init

.env.example

@@ -0,0 +1,12 @@
+# Backend API Configuration
+VITE_API_BASE_URL=http://localhost:8000
+VITE_WS_BASE_URL=ws://localhost:8000
+
+# Optional: Development Configuration
+VITE_DEV_MODE=true
+VITE_LOG_LEVEL=info
+
+# Optional: Feature Flags
+VITE_ENABLE_SPEECH_FEATURES=true
+VITE_ENABLE_AI_CHAT=true
+VITE_ENABLE_TRADITIONAL_MODE=true

.gitignore

@@ -0,0 +1,73 @@
+# Environment variables
+.env
+.env.local
+.env.development.local
+.env.test.local
+.env.production.local
+
+# Credentials and secrets
+credentials/
+*.json
+!package*.json
+!**/package*.json
+
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+pnpm-debug.log*
+lerna-debug.log*
+
+# Dependencies
+node_modules
+dist
+dist-ssr
+*.local
+
+# Editor directories and files
+.vscode/*
+!.vscode/extensions.json
+.idea
+.DS_Store
+*.suo
+*.ntvs*
+*.njsproj
+*.sln
+*.sw?
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Docker
+.dockerignore

README.md

@@ -0,0 +1,55 @@
+# Learn Indonesian App
+
+A Vue.js and Python application for learning Indonesian through realistic everyday scenarios.
+
+## Features
+
+- 🍽️ Restaurant scenarios
+- 🛒 Market interactions
+- 🚌 Transportation conversations
+- 🏨 Hotel check-ins
+- 🎤 Speech recognition practice
+- ✅ Interactive response checking
+
+## Setup
+
+### Frontend (Vue.js)
+```bash
+npm install
+npm run dev
+```
+
+### Backend (Python)
+```bash
+cd backend
+uv sync
+uv run python main.py
+```
+
+### Development
+```bash
+# Lint and format
+uv run ruff check .
+uv run ruff format .
+
+# Run tests
+uv run pytest
+```
+
+## Usage
+
+1. Start the backend server (port 8000)
+2. Start the frontend development server (port 3000)
+3. Navigate to http://localhost:3000
+4. Choose a scenario and practice Indonesian conversations
+
+## Scenarios
+
+Each scenario includes:
+- Realistic dialogue in Indonesian with English translations
+- Interactive response input
+- Vocabulary explanations
+- Speech recognition practice
+- Intelligent response checking
+
+Perfect for learning practical Indonesian for everyday situations!

SETUP.md

@@ -0,0 +1,168 @@
+# Indonesian Learning App with AI Speech Integration
+
+## Setup Instructions
+
+### 1. Prerequisites
+- Python 3.11+
+- Node.js 16+
+- Google Cloud Account
+- OpenAI API Key
+
+### 2. Google Cloud Setup
+1. Create a new Google Cloud project or use existing one
+2. Enable the following APIs:
+   - Cloud Speech-to-Text API
+   - Cloud Text-to-Speech API
+3. Create a service account with the following roles:
+   - Speech Client
+   - Text-to-Speech Client
+4. Download the service account key JSON file
+
+### 3. Environment Configuration
+
+#### Backend Configuration
+1. Copy the environment template:
+   ```bash
+   cd backend
+   cp .env.example .env
+   ```
+
+2. Edit `backend/.env` with your credentials:
+   ```bash
+   # Required
+   GOOGLE_APPLICATION_CREDENTIALS=path/to/your/service-account-key.json
+   OPENAI_API_KEY=your-openai-api-key-here
+   
+   # Optional - customize as needed
+   OPENAI_MODEL=gpt-4o-mini
+   GOOGLE_CLOUD_PROJECT=your-project-id
+   SPEECH_LANGUAGE_CODE=id-ID
+   TTS_VOICE_NAME=id-ID-Standard-A
+   TTS_VOICE_GENDER=FEMALE
+   HOST=0.0.0.0
+   PORT=8000
+   CORS_ORIGINS=http://localhost:3000,http://localhost:5173
+   ```
+
+#### Frontend Configuration  
+1. Copy the environment template:
+   ```bash
+   cp .env.example .env
+   ```
+
+2. Edit `.env` if needed (defaults should work):
+   ```bash
+   VITE_API_BASE_URL=http://localhost:8000
+   VITE_WS_BASE_URL=ws://localhost:8000
+   VITE_ENABLE_SPEECH_FEATURES=true
+   VITE_ENABLE_AI_CHAT=true
+   ```
+
+### 4. Backend Setup
+```bash
+cd backend
+pip install uv  # if not already installed
+uv sync
+```
+
+### 5. Frontend Setup
+```bash
+npm install
+```
+
+### 6. Running the Application
+
+#### Start the backend:
+```bash
+cd backend
+uv run python main.py
+```
+The backend will run on `http://localhost:8000`
+
+#### Start the frontend:
+```bash
+npm run dev
+```
+The frontend will run on `http://localhost:5173`
+
+### 7. Using the App
+
+1. **Traditional Mode**: The original structured learning experience
+2. **AI Chat Mode**: New conversational AI with speech-to-text and text-to-speech
+
+#### AI Chat Features:
+- **Speech Input**: Click "🎤 Speak" to record your voice in Indonesian
+- **Text Input**: Type messages in Indonesian
+- **AI Response**: GPT-4o-mini responds in Indonesian with educational guidance
+- **Speech Output**: AI responses are automatically converted to speech
+- **Real-time**: WebSocket streaming for low-latency conversation
+
+### 8. Environment Variables Summary
+
+#### Backend (.env file):
+```bash
+# Required
+GOOGLE_APPLICATION_CREDENTIALS=path/to/your/service-account-key.json
+OPENAI_API_KEY=your-openai-api-key
+
+# Optional Configuration
+OPENAI_MODEL=gpt-4o-mini
+GOOGLE_CLOUD_PROJECT=your-project-id
+SPEECH_LANGUAGE_CODE=id-ID
+SPEECH_SAMPLE_RATE=48000
+SPEECH_ENCODING=WEBM_OPUS
+TTS_LANGUAGE_CODE=id-ID
+TTS_VOICE_NAME=id-ID-Standard-A
+TTS_VOICE_GENDER=FEMALE
+TTS_SPEAKING_RATE=1.0
+TTS_PITCH=0.0
+HOST=0.0.0.0
+PORT=8000
+DEBUG=false
+CORS_ORIGINS=http://localhost:3000,http://localhost:5173
+```
+
+#### Frontend (.env file):
+```bash
+VITE_API_BASE_URL=http://localhost:8000
+VITE_WS_BASE_URL=ws://localhost:8000
+VITE_DEV_MODE=true
+VITE_LOG_LEVEL=info
+VITE_ENABLE_SPEECH_FEATURES=true
+VITE_ENABLE_AI_CHAT=true
+VITE_ENABLE_TRADITIONAL_MODE=true
+```
+
+### 9. Testing
+- Visit any scenario (warung, ojek, alfamart)
+- Toggle between "📝 Traditional" and "🗣️ AI Chat" modes
+- Test speech input (requires microphone permission)
+- Verify audio output plays automatically
+
+### 10. Troubleshooting
+
+#### Common Issues:
+1. **Microphone not working**: Check browser permissions
+2. **Audio not playing**: Check browser audio settings
+3. **Google Cloud errors**: Verify service account permissions
+4. **OpenAI errors**: Check API key and usage limits
+5. **WebSocket connection issues**: Check backend is running on port 8000
+
+#### Browser Compatibility:
+- Chrome/Edge: Full support
+- Firefox: Limited WebRTC support
+- Safari: May require additional permissions
+
+### 11. Architecture
+```
+User speaks → Browser captures audio → WebSocket → 
+Google Cloud Speech-to-Text → OpenAI GPT-4o-mini → 
+Google Cloud Text-to-Speech → WebSocket → Browser plays audio
+```
+
+### 12. Cost Considerations
+- Google Cloud Speech-to-Text: ~$0.006 per 15-second chunk
+- Google Cloud Text-to-Speech: ~$0.000004 per character
+- OpenAI GPT-4o-mini: ~$0.150 per 1M input tokens, ~$0.600 per 1M output tokens
+
+For typical usage (5-10 minutes of conversation), costs should be under $0.50 per session.

