Python/FastAPI)
 - **Frontend:** ~1,300 lines (React/JavaScript/CSS)
 - **Time to MVP:** 1 session
 - **Dependencies:** 8 Python packages, 5 npm packages (core)
 - **API Endpoints:** 6 REST + 2 WebSocket
 - **React Components:** 3 main + 1 router
 - **Supported LLMs:** 15+ models across 6 providers
 ---
 ## 🎓 Learning Resources Used
 ### Technologies
 - **FastAPI:** https://fastapi.tiangolo.com/
 - **WebSockets:** https://developer.mozilla.org/en-US/docs/Web/API/WebSocket
 - **React:** https://react.dev/
 - **OpenAI API:** https://platform.openai.com/docs
 - **OpenRouter:** https://openrouter.ai/docs
 ### Key Concepts Implemented
 - WebSocket bidirectional communication
 - Async Python with FastAPI
 - React state management with hooks
 - Multi-provider LLM routing
 - Real-time message delivery
 - Isolated conversation contexts
 ---
 ## 📝 Notes for Future You
 ### Why certain decisions were made:
 - **WebSocket instead of polling:** Real-time updates without constant HTTP requests
 - **Separate endpoints for character/storyteller:** Clean separation of concerns, different message types
 - **In-memory storage first:** Fastest MVP, can migrate to DB later
 - **Multi-LLM from start:** Makes the app unique and interesting
 - **No socket.io:** Native WebSocket simpler for this use case
 - **Private conversations:** Core feature that differentiates from group chat apps
 ### What went smoothly:
 - FastAPI made WebSocket implementation easy
 - React components stayed clean and modular
 - OpenRouter integration was straightforward
 - UI came together nicely with gradients
 ### What could be improved:
 - Database persistence is the obvious next step
 - Error handling could be more robust
 - Mobile experience needs work
 - Need proper authentication system
 - Testing suite would be valuable
 ---
 ## 🚀 Recommended Next Actions
 **Immediate (Next Session):**
 1. Test the app end-to-end to ensure everything works after IDE crash
 2. Add AI suggestion button to storyteller UI (backend ready, just needs frontend)
 3. Implement session persistence with SQLite
 **Short Term (This Week):**
 4. Add dice rolling system
 5. Add typing indicators
 6. Improve error messages
 **Medium Term (This Month):**
 7. Add authentication
 8. Implement character sheets
 9. Add image generation for scenes
 See **NEXT_STEPS.md** for detailed roadmap with priorities and implementation notes.
 ---
 ## 📞 Session Handoff Checklist
 - ✅ All files verified and up-to-date
 - ✅ Architecture documented
 - ✅ Key decisions explained
 - ✅ Next steps outlined
 - ✅ Common issues documented
 - ✅ Code structure mapped
 - ✅ API contracts specified
 - ✅ Testing instructions provided
 **You're ready to continue development!** 🎉
 ---
 *Generated: October 11, 2025*
 *Project Location: `/home/aodhan/projects/apps/storyteller`*
 *Status: Production-ready MVP*
--- a/docs/development/TESTING_GUIDE.md
+++ b/docs/development/TESTING_GUIDE.md
--- a/docs/development/TEST_RESULTS.md
+++ b/docs/development/TEST_RESULTS.md
--- a/docs/features/CONTEXTUAL_RESPONSE_FEATURE.md
+++ b/docs/features/CONTEXTUAL_RESPONSE_FEATURE.md
--- a/docs/features/DEMO_SESSION.md
+++ b/docs/features/DEMO_SESSION.md
--- a/docs/features/FIXES_SUMMARY.md
+++ b/docs/features/FIXES_SUMMARY.md
--- a/docs/features/PROMPT_IMPROVEMENTS.md
+++ b/docs/features/PROMPT_IMPROVEMENTS.md
--- a/docs/features/README.md
+++ b/docs/features/README.md
@@ -0,0 +1,179 @@
 # 🎭 Features Documentation
 Detailed documentation for all Storyteller RPG features.
 ---
 ## Feature Guides
 ### Core Features
 #### [Demo Session](./DEMO_SESSION.md)
 Pre-configured test session that auto-loads on startup. Includes two characters (Bargin & Willow) and "The Cursed Tavern" adventure. Perfect for development and testing.
 **Quick Access:**
 - Session ID: `demo-session-001`
 - One-click buttons on home page
 - No setup required
 ---
 #### [Context-Aware Response Generator](./CONTEXTUAL_RESPONSE_FEATURE.md)
 AI-powered tool for storytellers to generate responses considering multiple characters' actions simultaneously.
 **Key Features:**
 - Multi-character selection
 - Scene descriptions (broadcast to all)
 - Individual responses (private to each)
 - Automatic parsing and distribution
 - Smart context building
 ---
 ### Technical Documentation
 #### [Prompt Engineering Improvements](./PROMPT_IMPROVEMENTS.md)
 Details on how we improved the LLM prompts for reliable individual response parsing using the `[CharacterName]` format.
 **Topics Covered:**
 - Square bracket format rationale
 - Regex parsing patterns
 - System prompt enhancements
 - Edge case handling
 ---
 #### [Bug Fixes Summary](./FIXES_SUMMARY.md)
 Comprehensive list of bugs fixed in the latest release.
 **Fixed Issues:**
 - Character chat history showing only recent messages
 - Pydantic deprecation warnings (.dict → .model_dump)
 - WebSocket manager reference errors
 - Session ID copy functionality
 ---
 ## Feature Overview by Category
 ### For Storytellers 🎲
 | Feature | Description | Status |
 |---------|-------------|--------|
 | **Session Management** | Create/join sessions, manage characters | ✅ Complete |
 | **Scene Narration** | Broadcast scene descriptions to all players | ✅ Complete |
 | **Private Responses** | Send individual messages to characters | ✅ Complete |
 | **AI Suggestions** | Get AI-generated response suggestions | ✅ Complete |
 | **Context-Aware Generator** | Generate responses considering multiple characters | ✅ Complete |
 | **Pending Message Tracking** | See which characters need responses | ✅ Complete |
 | **Demo Session** | Pre-loaded test scenario for quick start | ✅ Complete |
 ### For Players 🎭
 | Feature | Description | Status |
 |---------|-------------|--------|
 | **Character Creation** | Define name, description, personality | ✅ Complete |
 | **Private Messages** | Send private messages to storyteller | ✅ Complete |
 | **Public Actions** | Broadcast actions visible to all players | ✅ Complete |
 | **Mixed Messages** | Public action + private thoughts | ✅ Complete |
 | **Scene Viewing** | See current scene description | ✅ Complete |
 | **Public Feed** | View all players' public actions | ✅ Complete |
 | **Conversation History** | Full chat log with storyteller | ✅ Complete |
 ### Message System 📨
 | Feature | Description | Status |
 |---------|-------------|--------|
 | **Private Messages** | One-on-one conversation | ✅ Complete |
 | **Public Messages** | Visible to all players | ✅ Complete |
 | **Mixed Messages** | Public + private components | ✅ Complete |
 | **Real-time Updates** | WebSocket-based live updates | ✅ Complete |
 | **Message Persistence** | In-memory storage (session lifetime) | ✅ Complete |
 ### AI Integration 🤖
 | Feature | Description | Status |
 |---------|-------------|--------|
 | **Multiple LLM Support** | GPT-4o, GPT-4, GPT-3.5, Claude, Llama | ✅ Complete |
 | **AI Response Suggestions** | Quick response generation | ✅ Complete |
 | **Context-Aware Generation** | Multi-character context building | ✅ Complete |
 | **Structured Output Parsing** | [CharacterName] format parsing | ✅ Complete |
 | **Temperature Control** | Creative vs. focused responses | ✅ Complete |
 ---
 ## Coming Soon 🚀
 ### Planned Features
 - **Database Persistence** - Save sessions and characters permanently
 - **Character Sheets** - Stats, inventory, abilities
 - **Dice Rolling** - Built-in dice mechanics
 - **Combat System** - Turn-based combat management
 - **Image Generation** - AI-generated scene/character images
 - **Voice Messages** - Audio message support
 - **Session Export** - Export conversation logs
 - **User Authentication** - Account system with saved preferences
 ---
 ## Feature Request Process
 Want to suggest a new feature?
 1. **Check existing documentation** - Feature might already exist
 2. **Review roadmap** - Check if it's already planned (see [MVP_ROADMAP.md](../planning/MVP_ROADMAP.md))
 3. **Create an issue** - Describe the feature and use case
 4. **Discuss implementation** - We'll evaluate feasibility and priority
 ---
 ## Version History
 ### v0.2.0 - Context-Aware Features (October 2025)
 - ✅ Context-aware response generator
 - ✅ Demo session with pre-configured characters
 - ✅ Improved prompt engineering for parsing
 - ✅ Bug fixes (chat history, Pydantic warnings)
 - ✅ Session ID copy button
 ### v0.1.0 - MVP Phase 1 (October 2025)
 - ✅ Basic session management
 - ✅ Character creation and joining
 - ✅ Private/public/mixed messaging
 - ✅ Real-time WebSocket communication
 - ✅ Scene narration
 - ✅ AI-assisted responses
 - ✅ Multiple LLM support
 ---
 ## Documentation Structure
 ```
 docs/
 ├── features/           ← You are here
 │   ├── README.md
 │   ├── DEMO_SESSION.md
 │   ├── CONTEXTUAL_RESPONSE_FEATURE.md
 │   ├── PROMPT_IMPROVEMENTS.md
 │   └── FIXES_SUMMARY.md
 ├── development/
 │   ├── MVP_PROGRESS.md
 │   ├── TESTING_GUIDE.md
 │   └── TEST_RESULTS.md
 ├── planning/
 │   ├── MVP_ROADMAP.md
 │   ├── PROJECT_PLAN.md
 │   └── NEXT_STEPS.md
 ├── setup/
 │   ├── QUICKSTART.md
 │   └── QUICK_REFERENCE.md
 └── reference/
    ├── PROJECT_FILES_REFERENCE.md
    └── LLM_GUIDE.md
 ```
 ---
 **Need help?** Check the [main README](../../README.md) or the [Quick Start Guide](../setup/QUICKSTART.md).
--- a/docs/reference/UI_DESIGN_PROMPTS.md
+++ b/docs/reference/UI_DESIGN_PROMPTS.md
@@ -0,0 +1,654 @@
 # UI Design Prompts - Ready to Use
 **Purpose:** Copy-paste prompts for UI design LLMs (v0.dev, Midjourney, etc.)  
 **Date:** October 12, 2025
 ---
 ## 🎨 Base Prompt Template
 ```
 Design a modern dark-themed web application interface for a tabletop RPG storytelling platform.
 Visual Style:
 - Dark theme with purple gradient accents (#667eea to #764ba2)
 - Card-based layout with rounded corners (8-12px radius)
 - Smooth shadows for depth and elevation
 - Clean, modern sans-serif typography
 - RPG fantasy aesthetic with subtle magical elements
 Color Palette:
 - Background: Deep dark blue (#1a1a2e, #16213e)
 - Surface: Dark slate (#2d3748)
 - Primary: Purple gradient (#667eea to #764ba2)
 - Text: White/light gray (#ffffff, #e2e8f0)
 - Accent: Bright purple (#667eea)
 Design Principles:
 - Clear visual hierarchy
 - Generous white space
 - Accessible contrast ratios
 - Smooth animations and transitions
 - Mobile-responsive design
 ```
 ---
 ## 📄 Prompt 1: Session Setup / Landing Page
 ```
 Create a modern dark-themed landing page for an RPG storytelling web app called "Storyteller RPG"
 Page Components:
 1. Header Section:
   - Large app title with dice emoji (🎭 Storyteller RPG)
   - Subtitle: "Private character-storyteller interactions"
   - Centered layout
 2. Demo Session Card:
   - Title: "🎲 Demo Session - The Cursed Tavern"
   - Short description text
   - Three horizontally arranged buttons:
     * "🎲 Join as Storyteller" (primary gradient button)
     * "⚔️ Play as Bargin (Dwarf Warrior)" (character button)
     * "🏹 Play as Willow (Elf Ranger)" (character button)
   - Gradient background (gold #ffd89b to teal #19547b)
   - Rounded corners with padding
 3. Divider:
   - Horizontal line with centered text "OR CREATE YOUR OWN"
 4. Create Session Section:
   - White card with shadow
   - Title: "Create New Session"
   - Description: "Start a new game as the storyteller"
   - Text input field for session name
   - Full-width primary button: "Create Session"
 5. Divider:
   - Horizontal line with "OR"
 6. Join Session Section:
   - White card with shadow
   - Title: "Join Existing Session"
   - Form with inputs:
     * Session ID field
     * Character name field
     * Character description textarea
     * Personality textarea (optional)
     * Model selector dropdown
   - Large gradient button: "✨ Create Character (Wizard)"
   - Secondary toggle: "↓ Quick Create"
 Visual Style:
 - Purple gradient background for page
 - White content cards with soft shadows
 - Centered layout, max-width 600px
 - Generous padding and spacing
 - Modern, clean, inviting design
 ```
 ---
 ## 📄 Prompt 2: Character View (Player Interface)
 ```
 Design a dark-themed character view interface for a player in an RPG session
 Layout Structure:
 - Full-height application with header, scrollable content, and fixed message composer
 Components:
 1. Character Header (Dark gradient #2d3748):
   - Left side:
     * Character name (large, white)
     * Character description (gray text)
     * Personality trait with emoji (🎭)
     * Three profile badges: Race | Class | Personality
       (Pills with purple accent color)
   - Right side:
     * Export button (📥 Export) with subtle purple background
     * Connection status indicator:
       - Green dot "● Connected" when active
       - Gray dot "○ Disconnected" when offline
 2. Current Scene Card (if active):
   - Highlighted card with scene icon (📜)
   - Title: "Current Scene"
   - Scene description text
   - Distinct background color from messages
 3. Two-Column Content Area:
   Left Column - Public Messages Feed:
   - Title: "📢 Public Actions (All Players See)"
   - Message cards with:
     * Sender name/icon
     * Message content
     * Timestamp
     * Light background with left purple border accent
   Right Column - Private Conversation:
   - Title: "💬 Private Conversation with Storyteller"
   - Chat-style message bubbles:
     * Character messages: Right-aligned, purple gradient
     * Storyteller messages: Left-aligned, darker color
     * Timestamps below each message
   - Auto-scroll to bottom
 4. Message Composer (Fixed Bottom):
   - Visibility dropdown selector (Private | Public | Mixed)
   - For "Mixed" mode:
     * Two textareas stacked:
       - "Public action (all players see)..."