STREET_LINGO_README.md

@@ -0,0 +1,205 @@
+# Street Lingo Platform 🌍
+
+Learn languages through real-world scenarios with AI-powered conversations.
+
+## Available Languages
+
+### 🇮🇩 Indonesian (Learn Indonesian)
+- **URL**: `http://localhost:3000`
+- **Scenarios**: Warung, Ojek, Alfamart, Coffee Shop
+- **Focus**: Everyday Indonesian conversations and cultural contexts
+
+### 🇩🇪 German (Deutsch lernen in Berlin)
+- **URL**: `http://localhost:3001`  
+- **Scenarios**: Späti, WG Viewing, Bürgeramt, Biergarten, U-Bahn
+- **Focus**: Berlin-specific German for expats
+
+## Quick Start
+
+### Prerequisites
+- Python 3.8+
+- Node.js 16+
+- Google Cloud credentials (for Speech-to-Text and Text-to-Speech)
+- OpenAI API key
+
+### 1. Environment Setup
+```bash
+# Backend environment
+cp backend/.env.example backend/.env
+# Edit backend/.env with your API keys
+
+# Set up Google Cloud credentials
+export GOOGLE_APPLICATION_CREDENTIALS="path/to/your/service-account-key.json"
+```
+
+### 2. Install Dependencies
+```bash
+# Backend dependencies
+cd backend
+pip install -r requirements.txt
+
+# Indonesian app dependencies (if not already installed)
+cd ..
+npm install
+
+# German app dependencies
+cd apps/german-app
+npm install
+```
+
+### 3. Start All Services
+```bash
+# From the project root
+./start-street-lingo.sh
+```
+
+This will start:
+- Backend API server on port 8000
+- Indonesian app on port 3000
+- German app on port 3001
+
+## Manual Setup (Alternative)
+
+### Backend
+```bash
+cd backend
+python main.py
+```
+
+### Indonesian App
+```bash
+npm run dev
+```
+
+### German App
+```bash
+cd apps/german-app
+npm run dev
+```
+
+## API Endpoints
+
+### Language-Specific Scenarios
+- `GET /api/scenarios/indonesian` - Indonesian scenarios
+- `GET /api/scenarios/german` - German scenarios
+- `GET /api/scenarios` - All scenarios for all languages
+
+### WebSocket Connections
+- `ws://localhost:8000/ws/speech/indonesian` - Indonesian speech interface
+- `ws://localhost:8000/ws/speech/german` - German speech interface
+
+### Translation
+- `POST /api/translate` - Translate text between languages
+
+## Architecture
+
+```
+street-lingo/
+├── backend/                    # Shared backend
+│   ├── core/                  # Core language-agnostic services
+│   ├── languages/             # Language-specific implementations
+│   │   ├── indonesian/        # Indonesian models & services
+│   │   └── german/            # German models & services
+│   └── main.py               # Main FastAPI application
+├── src/                       # Indonesian frontend
+├── apps/german-app/           # German frontend
+└── start-street-lingo.sh     # Startup script
+```
+
+## Features
+
+### 🎙️ Speech Recognition
+- Real-time speech-to-text in Indonesian and German
+- Optimized for conversational speech patterns
+
+### 🗣️ Text-to-Speech
+- Character-specific voices for immersive conversations
+- Indonesian: Chirp3-HD voices
+- German: Neural2 voices with regional characteristics
+
+### 🤖 AI Conversations
+- Context-aware conversations using OpenAI GPT
+- Goal-based learning with progress tracking
+- Cultural and linguistic authenticity
+
+### 🎯 Scenario-Based Learning
+- Real-world situations you'll encounter
+- Progressive difficulty and goal completion
+- Immediate feedback and corrections
+
+## Development
+
+### Adding New Languages
+1. Create new language directory in `backend/languages/`
+2. Implement language-specific models and services
+3. Create frontend app in `apps/[language]-app/`
+4. Update routing in `main.py`
+
+### Adding New Scenarios
+1. Define scenarios in `backend/languages/[language]/models.py`
+2. Create personality with goals and helpful phrases
+3. Add to `SCENARIO_PERSONALITIES` dictionary
+
+## Environment Variables
+
+### Backend (.env)
+```
+OPENAI_API_KEY=your_openai_api_key
+GOOGLE_APPLICATION_CREDENTIALS=path/to/service-account.json
+SPEECH_ENCODING=WEBM_OPUS
+SPEECH_SAMPLE_RATE=48000
+TTS_LANGUAGE_CODE=id-ID  # or de-DE
+HOST=localhost
+PORT=8000
+DEBUG=true
+```
+
+### Frontend
+```
+VITE_WS_BASE_URL=ws://localhost:8000
+VITE_API_BASE_URL=http://localhost:8000
+```
+
+## Troubleshooting
+
+### Common Issues
+
+1. **WebSocket Connection Failed**
+   - Check if backend is running on port 8000
+   - Verify CORS settings in backend
+
+2. **Speech Recognition Not Working**
+   - Ensure microphone permissions are granted
+   - Check Google Cloud credentials
+
+3. **Audio Playback Issues**
+   - Verify browser audio permissions
+   - Check TTS service configuration
+
+4. **API Errors**
+   - Verify OpenAI API key is valid
+   - Check Google Cloud Speech/TTS quotas
+
+### Logs
+- Backend logs: Console output from `python main.py`
+- Frontend logs: Browser developer console
+- WebSocket logs: Network tab in browser dev tools
+
+## Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests for new features
+5. Submit a pull request
+
+## License
+
+This project is licensed under the MIT License. See LICENSE file for details.
+
+## Support
+
+For issues and questions:
+- Open an issue on GitHub
+- Check the troubleshooting section
+- Review API documentation at `http://localhost:8000/docs`

STRUCTURE.md

@@ -0,0 +1,109 @@
+# Project Structure
+
+This project is organized as a monorepo with multiple frontend applications and a shared backend.
+
+## Directory Structure
+
+```
+learn-indo/
+├── apps/
+│   ├── indonesian-app/          # Indonesian language learning app
+│   │   ├── src/
+│   │   │   ├── components/
+│   │   │   │   ├── SpeechInterface.vue
+│   │   │   │   └── ScenarioView.vue
+│   │   │   ├── App.vue
+│   │   │   └── main.js
+│   │   ├── package.json
+│   │   ├── vite.config.js
+│   │   └── index.html
+│   │
+│   └── german-app/             # German language learning app
+│       ├── src/
+│       │   ├── components/
+│       │   │   └── GermanSpeechInterface.vue
+│       │   ├── views/
+│       │   │   ├── HomeView.vue
+│       │   │   └── ScenarioView.vue
+│       │   ├── App.vue
+│       │   └── main.js
+│       ├── package.json
+│       ├── vite.config.js
+│       └── index.html
+│
+├── backend/                    # Shared FastAPI backend
+│   ├── languages/
+│   │   ├── indonesian/
+│   │   └── german/
+│   ├── core/
+│   ├── main.py
+│   └── pyproject.toml
+│
+├── package.json               # Root workspace configuration
+└── start-street-lingo.sh    # Development startup script
+```
+
+## Applications
+
+### Indonesian App
+- **Port**: 3000
+- **URL**: http://localhost:3000
+- **Features**: Indonesian language learning with speech recognition and AI conversation
+
+### German App
+- **Port**: 3001
+- **URL**: http://localhost:3001
+- **Features**: German language learning with speech recognition and AI conversation
+
+### Backend API
+- **Port**: 8000
+- **URL**: http://localhost:8000
+- **Features**: Shared API serving both frontend applications
+
+## Development Commands
+
+### Root Level Commands
+```bash
+# Install dependencies for all apps
+npm run install:all
+
+# Start all services (backend + both frontends)
+npm run dev:all
+
+# Build all frontend apps
+npm run build:all
+
+# Start individual services
+npm run dev:indonesian
+npm run dev:german
+npm run dev:backend
+```
+
+### Individual App Commands
+```bash
+# Indonesian app
+cd apps/indonesian-app
+npm install
+npm run dev
+
+# German app
+cd apps/german-app
+npm install
+npm run dev
+```
+
+### Quick Start
+```bash
+# Use the convenience script
+./start-street-lingo.sh
+```
+
+## API Endpoints
+
+- **Indonesian scenarios**: `/api/scenarios/indonesian`
+- **German scenarios**: `/api/scenarios/german`
+- **WebSocket - Indonesian**: `/ws/speech/indonesian`
+- **WebSocket - German**: `/ws/speech/german`
+- **Conversation feedback**: `/api/conversation-feedback`
+- **Suggestions**: `/api/suggestions`
+- **Translation**: `/api/translate`

apps/german-app/Dockerfile

@@ -0,0 +1,35 @@
+# Build stage
+FROM node:18-alpine AS builder
+
+WORKDIR /app
+
+# Copy package files
+COPY package*.json ./
+
+# Install dependencies
+RUN npm ci --only=production
+
+# Copy source code
+COPY . .
+
+# Build the application
+RUN npm run build
+
+# Production stage
+FROM nginx:alpine
+
+# Copy built assets from builder stage
+COPY --from=builder /app/dist /usr/share/nginx/html
+
+# Copy nginx configuration
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# Expose port 80
+EXPOSE 80
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD wget --no-verbose --tries=1 --spider http://localhost:80/ || exit 1
+
+# Start nginx
+CMD ["nginx", "-g", "daemon off;"]

apps/german-app/index.html

@@ -0,0 +1,14 @@
+<!DOCTYPE html>
+<html lang="de">
+  <head>
+    <meta charset="UTF-8" />
+    <link rel="icon" type="image/svg+xml" href="/vite.svg" />
+    <meta name="viewport" content="width=device-width, initial-scale=1.0" />
+    <title>Street Lingo - Deutsch lernen in Berlin</title>
+    <meta name="description" content="Learn German through real Berlin scenarios. Master everyday German conversations with locals." />
+  </head>
+  <body>
+    <div id="app"></div>
+    <script type="module" src="/src/main.js"></script>
+  </body>
+</html>

apps/german-app/nginx.conf

@@ -0,0 +1,39 @@
+server {
+    listen 80;
+    server_name localhost;
+    root /usr/share/nginx/html;
+    index index.html;
+
+    # Enable gzip compression
+    gzip on;
+    gzip_vary on;
+    gzip_min_length 1024;
+    gzip_proxied any;
+    gzip_comp_level 6;
+    gzip_types
+        text/plain
+        text/css
+        text/xml
+        text/javascript
+        application/javascript
+        application/xml+rss
+        application/json;
+
+    # Cache static assets
+    location ~* \.(js|css|png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf|eot)$ {
+        expires 1y;
+        add_header Cache-Control "public, immutable";
+    }
+
+    # Handle client-side routing
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+
+    # Health check endpoint
+    location /health {
+        access_log off;
+        return 200 "healthy\n";
+        add_header Content-Type text/plain;
+    }
+}

apps/german-app/package.json

@@ -0,0 +1,18 @@
+{
+  "name": "street-lingo-german",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "dev": "vite --port 3001",
+    "build": "vite build",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "vue": "^3.4.0",
+    "vue-router": "^4.2.5"
+  },
+  "devDependencies": {
+    "@vitejs/plugin-vue": "^4.5.0",
+    "vite": "^5.0.0"
+  }
+}