       - "Private action (only storyteller sees)..."
     * "Send Mixed Message" button
   - For simple mode:
     * Single input field (placeholder changes by visibility)
     * "Send" button
   - Elevated shadow, dark background
 Visual Style:
 - Dark theme throughout
 - Purple accent colors for character messages
 - Clear visual separation between public and private
 - Smooth scrolling
 - Professional messaging interface aesthetic
 ```
 ---
 ## 📄 Prompt 3: Character Creation Wizard
 ```
 Design a beautiful multi-step character creation wizard modal for an RPG application
 Modal Structure:
 - Full-screen dark overlay (semi-transparent)
 - Centered wizard container (max 800px wide)
 - Dark gradient background (#1a1a2e to #16213e)
 - Rounded corners with border
 Components:
 1. Wizard Header:
   - Large title: "Create Your Character"
   - Progress indicator: 6 step pills arranged horizontally
     * "1. Basic Info" | "2. Description" | "3. Race & Class" | "4. Personality" | "5. AI Model" | "6. Review"
     * Active step: Purple gradient background, white text
     * Inactive steps: Muted gray background, gray text
     * Completed steps: Dimmed purple
   - Steps wrap on mobile
 2. Content Area (Changes per step):
   Step 1 - Basic Info:
   - Text input: "Character Name" (with autofocus glow)
   - Dropdown: "Gender" (Male, Female, Non-binary, Custom)
   - Import section:
     * Light text: "💡 Have an existing character?"
     * Button: "📥 Import from JSON" (outlined style)
   Step 3 - Race & Class (example):
   - Grid of 5 selection cards (2-3 columns responsive)
   - Each card:
     * Race/Class name (bold white)
     * Short description (gray)
     * Unselected: Dark background, light border
     * Selected: Purple gradient background, bright border, slight shadow
     * Hover: Lift effect with shadow
   - Two sections: Race cards, then Class cards
   Step 6 - Review:
   - Preview card with sections:
     * Basic Information (list of key-value pairs)
     * Description (paragraph)
     * Background (if provided)
     * AI Model
   - Summary box at bottom:
     * Purple gradient background
     * "Character Summary" heading
     * Natural language sentence about the character
 3. Wizard Footer:
   - Left: "Cancel" button (secondary)
   - Right: Navigation buttons
     * "← Back" (secondary, only shows steps 2-6)
     * "Next →" (primary purple gradient, steps 1-5)
     * "✨ Create Character" (primary gradient, step 6)
 Animations:
 - Step content fades in with slight upward movement
 - Card selection: Scale transform + glow
 - Progress indicator: Smooth transitions
 - Button hovers: Elevation effect
 Visual Style:
 - Dark, immersive wizard experience
 - Purple accent throughout
 - Clear visual hierarchy
 - Smooth, modern interactions
 - Feels guided and professional
 ```
 ---
 ## 📄 Prompt 4: Storyteller View Dashboard
 ```
 Design a comprehensive storyteller dashboard for managing an RPG game session
 Layout:
 - Sidebar + main content area (grid layout)
 - Dark theme with purple accents
 Components:
 1. Header Bar:
   - Session name (large white text)
   - Session ID with copy button
   - "Generate Contextual Response" button (purple gradient)
   - Connection status indicator
 2. Left Sidebar - Character List:
   - Title: "Characters in Session"
   - Scrollable character cards (one per character):
     * Character name (white)
     * Small profile badges (Race | Class | Personality)
     * "Needs Response" red indicator (if pending)
     * Hover: Light background
     * Selected: Purple left border + highlighted background
   - Empty state: "No characters yet" with muted text
 3. Main Content Area - Tabs:
   Tab 1 - Public Actions Feed:
   - Title: "📢 Recent Public Actions"
   - Timeline/feed of public messages:
     * Character avatar/icon
     * Character name
     * Action text
     * Timestamp
     * Compact card style with left accent
   Tab 2 - Character Conversation (selected character):
   - Character header showing their profile
   - Message thread (scrollable):
     * Character messages (left-aligned)
     * Storyteller responses (right-aligned, purple)
     * Timestamps
   - Response composer section:
     * Large textarea "Write your response..."
     * "✨ AI Suggest" button (secondary)
     * "Send Private Response" button (primary)
   Tab 3 - Scene Narration:
   - Title: "📜 Broadcast Scene to All Players"
   - Large textarea for scene description
   - Context options:
     * Character selection checkboxes
     * Additional context input
   - "Generate with AI" button (secondary)
   - "Broadcast Scene" button (primary, large)
 4. AI Suggestion Panel (conditional):
   - Appears when "AI Suggest" clicked
   - Green accent background
   - Title: "AI-Generated Suggestion"
   - Editable textarea with generated response
   - Model indicator (small text)
   - Action buttons:
     * "Use This Response" (success green)
     * "Regenerate" (secondary)
     * "Cancel" (text button)
 Visual Style:
 - Dark command center aesthetic
 - Clear information hierarchy
 - Easy to scan character list
 - Comfortable reading for long text
 - Purple highlights for storyteller actions
 - Green highlights for AI features
 ```
 ---
 ## 📄 Prompt 5: Gamemaster Control Panel
 ```
 Design a powerful gamemaster control panel for managing RPG game sessions
 Layout:
 - Command center dashboard style
 - Sidebar navigation + main content panels
 - Dark theme with multiple accent colors
 Components:
 1. Header:
   - Title: "Gamemaster Control Panel"
   - Current game indicator (pill badge)
   - Quick action buttons:
     * "Create New Game" (purple gradient)
     * "Load Game" (secondary)
     * "Save Game" (secondary)
 2. Left Navigation:
   - Vertical menu with icons:
     * Dashboard (overview icon)
     * Games (list icon)
     * Players (users icon)
     * Settings (gear icon)
   - Active item: Purple left border + highlight
 3. Main Content - Game Creation Wizard:
   Step 2 - Player Slots:
   - Grid of player slot cards (2-3 columns):
     * Slot number badge (top-right)
     * Type toggle: Human | AI (switch component)
     * If Human:
       - User selector dropdown
       - Character assignment
     * If AI:
       - AI model dropdown
       - Personality/behavior settings
     * Drag handle (for reordering)
   - "Add Slot" button at end
   Each slot card:
   - Dark background with border
   - Assigned: Green accent border
   - Empty: Dashed border
   - Hover: Lift effect
 4. Main Content - Game Overview Dashboard:
   - Metric cards row (4 cards):
     * Active Players (number + icon)
     * Total Messages (number + icon)
     * Session Duration (time + icon)
     * AI Usage Cost ($ + icon)
   - Current scene card (large, highlighted)
   - Recent activity feed
   - Quick actions panel
 5. Role Assignment Interface:
   - Drag-and-drop layout:
     * Left: Available players list (cards)
     * Right: Game slots (drop zones)
     * Visual feedback during drag
   - Each player card:
     * Avatar/icon
     * Username
     * Online status
     * Drag handle
 Visual Style:
 - Professional dashboard aesthetic
 - Multiple status colors (green=good, red=alert, yellow=warning)
 - Clear data visualization
 - Interactive drag-and-drop
 - Elevated cards with shadows
 - Purple primary, green success, red danger
 ```
 ---
 ## 📄 Prompt 6: Admin Dashboard
 ```
 Design a comprehensive system administration dashboard for monitoring and management
 Layout:
 - Full-width dashboard with sidebar navigation
 - Dark theme with data visualization focus
 Components:
 1. Top Header:
   - Title: "System Administration"
   - System status indicators (colored dots):
     * API Status (green/red)
     * Database (green/red)
     * WebSocket (green/red)
   - Global stats (small numbers):
     * Active Games: 12
     * Active Users: 48
     * API Calls Today: 1,234
 2. Sidebar Navigation:
   - Vertical menu items:
     * Dashboard (home icon)
     * Games (controller icon)
     * Users (people icon)
     * LLM Config (brain icon)
     * Analytics (chart icon)
     * Costs (dollar icon)
     * Logs (terminal icon)
   - Active: Purple background + white icon
 3. Dashboard Overview:
   - 4 metric cards (top row):
     * Total Games (number, trend arrow, sparkline)
     * Total Users (number, trend arrow, sparkline)
     * Today's Cost ($, trend arrow)
     * System Health (percentage, circular progress)
   - Charts section:
     * Line chart: "Games Created Over Time" (7 days)
     * Bar chart: "Model Usage Distribution"
     * Pie chart: "Cost Breakdown by Model"
   - Recent Activity Feed:
     * Timeline of recent events
     * Color-coded by type (create, error, warning)
     * Timestamps
     * Quick action buttons
 4. Games Management Table:
   - Data table with columns:
     * ID | Name | GM | Players | Status | Created | Actions
   - Features:
     * Sort arrows in headers
     * Search bar (top-right)
     * Filter chips (by status)
     * Pagination controls (bottom)
   - Row actions:
     * View (eye icon)
     * Edit (pencil icon)
     * Delete (trash icon)
   - Status badges (colored):
     * Active (green)
     * Paused (yellow)
     * Completed (gray)
 5. Cost Analytics View:
   - Summary cards (top):
     * This Month ($)
     * Per Game Average ($)
     * Most Expensive Model (name + $)
   - Cost breakdown table:
     * Model | Calls | Total Cost | Avg Per Call
     * Sortable columns
   - Date range picker (top-right)
   - Export CSV button
 Visual Style:
 - Professional admin interface
 - Data-focused with clear metrics
 - Color-coded status indicators
 - Clean tables with good readability
 - Charts with tooltips
 - Responsive grid layouts
 ```
 ---
 ## 🎯 Specialized Component Prompts
 ### Prompt: Message Bubble Component
 ```
 Design a modern chat message bubble component for a dark-themed RPG interface
 Requirements:
 - Two variants: Character (sent) and Storyteller (received)
 - Character messages:
  * Right-aligned
  * Purple gradient background (#667eea to #764ba2)
  * White text
  * Rounded corners (more rounded on left side)
  * Small shadow
 - Storyteller messages:
  * Left-aligned
  * Dark gray background (#374151)
  * Light gray text
  * Rounded corners (more rounded on right side)
  * Subtle border
 - Both include:
  * Message content (wrapped text)
  * Timestamp (small, muted, below bubble)
  * Sender name (optional, above bubble)
 - Smooth entry animation (fade + slide)
 - Hover: Slight shadow increase
 ```
 ### Prompt: Selection Card Component
 ```
 Design an interactive selection card for character race/class/personality selection
 States:
 1. Default:
   - Dark background (#2d3748)
   - Light border (rgba(255,255,255,0.1))
   - Rounded corners (10px)
   - Padding: 20px
   - Content:
     * Title (bold, white, 16px)
     * Description (gray, 13px)
 2. Hover:
   - Background: Slightly lighter
   - Border: Purple tint
   - Transform: translateY(-2px)
   - Shadow: Elevated
 3. Selected:
   - Background: Purple gradient (subtle)
   - Border: Bright purple (#667eea)
   - Shadow: Purple glow
   - Checkmark icon (top-right corner)
 Animation:
 - Smooth transition on all state changes
 - Scale slightly on click
 - Ripple effect on selection
 Size:
 - Min width: 200px
 - Flexible height based on content
 - Grid-friendly
 ```
 ### Prompt: Progress Indicator Component
 ```
 Design a multi-step progress indicator for a wizard interface
 Components:
 - 6 steps arranged horizontally
 - Each step:
  * Number or icon
  * Label text below
  * Connecting line to next step
 States per step:
 1. Completed:
   - Checkmark icon (white)
   - Purple filled circle
   - Purple line to next
   - Label: Purple, smaller
 2. Active/Current:
   - Number in white
   - Purple gradient circle (larger)
   - Pulsing glow animation
   - Label: White, bold
 3. Upcoming:
   - Number in gray
   - Gray outlined circle
   - Gray dashed line to next
   - Label: Gray, normal
 Responsive:
 - Desktop: Horizontal line
 - Mobile: Vertical or wrapped
 Visual Style:
 - Modern, clean
 - Clear current position
 - Motivating progress visualization
 ```
 ---
 ## 📱 Mobile-Specific Prompts
 ### Prompt: Mobile Navigation
 ```
 Design a mobile-friendly bottom navigation bar for the RPG app
 Requirements:
 - Fixed to bottom of screen
 - Dark background with slight transparency
 - 4-5 navigation items:
  * Home/Session (house icon)
  * Character (person icon)
  * Messages (chat icon)
  * More (dots icon)
 - Active item:
  * Purple icon color
  * Label text (white)
  * Indicator line on top
 - Inactive items:
  * Gray icon
  * Small label (optional)
 - Badge notifications (red dot on icons)
 - Safe area insets for iOS
 - Subtle shadow on top edge
 ```
 ---
 ## 🎨 Using These Prompts
 ### With v0.dev (Vercel):
 ```
 Copy base template + specific page prompt
 Add: "Generate React/Next.js components with Tailwind CSS"
 Review generated code and iterate
 ```
 ### With Midjourney/DALL-E:
 ```
 Copy prompt
 Add: "UI mockup, high fidelity, Figma style"
 Generate multiple variations
 Use as design reference
 ```
 ### With Claude/GPT:
 ```
 Copy prompt
 Add: "Generate HTML/CSS code for this design"
 or "Create a React component for this"