apps/german-app/src/App.vue

@@ -0,0 +1,348 @@
+<template>
+  <div id="app">
+    <header class="header">
+      <div class="header-content">
+        <div class="logo-section">
+          <div class="logo">
+            <span class="flag">🇩🇪</span>
+            <h1>Street Lingo</h1>
+          </div>
+          <p class="tagline">Deutsch lernen in Berlin - Learn German through real Berlin scenarios</p>
+        </div>
+      </div>
+    </header>
+
+    <nav class="scenario-nav">
+      <div class="nav-container">
+        <div class="nav-tabs">
+          <a
+            v-for="scenario in scenarios" 
+            :key="scenario.type"
+            @click="handleScenarioSwitch(scenario.type)"
+            :class="['nav-tab', { active: $route.params.type === scenario.type }]"
+            href="#"
+          >
+            <span class="tab-emoji">{{ scenario.emoji }}</span>
+            <span class="tab-text">{{ scenario.name }}</span>
+          </a>
+        </div>
+      </div>
+    </nav>
+
+    <main class="main-content">
+      <router-view />
+    </main>
+  </div>
+</template>
+
+<script>
+export default {
+  name: 'App',
+  data() {
+    return {
+      scenarios: [],
+      hasConversationProgress: false
+    }
+  },
+  provide() {
+    return {
+      updateConversationProgress: this.updateConversationProgress
+    }
+  },
+  async mounted() {
+    await this.loadScenarios()
+  },
+  methods: {
+    async loadScenarios() {
+      try {
+        const response = await fetch('/api/scenarios/german')
+        const scenariosData = await response.json()
+        
+        this.scenarios = Object.entries(scenariosData).map(([type, scenario]) => ({
+          type: type,
+          name: scenario.title,
+          emoji: this.getScenarioEmoji(type),
+          description: scenario.description,
+          challenge: scenario.challenge,
+          goal: scenario.goal
+        }))
+      } catch (error) {
+        console.error('Failed to load scenarios:', error)
+        this.scenarios = [
+          { type: 'spati', name: 'At a Späti', emoji: '🏪' },
+          { type: 'wg_viewing', name: 'WG Room Viewing', emoji: '🏠' },
+          { type: 'burgeramt', name: 'At the Bürgeramt', emoji: '🏛️' },
+          { type: 'biergarten', name: 'At a Biergarten', emoji: '🍺' },
+          { type: 'ubahn', name: 'U-Bahn Help', emoji: '🚇' }
+        ]
+      }
+    },
+    getScenarioEmoji(type) {
+      const emojiMap = {
+        'spati': '🏪',
+        'wg_viewing': '🏠',
+        'burgeramt': '🏛️',
+        'biergarten': '🍺',
+        'ubahn': '🚇'
+      }
+      return emojiMap[type] || '📍'
+    },
+    updateConversationProgress(hasProgress) {
+      this.hasConversationProgress = hasProgress
+    },
+    handleScenarioSwitch(newScenarioType) {
+      event.preventDefault()
+      
+      if (this.$route.params.type === newScenarioType) {
+        return
+      }
+      
+      if (this.hasConversationProgress) {
+        const confirmed = confirm(
+          `Das Wechseln der Szenarien setzt Ihren aktuellen Gesprächsverlauf zurück.\n\nSind Sie sicher, dass Sie zu "${this.scenarios.find(s => s.type === newScenarioType)?.name}" wechseln möchten?`
+        )
+        
+        if (!confirmed) {
+          return
+        }
+      }
+      
+      this.$router.push(`/scenario/${newScenarioType}`)
+    }
+  }
+}
+</script>
+
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Crimson+Pro:wght@400;500;600;700&family=DM+Sans:wght@300;400;500;600;700&display=swap');
+
+* {
+  margin: 0;
+  padding: 0;
+  box-sizing: border-box;
+}
+
+:root {
+  /* German/Berlin-inspired colors */
+  --primary: #d4af37;        /* German gold */
+  --primary-light: #e8c547;  
+  --primary-dark: #b8941f;   
+  --secondary: #cc0000;      /* German red */
+  --accent: #2d5a3d;         /* Forest green */
+  --surface: #f8f9fa;        /* Light gray */
+  --surface-alt: #e9ecef;    
+  --surface-dark: #2d3748;
+  --text: #1a1a1a;           /* Dark gray */
+  --text-light: #495057;     
+  --text-muted: #6c757d;
+  --border: #dee2e6;         
+  --shadow-sm: 0 1px 2px 0 rgb(29 35 42 / 0.05);
+  --shadow: 0 4px 6px -1px rgb(29 35 42 / 0.1);
+  --shadow-lg: 0 10px 15px -3px rgb(29 35 42 / 0.1);
+  --radius: 12px;
+  --radius-lg: 16px;
+}
+
+body {
+  font-family: 'DM Sans', -apple-system, BlinkMacSystemFont, system-ui, sans-serif;
+  background: var(--surface);
+  min-height: 100vh;
+  color: var(--text);
+  font-feature-settings: 'liga' 1, 'kern' 1;
+  -webkit-font-smoothing: antialiased;
+  -moz-osx-font-smoothing: grayscale;
+}
+
+#app {
+  min-height: 100vh;
+  display: flex;
+  flex-direction: column;
+}
+
+.header {
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+  color: white;
+  padding: 1.5rem 0;
+  position: sticky;
+  top: 0;
+  z-index: 100;
+  backdrop-filter: blur(12px);
+  box-shadow: var(--shadow);
+}
+
+.header-content {
+  max-width: 1200px;
+  margin: 0 auto;
+  padding: 0 2rem;
+}
+
+.logo-section {
+  text-align: center;
+}
+
+.logo {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  gap: 0.75rem;
+  margin-bottom: 0.5rem;
+}
+
+.flag {
+  font-size: 2rem;
+  filter: drop-shadow(0 2px 4px rgba(0, 0, 0, 0.2));
+}
+
+.logo h1 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 2rem;
+  font-weight: 600;
+  letter-spacing: -0.02em;
+  text-shadow: 0 2px 4px rgba(0, 0, 0, 0.2);
+}
+
+.tagline {
+  font-size: 1rem;
+  opacity: 0.9;
+  font-weight: 400;
+  letter-spacing: 0.01em;
+  text-shadow: 0 1px 2px rgba(0, 0, 0, 0.1);
+}
+
+.scenario-nav {
+  background: var(--surface-alt);
+  border-bottom: 1px solid var(--border);
+  padding: 1rem 0;
+  box-shadow: var(--shadow-sm);
+}
+
+.nav-container {
+  max-width: 1200px;
+  margin: 0 auto;
+  padding: 0 2rem;
+}
+
+.nav-tabs {
+  display: flex;
+  gap: 0.5rem;
+  justify-content: center;
+  flex-wrap: wrap;
+}
+
+.nav-tab {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  padding: 0.75rem 1.25rem;
+  border-radius: var(--radius);
+  text-decoration: none;
+  color: var(--text-light);
+  font-weight: 500;
+  font-size: 0.9rem;
+  transition: all 0.2s cubic-bezier(0.4, 0, 0.2, 1);
+  background: var(--surface);
+  border: 1px solid var(--border);
+  position: relative;
+  overflow: hidden;
+}
+
+.nav-tab::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  bottom: 0;
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+  opacity: 0;
+  transition: opacity 0.2s ease;
+  z-index: -1;
+}
+
+.nav-tab:hover {
+  color: var(--text);
+  border-color: var(--primary-light);
+  box-shadow: var(--shadow-sm);
+  transform: translateY(-1px);
+}
+
+.nav-tab.active {
+  color: white;
+  background: var(--primary);
+  border-color: var(--primary);
+  box-shadow: var(--shadow);
+}
+
+.nav-tab.active::before {
+  opacity: 0;
+}
+
+.tab-emoji {
+  font-size: 1.1rem;
+  filter: grayscale(0.3);
+  transition: filter 0.2s ease;
+}
+
+.nav-tab:hover .tab-emoji,
+.nav-tab.active .tab-emoji {
+  filter: grayscale(0);
+}
+
+.tab-text {
+  white-space: nowrap;
+}
+
+.main-content {
+  flex: 1;
+  padding: 2rem;
+  max-width: 1400px;
+  margin: 0 auto;
+  width: 100%;
+}
+
+@media (max-width: 768px) {
+  .header-content,
+  .nav-container {
+    padding: 0 1rem;
+  }
+  
+  .logo h1 {
+    font-size: 1.75rem;
+  }
+  
+  .tagline {
+    font-size: 0.9rem;
+  }
+  
+  .nav-tabs {
+    gap: 0.25rem;
+  }
+  
+  .nav-tab {
+    padding: 0.625rem 1rem;
+    font-size: 0.85rem;
+  }
+  
+  .main-content {
+    padding: 1rem;
+  }
+}
+
+@media (max-width: 480px) {
+  .logo {
+    flex-direction: column;
+    gap: 0.5rem;
+  }
+  
+  .nav-tabs {
+    flex-direction: column;
+    align-items: center;
+  }
+  
+  .nav-tab {
+    width: 100%;
+    max-width: 280px;
+    justify-content: center;
+  }
+}
+</style>

apps/german-app/src/main.js

@@ -0,0 +1,16 @@
+import { createApp } from 'vue'
+import { createRouter, createWebHistory } from 'vue-router'
+import App from './App.vue'
+import ScenarioView from './views/ScenarioView.vue'
+
+const routes = [
+  { path: '/', redirect: '/scenario/spati' },
+  { path: '/scenario/:type', component: ScenarioView, props: true }
+]
+
+const router = createRouter({
+  history: createWebHistory(),
+  routes
+})
+
+createApp(App).use(router).mount('#app')

apps/german-app/src/views/HomeView.vue

@@ -0,0 +1,438 @@
+<template>
+  <div class="home-container">
+    <div class="hero-section">
+      <div class="hero-content">
+        <h1>Willkommen bei Street Lingo</h1>
+        <p class="hero-subtitle">
+          Master everyday German through real Berlin scenarios
+        </p>
+        <p class="hero-description">
+          Learn German the way Berliners actually speak. Practice conversations in real-life situations - 
+          from ordering at a Späti to navigating the Bürgeramt.
+        </p>
+        <div class="cta-buttons">
+          <button @click="startLearning" class="primary-btn">
+            🚀 Start Learning
+          </button>
+        </div>
+      </div>
+      <div class="hero-image">
+        <div class="berlin-icon">🏙️</div>
+      </div>
+    </div>
+
+    <div class="features-section">
+      <h2>Why Street Lingo?</h2>
+      <div class="features-grid">
+        <div class="feature-card">
+          <div class="feature-icon">🎯</div>
+          <h3>Real Berlin Scenarios</h3>
+          <p>Practice conversations in authentic situations you'll encounter as a Berlin expat</p>
+        </div>
+        <div class="feature-card">
+          <div class="feature-icon">🎙️</div>
+          <h3>Speech Recognition</h3>
+          <p>Improve your pronunciation with advanced German speech recognition technology</p>
+        </div>
+        <div class="feature-card">
+          <div class="feature-icon">🏆</div>
+          <h3>Goal-Based Learning</h3>
+          <p>Complete specific objectives in each scenario to track your progress</p>
+        </div>
+        <div class="feature-card">
+          <div class="feature-icon">🗣️</div>
+          <h3>Natural Conversations</h3>
+          <p>AI-powered conversations that adapt to your German level and learning pace</p>
+        </div>
+      </div>
+    </div>
+
+    <div class="scenarios-section">
+      <h2>Berlin Scenarios</h2>
+      <div class="scenarios-grid">
+        <div 
+          v-for="scenario in scenarios" 
+          :key="scenario.type"
+          class="scenario-card"
+          @click="selectScenario(scenario.type)"
+        >
+          <div class="scenario-header">
+            <span class="scenario-emoji">{{ getScenarioEmoji(scenario.type) }}</span>
+            <h3>{{ scenario.name }}</h3>
+          </div>
+          <p class="scenario-description">{{ scenario.description }}</p>
+          <div class="scenario-challenge">
+            <strong>Challenge:</strong> {{ scenario.challenge }}
+          </div>
+          <div class="scenario-goal">
+            <strong>Goal:</strong> {{ scenario.goal }}
+          </div>
+        </div>
+      </div>
+    </div>
+
+    <div class="about-section">
+      <h2>Perfect for Berlin Expats</h2>
+      <div class="about-content">
+        <p>
+          Whether you're navigating German bureaucracy, looking for a WG room, or just want to chat 
+          with your neighbors, Street Lingo helps you learn the German you actually need in Berlin.
+        </p>
+        <p>
+          Our AI characters speak like real Berliners - casual, direct, and authentic. No textbook 
+          German here, just the language you'll hear on the streets of Kreuzberg, Mitte, and beyond.
+        </p>
+      </div>
+    </div>
+  </div>
+</template>
+
+<script>
+export default {
+  name: 'HomeView',
+  data() {
+    return {
+      scenarios: []
+    }
+  },
+  async mounted() {
+    await this.loadScenarios()
+  },
+  methods: {
+    async loadScenarios() {
+      try {
+        const response = await fetch('/api/scenarios/german')
+        const scenariosData = await response.json()
+        
+        this.scenarios = Object.entries(scenariosData).map(([type, scenario]) => ({
+          type: type,
+          name: scenario.title,
+          description: scenario.description,
+          challenge: scenario.challenge,
+          goal: scenario.goal
+        }))
+      } catch (error) {
+        console.error('Failed to load scenarios:', error)
+        this.scenarios = [
+          {
+            type: 'spati',
+            name: 'At a Späti',
+            description: 'Buy late-night essentials at a Berlin convenience store',
+            challenge: 'Understanding Berlin street German and Späti culture',
+            goal: 'Buy a beer and some snacks'
+          },
+          {
+            type: 'wg_viewing',
+            name: 'WG Room Viewing',
+            description: 'View a shared apartment room in Berlin',
+            challenge: 'Housing terminology and presenting yourself as a good flatmate',
+            goal: 'Ask about rent, house rules, and express interest'
+          },
+          {
+            type: 'burgeramt',
+            name: 'At the Bürgeramt',
+            description: 'Deal with German bureaucracy and registration',
+            challenge: 'Formal German and bureaucratic terminology',
+            goal: 'Complete address registration (Anmeldung)'
+          },
+          {
+            type: 'biergarten',
+            name: 'At a Biergarten',
+            description: 'Order drinks and food at a traditional beer garden',
+            challenge: 'German beer terminology and traditional etiquette',
+            goal: 'Order a beer and traditional German food'
+          },
+          {
+            type: 'ubahn',
+            name: 'U-Bahn Help',
+            description: 'Get help with public transport in Berlin',
+            challenge: 'Transport terminology and directions',
+            goal: 'Get directions and buy appropriate ticket'
+          }
+        ]
+      }
+    },
+    getScenarioEmoji(type) {
+      const emojiMap = {
+        'spati': '🏪',
+        'wg_viewing': '🏠',
+        'burgeramt': '🏛️',
+        'biergarten': '🍺',
+        'ubahn': '🚇'
+      }
+      return emojiMap[type] || '📍'
+    },
+    selectScenario(scenarioType) {
+      this.$router.push(`/scenario/${scenarioType}`)
+    },
+    startLearning() {
+      if (this.scenarios.length > 0) {
+        this.selectScenario(this.scenarios[0].type)
+      } else {
+        this.selectScenario('spati')
+      }
+    }
+  }
+}
+</script>
+
+<style scoped>
+.home-container {
+  max-width: 1200px;
+  margin: 0 auto;
+  padding: 0 2rem;
+}
+
+.hero-section {
+  display: grid;
+  grid-template-columns: 1fr 1fr;
+  gap: 4rem;
+  align-items: center;
+  margin-bottom: 4rem;
+  padding: 2rem 0;
+}
+
+.hero-content h1 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 3rem;
+  font-weight: 700;
+  color: var(--text);
+  margin-bottom: 1rem;
+  line-height: 1.1;
+}
+
+.hero-subtitle {
+  font-size: 1.5rem;
+  color: var(--primary);
+  font-weight: 600;
+  margin-bottom: 1.5rem;
+}
+
+.hero-description {
+  font-size: 1.1rem;
+  color: var(--text-light);
+  line-height: 1.6;
+  margin-bottom: 2rem;
+}
+
+.cta-buttons {
+  display: flex;
+  gap: 1rem;
+}
+
+.primary-btn {
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+  color: white;
+  border: none;
+  padding: 1rem 2rem;
+  border-radius: var(--radius-lg);
+  font-size: 1.1rem;
+  font-weight: 600;
+  cursor: pointer;
+  transition: all 0.3s ease;
+  box-shadow: var(--shadow);
+}
+
+.primary-btn:hover {
+  transform: translateY(-2px);
+  box-shadow: var(--shadow-lg);
+}
+
+.hero-image {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.berlin-icon {
+  font-size: 8rem;
+  opacity: 0.8;
+  filter: drop-shadow(0 4px 8px rgba(0, 0, 0, 0.1));
+}
+
+.features-section {
+  margin-bottom: 4rem;
+}
+
+.features-section h2 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 2.5rem;
+  text-align: center;
+  color: var(--text);
+  margin-bottom: 3rem;
+}
+
+.features-grid {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
+  gap: 2rem;
+}
+
+.feature-card {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 2rem;
+  text-align: center;
+  transition: all 0.3s ease;
+  box-shadow: var(--shadow-sm);
+}
+
+.feature-card:hover {
+  transform: translateY(-4px);
+  box-shadow: var(--shadow-lg);
+  border-color: var(--primary-light);
+}
+
+.feature-icon {
+  font-size: 3rem;
+  margin-bottom: 1rem;
+}
+
+.feature-card h3 {
+  font-size: 1.25rem;
+  font-weight: 600;
+  color: var(--text);
+  margin-bottom: 1rem;
+}
+
+.feature-card p {
+  color: var(--text-light);
+  line-height: 1.5;
+}
+
+.scenarios-section {
+  margin-bottom: 4rem;
+}
+
+.scenarios-section h2 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 2.5rem;
+  text-align: center;
+  color: var(--text);
+  margin-bottom: 3rem;
+}
+
+.scenarios-grid {
+  display: grid;
+  grid-template-columns: repeat(auto-fit, minmax(320px, 1fr));
+  gap: 2rem;
+}
+
+.scenario-card {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 2rem;
+  transition: all 0.3s ease;
+  cursor: pointer;
+  box-shadow: var(--shadow-sm);
+}
+
+.scenario-card:hover {
+  transform: translateY(-4px);
+  box-shadow: var(--shadow-lg);
+  border-color: var(--primary-light);
+}
+
+.scenario-header {
+  display: flex;
+  align-items: center;
+  gap: 1rem;
+  margin-bottom: 1rem;
+}
+
+.scenario-emoji {
+  font-size: 2rem;
+}
+
+.scenario-header h3 {
+  font-size: 1.25rem;
+  font-weight: 600;
+  color: var(--text);
+}
+
+.scenario-description {
+  color: var(--text-light);
+  line-height: 1.5;
+  margin-bottom: 1rem;
+}
+
+.scenario-challenge,
+.scenario-goal {
+  font-size: 0.9rem;
+  color: var(--text-light);
+  margin-bottom: 0.5rem;
+}
+
+.scenario-challenge strong,
+.scenario-goal strong {
+  color: var(--primary);
+}
+
+.about-section {
+  background: var(--surface-alt);
+  border-radius: var(--radius-lg);
+  padding: 3rem;
+  text-align: center;
+}
+
+.about-section h2 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 2.5rem;
+  color: var(--text);
+  margin-bottom: 2rem;
+}
+
+.about-content p {
+  font-size: 1.1rem;
+  color: var(--text-light);
+  line-height: 1.6;
+  margin-bottom: 1.5rem;
+  max-width: 800px;
+  margin-left: auto;
+  margin-right: auto;
+}
+
+.about-content p:last-child {
+  margin-bottom: 0;
+}
+
+@media (max-width: 768px) {
+  .home-container {
+    padding: 0 1rem;
+  }
+  
+  .hero-section {
+    grid-template-columns: 1fr;
+    gap: 2rem;
+    text-align: center;
+  }
+  
+  .hero-content h1 {
+    font-size: 2.5rem;
+  }
+  
+  .hero-subtitle {
+    font-size: 1.25rem;
+  }
+  
+  .berlin-icon {
+    font-size: 6rem;
+  }
+  
+  .features-section h2,
+  .scenarios-section h2,
+  .about-section h2 {
+    font-size: 2rem;
+  }
+  
+  .scenarios-grid {
+    grid-template-columns: 1fr;
+  }
+  
+  .about-section {
+    padding: 2rem;
+  }
+}
+</style>