 Iterate on the implementation
 ```
 ---
 **All prompts are ready to copy and use!** Customize colors, spacing, or specific elements as needed.
--- a/docs/reference/UI_ELEMENTS_INVENTORY.md
+++ b/docs/reference/UI_ELEMENTS_INVENTORY.md
@@ -0,0 +1,890 @@
 # UI Elements Inventory - Storyteller RPG
 **Purpose:** Comprehensive list of UI elements organized by page for design template generation  
 **Date:** October 12, 2025  
 **Status:** Phase 2 Complete, Planning Phase 3
 ---
 ## 🎨 Design System Overview
 ### Color Palette
 - **Primary Gradient:** #667eea to #764ba2 (purple gradient)
 - **Secondary Gradient:** #ffd89b to #19547b (gold to teal)
 - **Background Dark:** #1a1a2e, #16213e
 - **Surface Dark:** #2d3748
 - **Text Light:** #ffffff, #e2e8f0
 - **Text Muted:** #a0aec0, #718096
 - **Accent:** #667eea (purple)
 - **Success:** #10b981, #34d399
 - **Warning:** #f59e0b
 - **Error:** #ef4444
 ### Typography
 - **Font Family:** -apple-system, BlinkMacSystemFont, 'Segoe UI', 'Roboto', sans-serif
 - **H1:** 2.5rem, bold
 - **H2:** 2rem, bold
 - **H3:** 1.5rem, semibold
 - **Body:** 1rem
 - **Small:** 0.875rem
 ### Spacing Scale
 - **xs:** 0.25rem (4px)
 - **sm:** 0.5rem (8px)
 - **md:** 1rem (16px)
 - **lg:** 1.5rem (24px)
 - **xl:** 2rem (32px)
 - **2xl:** 3rem (48px)
 ### Border Radius
 - **Small:** 6px
 - **Medium:** 8px
 - **Large:** 12px
 - **XLarge:** 20px
 ---
 ## 📄 Page 1: Session Setup / Landing Page
 ### Purpose
 Entry point for creating or joining game sessions
 ### Layout Structure
 ```
 ┌─────────────────────────────────────┐
 │         Header (Logo + Title)       │
 ├─────────────────────────────────────┤
 │                                     │
 │         Demo Session Cards          │
 │                                     │
 ├─────────────────────────────────────┤
 │                                     │
 │     Create New Session Section      │
 │                                     │
 ├─────────────────────────────────────┤
 │                                     │
 │    Join Existing Session Section    │
 │                                     │
 └─────────────────────────────────────┘
 ```
 ### UI Elements
 #### **Header Section**
 - **App Title:** Large heading with emoji (🎭 Storyteller RPG)
 - **Subtitle:** Descriptive tagline
 - **Logo/Icon:** Optional app icon
 #### **Demo Section**
 - **Section Title:** "🎲 Demo Session - The Cursed Tavern"
 - **Description Text:** Short description paragraph
 - **Button Group (3 buttons):**
  - Storyteller button (🎲 icon, primary style)
  - Character 1 button (⚔️ icon, character style)
  - Character 2 button (🏹 icon, character style)
 - **Visual Style:** Gradient background, rounded corners
 #### **Divider Elements**
 - **Text Divider:** "OR CREATE YOUR OWN" / "OR"
 - **Horizontal line with text overlay**
 #### **Create Session Section**
 - **Section Title:** "Create New Session"
 - **Section Description:** "Start a new game as the storyteller"
 - **Input Field:** Text input for session name
 - **Primary Button:** "Create Session" (full width)
 - **Visual Style:** White card with shadow
 #### **Join Session Section**
 - **Section Title:** "Join Existing Session"
 - **Section Description:** "Play as a character in an ongoing game"
 - **Form Elements:**
  - Session ID input field
  - Character name input field
  - Character description textarea
  - Personality traits textarea (optional)
  - Model selector dropdown (grouped options)
  - Model hint text
 - **Action Buttons:**
  - "✨ Create Character (Wizard)" - Primary gradient button
  - "↓ Quick Create" toggle - Secondary button
  - "Join Session (Simple)" - Conditional primary button
 - **Visual Style:** White card with shadow
 ### Responsive Behavior
 - **Desktop:** Single column, max-width 600px, centered
 - **Mobile:** Full width, stacked elements
 ---
 ## 📄 Page 2: Character View (Player Interface)
 ### Purpose
 Interface for players to interact with storyteller and view game state
 ### Layout Structure
 ```
 ┌─────────────────────────────────────────────────┐
 │  Character Header (Info + Status)               │
 ├─────────────────────────────────────────────────┤
 │  Current Scene Card (if active)                 │
 ├─────────────────────────────────────────────────┤
 │                                                 │
 │  ┌─────────────────┬─────────────────────────┐ │
 │  │ Public Messages │ Private Conversation    │ │
 │  │ Feed            │ with Storyteller        │ │
 │  │                 │                         │ │
 │  │                 │                         │ │
 │  └─────────────────┴─────────────────────────┘ │
 │                                                 │
 ├─────────────────────────────────────────────────┤
 │  Message Composer (Bottom)                      │
 └─────────────────────────────────────────────────┘
 ```
 ### UI Elements
 #### **Character Header**
 - **Character Name:** Large heading
 - **Character Description:** Paragraph text
 - **Personality Trait:** Small text with emoji (🎭)
 - **Profile Badges:** 3 pill-shaped badges
  - Race badge
  - Class badge
  - Personality type badge
 - **Action Buttons:**
  - Export button (📥 Export)
 - **Status Indicator:** Connection status dot
  - Connected: Green dot + "● Connected"
  - Disconnected: Gray dot + "○ Disconnected"
 - **Visual Style:** Dark gradient background, rounded top corners
 #### **Current Scene Card** (Conditional)
 - **Section Title:** "📜 Current Scene"
 - **Scene Text:** Paragraph with scene description
 - **Visual Style:** Highlighted card, distinct from messages
 #### **Public Messages Section**
 - **Section Title:** "📢 Public Actions (All Players See)"
 - **Message List:**
  - Message bubble/card per public action
  - Sender indicator (🎭 Public Action / 🎲 Scene)
  - Message content
  - Timestamp (small, muted)
 - **Visual Style:** Light background, left border accent
 #### **Private Conversation Section**
 - **Section Title:** "💬 Private Conversation with Storyteller"
 - **Message List:**
  - Message bubbles alternating left/right
  - Character messages (right aligned, purple)
  - Storyteller messages (left aligned, different color)
  - Timestamps
 - **Scroll Behavior:** Auto-scroll to bottom on new message
 #### **Message Composer** (Bottom Section)
 - **Visibility Selector:** Dropdown
  - Options: Private, Public, Mixed
 - **Mixed Mode Form:**
  - Public textarea: "Public action (all players see)..."
  - Private textarea: "Private action (only storyteller sees)..."
  - Send button: "Send Mixed Message"
 - **Simple Mode Form:**
  - Single input field (changes placeholder by visibility)
  - Send button
 - **Visual Style:** Fixed to bottom, elevated shadow
 ### Component States
 - **Connected State:** Full functionality enabled
 - **Disconnected State:** Inputs disabled, gray overlay
 - **Loading State:** Skeleton screens
 - **Empty State:** "No messages yet" placeholder
 ---
 ## 📄 Page 3: Character Creation Wizard
 ### Purpose
 Multi-step guided character creation with profile system
 ### Layout Structure
 ```
 ┌─────────────────────────────────────────┐
 │  Wizard Header (Title + Progress)       │
 ├─────────────────────────────────────────┤
 │                                         │
 │                                         │
 │        Step Content Area                │
 │        (Changes per step)               │
 │                                         │
 │                                         │
 ├─────────────────────────────────────────┤
 │  Footer (Cancel | Back | Next/Create)  │
 └─────────────────────────────────────────┘
 ```
 ### UI Elements
 #### **Wizard Overlay**
 - **Full-screen modal:** Dark semi-transparent background
 - **Centered container:** Max 800px width
 - **Visual Style:** Dark gradient card with border
 #### **Wizard Header**
 - **Title:** "Create Your Character" (large heading)
 - **Progress Indicator:** 6 steps
  - Step pills showing: "1. Basic Info", "2. Description", etc.
  - Active step highlighted
  - Completed steps dimmed
  - Responsive: Wraps on mobile
 #### **Step 1: Basic Info**
 - **Step Title:** "Basic Information"
 - **Input Fields:**
  - Character name (text input, required, autofocus)
  - Gender dropdown (4 options)
 - **Import Section:**
  - Import hint text: "💡 Have an existing character?"
  - File upload button: "📥 Import from JSON"
  - Hidden file input (accepts .json)
 - **Visual Style:** Form inputs with dark theme
 #### **Step 2: Description**
 - **Step Title:** "Character Description"
 - **Input Fields:**
  - Description textarea (required, 4 rows)
  - Background textarea (optional, 3 rows)
 - **Visual Style:** Larger text areas, clear labels
 #### **Step 3: Race & Class**
 - **Step Title:** "Race & Class"
 - **Race Selection:**
  - Label: "Race"
  - Selection grid (responsive, min 200px cards)
  - 5 clickable cards:
    - Race name (bold)
    - Race description (smaller text)
    - Selected state: gradient background + border
    - Hover state: slight elevation
 - **Class Selection:**
  - Same layout as Race
  - 5 class cards
 - **Visual Style:** Grid layout, interactive cards
 #### **Step 4: Personality**
 - **Step Title:** "Personality Type"
 - **Selection Grid:**
  - 4 personality type cards
  - Same card style as race/class
 - **Additional Input:**
  - "Additional Personality Traits" textarea (optional, 3 rows)
 - **Visual Style:** Consistent with Step 3
 #### **Step 5: AI Model**
 - **Step Title:** "AI Model Selection"
 - **Model Dropdown:**
  - Large dropdown (bigger padding/font)
  - Grouped options (OpenAI / OpenRouter)
  - Shows provider in parentheses
 - **Help Text:**
  - "💡 Different models give different personalities!"
  - Multi-line hint text
 - **Visual Style:** Prominent dropdown, informative hint
 #### **Step 6: Review**
 - **Step Title:** "Review Your Character"
 - **Preview Card:**
  - Multiple sections with borders between:
    - Basic Information (name, gender, race, class, personality)
    - Description
    - Background (if provided)
    - Additional Traits (if provided)
    - AI Model
  - Summary box at bottom:
    - Highlighted background
    - "Character Summary" heading
    - Natural language summary sentence
 - **Visual Style:** Clean, organized, easy to scan
 #### **Wizard Footer**
 - **Button Layout:**
  - Cancel (left, secondary)
  - Navigation (right):
    - Back button (steps 2-6, secondary)
    - Next button (steps 1-5, primary)
    - Create button (step 6, primary with sparkles)
 - **Visual Style:** Fixed footer, clear hierarchy
 ### Animation & Transitions
 - **Step Changes:** Fade in with slight upward movement
 - **Card Selection:** Transform scale + shadow on selection
 - **Button Hovers:** Slight elevation, color shift
 - **Progress Indicator:** Smooth transitions between steps
 ---
 ## 📄 Page 4: Storyteller View
 ### Purpose
 Interface for storyteller to manage game, view all character actions, and respond
 ### Layout Structure
 ```
 ┌──────────────────────────────────────────────────┐
 │  Header (Session Info + Controls)                │
 ├──────────────────────────────────────────────────┤
 │                                                  │
 │  ┌───────────────┬────────────────────────────┐ │
 │  │ Character     │ Main Content Area:         │ │
 │  │ List          │                            │ │
 │  │ (Sidebar)     │ - Public Actions Feed      │ │
 │  │               │ - Selected Character View  │ │
 │  │               │ - Scene Narration          │ │
 │  │               │                            │ │
 │  └───────────────┴────────────────────────────┘ │
 │                                                  │
 └──────────────────────────────────────────────────┘
 ```
 ### UI Elements
 #### **Storyteller Header**
 - **Session Name:** Large heading
 - **Session ID:** Copy button with ID
 - **Control Buttons:**
  - Generate contextual response button
  - Other session controls
 - **Visual Style:** Dark header, elevated
 #### **Character List Sidebar**
 - **Section Title:** "Characters in Session"
 - **Character Cards:** (One per character)
  - Character name
  - Race/Class/Personality badges
  - "Needs Response" indicator (conditional)
  - Click to select
  - Active state highlighting
 - **Empty State:** "No characters yet" message
 - **Visual Style:** Scrollable sidebar, clear selection state
 #### **Public Actions Feed**
 - **Section Title:** "📢 Recent Public Actions"
 - **Feed Items:**
  - Character name/avatar
  - Public action text
  - Timestamp
  - Compact card style
 - **Visual Style:** Timeline/feed layout
 #### **Character Conversation View**
 - **Character Header:**
  - Selected character name
  - Profile info
 - **Conversation Thread:**
  - Message list (character + storyteller messages)
  - Clear visual distinction between senders
  - Timestamps
 - **Response Composer:**
  - Textarea for response
  - "✨ AI Suggest" button
  - "Send Private Response" button
 - **Visual Style:** Similar to character view but reversed perspective
 #### **AI Suggestion Modal/Section**
 - **Generated Response Display:**
  - Title: "AI-Generated Suggestion"
  - Response content (editable)
  - Model used indicator
 - **Action Buttons:**
  - "Use This Response"
  - "Regenerate"
  - "Cancel"
 - **Visual Style:** Highlighted section, easy to edit
 #### **Scene Narration Section**
 - **Section Title:** "Broadcast Scene to All Players"
 - **Input Field:**
  - Large textarea for scene description
  - Character count/hint
 - **Contextual Generation:**
  - "Generate with AI" button
  - Character selection checkboxes
  - Additional context input
 - **Send Button:** "📜 Broadcast Scene"
 - **Visual Style:** Prominent, distinct from private responses
 ### Responsive Behavior
 - **Desktop:** Sidebar + main content (grid layout)
 - **Tablet:** Collapsible sidebar
 - **Mobile:** Stack vertically, tab navigation
 ---
 ## 📄 Page 5: Gamemaster Control Panel (Phase 3)
 ### Purpose
 Admin interface to create games, assign roles, and manage session
 ### Layout Structure
 ```
 ┌────────────────────────────────────────────┐
 │  GM Header (Game Info + Quick Actions)     │
 ├────────────────────────────────────────────┤
 │                                            │
 │  ┌──────────────┬──────────────────────┐  │
 │  │ Game         │ Main Panel:          │  │
 │  │ Sessions     │                      │  │
 │  │ List         │ - Game Setup Wizard  │  │
 │  │              │ - Role Assignment    │  │
 │  │              │ - Player Management  │  │
 │  │              │ - Game State View    │  │
 │  │              │                      │  │
 │  └──────────────┴──────────────────────┘  │
 │                                            │
 └────────────────────────────────────────────┘
 ```
 ### UI Elements
 #### **GM Dashboard Header**
 - **Title:** "Gamemaster Control Panel"
 - **Active Game Indicator:** Current game name
 - **Quick Actions:**
  - "Create New Game" button
  - "Load Game" button
  - "Save Game" button
 - **Visual Style:** Command center aesthetic
 #### **Game Sessions List**
 - **List Items:** (Per game)
  - Game name
  - Status badge (not started, active, paused, completed)
  - Player count
  - Created date
  - Actions: View, Edit, Delete
 - **Visual Style:** Card list, status colors
 #### **Game Creation Wizard**
 - **Step 1: Game Info**
  - Game name input
  - Scenario/setting textarea
  - Genre/theme selector
 - **Step 2: Player Slots**
  - Slot configuration (number input)
  - Slot cards:
    - Slot type (Human/AI toggle)
    - Player assignment (if human)
    - AI configuration (if AI)
 - **Step 3: Storyteller Assignment**
  - Radio buttons: Human / AI
  - User selector (if human)
  - AI model selector (if AI)
  - Storytelling style dropdown
 - **Step 4: Game Settings**
  - Turn-based toggle
  - Auto-save interval
  - Other game rules
 - **Visual Style:** Multi-step wizard like character creation
 #### **Role Assignment Interface**
 - **Player Slots Grid:**
  - Drag-and-drop cards
  - Each slot shows:
    - Slot number
    - Assigned player/AI
    - Character info (if selected)
    - Edit button
 - **Available Players Panel:**
  - List of users
  - Drag to assign
 - **Visual Style:** Interactive, clear assignment state
 #### **Game State Overview**
 - **Tabs:**
  - Overview
  - Characters
  - Messages
  - Timeline
 - **Overview Tab:**
  - Game status
  - Current scene
  - Active players
  - Statistics (messages, actions, etc.)