apps/german-app/src/views/ScenarioView.vue

@@ -0,0 +1,456 @@
+<template>
+  <div class="scenario-container">
+    <div class="scenario-header" v-if="scenarioData">
+      <h2>{{ getScenarioEmoji(type) }} {{ scenarioData.title }}</h2>
+      <div class="scenario-goal">
+        <strong>Ziel:</strong> {{ scenarioData.goal }}
+      </div>
+    </div>
+
+    <div class="conversation-area">
+      <div class="left-panel">
+        <div class="character-section" v-if="scenarioData">
+          <div class="character-header">
+            <div class="character-avatar">
+              {{ getCharacterAvatar(type) }}
+            </div>
+            <div class="character-info">
+              <h3>{{ scenarioData.character }}</h3>
+              <p class="character-description">{{ scenarioData.character_background }}</p>
+            </div>
+          </div>
+        </div>
+
+        <div class="ai-chat-section">
+          <GermanSpeechInterface :scenario="type" />
+        </div>
+      </div>
+
+      <div class="right-panel">
+        <div class="context-section" v-if="scenarioData">
+          <h3>📍 Situationskontext</h3>
+          <div class="context-info">
+            <div class="context-item">
+              <div class="context-label">Ort</div>
+              <div class="context-value">{{ scenarioData.location }}</div>
+            </div>
+            <div class="context-item">
+              <div class="context-label">Beschreibung</div>
+              <div class="context-value">{{ scenarioData.description }}</div>
+            </div>
+            <div class="context-item">
+              <div class="context-label">Herausforderung</div>
+              <div class="context-value">{{ scenarioData.challenge }}</div>
+            </div>
+          </div>
+        </div>
+
+        <div class="helpful-phrases" v-if="scenarioData?.helpful_phrases">
+          <h4>💬 Hilfreiche Phrasen:</h4>
+          <div class="phrases-list">
+            <div 
+              v-for="phrase in scenarioData.helpful_phrases" 
+              :key="phrase.native"
+              class="phrase-item"
+            >
+              <div class="phrase-german">{{ phrase.native }}</div>
+              <div class="phrase-english">{{ phrase.english }}</div>
+            </div>
+          </div>
+        </div>
+      </div>
+    </div>
+  </div>
+</template>
+
+<script>
+import GermanSpeechInterface from '../components/GermanSpeechInterface.vue'
+
+export default {
+  name: 'ScenarioView',
+  components: {
+    GermanSpeechInterface
+  },
+  props: {
+    type: {
+      type: String,
+      required: true
+    }
+  },
+  data() {
+    return {
+      scenarioData: null
+    }
+  },
+  async mounted() {
+    await this.loadScenarioData()
+  },
+  watch: {
+    type: {
+      immediate: true,
+      async handler(newType) {
+        if (newType) {
+          await this.loadScenarioData()
+        }
+      }
+    }
+  },
+  methods: {
+    async loadScenarioData() {
+      try {
+        console.log('Loading German scenario data for type:', this.type)
+        const response = await fetch('/api/scenarios/german')
+        const scenarios = await response.json()
+        console.log('All German scenarios:', scenarios)
+        this.scenarioData = scenarios[this.type]
+        console.log('Selected German scenario data:', this.scenarioData)
+      } catch (error) {
+        console.error('Failed to load German scenario data:', error)
+      }
+    },
+    getScenarioEmoji(type) {
+      const emojiMap = {
+        'spati': '🏪',
+        'wg_viewing': '🏠',
+        'burgeramt': '🏛️',
+        'biergarten': '🍺',
+        'ubahn': '🚇'
+      }
+      return emojiMap[type] || '📍'
+    },
+    getCharacterAvatar(type) {
+      const avatarMap = {
+        'spati': '👨‍💼',
+        'wg_viewing': '👩‍🎓',
+        'burgeramt': '👩‍💼',
+        'biergarten': '👨‍🍳',
+        'ubahn': '👨‍🚀'
+      }
+      return avatarMap[type] || '👤'
+    }
+  }
+}
+</script>
+
+<style scoped>
+.scenario-container {
+  max-width: 1400px;
+  margin: 0 auto;
+  width: 100%;
+  padding: 0 2rem;
+}
+
+.scenario-header {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 2rem;
+  margin-bottom: 2rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.scenario-header::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+}
+
+.scenario-header h2 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 1.75rem;
+  font-weight: 600;
+  color: var(--text);
+  margin-bottom: 0.5rem;
+  letter-spacing: -0.01em;
+}
+
+.scenario-goal {
+  color: var(--text-light);
+  font-size: 1rem;
+  font-weight: 400;
+}
+
+.scenario-goal strong {
+  color: var(--primary);
+  font-weight: 500;
+}
+
+.conversation-area {
+  display: grid;
+  grid-template-columns: 1fr 320px;
+  gap: 2rem;
+  min-height: calc(100vh - 300px);
+}
+
+.left-panel {
+  display: flex;
+  flex-direction: column;
+  gap: 1.5rem;
+}
+
+.character-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.character-section::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: var(--accent);
+}
+
+.character-header {
+  display: flex;
+  align-items: center;
+  gap: 1rem;
+  margin-bottom: 1rem;
+}
+
+.character-avatar {
+  width: 60px;
+  height: 60px;
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+  border-radius: 50%;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  font-size: 1.75rem;
+  box-shadow: var(--shadow);
+  position: relative;
+}
+
+.character-info h3 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 1.25rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0;
+  letter-spacing: -0.01em;
+}
+
+.character-description {
+  color: var(--text-light);
+  margin: 0;
+  line-height: 1.5;
+  font-size: 0.9rem;
+}
+
+.ai-chat-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  overflow: hidden;
+  box-shadow: var(--shadow-sm);
+  min-height: 500px;
+}
+
+.right-panel {
+  display: flex;
+  flex-direction: column;
+  gap: 1.5rem;
+}
+
+.context-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.context-section::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: var(--primary);
+}
+
+.context-section h3 {
+  font-size: 1rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0 0 1rem 0;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.context-info {
+  display: flex;
+  flex-direction: column;
+  gap: 1rem;
+}
+
+.context-item {
+  display: flex;
+  flex-direction: column;
+  gap: 0.25rem;
+}
+
+.context-label {
+  font-size: 0.8rem;
+  font-weight: 500;
+  color: var(--text-muted);
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+}
+
+.context-value {
+  color: var(--text-light);
+  line-height: 1.4;
+  font-size: 0.9rem;
+}
+
+.helpful-phrases {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.helpful-phrases::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: var(--accent);
+}
+
+.helpful-phrases h4 {
+  font-size: 1rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0 0 1rem 0;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.phrases-list {
+  display: flex;
+  flex-direction: column;
+  gap: 0.75rem;
+}
+
+.phrase-item {
+  background: var(--surface-alt);
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  padding: 1rem;
+  transition: all 0.2s cubic-bezier(0.4, 0, 0.2, 1);
+  cursor: pointer;
+  position: relative;
+}
+
+.phrase-item:hover {
+  border-color: var(--primary-light);
+  box-shadow: var(--shadow-sm);
+  transform: translateY(-1px);
+}
+
+.phrase-item::before {
+  content: '';
+  position: absolute;
+  left: 0;
+  top: 0;
+  bottom: 0;
+  width: 3px;
+  background: var(--accent);
+  border-radius: 0 2px 2px 0;
+  transform: scaleY(0);
+  transition: transform 0.2s ease;
+}
+
+.phrase-item:hover::before {
+  transform: scaleY(1);
+}
+
+.phrase-german {
+  font-weight: 500;
+  color: var(--text);
+  margin-bottom: 0.25rem;
+  font-size: 0.9rem;
+}
+
+.phrase-english {
+  font-size: 0.8rem;
+  color: var(--text-muted);
+  font-style: italic;
+  opacity: 0.8;
+}
+
+@media (max-width: 1024px) {
+  .conversation-area {
+    grid-template-columns: 1fr;
+    gap: 1.5rem;
+  }
+  
+  .character-section {
+    padding: 1.25rem;
+  }
+  
+  .character-header {
+    justify-content: center;
+    text-align: center;
+  }
+  
+  .ai-chat-section {
+    min-height: 400px;
+  }
+}
+
+@media (max-width: 768px) {
+  .scenario-container {
+    padding: 0 1rem;
+  }
+  
+  .scenario-header {
+    padding: 1.5rem;
+  }
+  
+  .scenario-header h2 {
+    font-size: 1.5rem;
+  }
+  
+  .character-section,
+  .context-section,
+  .helpful-phrases {
+    padding: 1rem;
+  }
+  
+  .character-avatar {
+    width: 50px;
+    height: 50px;
+    font-size: 1.5rem;
+  }
+  
+  .character-info h3 {
+    font-size: 1.1rem;
+  }
+}
+</style>