 - **Characters Tab:**
  - All character profiles
  - Stats/inventory (if applicable)
 - **Messages Tab:**
  - All messages (public + private)
  - Filter controls
 - **Visual Style:** Dashboard with data cards
 #### **AI Storyteller Command Interface**
 - **Command Input:**
  - Special input for GM → AI storyteller
  - Examples: "Introduce a plot twist", "Increase difficulty"
 - **AI Status:**
  - Active/paused toggle
  - Last action timestamp
  - Response queue
 - **Override Controls:**
  - Edit AI responses
  - Take manual control
 - **Visual Style:** Distinct command interface
 ---
 ## 📄 Page 6: Admin Dashboard (Development/Future)
 ### Purpose
 System-wide administration, monitoring, and configuration
 ### Layout Structure
 ```
 ┌────────────────────────────────────────┐
 │  Admin Header (System Status)          │
 ├────────────────────────────────────────┤
 │                                        │
 │  ┌──────────┬──────────────────────┐  │
 │  │ Nav Menu │ Content Panel        │  │
 │  │          │                      │  │
 │  │ - Games  │ (Changes per menu)   │  │
 │  │ - Users  │                      │  │
 │  │ - Models │                      │  │
 │  │ - Costs  │                      │  │
 │  │ - Logs   │                      │  │
 │  │          │                      │  │
 │  └──────────┴──────────────────────┘  │
 │                                        │
 └────────────────────────────────────────┘
 ```
 ### UI Elements
 #### **Admin Header**
 - **Title:** "System Administration"
 - **System Status Indicators:**
  - API status (green/red dot)
  - Active games count
  - Active users count
 - **Visual Style:** Dark header, status indicators
 #### **Navigation Menu**
 - **Menu Items:**
  - Dashboard (overview)
  - Games Management
  - User Management
  - LLM Configuration
  - Cost Analytics
  - System Logs
  - Settings
 - **Visual Style:** Vertical menu, active state highlighting
 #### **Dashboard Overview**
 - **Metric Cards:**
  - Total games (number + trend)
  - Total users (number + trend)
  - API calls today (number + cost)
  - System health (percentage)
 - **Recent Activity Feed:**
  - Latest games created
  - Recent errors
  - High-cost requests
 - **Charts:**
  - Games over time
  - Cost over time
  - Model usage distribution
 - **Visual Style:** Grid of cards, charts with tooltips
 #### **Games Management**
 - **Games Table:**
  - Columns: ID, Name, GM, Players, Status, Created, Actions
  - Sort controls
  - Filter controls
  - Pagination
 - **Actions:**
  - View details
  - Force end
  - Delete
 - **Visual Style:** Data table with actions
 #### **User Management**
 - **Users Table:**
  - Columns: Username, Email, Role, Games, Joined, Status, Actions
  - Search bar
  - Role filter
 - **Actions:**
  - Edit role
  - Suspend/activate
  - View activity
 - **Visual Style:** Data table with user cards
 #### **LLM Configuration**
 - **Model Cards:** (Per model)
  - Model name
  - Provider
  - Status (enabled/disabled toggle)
  - Usage stats
  - Cost per token
  - Edit button
 - **Add Model Form:**
  - Model ID input
  - API key input
  - Configuration options
 - **Visual Style:** Grid of model cards
 #### **Cost Analytics**
 - **Summary Cards:**
  - Total cost this month
  - Average per game
  - Most expensive model
 - **Cost Breakdown:**
  - Per model chart
  - Per game table
  - Per user table
 - **Date Range Selector:**
  - Preset ranges (Today, Week, Month)
  - Custom range picker
 - **Export Button:** Download CSV
 - **Visual Style:** Charts and tables
 #### **System Logs**
 - **Log Viewer:**
  - Real-time log stream
  - Log level filter (Info, Warning, Error)
  - Search/filter input
  - Timestamp
  - Auto-scroll toggle
 - **Visual Style:** Terminal/console aesthetic
 ---
 ## 🎯 Common UI Components (Used Across Pages)
 ### Buttons
 - **Primary Button:**
  - Gradient background (#667eea to #764ba2)
  - White text, rounded corners
  - Hover: Slight lift, darker gradient
  - Sizes: Small, Medium, Large
 - **Secondary Button:**
  - Transparent/outlined style
  - Border color matches theme
  - Hover: Background color change
 - **Icon Buttons:**
  - Circular or square
  - Icon only, tooltip on hover
 - **Danger Button:**
  - Red color scheme
  - Used for delete/destructive actions
 ### Input Fields
 - **Text Input:**
  - Dark background with light border
  - Focus: Border color change, glow effect
  - Error state: Red border + error message below
  - Success state: Green border
 - **Textarea:**
  - Same as text input but multi-line
  - Resize handle
 - **Dropdown/Select:**
  - Custom styled select
  - Grouped options support
  - Search/filter (for long lists)
 - **Checkbox:**
  - Custom checkbox with checkmark animation
  - Label click support
 - **Radio Buttons:**
  - Custom styled radio
  - Clear selected state
 - **File Upload:**
  - Drag-and-drop zone
  - File type indicator
  - Upload progress
 ### Cards
 - **Base Card:**
  - Rounded corners (8-12px)
  - Shadow for elevation
  - Padding: 1-2rem
  - Background: White or dark surface
 - **Interactive Card:**
  - Hover state: Lift effect
  - Click state: Scale slightly
  - Selection state: Border highlight
 - **Info Card:**
  - Icon + title + content
  - Color-coded by type
 ### Badges/Pills
 - **Status Badge:**
  - Small, rounded pill
  - Color-coded (green=active, red=error, yellow=warning)
  - Sizes: XS, SM, MD
 - **Count Badge:**
  - Circular badge with number
  - Often overlays buttons/icons
 ### Modals/Overlays
 - **Modal:**
  - Full-screen semi-transparent overlay
  - Centered content container
  - Close button (X) in top-right
  - Click outside to close (optional)
 - **Toast/Notification:**
  - Slide in from top-right
  - Auto-dismiss after timeout
  - Close button
  - Type: Success, Error, Warning, Info
 ### Navigation
 - **Tabs:**
  - Horizontal tabs with active state
  - Underline or background highlight
 - **Breadcrumbs:**
  - Path navigation
  - Separator (/ or >)
  - Click to navigate
 - **Pagination:**
  - Previous/Next buttons
  - Page numbers
  - Jump to page input
 ### Loading States
 - **Spinner:**
  - Circular spinner (small, medium, large)
  - Themed color
 - **Skeleton Screen:**
  - Gray placeholder boxes
  - Shimmer animation
 - **Progress Bar:**
  - Linear progress indicator
  - Percentage display (optional)
 ### Empty States
 - **No Data:**
  - Icon + message
  - Call-to-action button
  - Helpful hint text
 - **Error State:**
  - Error icon + message
  - Retry button
  - Support link
 ---
 ## 📱 Responsive Breakpoints
 ### Desktop (1024px+)
 - Multi-column layouts
 - Sidebars visible
 - Full navigation
 ### Tablet (768px - 1023px)
 - Collapsible sidebars
 - Stacked cards
 - Simplified navigation
 ### Mobile (<768px)
 - Single column
 - Bottom navigation
 - Hamburger menu
 - Full-screen modals
 - Larger tap targets
 ---
 ## ♿ Accessibility Requirements
 ### Keyboard Navigation
 - All interactive elements focusable
 - Logical tab order
 - Focus indicators (outline)
 - Keyboard shortcuts (optional)
 ### Screen Reader Support
 - Semantic HTML
 - ARIA labels where needed
 - Alt text for images
 - Form labels associated
 ### Color Contrast
 - WCAG AA minimum (4.5:1 for text)
 - Color not sole indicator
 - High contrast mode support
 ### Interaction
 - Minimum touch target: 44x44px
 - No timing-critical interactions
 - Error prevention and recovery
 ---
 ## 🎨 Animation Guidelines
 ### Durations
 - **Micro:** 100-200ms (hover, focus)
 - **Short:** 200-300ms (buttons, tooltips)
 - **Medium:** 300-500ms (modals, page transitions)
 - **Long:** 500-800ms (complex animations)
 ### Easing
 - **Ease-out:** UI appearing (modal open)
 - **Ease-in:** UI disappearing (modal close)
 - **Ease-in-out:** Smooth transitions
 ### Motion Preferences
 - Respect `prefers-reduced-motion`
 - Disable decorative animations
 - Keep functional animations
 ---
 ## 📐 Layout Patterns
 ### Container Widths
 - **Max Width:** 1200px (main content)
 - **Narrow:** 600px (forms, wizards)
 - **Wide:** 1400px (dashboards)
 ### Grid Systems
 - **12-column grid** for complex layouts
 - **Flexbox** for simple layouts
 - **CSS Grid** for card grids
 ### Spacing Rhythm
 - Consistent vertical rhythm (8px base unit)
 - Component spacing: 16px, 24px, 32px
 - Section spacing: 48px, 64px
 ---
 ## 🎯 Priority Elements for UI Design Templates
 ### High Priority (MVP Essential)
 1. Session Setup page
 2. Character View
 3. Character Creation Wizard
 4. Storyteller View
 5. Primary buttons and inputs
 ### Medium Priority (Phase 3)
 6. Gamemaster Control Panel
 7. Role assignment interface
 8. Game state dashboard
 ### Low Priority (Future)
 9. Admin Dashboard
 10. Analytics views
 11. Advanced settings
 ---
 **Use this document to prompt UI design tools with specific page requirements!**
 Example prompt structure:
 ```
 Create a modern dark-themed UI design for [PAGE NAME] with the following elements:
 [List specific elements from above]
 Color scheme: Purple gradient (#667eea to #764ba2)
 Style: Modern, RPG-themed, clean
 ```
--- a/docs/reference/UI_ELEMENTS_REFERENCE.md
+++ b/docs/reference/UI_ELEMENTS_REFERENCE.md
@@ -0,0 +1,401 @@
 # UI Elements Reference - Storyteller RPG
 **Purpose:** Complete catalog of UI elements for design system templates  
 **Date:** October 12, 2025
 ---
 ## 🎨 Design System Overview
 ### Color Palette
 - **Primary:** Purple gradient (#667eea to #764ba2)
 - **Background:** Dark theme (#1a1a2e, #16213e)
 - **Success:** Green (#10b981, #86efac)
 - **Text:** White (#fff), Light gray (#aaa, #ccc)
 - **Borders:** Subtle white rgba (0.1 opacity)
 ### Typography
 - **Headings:** 24-32px, bold
 - **Body:** 14-16px, normal
 - **Small:** 12-13px, secondary info
 ---
 ## 📄 Page 1: Session Setup / Landing Page
 ### Purpose
 Entry point for creating/joining sessions and characters
 ### Key Sections
 #### 1. Header Area
 - **App Title:** "🎭 Storyteller RPG"
 - **Subtitle:** Brief tagline
 - **Logo placeholder** (future)
 #### 2. Demo Session Quick Access
 - **Section Title:** "🎲 Demo Session - 'The Cursed Tavern'"
 - **Description text:** Brief explanation
 - **Three action buttons:**
  - Join as Storyteller (gold gradient)
  - Play as Bargin (character 1)
  - Play as Willow (character 2)
 - **Button styling:** Large, prominent, with icons
 #### 3. Session Creation Section
 - **Section Title:** "Create New Session"
 - **Description:** "Start a new game as the storyteller"
 - **Input field:** Session name (text)
 - **Primary button:** "Create Session"
 #### 4. Session Join Section
 - **Section Title:** "Join Existing Session"
 - **Description:** "Play as a character in an ongoing game"
 - **Form elements:**
  - Session ID input (text)
  - Character name input (text, required)
  - Description textarea (3 rows)
  - Personality textarea (2 rows, optional)
  - Model selector (dropdown with optgroups)
  - Model hint text (small, gray)
 - **Character creation options:**
  - Primary button: "✨ Create Character (Wizard)"
  - Divider: "or"
  - Toggle button: "Quick Create" (shows simple form)
 - **Submit button:** "Join Session (Simple)" (conditional)
 #### 5. Dividers
 - Horizontal rule with centered text ("OR")
 - Visual separation between sections
 ---
 ## 📄 Page 2: Character View (Player Perspective)
 ### Purpose
 Player's interface for interacting with storyteller
 ### Layout Structure
 Three-column layout: Info | Messages | Public Feed
 ### Key Sections
 #### 1. Character Header
 - **Character name** (h2, white, bold)
 - **Description text** (gray, italic)
 - **Personality traits** (with emoji prefix)
 - **Profile badges** (if profile exists):
  - Race badge
  - Class badge
  - Personality type badge
 - **Action buttons:**
  - Export button (📥)
  - Connection status indicator (● Connected / ○ Disconnected)
 #### 2. Current Scene Panel (if active)
 - **Section title:** "📜 Current Scene"
 - **Scene text** (large, prominent)
 - **Background:** Highlighted panel
 #### 3. Public Messages Section
 - **Section title:** "📢 Public Actions (All Players See)"
 - **Message list:**
  - Message sender label
  - Timestamp
  - Message content
  - Visual distinction from private messages