apps/german-app/vite.config.js

@@ -0,0 +1,20 @@
+import { defineConfig } from 'vite'
+import vue from '@vitejs/plugin-vue'
+
+export default defineConfig({
+  plugins: [vue()],
+  server: {
+    port: 3001,
+    proxy: {
+      '/api': {
+        target: 'http://localhost:8000',
+        changeOrigin: true
+      },
+      '/ws': {
+        target: 'ws://localhost:8000',
+        ws: true,
+        changeOrigin: true
+      }
+    }
+  }
+})

apps/indonesian-app/Dockerfile

@@ -0,0 +1,35 @@
+# Build stage
+FROM node:18-alpine AS builder
+
+WORKDIR /app
+
+# Copy package files
+COPY package*.json ./
+
+# Install dependencies
+RUN npm ci --only=production
+
+# Copy source code
+COPY . .
+
+# Build the application
+RUN npm run build
+
+# Production stage
+FROM nginx:alpine
+
+# Copy built assets from builder stage
+COPY --from=builder /app/dist /usr/share/nginx/html
+
+# Copy nginx configuration
+COPY nginx.conf /etc/nginx/conf.d/default.conf
+
+# Expose port 80
+EXPOSE 80
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD wget --no-verbose --tries=1 --spider http://localhost:80/ || exit 1
+
+# Start nginx
+CMD ["nginx", "-g", "daemon off;"]

apps/indonesian-app/index.html

@@ -0,0 +1,12 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>Learn Indonesian - Realistic Scenarios</title>
+</head>
+<body>
+    <div id="app"></div>
+    <script type="module" src="/src/main.js"></script>
+</body>
+</html>

apps/indonesian-app/nginx.conf

@@ -0,0 +1,39 @@
+server {
+    listen 80;
+    server_name localhost;
+    root /usr/share/nginx/html;
+    index index.html;
+
+    # Enable gzip compression
+    gzip on;
+    gzip_vary on;
+    gzip_min_length 1024;
+    gzip_proxied any;
+    gzip_comp_level 6;
+    gzip_types
+        text/plain
+        text/css
+        text/xml
+        text/javascript
+        application/javascript
+        application/xml+rss
+        application/json;
+
+    # Cache static assets
+    location ~* \.(js|css|png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf|eot)$ {
+        expires 1y;
+        add_header Cache-Control "public, immutable";
+    }
+
+    # Handle client-side routing
+    location / {
+        try_files $uri $uri/ /index.html;
+    }
+
+    # Health check endpoint
+    location /health {
+        access_log off;
+        return 200 "healthy\n";
+        add_header Content-Type text/plain;
+    }
+}

apps/indonesian-app/package.json

@@ -0,0 +1,19 @@
+{
+  "name": "learn-indonesian-app",
+  "version": "1.0.0",
+  "description": "A Vue.js app for learning Indonesian through realistic scenarios",
+  "scripts": {
+    "dev": "vite --port 3000",
+    "build": "vite build",
+    "preview": "vite preview"
+  },
+  "dependencies": {
+    "vue": "^3.3.4",
+    "vue-router": "^4.2.4",
+    "axios": "^1.4.0"
+  },
+  "devDependencies": {
+    "@vitejs/plugin-vue": "^4.2.3",
+    "vite": "^4.4.5"
+  }
+}