 #### 4. Private Conversation Area
 - **Section title:** "💬 Private Conversation with Storyteller"
 - **Message thread:**
  - Character messages (right-aligned, colored)
  - Storyteller messages (left-aligned, different color)
  - Timestamps
  - Message bubbles
 - **Auto-scroll to latest**
 #### 5. Message Composer
 - **Message visibility selector** (dropdown):
  - Private
  - Public
  - Mixed
 - **Input area (varies by type):**
  - Private/Public: Single text input
  - Mixed: Two textareas (public + private)
 - **Send button** (primary, disabled when disconnected)
 #### 6. AI Generation Section (future)
 - Generate suggestion button
 - Prompt customization
 - Regenerate option
 ---
 ## 📄 Page 3: Storyteller View (GM Perspective)
 ### Purpose
 Game master interface to manage all players and narrate story
 ### Layout Structure
 Two-column: Character list sidebar | Main content area
 ### Key Sections
 #### 1. Session Header
 - **Session name** (h2)
 - **Session ID display** with copy button
 - **Quick copy feedback** (tooltip/toast)
 #### 2. Character List Sidebar
 - **Section title:** "Active Characters"
 - **Character cards:**
  - Character name
  - "💬 View" button (per character)
  - Highlight active selection
  - Pending response indicator (red dot)
 - **Scrollable list**
 #### 3. Scene Narration Panel
 - **Section title:** "📜 Scene Narration"
 - **Textarea:** Large input for scene description
 - **Buttons:**
  - "Broadcast Scene" (primary)
  - "✨ AI Suggest" (secondary, generates scene)
 #### 4. Public Actions Feed
 - **Section title:** "📢 Recent Public Actions"
 - **Message list:**
  - Character name
  - Action content
  - Timestamp
 - **Latest 5 messages shown**
 #### 5. Character Conversation View
 - **Header:** Selected character name
 - **Conversation thread:**
  - Character messages
  - Your responses
  - Timestamps
 - **Response composer:**
  - Large textarea
  - Button group:
    - "✨ AI Suggest"
    - "Send Private Response"
 #### 6. Multi-Character Response (future)
 - Select multiple characters
 - Generate context-aware response
 - Broadcast to selected players
 ---
 ## 📄 Page 4: Character Creation Wizard
 ### Purpose
 6-step guided character creation with profiles
 ### Layout Structure
 Modal overlay with centered card
 ### Key Sections
 #### 1. Wizard Header
 - **Title:** "Create Your Character"
 - **Progress indicator:**
  - 6 steps shown
  - Active step highlighted
  - Step labels visible
 #### 2. Step Navigation
 - **Footer buttons:**
  - Cancel (left)
  - Back (if not step 1)
  - Next (steps 1-5)
  - Create Character (step 6)
 ### Step-by-Step UI Elements
 #### Step 1: Basic Info
 - **Form elements:**
  - Name input (required)
  - Gender selector (dropdown)
 - **Import section:**
  - Hint text
  - Import from JSON button (file picker)
 #### Step 2: Description
 - **Form elements:**
  - Description textarea (4 rows, required)
  - Background textarea (3 rows, optional)
 #### Step 3: Race & Class
 - **Selection grids:** (2x3 or responsive)
  - Race cards (clickable)
  - Class cards (clickable)
 - **Card elements:**
  - Name (bold)
  - Description (gray)
  - Selected state (highlighted border, gradient background)
  - Hover effects
 #### Step 4: Personality
 - **Selection grid:** 2x2
  - Personality type cards
  - Same card styling as Step 3
 - **Additional traits textarea** (optional)
 #### Step 5: AI Model
 - **Model selector:** Large dropdown
  - Optgroups (OpenAI, OpenRouter)
  - Model names with providers
 - **Hint text:** Model personality differences
 #### Step 6: Review
 - **Preview panels:**
  - Basic Information
  - Description
  - Background (if provided)
  - Additional Traits (if provided)
  - AI Model
 - **Summary card:**
  - Character identity statement
  - Highlighted/special styling
 ---
 ## 📄 Future Pages (Phase 3+)
 ### Gamemaster Dashboard
 - **Game creation wizard**
 - **Player slot assignment**
 - **Role management grid**
 - **Game state overview**
 - **AI control panel**
 ### Admin Panel
 - **System overview**
 - **User management**
 - **LLM configuration**
 - **Cost tracking dashboard**
 - **Analytics charts**
 ### Character Sheet (Enhanced)
 - **Stats display**
 - **Inventory grid**
 - **Skills list**
 - **Equipment slots**
 - **Character progression**
 ---
 ## 🎨 Common UI Components
 ### Buttons
 1. **Primary button:** Purple gradient, white text
 2. **Secondary button:** Transparent, border, hover effect
 3. **Wizard button:** Extra gradient styling
 4. **Export/Action buttons:** Subtle rgba background
 5. **Icon buttons:** Small, inline
 ### Form Elements
 1. **Text inputs:** Dark background, subtle border, focus glow
 2. **Textareas:** Resizable, same styling as inputs
 3. **Dropdowns:** Custom styling, optgroups
 4. **File pickers:** Hidden, triggered by styled button
 ### Cards
 1. **Selection cards:** Clickable, hover lift, selected state
 2. **Character cards:** Compact, button included
 3. **Message cards:** Bubbles, aligned left/right
 4. **Preview panels:** Bordered sections with headers
 ### Indicators
 1. **Status dots:** Colored circles (● ○)
 2. **Badges:** Rounded rectangles, colored background
 3. **Progress bars:** Step indicators
 4. **Loading states:** Spinners, skeleton screens
 ### Feedback
 1. **Toasts/Alerts:** Success/error messages
 2. **Tooltips:** Hover information
 3. **Validation messages:** Inline form errors
 4. **Empty states:** No data placeholders
 ---
 ## 📐 Layout Patterns
 ### Responsive Breakpoints
 - **Desktop:** > 768px (multi-column)
 - **Mobile:** ≤ 768px (single column, stacked)
 ### Grid Systems
 - **2-column:** Sidebar + main content
 - **3-column:** Info + center + sidebar
 - **Selection grids:** Auto-fit, min 200px
 ### Spacing
 - **Sections:** 2-3rem padding
 - **Elements:** 1-1.5rem gaps
 - **Inline:** 0.5-1rem margins
 ---
 ## 🎯 Design Prompt Template
 **For UI Design LLM:**
 ```
 Create a modern, dark-themed UI design for [PAGE NAME] with these elements:
 **Color Scheme:**
 - Primary: Purple gradient (#667eea to #764ba2)
 - Background: Dark navy (#1a1a2e, #16213e)
 - Accents: White with 10% opacity borders
 - Text: White and light gray
 **Layout:**
 [Describe specific layout]
 **Components Needed:**
 [List specific elements for that page]
 **Style:**
 - Modern, clean, RPG-themed
 - Smooth gradients and shadows
 - Glassmorphism effects
 - Smooth hover animations
 - Mobile responsive
 **Inspiration:**
 Discord's UI, modern game interfaces, fantasy themes
 ```
 ---
 ## 📊 Component Priority
 ### Essential (Implement First)
 1. Session setup forms
 2. Message display/composer
 3. Character header/info
 4. Navigation/buttons
 ### Important (Phase 2-3)
 1. Character creation wizard
 2. Storyteller dashboard
 3. Profile displays
 4. Export/import UI
 ### Nice-to-Have (Phase 4+)
 1. Character sheets with stats
 2. Inventory management
 3. Dice roller UI
 4. Image generation panels
 5. Analytics dashboards
 ---
 **Total UI Elements Cataloged:** 100+  
 **Pages Documented:** 4 (+ 3 future)  
 **Ready for design system creation** ✅
--- a/docs/reference/UI_QUICK_REFERENCE.md
+++ b/docs/reference/UI_QUICK_REFERENCE.md
@@ -0,0 +1,343 @@
 # UI Design Quick Reference
 **TL;DR guide for getting UI designs quickly**
 ---
 ## 🎯 Priority Order
 ### Phase 2 (Current - Already Built)
 ✅ Session Setup Page  
 ✅ Character View  
 ✅ Character Creation Wizard  
 ✅ Storyteller View
 ### Phase 3 (Next - Need Designs)
 🎨 Gamemaster Control Panel  
 🎨 Game Creation Wizard  
 🎨 Role Assignment Interface
 ### Phase 4+ (Future)
 ⏳ Admin Dashboard  
 ⏳ Analytics Views
 ---
 ## 📄 6 Core Pages Summary
 | Page | Purpose | Complexity | Priority |
 |------|---------|------------|----------|
 | **Session Setup** | Landing, join/create | Low | ✅ Built |
 | **Character View** | Player interface | Medium | ✅ Built |
 | **Character Wizard** | Character creation | Medium | ✅ Built |
 | **Storyteller View** | GM interface | High | ✅ Built |
 | **Gamemaster Panel** | Game management | High | 🎨 Next |
 | **Admin Dashboard** | System admin | High | ⏳ Future |
 ---
 ## 🎨 Design Files Location
 All design documentation in `/docs/reference/`:
 - **UI_ELEMENTS_INVENTORY.md** - Complete element list by page (15,000+ words)
 - **UI_DESIGN_PROMPTS.md** - Copy-paste prompts for LLMs
 - **UI_QUICK_REFERENCE.md** - This file
 ---
 ## ⚡ Quick Start
 ### To Get Designs Fast:
 1. **Read the prompts file:**
   - `/docs/reference/UI_DESIGN_PROMPTS.md`
   - Find the page you need
   - Copy the full prompt
 2. **Choose your tool:**
   - **v0.dev** (Vercel) - Best for React/Tailwind code
   - **Midjourney/DALL-E** - Best for visual mockups
   - **Claude/GPT-4** - Best for HTML/CSS implementation
 3. **Generate:**
   - Paste prompt
   - Add tool-specific instructions
   - Generate multiple variations
   - Iterate and refine
 ---
 ## 🎨 Current Design System (Already Implemented)
 ### Colors
 ```css
 --primary-gradient: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
 --bg-dark: #1a1a2e;
 --surface-dark: #2d3748;
 --text-light: #ffffff;
 --accent-purple: #667eea;
 ```
 ### Components We Have
 - ✅ Buttons (primary, secondary, icon)
 - ✅ Input fields (text, textarea, dropdown)
 - ✅ Cards (base, interactive, info)
 - ✅ Badges/Pills
 - ✅ Message bubbles
 - ✅ Selection cards (wizard)
 - ✅ Progress indicator
 - ✅ Form layouts
 - ✅ Modal overlays
 ### Components We Need
 - 🎨 Data tables
 - 🎨 Drag-and-drop cards
 - 🎨 Charts (line, bar, pie)
 - 🎨 Timeline/activity feed
 - 🎨 Tabs component
 - 🎨 Metric cards with trends
 - 🎨 Role assignment slots
 ---
 ## 📋 Example: Getting Gamemaster Panel Design
 ### Option 1: v0.dev (Code + Design)
 ```
 Prompt: [Copy from UI_DESIGN_PROMPTS.md - Prompt 5]
 Add: "Generate as Next.js components with Tailwind CSS and shadcn/ui"
 Output: Working React code + visual preview
 ```
 ### Option 2: Midjourney (Mockup)
 ```
 Prompt: [Copy from UI_DESIGN_PROMPTS.md - Prompt 5]
 Add: "UI mockup, high fidelity, Figma style, dark theme, 4k"
 Output: Visual design to reference
 ```
 ### Option 3: Manual Implementation
 ```
 1. Read element list in UI_ELEMENTS_INVENTORY.md
 2. Sketch/wireframe layout
 3. Build components one by one
 4. Match existing design system colors/spacing
 ```
 ---
 ## 🔧 Common Customizations
 ### To Match Different Styles:
 **Sci-Fi Theme:**
 ```
 Change gradient to: #00d9ff to #0099ff (cyan)
 Add: Glowing borders, neon accents
 Fonts: Orbitron or Exo 2
 ```
 **Fantasy Theme:**
 ```
 Keep purple gradient
 Add: Texture overlays, paper-like cards
 Fonts: Cinzel or IM Fell
 Decorative borders
 ```
 **Minimal Theme:**
 ```
 Change to monochrome: #000000 to #ffffff
 Remove: Gradients, decorative elements
 Fonts: Inter or System UI
 Flat design
 ```
 ---
 ## 📐 Layout Templates
 ### Dashboard Layout (Gamemaster/Admin)
 ```
 ┌─────────────────────────────────┐
 │  Header (Global Actions)        │
 ├──────┬──────────────────────────┤
 │ Nav  │ Main Content Area        │
 │ Bar  │                          │
 │      │ ┌────────┬────────┐     │
 │      │ │ Card   │ Card   │     │
 │      │ └────────┴────────┘     │
 │      │                          │
 │      │ [Tables/Charts/Forms]    │
 └──────┴──────────────────────────┘
 Sidebar: 240px
 Content: flex-1
 Gap: 24px
 ```
 ### Chat Layout (Character/Storyteller)
 ```
 ┌─────────────────────────────────┐
 │  Header (Info + Actions)        │
 ├─────────────────────────────────┤
 │                                 │
 │  Scrollable Message Area        │
 │  (Messages stacked vertically)  │
 │                                 │
 ├─────────────────────────────────┤
 │  Fixed Composer (Bottom)        │
 └─────────────────────────────────┘
 Header: Auto height
 Messages: flex-1, overflow-auto
 Composer: Auto height, fixed position
 ```
 ### Wizard Layout
 ```
 ┌─────────────────────────────────┐
 │  Wizard Header + Progress       │
 ├─────────────────────────────────┤
 │                                 │
 │                                 │
 │  Step Content (Centered)        │
 │  Max Width: 600px               │
 │                                 │
 │                                 │
 ├─────────────────────────────────┤
 │  Footer (Cancel | Back | Next)  │
 └─────────────────────────────────┘
 Modal: Max 800px width, centered
 Content: Vertical padding 48px
 Footer: Sticky bottom
 ```
 ---
 ## 🎯 Phase 3 Design Priorities
 ### Must Have First:
 1. **Gamemaster Dashboard** - Overview/home screen
 2. **Game Creation Form** - Simple version
 3. **Player Slot Cards** - Assignment interface
 ### Can Wait:
 4. Role drag-and-drop (use simple assignment first)
 5. Advanced analytics
 6. Detailed configuration screens
 ---
 ## 💡 Tips for Design Consistency
 ### When Designing New Pages:
 1. **Reuse existing components**
   - Check what's already built
   - Extend rather than recreate
 2. **Match spacing**
   - Use 8px grid system
   - Common gaps: 16px, 24px, 32px
 3. **Follow color usage**
   - Purple for primary actions
   - Dark backgrounds (#2d3748)
   - White/light text
 4. **Keep hierarchy clear**
   - Largest: Page titles (2rem)
   - Medium: Section titles (1.5rem)
   - Normal: Body text (1rem)
 5. **Maintain card style**
   - Rounded 8-12px
   - Subtle shadows
   - Padding 1-2rem
 ---
 ## 📱 Responsive Breakpoints
 ```css
 /* Mobile First */
 .container {
  width: 100%;
  padding: 16px;
 }
 /* Tablet - 768px */
@media (min-width: 768px) {
  .container {
    padding: 24px;
  }
  .grid {
    grid-template-columns: repeat(2, 1fr);
  }
 }
 /* Desktop - 1024px */
@media (min-width: 1024px) {
  .container {
    max-width: 1200px;
    margin: 0 auto;
  }
  .grid {
    grid-template-columns: repeat(3, 1fr);
  }
 }
 ```
 ---
 ## 🚀 Workflow Recommendation
 ### For Phase 3 Implementation:
 **Week 1:** Design Phase
 - Day 1: Generate Gamemaster dashboard mockups
 - Day 2: Review and refine designs
 - Day 3: Generate component mockups
 - Day 4: Finalize design system updates
 - Day 5: Create component specifications
 **Week 2-3:** Implementation
 - Build reusable components
 - Implement layouts
 - Connect to backend
 - Test responsive behavior
 - Polish animations
 **Week 4:** Polish
 - Fix edge cases
 - Accessibility improvements
 - Performance optimization
 - User testing
 ---
 ## 📚 Resources
 ### Design Tools
 - **v0.dev** - https://v0.dev (AI code generation)
 - **Figma** - https://figma.com (Design/prototype)
 - **Tailwind UI** - https://tailwindui.com (Component library)
 - **shadcn/ui** - https://ui.shadcn.com (React components)
 ### Inspiration
 - **Dribbble** - Search "RPG dashboard dark theme"
 - **Behance** - Search "game master interface"
 - **Awwwards** - Dark themed web apps
 ### Color Tools
 - **Coolors** - Generate palette variations
 - **Color Hunt** - Find complementary palettes
 - **Contrast Checker** - Ensure accessibility
 ---
 **Everything you need to get UI designs for Phase 3 is ready!** 🎨✨
 Start with the Gamemaster Control Panel - that's the biggest design challenge for Phase 3.
--- a/frontend/src/App.css
+++ b/frontend/src/App.css
@@ -954,6 +954,16 @@ body {
  font-size: 0.9rem;
 }
 .public-message-character-header {
  background: #2d3748;
  padding: 1.5rem;
  border-radius: 8px 8px 0 0;
  display: flex;
  justify-content: space-between;
  align-items: flex-start;
  gap: 1rem;
 }
 .public-msg-content {
  flex: 1;
  color: #2d3748;
@@ -1223,6 +1233,75 @@ body {
  flex: 1;
 }
 /* Character Profile Display */
 .character-profile-summary {
  display: flex;
  gap: 0.5rem;
  margin-top: 0.5rem;
  flex-wrap: wrap;
 }
 .profile-badge {
  background: rgba(102, 126, 234, 0.2);
  color: #667eea;
  padding: 0.25rem 0.75rem;
  border-radius: 12px;
  font-size: 0.85rem;
  font-weight: 500;
  border: 1px solid rgba(102, 126, 234, 0.3);
 }
 .character-actions {
  display: flex;
  flex-direction: column;
  gap: 0.75rem;
  align-items: flex-end;
 }
 .btn-export {
  background: rgba(102, 126, 234, 0.2);
  color: #fff;
  border: 1px solid rgba(102, 126, 234, 0.5);
  padding: 0.5rem 1rem;
  border-radius: 6px;
  cursor: pointer;
  font-size: 0.9rem;
  transition: all 0.2s ease;
 }
 .btn-export:hover {
  background: rgba(102, 126, 234, 0.3);
  border-color: #667eea;
  transform: translateY(-1px);
 }
 /* Character Creation Options */
 .character-creation-options {
  display: flex;
  align-items: center;
  gap: 1rem;
  margin-top: 1.5rem;
  margin-bottom: 1rem;
 }
 .btn-wizard {
  background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
  border: none;
  flex: 1;
 }
 .btn-wizard:hover {
  background: linear-gradient(135deg, #5568d3 0%, #65408b 100%);
  transform: translateY(-2px);
  box-shadow: 0 6px 20px rgba(102, 126, 234, 0.4);
 }
 .option-divider {
  color: #718096;
  font-size: 0.9rem;
  font-weight: 500;
 }
@media (max-width: 768px) {
  .storyteller-content {
    grid-template-columns: 1fr;
@@ -1235,4 +1314,12 @@ body {
  .message {
    max-width: 85%;
  }
  .character-creation-options {
    flex-direction: column;
  }
  .option-divider {
    margin: 0.5rem 0;
  }
 }
--- a/frontend/src/components/CharacterCreationWizard.css
+++ b/frontend/src/components/CharacterCreationWizard.css
@@ -0,0 +1,321 @@
 .wizard-overlay {
  position: fixed;
  top: 0;
  left: 0;
  right: 0;
  bottom: 0;
  background-color: rgba(0, 0, 0, 0.8);
  display: flex;
  justify-content: center;
  align-items: center;
  z-index: 1000;
  padding: 20px;
 }
 .wizard-container {
  background: linear-gradient(135deg, #1a1a2e 0%, #16213e 100%);
  border-radius: 15px;
  max-width: 800px;
  width: 100%;
  max-height: 90vh;
  display: flex;
  flex-direction: column;
  box-shadow: 0 10px 40px rgba(0, 0, 0, 0.5);
  border: 1px solid rgba(255, 255, 255, 0.1);
 }
 .wizard-header {
  padding: 30px;
  border-bottom: 1px solid rgba(255, 255, 255, 0.1);
 }
 .wizard-header h2 {
  margin: 0 0 20px 0;
  color: #fff;
  font-size: 28px;
  text-align: center;
 }
 .wizard-progress {
  display: flex;
  justify-content: space-between;
  gap: 10px;
  flex-wrap: wrap;
 }
 .progress-step {
  flex: 1;
  min-width: 100px;
  padding: 10px;
  background: rgba(255, 255, 255, 0.05);
  border-radius: 8px;
  text-align: center;
  font-size: 12px;
  color: #888;
  transition: all 0.3s ease;
 }
 .progress-step.active {
  background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
  color: #fff;
  font-weight: bold;
 }
 .wizard-content {
  flex: 1;
  overflow-y: auto;
  padding: 30px;
 }
 .wizard-step {
  animation: fadeIn 0.3s ease;
 }
@keyframes fadeIn {
  from { opacity: 0; transform: translateY(10px); }
  to { opacity: 1; transform: translateY(0); }
 }
 .wizard-step h3 {
  margin: 0 0 25px 0;
  color: #fff;
  font-size: 22px;
 }
 .form-group {
  margin-bottom: 25px;
 }
 .form-group label {
  display: block;
  margin-bottom: 8px;
  color: #aaa;
  font-weight: 500;
  font-size: 14px;
 }
 .form-group input[type="text"],
 .form-group textarea,
 .form-group select {
  width: 100%;
  padding: 12px;
  background: rgba(255, 255, 255, 0.05);
  border: 1px solid rgba(255, 255, 255, 0.1);
  border-radius: 8px;
  color: #fff;
  font-size: 14px;
  font-family: inherit;
  transition: all 0.3s ease;
 }
 .form-group input[type="text"]:focus,
 .form-group textarea:focus,
 .form-group select:focus {
  outline: none;
  border-color: #667eea;
  background: rgba(102, 126, 234, 0.1);
 }
 .form-group textarea {
  resize: vertical;
  min-height: 80px;
 }
 .selection-grid {
  display: grid;
  grid-template-columns: repeat(auto-fit, minmax(200px, 1fr));
  gap: 15px;
  margin-top: 15px;
 }
 .selection-card {
  padding: 20px;
  background: rgba(255, 255, 255, 0.05);
  border: 2px solid rgba(255, 255, 255, 0.1);
  border-radius: 10px;
  cursor: pointer;
  transition: all 0.3s ease;
 }
 .selection-card:hover {
  background: rgba(255, 255, 255, 0.08);
  border-color: rgba(102, 126, 234, 0.5);
  transform: translateY(-2px);
 }
 .selection-card.selected {
  background: linear-gradient(135deg, rgba(102, 126, 234, 0.2) 0%, rgba(118, 75, 162, 0.2) 100%);
  border-color: #667eea;
  box-shadow: 0 4px 15px rgba(102, 126, 234, 0.3);
 }
 .selection-name {
  font-size: 16px;
  font-weight: bold;
  color: #fff;
  margin-bottom: 8px;
 }
 .selection-desc {
  font-size: 13px;
  color: #aaa;
  line-height: 1.4;
 }
 .import-section {
  margin-top: 30px;
  padding: 20px;
  background: rgba(102, 126, 234, 0.1);
  border: 1px dashed rgba(102, 126, 234, 0.3);
  border-radius: 10px;
  text-align: center;
 }
 .import-hint {
  margin: 0 0 10px 0;
  color: #aaa;
  font-size: 14px;
 }
 .btn-import {
  display: inline-block;
  padding: 10px 20px;
  background: rgba(102, 126, 234, 0.2);
  border: 1px solid #667eea;
  border-radius: 8px;
  color: #fff;
  cursor: pointer;
  transition: all 0.3s ease;
  font-size: 14px;
 }
 .btn-import:hover {
  background: rgba(102, 126, 234, 0.3);
  transform: translateY(-1px);
 }
 .model-select-large {
  padding: 15px !important;
  font-size: 15px !important;
 }
 .model-hint {
  margin-top: 10px;
  font-size: 13px;
  color: #aaa;
  line-height: 1.5;
 }
 .character-preview {
  background: rgba(255, 255, 255, 0.03);
  border-radius: 10px;
  padding: 20px;
 }
 .preview-section {
  margin-bottom: 20px;
  padding-bottom: 20px;
  border-bottom: 1px solid rgba(255, 255, 255, 0.1);
 }
 .preview-section:last-child {
  border-bottom: none;
  margin-bottom: 0;
  padding-bottom: 0;
 }
 .preview-section h4 {
  margin: 0 0 10px 0;
  color: #667eea;
  font-size: 16px;
 }
 .preview-section p {
  margin: 5px 0;
  color: #ccc;
  line-height: 1.6;
 }
 .preview-section strong {
  color: #fff;
  margin-right: 5px;
 }
 .preview-summary {
  margin-top: 20px;
  padding: 20px;
  background: linear-gradient(135deg, rgba(102, 126, 234, 0.2) 0%, rgba(118, 75, 162, 0.2) 100%);
  border-radius: 10px;
  border: 1px solid rgba(102, 126, 234, 0.3);
 }
 .preview-summary h4 {
  margin: 0 0 10px 0;
  color: #fff;
  font-size: 18px;
 }
 .summary-text {
  font-size: 16px;
  color: #fff;
  line-height: 1.6;
  font-style: italic;
 }
 .wizard-footer {
  padding: 20px 30px;
  border-top: 1px solid rgba(255, 255, 255, 0.1);
 }
 .wizard-actions {
  display: flex;
  justify-content: space-between;
  align-items: center;
 }
 .wizard-navigation {
  display: flex;
  gap: 10px;
 }
 .wizard-loading {
  padding: 50px;
  text-align: center;
  color: #aaa;
  font-size: 16px;
 }
 /* Responsive */
@media (max-width: 768px) {
  .wizard-container {
    max-width: 100%;
    max-height: 100vh;
    border-radius: 0;
  }
  .wizard-progress {
    gap: 5px;
  }
  .progress-step {
    min-width: 60px;
    padding: 8px 5px;
    font-size: 10px;
  }
  .selection-grid {
    grid-template-columns: 1fr;
  }
  .wizard-content {
    padding: 20px;
  }
  .wizard-header {
    padding: 20px;
  }
  .wizard-header h2 {
    font-size: 22px;
  }
 }
--- a/frontend/src/components/CharacterCreationWizard.js
+++ b/frontend/src/components/CharacterCreationWizard.js
@@ -0,0 +1,389 @@
 import React, { useState, useEffect } from 'react';
 import './CharacterCreationWizard.css';
 const API_URL = 'http://localhost:8000';
 function CharacterCreationWizard({ sessionId, onCharacterCreated, onCancel }) {
  const [step, setStep] = useState(1);
  const [profileOptions, setProfileOptions] = useState(null);
  const [availableModels, setAvailableModels] = useState({ openai: [], openrouter: [] });
  // Character data
  const [characterData, setCharacterData] = useState({
    name: '',
    description: '',
    personality: '',
    llm_model: 'gpt-3.5-turbo',
    profile: {
      gender: 'Male',
      race: 'Human',
      character_class: 'Warrior',
      personality_type: 'Friendly',
      background: '',
      avatar_data: null
    }
  });
  useEffect(() => {
    // Fetch profile options
    fetch(`${API_URL}/profile/options`)
      .then(res => res.json())
      .then(data => setProfileOptions(data))
      .catch(err => console.error('Error fetching profile options:', err));
    // Fetch available models
    fetch(`${API_URL}/models`)
      .then(res => res.json())
      .then(data => {
        setAvailableModels(data);
        if (data.openai.length > 0) {
          updateCharacterData('llm_model', data.openai[0].id);
        } else if (data.openrouter.length > 0) {
          updateCharacterData('llm_model', data.openrouter[0].id);
        }
      })
      .catch(err => console.error('Error fetching models:', err));
  }, []);
  const updateCharacterData = (field, value) => {
    setCharacterData(prev => ({ ...prev, [field]: value }));
  };
  const updateProfile = (field, value) => {
    setCharacterData(prev => ({
      ...prev,
      profile: { ...prev.profile, [field]: value }
    }));
  };
  const handleNext = () => {
    if (step === 1 && !characterData.name.trim()) {
      alert('Please enter a character name');
      return;
    }
    if (step === 2 && !characterData.description.trim()) {
      alert('Please enter a character description');
      return;
    }
    setStep(step + 1);
  };
  const handleBack = () => {
    setStep(step - 1);
  };
  const handleCreate = async () => {
    try {
      const response = await fetch(`${API_URL}/sessions/${sessionId}/characters/`, {
        method: 'POST',
        headers: {
          'Content-Type': 'application/json',
        },
        body: JSON.stringify(characterData),
      });
      if (!response.ok) {
        throw new Error('Failed to create character');
      }
      const character = await response.json();
      onCharacterCreated(character);
    } catch (error) {
      console.error('Error creating character:', error);
      alert('Failed to create character: ' + error.message);
    }
  };
  const handleImport = async (event) => {
    const file = event.target.files[0];
    if (!file) return;
    try {
      const text = await file.text();
      const importedData = JSON.parse(text);
      // Extract character data
      const charData = importedData.character || importedData;
      // Update form with imported data
      setCharacterData({
        name: charData.name || '',
        description: charData.description || '',
        personality: charData.personality || '',
        llm_model: charData.llm_model || 'gpt-3.5-turbo',
        profile: charData.profile || characterData.profile
      });
      setStep(1); // Go to first step to review
      alert('Character imported! Review and modify as needed.');
    } catch (error) {
      console.error('Error importing character:', error);
      alert('Failed to import character. Please check the file format.');
    }
  };
  if (!profileOptions) {
    return <div className="wizard-loading">Loading character creation wizard...</div>;
  }
  return (
    <div className="wizard-overlay">
      <div className="wizard-container">
        <div className="wizard-header">
          <h2>Create Your Character</h2>
          <div className="wizard-progress">
            <div className={`progress-step ${step >= 1 ? 'active' : ''}`}>1. Basic Info</div>
            <div className={`progress-step ${step >= 2 ? 'active' : ''}`}>2. Description</div>
            <div className={`progress-step ${step >= 3 ? 'active' : ''}`}>3. Race & Class</div>
            <div className={`progress-step ${step >= 4 ? 'active' : ''}`}>4. Personality</div>
            <div className={`progress-step ${step >= 5 ? 'active' : ''}`}>5. AI Model</div>
            <div className={`progress-step ${step >= 6 ? 'active' : ''}`}>6. Review</div>
          </div>
        </div>
        <div className="wizard-content">
          {/* Step 1: Basic Info */}
          {step === 1 && (
            <div className="wizard-step">
              <h3>Basic Information</h3>
              <div className="form-group">
                <label>Character Name *</label>
                <input
                  type="text"
                  value={characterData.name}
                  onChange={(e) => updateCharacterData('name', e.target.value)}
                  placeholder="Enter your character's name"
                  autoFocus
                />
              </div>
              <div className="form-group">
                <label>Gender</label>
                <select
                  value={characterData.profile.gender}
                  onChange={(e) => updateProfile('gender', e.target.value)}
                >
                  {profileOptions.genders.map(gender => (
                    <option key={gender} value={gender}>{gender}</option>
                  ))}
                </select>
              </div>
              <div className="import-section">
                <p className="import-hint">💡 Have an existing character?</p>
                <label className="btn-import">
                  📥 Import from JSON
                  <input
                    type="file"
                    accept=".json"
                    onChange={handleImport}
                    style={{ display: 'none' }}
                  />
                </label>
              </div>
            </div>
          )}
          {/* Step 2: Description */}
          {step === 2 && (
            <div className="wizard-step">
              <h3>Character Description</h3>
              <div className="form-group">
                <label>Description *</label>
                <textarea
                  value={characterData.description}
                  onChange={(e) => updateCharacterData('description', e.target.value)}
                  placeholder="Describe your character (e.g., A brave knight seeking redemption)"
                  rows="4"
                  autoFocus
                />
              </div>
              <div className="form-group">
                <label>Background Story (Optional)</label>
                <textarea
                  value={characterData.profile.background}
                  onChange={(e) => updateProfile('background', e.target.value)}
                  placeholder="Additional background or backstory"
                  rows="3"
                />
              </div>
            </div>
          )}
          {/* Step 3: Race & Class */}
          {step === 3 && (
            <div className="wizard-step">
              <h3>Race & Class</h3>
              <div className="form-group">
                <label>Race</label>
                <div className="selection-grid">
                  {profileOptions.races.map(race => (
                    <div
                      key={race}
                      className={`selection-card ${characterData.profile.race === race ? 'selected' : ''}`}
                      onClick={() => updateProfile('race', race)}
                    >
                      <div className="selection-name">{race}</div>
                      <div className="selection-desc">{profileOptions.race_descriptions[race]}</div>
                    </div>
                  ))}
                </div>
              </div>
              <div className="form-group">
                <label>Class</label>
                <div className="selection-grid">
                  {profileOptions.classes.map(cls => (
                    <div
                      key={cls}
                      className={`selection-card ${characterData.profile.character_class === cls ? 'selected' : ''}`}
                      onClick={() => updateProfile('character_class', cls)}
                    >
                      <div className="selection-name">{cls}</div>
                      <div className="selection-desc">{profileOptions.class_descriptions[cls]}</div>
                    </div>
                  ))}
                </div>
              </div>
            </div>
          )}
          {/* Step 4: Personality */}
          {step === 4 && (
            <div className="wizard-step">
              <h3>Personality Type</h3>
              <div className="form-group">
                <label>Choose a personality that defines your character's behavior</label>
                <div className="selection-grid">
                  {profileOptions.personality_types.map(personality => (
                    <div
                      key={personality}
                      className={`selection-card ${characterData.profile.personality_type === personality ? 'selected' : ''}`}
                      onClick={() => updateProfile('personality_type', personality)}
                    >
                      <div className="selection-name">{personality}</div>
                      <div className="selection-desc">{profileOptions.personality_descriptions[personality]}</div>
                    </div>
                  ))}
                </div>
              </div>
              <div className="form-group">
                <label>Additional Personality Traits (Optional)</label>
                <textarea
                  value={characterData.personality}
                  onChange={(e) => updateCharacterData('personality', e.target.value)}
                  placeholder="Any additional personality traits or quirks"
                  rows="3"
                />
              </div>
            </div>
          )}
          {/* Step 5: AI Model */}
          {step === 5 && (
            <div className="wizard-step">
              <h3>AI Model Selection</h3>
              <div className="form-group">
                <label>Choose the AI model for this character</label>
                <select
                  value={characterData.llm_model}
                  onChange={(e) => updateCharacterData('llm_model', e.target.value)}
                  className="model-select-large"
                >
                  {availableModels.openai.length > 0 && (
                    <optgroup label="OpenAI Models">
                      {availableModels.openai.map(model => (
                        <option key={model.id} value={model.id}>
                          {model.name}
                        </option>
                      ))}
                    </optgroup>
                  )}
                  {availableModels.openrouter.length > 0 && (
                    <optgroup label="OpenRouter Models">
                      {availableModels.openrouter.map(model => (
                        <option key={model.id} value={model.id}>
                          {model.name} ({model.provider})
                        </option>
                      ))}
                    </optgroup>
                  )}
                </select>
                <p className="model-hint">
                  💡 Different models give different personalities! Try Claude for creative responses,
                  GPT-4 for detailed reasoning, or Llama for faster interactions.
                </p>
              </div>
            </div>
          )}
          {/* Step 6: Review */}
          {step === 6 && (
            <div className="wizard-step">
              <h3>Review Your Character</h3>
              <div className="character-preview">
                <div className="preview-section">
                  <h4>Basic Information</h4>
                  <p><strong>Name:</strong> {characterData.name}</p>
                  <p><strong>Gender:</strong> {characterData.profile.gender}</p>
                  <p><strong>Race:</strong> {characterData.profile.race}</p>
                  <p><strong>Class:</strong> {characterData.profile.character_class}</p>
                  <p><strong>Personality:</strong> {characterData.profile.personality_type}</p>
                </div>
                <div className="preview-section">
                  <h4>Description</h4>
                  <p>{characterData.description}</p>
                </div>
                {characterData.profile.background && (
                  <div className="preview-section">
                    <h4>Background</h4>
                    <p>{characterData.profile.background}</p>
                  </div>
                )}
                {characterData.personality && (
                  <div className="preview-section">
                    <h4>Additional Traits</h4>
                    <p>{characterData.personality}</p>
                  </div>
                )}
                <div className="preview-section">
                  <h4>AI Model</h4>
                  <p>{characterData.llm_model}</p>
                </div>
                <div className="preview-summary">
                  <h4>Character Summary</h4>
                  <p className="summary-text">
                    {characterData.name} is a {characterData.profile.gender.toLowerCase()} {characterData.profile.race} {characterData.profile.character_class} with a {characterData.profile.personality_type.toLowerCase()} personality.
                  </p>
                </div>
              </div>
            </div>
          )}
        </div>
        <div className="wizard-footer">
          <div className="wizard-actions">
            <button className="btn-secondary" onClick={onCancel}>
              Cancel
            </button>
            <div className="wizard-navigation">
              {step > 1 && (
                <button className="btn-secondary" onClick={handleBack}>
                  ← Back
                </button>
              )}
              {step < 6 ? (
                <button className="btn-primary" onClick={handleNext}>
                  Next →
                </button>
              ) : (
                <button className="btn-primary" onClick={handleCreate}>
                  ✨ Create Character
                </button>
              )}
            </div>
          </div>
        </div>
      </div>
    </div>
  );
 }
 export default CharacterCreationWizard;
--- a/frontend/src/components/CharacterView.js
+++ b/frontend/src/components/CharacterView.js
@@ -16,6 +16,30 @@ function CharacterView({ sessionId, characterId }) {
  const wsRef = useRef(null);
  const messagesEndRef = useRef(null);
  const handleExportCharacter = async () => {
    try {
      const response = await fetch(`${API_URL}/sessions/${sessionId}/characters/${characterId}/export`);
      const data = await response.json();
      // Create download link
      const dataStr = JSON.stringify(data, null, 2);
      const dataBlob = new Blob([dataStr], { type: 'application/json' });
      const url = URL.createObjectURL(dataBlob);
      const link = document.createElement('a');
      link.href = url;
      link.download = `${characterInfo?.name || 'character'}_${new Date().toISOString().split('T')[0]}.json`;
      document.body.appendChild(link);
      link.click();
      document.body.removeChild(link);
      URL.revokeObjectURL(url);
      alert('Character exported successfully!');
    } catch (error) {
      console.error('Error exporting character:', error);
      alert('Failed to export character');
    }
  };
  useEffect(() => {
    // Fetch character info
    fetch(`${API_URL}/sessions/${sessionId}/characters/${characterId}/conversation`)
@@ -109,8 +133,18 @@ function CharacterView({ sessionId, characterId }) {
          {characterInfo?.personality && (
            <p className="character-personality">🎭 {characterInfo.personality}</p>
          )}
          {characterInfo?.profile && (
            <div className="character-profile-summary">
              <span className="profile-badge">{characterInfo.profile.race}</span>
              <span className="profile-badge">{characterInfo.profile.character_class}</span>
              <span className="profile-badge">{characterInfo.profile.personality_type}</span>
            </div>
-        <div className="connection-status">
+          )}
        </div>
        <div className="character-actions">
          <button className="btn-export" onClick={handleExportCharacter} title="Export character">
            📥 Export
          </button>
          <span className={`status-indicator ${isConnected ? 'connected' : 'disconnected'}`}>
            {isConnected ? '● Connected' : '○ Disconnected'}
          </span>
--- a/frontend/src/components/SessionSetup.js
+++ b/frontend/src/components/SessionSetup.js
@@ -1,4 +1,5 @@
 import React, { useState, useEffect } from 'react';
 import CharacterCreationWizard from './CharacterCreationWizard';
 const API_URL = 'http://localhost:8000';
@@ -10,6 +11,8 @@ function SessionSetup({ onCreateSession, onJoinSession }) {
  const [characterPersonality, setCharacterPersonality] = useState('');
  const [selectedModel, setSelectedModel] = useState('gpt-3.5-turbo');
  const [availableModels, setAvailableModels] = useState({ openai: [], openrouter: [] });
  const [showWizard, setShowWizard] = useState(false);
  const [useSimpleMode, setUseSimpleMode] = useState(false);
  useEffect(() => {
    // Fetch available models
@@ -66,7 +69,7 @@ function SessionSetup({ onCreateSession, onJoinSession }) {
        llm_model: selectedModel,
      });
-      const charResponse = await fetch(`${API_URL}/sessions/${joinSessionId}/characters/?${params}`, {
+      const charResponse = await fetch(`${API_URL}/sessions/${joinSessionId}/characters/legacy/?${params}`, {
        method: 'POST',
      });
@@ -78,6 +81,19 @@ function SessionSetup({ onCreateSession, onJoinSession }) {
    }
  };
  const handleCharacterCreated = (character) => {
    setShowWizard(false);
    onJoinSession(joinSessionId, character.id);
  };
  const openWizard = () => {
    if (!joinSessionId.trim()) {
      alert('Please enter a Session ID first');
      return;
    }
    setShowWizard(true);
  };
  // Quick join demo session functions
  const joinDemoStoryteller = () => {
    onCreateSession("demo-session-001");
@@ -144,6 +160,15 @@ function SessionSetup({ onCreateSession, onJoinSession }) {
        <div className="setup-section">
          <h2>Join Existing Session</h2>
          <p className="section-description">Play as a character in an ongoing game</p>
          {showWizard && (
            <CharacterCreationWizard
              sessionId={joinSessionId}
              onCharacterCreated={handleCharacterCreated}
              onCancel={() => setShowWizard(false)}
            />
          )}
          <div className="input-group">
            <input
              type="text"
@@ -202,9 +227,21 @@ function SessionSetup({ onCreateSession, onJoinSession }) {
              </p>
            </div>
-            <button className="btn-primary" onClick={joinSession}>
+            <div className="character-creation-options">
-              Join Session
+              <button className="btn-primary btn-wizard" onClick={openWizard}>
                ✨ Create Character (Wizard)
              </button>
              <span className="option-divider">or</span>
              <button className="btn-secondary" onClick={() => setUseSimpleMode(!useSimpleMode)}>
                {useSimpleMode ? '↑ Hide' : '↓ Quick Create'}
              </button>
            </div>
            {useSimpleMode && (
              <button className="btn-primary" onClick={joinSession}>
                Join Session (Simple)
              </button>
            )}
          </div>
        </div>
      </div>
--- a/main.py
+++ b/main.py
@@ -42,11 +42,21 @@ class Message(BaseModel):
    public_content: Optional[str] = None  # For mixed messages - visible to all
    private_content: Optional[str] = None  # For mixed messages - only storyteller sees
 class CharacterProfile(BaseModel):
    """Character profile with race, class, gender, and personality traits"""
    gender: str = "Male"  # Male, Female, Non-binary, Custom
    race: str = "Human"  # Human, Elf, Dwarf, Orc, Halfling
    character_class: str = "Warrior"  # Warrior, Wizard, Cleric, Archer, Rogue
    personality_type: str = "Friendly"  # Friendly, Serious, Doubtful, Measured
    background: str = ""  # Custom background story
    avatar_data: Optional[str] = None  # base64 encoded avatar image
 class Character(BaseModel):
    id: str = Field(default_factory=lambda: str(uuid.uuid4()))
    name: str
    description: str
-    personality: str = ""  # Additional personality traits
+    personality: str = ""  # Additional personality traits (legacy field)
    profile: Optional[CharacterProfile] = None  # Structured profile
    llm_model: str = "gpt-3.5-turbo"  # LLM model for this character
    conversation_history: List[Message] = []  # Private conversation with storyteller
    pending_response: bool = False  # Waiting for storyteller response
@@ -63,6 +73,61 @@ class GameSession(BaseModel):
    scene_history: List[str] = []  # All scenes narrated
    public_messages: List[Message] = []  # Public messages visible to all characters
 # Character Profile Prompt Templates
 RACE_PROMPTS = {
    "Human": "You are a human character, versatile and adaptable to any situation. You have a balanced approach to problem-solving.",
    "Elf": "You are an elf, graceful and wise with centuries of experience. You have keen senses and a deep connection to nature and magic.",
    "Dwarf": "You are a dwarf, stout and honorable with deep knowledge of stone and metal. You are loyal, practical, and value tradition.",
    "Orc": "You are an orc, powerful and direct with a strong sense of honor and combat prowess. You value strength and straightforward action.",
    "Halfling": "You are a halfling, small but brave with natural luck and a cheerful disposition. You are resourceful and enjoy the simple pleasures of life."
 }
 CLASS_PROMPTS = {
    "Warrior": "You excel in physical combat and tactics, preferring direct action and protecting your allies. You are brave and decisive in battle.",
    "Wizard": "You are a master of arcane arts, solving problems with magic and knowledge. You are intellectual, curious, and often seek understanding before action.",
    "Cleric": "You channel divine power to heal and protect, guided by faith and compassion. You support your allies and seek to help those in need.",
    "Archer": "You are a skilled marksman, preferring distance and precision in combat. You are patient, observant, and value accuracy over brute force.",
    "Rogue": "You rely on stealth and cunning, using tricks and skills to overcome obstacles. You are clever, adaptable, and often find unconventional solutions."
 }
 PERSONALITY_PROMPTS = {
    "Friendly": "You are friendly and approachable, always looking for the good in others. You prefer cooperation and building positive relationships.",
    "Serious": "You are serious and focused, prioritizing efficiency and practical solutions. You are disciplined and value getting things done.",
    "Doubtful": "You are cautious and skeptical, questioning motives and analyzing situations carefully. You prefer to be prepared for potential threats.",
    "Measured": "You are measured and thoughtful, weighing options carefully before acting. You seek balance and consider multiple perspectives."
 }
 def build_character_system_prompt(character: Character) -> str:
    """Build system prompt from character profile"""
    if not character.profile:
        # Legacy character without profile
        base_prompt = f"You are {character.name}. {character.description}"
        if character.personality:
            base_prompt += f" {character.personality}"
        return base_prompt
    # Build prompt from profile
    profile = character.profile
    race_trait = RACE_PROMPTS.get(profile.race, "")
    class_trait = CLASS_PROMPTS.get(profile.character_class, "")
    personality_trait = PERSONALITY_PROMPTS.get(profile.personality_type, "")
    prompt_parts = [
        f"You are {character.name}, a {profile.gender.lower()} {profile.race} {profile.character_class}.",
        character.description,
        race_trait,
        class_trait,
        personality_trait,
    ]
    if profile.background:
        prompt_parts.append(f"Background: {profile.background}")
    if character.personality:  # Legacy personality field
        prompt_parts.append(character.personality)
    return " ".join(filter(None, prompt_parts))
 # In-memory storage (replace with database in production)
 sessions: Dict[str, GameSession] = {}
@@ -98,22 +163,27 @@ async def get_session(session_id: str):
        raise HTTPException(status_code=404, detail="Session not found")
    return sessions[session_id]
 class CreateCharacterRequest(BaseModel):
    name: str
    description: str
    personality: str = ""  # Legacy field
    llm_model: str = "gpt-3.5-turbo"
    profile: Optional[CharacterProfile] = None
@app.post("/sessions/{session_id}/characters/")
 async def add_character(
    session_id: str, 
-    name: str, 
+    request: CreateCharacterRequest
    description: str, 
    personality: str = "",
    llm_model: str = "gpt-3.5-turbo"
 ):
    if session_id not in sessions:
        raise HTTPException(status_code=404, detail="Session not found")
    character = Character(
-        name=name, 
+        name=request.name, 
-        description=description, 
+        description=request.description, 
-        personality=personality,
+        personality=request.personality,
-        llm_model=llm_model
+        profile=request.profile,
        llm_model=request.llm_model
    )
    session = sessions[session_id]
    session.characters[character.id] = character
@@ -127,12 +197,128 @@ async def add_character(
                "id": character.id, 
                "name": character.name, 
                "description": character.description,
-                "llm_model": character.llm_model
+                "llm_model": character.llm_model,
                "profile": character.profile.dict() if character.profile else None
            }
        })
    return character
 # Legacy endpoint for backward compatibility
@app.post("/sessions/{session_id}/characters/legacy/")
 async def add_character_legacy(
    session_id: str, 
    name: str, 
    description: str, 
    personality: str = "",
    llm_model: str = "gpt-3.5-turbo"
 ):
    request = CreateCharacterRequest(
        name=name,
        description=description,
        personality=personality,
        llm_model=llm_model
    )
    return await add_character(session_id, request)
 # Export character to JSON
@app.get("/sessions/{session_id}/characters/{character_id}/export")
 async def export_character(session_id: str, character_id: str):
    """Export character profile to JSON"""
    if session_id not in sessions:
        raise HTTPException(status_code=404, detail="Session not found")
    session = sessions[session_id]
    if character_id not in session.characters:
        raise HTTPException(status_code=404, detail="Character not found")
    character = session.characters[character_id]
    export_data = {
        "version": "1.0",
        "character": character.model_dump(),
        "created_at": datetime.now().isoformat(),
        "export_type": "storyteller_rpg_character"
    }
    return export_data
 # Import character from JSON
 class ImportCharacterRequest(BaseModel):
    character_data: dict
@app.post("/sessions/{session_id}/characters/import")
 async def import_character(session_id: str, request: ImportCharacterRequest):
    """Import character from exported JSON"""
    if session_id not in sessions:
        raise HTTPException(status_code=404, detail="Session not found")
    try:
        # Validate and extract character data
        char_data = request.character_data
        if "character" in char_data:
            char_data = char_data["character"]
        # Create character from imported data
        character = Character(**char_data)
        # Generate new ID to avoid conflicts
        character.id = str(uuid.uuid4())
        # Clear conversation history
        character.conversation_history = []
        character.pending_response = False
        session = sessions[session_id]
        session.characters[character.id] = character
        # Notify storyteller
        storyteller_key = f"{session_id}_storyteller"
        if storyteller_key in manager.active_connections:
            await manager.send_to_client(storyteller_key, {
                "type": "character_joined",
                "character": {
                    "id": character.id, 
                    "name": character.name, 
                    "description": character.description,
                    "llm_model": character.llm_model,
                    "profile": character.profile.dict() if character.profile else None
                }
            })
        return character
    except Exception as e:
        raise HTTPException(status_code=400, detail=f"Invalid character data: {str(e)}")
 # Get profile options
@app.get("/profile/options")
 async def get_profile_options():
    """Get available profile options for character creation"""
    return {
        "genders": ["Male", "Female", "Non-binary", "Custom"],
        "races": list(RACE_PROMPTS.keys()),
        "classes": list(CLASS_PROMPTS.keys()),
        "personality_types": list(PERSONALITY_PROMPTS.keys()),
        "race_descriptions": {
            "Human": "Versatile and adaptable",
            "Elf": "Graceful, wise, with keen senses",
            "Dwarf": "Stout, loyal, master craftsmen",
            "Orc": "Powerful, direct, honorable",
            "Halfling": "Small, brave, lucky"
        },
        "class_descriptions": {
            "Warrior": "Physical combat and tactics",
            "Wizard": "Arcane magic and knowledge",
            "Cleric": "Divine power and healing",
            "Archer": "Ranged combat and precision",
            "Rogue": "Stealth, cunning, and skills"
        },
        "personality_descriptions": {
            "Friendly": "Optimistic and cooperative",
            "Serious": "Focused and pragmatic",
            "Doubtful": "Cautious and analytical",
            "Measured": "Balanced and thoughtful"
        }
    }
 # WebSocket endpoint for character interactions (character view)
@app.websocket("/ws/character/{session_id}/{character_id}")
 async def character_websocket(websocket: WebSocket, session_id: str, character_id: str):
@@ -338,11 +524,15 @@ async def generate_suggestion(session_id: str, character_id: str, context: str =
    character = session.characters[character_id]
-    # Prepare context for AI suggestion
+    # Prepare context for AI suggestion using character profile
    system_prompt = build_character_system_prompt(character)
    if session.current_scene:
        system_prompt += f" Current scene: {session.current_scene}"
    messages = [
        {
            "role": "system",
-            "content": f"You are {character.name} in an RPG. Respond in character. Character description: {character.description}. Personality: {character.personality}. Current scene: {session.current_scene}"
+            "content": system_prompt
        }
    ]