apps/indonesian-app/src/App.vue

@@ -0,0 +1,343 @@
+<template>
+  <div id="app">
+    <header class="header">
+      <div class="header-content">
+        <div class="logo-section">
+          <div class="logo">
+            <span class="flag">🇮🇩</span>
+            <h1>Learn Indonesian</h1>
+          </div>
+          <p class="tagline">Learn Indonesian through everyday scenarios</p>
+        </div>
+      </div>
+    </header>
+
+    <nav class="scenario-nav">
+      <div class="nav-container">
+        <div class="nav-tabs">
+          <a
+            v-for="scenario in scenarios" 
+            :key="scenario.type"
+            @click="handleScenarioSwitch(scenario.type)"
+            :class="['nav-tab', { active: $route.params.type === scenario.type }]"
+            href="#"
+          >
+            <span class="tab-emoji">{{ scenario.emoji }}</span>
+            <span class="tab-text">{{ scenario.name }}</span>
+          </a>
+        </div>
+      </div>
+    </nav>
+
+    <main class="main-content">
+      <router-view />
+    </main>
+  </div>
+</template>
+
+<script>
+export default {
+  name: 'App',
+  data() {
+    return {
+      scenarios: [],
+      hasConversationProgress: false
+    }
+  },
+  provide() {
+    return {
+      updateConversationProgress: this.updateConversationProgress
+    }
+  },
+  async mounted() {
+    await this.loadScenarios()
+  },
+  methods: {
+    async loadScenarios() {
+      try {
+        const response = await fetch('/api/scenarios/indonesian')
+        const scenariosData = await response.json()
+        
+        this.scenarios = Object.entries(scenariosData).map(([type, scenario]) => ({
+          type: type,
+          name: scenario.title,
+          emoji: this.getScenarioEmoji(type),
+          description: scenario.description,
+          challenge: scenario.challenge,
+          goal: scenario.goal
+        }))
+      } catch (error) {
+        console.error('Failed to load scenarios:', error)
+        this.scenarios = [
+          { type: 'warung', name: 'At a Warung', emoji: '🍜' },
+          { type: 'ojek', name: 'Taking an Ojek', emoji: '🏍️' },
+          { type: 'alfamart', name: 'At Alfamart', emoji: '🏪' },
+          { type: 'coffee_shop', name: 'Coffee Shop Small Talk', emoji: '☕' }
+        ]
+      }
+    },
+    getScenarioEmoji(type) {
+      const emojiMap = {
+        'warung': '🍜',
+        'ojek': '🏍️',
+        'alfamart': '🏪',
+        'coffee_shop': '☕'
+      }
+      return emojiMap[type] || '📍'
+    },
+    updateConversationProgress(hasProgress) {
+      this.hasConversationProgress = hasProgress
+    },
+    handleScenarioSwitch(newScenarioType) {
+      event.preventDefault()
+      
+      if (this.$route.params.type === newScenarioType) {
+        return
+      }
+      
+      if (this.hasConversationProgress) {
+        const confirmed = confirm(
+          `Switching scenarios will reset your current conversation progress.\n\nAre you sure you want to switch to "${this.scenarios.find(s => s.type === newScenarioType)?.name}"?`
+        )
+        
+        if (!confirmed) {
+          return
+        }
+      }
+      
+      this.$router.push(`/scenario/${newScenarioType}`)
+    }
+  }
+}
+</script>
+
+<style>
+@import url('https://fonts.googleapis.com/css2?family=Inter:wght@300;400;500;600;700&family=Crimson+Pro:wght@400;500;600;700&family=DM+Sans:wght@300;400;500;600;700&display=swap');
+
+* {
+  margin: 0;
+  padding: 0;
+  box-sizing: border-box;
+}
+
+:root {
+  --primary: #c53030;
+  --primary-light: #e53e3e;
+  --primary-dark: #9c1c1c;
+  --secondary: #dd6b20;
+  --accent: #38a169;
+  --surface: #fefcf7;
+  --surface-alt: #f7f5f0;
+  --surface-dark: #2d3748;
+  --text: #2d3748;
+  --text-light: #4a5568;
+  --text-muted: #718096;
+  --border: #e2d8cc;
+  --shadow-sm: 0 1px 2px 0 rgb(45 55 72 / 0.05);
+  --shadow: 0 4px 6px -1px rgb(45 55 72 / 0.1);
+  --shadow-lg: 0 10px 15px -3px rgb(45 55 72 / 0.1);
+  --radius: 12px;
+  --radius-lg: 16px;
+}
+
+body {
+  font-family: 'DM Sans', -apple-system, BlinkMacSystemFont, system-ui, sans-serif;
+  background: var(--surface);
+  min-height: 100vh;
+  color: var(--text);
+  font-feature-settings: 'liga' 1, 'kern' 1;
+  -webkit-font-smoothing: antialiased;
+  -moz-osx-font-smoothing: grayscale;
+}
+
+#app {
+  min-height: 100vh;
+  display: flex;
+  flex-direction: column;
+}
+
+.header {
+  background: var(--surface);
+  border-bottom: 1px solid var(--border);
+  padding: 1.5rem 0;
+  position: sticky;
+  top: 0;
+  z-index: 100;
+  backdrop-filter: blur(12px);
+  -webkit-backdrop-filter: blur(12px);
+}
+
+.header-content {
+  max-width: 1200px;
+  margin: 0 auto;
+  padding: 0 2rem;
+}
+
+.logo-section {
+  text-align: center;
+}
+
+.logo {
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  gap: 0.75rem;
+  margin-bottom: 0.5rem;
+}
+
+.flag {
+  font-size: 2rem;
+  filter: drop-shadow(0 2px 4px rgba(0, 0, 0, 0.1));
+}
+
+.logo h1 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 2rem;
+  font-weight: 600;
+  color: var(--text);
+  letter-spacing: -0.02em;
+}
+
+.tagline {
+  font-size: 1rem;
+  color: var(--text-light);
+  font-weight: 400;
+  letter-spacing: 0.01em;
+}
+
+.scenario-nav {
+  background: var(--surface-alt);
+  border-bottom: 1px solid var(--border);
+  padding: 1rem 0;
+}
+
+.nav-container {
+  max-width: 1200px;
+  margin: 0 auto;
+  padding: 0 2rem;
+}
+
+.nav-tabs {
+  display: flex;
+  gap: 0.5rem;
+  justify-content: center;
+  flex-wrap: wrap;
+}
+
+.nav-tab {
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+  padding: 0.75rem 1.25rem;
+  border-radius: var(--radius);
+  text-decoration: none;
+  color: var(--text-light);
+  font-weight: 500;
+  font-size: 0.9rem;
+  transition: all 0.2s cubic-bezier(0.4, 0, 0.2, 1);
+  background: var(--surface);
+  border: 1px solid var(--border);
+  position: relative;
+  overflow: hidden;
+}
+
+.nav-tab::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  bottom: 0;
+  background: linear-gradient(135deg, var(--primary) 0%, var(--primary-light) 100%);
+  opacity: 0;
+  transition: opacity 0.2s ease;
+  z-index: -1;
+}
+
+.nav-tab:hover {
+  color: var(--text);
+  border-color: var(--primary-light);
+  box-shadow: var(--shadow-sm);
+  transform: translateY(-1px);
+}
+
+.nav-tab.active {
+  color: white;
+  background: var(--primary);
+  border-color: var(--primary);
+  box-shadow: var(--shadow);
+}
+
+.nav-tab.active::before {
+  opacity: 0;
+}
+
+.tab-emoji {
+  font-size: 1.1rem;
+  filter: grayscale(0.3);
+  transition: filter 0.2s ease;
+}
+
+.nav-tab:hover .tab-emoji,
+.nav-tab.active .tab-emoji {
+  filter: grayscale(0);
+}
+
+.tab-text {
+  white-space: nowrap;
+}
+
+.main-content {
+  flex: 1;
+  padding: 2rem;
+  max-width: 1400px;
+  margin: 0 auto;
+  width: 100%;
+}
+
+@media (max-width: 768px) {
+  .header-content,
+  .nav-container {
+    padding: 0 1rem;
+  }
+  
+  .logo h1 {
+    font-size: 1.75rem;
+  }
+  
+  .tagline {
+    font-size: 0.9rem;
+  }
+  
+  .nav-tabs {
+    gap: 0.25rem;
+  }
+  
+  .nav-tab {
+    padding: 0.625rem 1rem;
+    font-size: 0.85rem;
+  }
+  
+  .main-content {
+    padding: 1rem;
+  }
+}
+
+@media (max-width: 480px) {
+  .logo {
+    flex-direction: column;
+    gap: 0.5rem;
+  }
+  
+  .nav-tabs {
+    flex-direction: column;
+    align-items: center;
+  }
+  
+  .nav-tab {
+    width: 100%;
+    max-width: 200px;
+    justify-content: center;
+  }
+}
+</style>

apps/indonesian-app/src/components/ScenarioView.vue

@@ -0,0 +1,428 @@
+<template>
+  <div class="scenario-container">
+    <div class="scenario-header" v-if="scenarioData">
+      <h2>{{ getScenarioEmoji(type) }} {{ scenarioData.title }}</h2>
+      <div class="scenario-goal">
+        <strong>Goal:</strong> {{ scenarioData.goal }}
+      </div>
+    </div>
+
+    <div class="conversation-area">
+      <div class="left-panel">
+        <div class="character-section" v-if="scenarioData">
+          <div class="character-header">
+            <div class="character-avatar">
+              {{ getCharacterAvatar(type) }}
+            </div>
+            <div class="character-info">
+              <h3>{{ scenarioData.character }}</h3>
+              <p class="character-description">{{ scenarioData.character_background }}</p>
+            </div>
+          </div>
+        </div>
+
+        <div class="ai-chat-section">
+          <SpeechInterface :scenario="type" />
+        </div>
+      </div>
+
+      <div class="right-panel">
+        <div class="context-section" v-if="scenarioData">
+          <h3>📍 Situation Context</h3>
+          <div class="context-info">
+            <div class="context-item">
+              <div class="context-label">Location</div>
+              <div class="context-value">{{ scenarioData.location }}</div>
+            </div>
+            <div class="context-item">
+              <div class="context-label">Description</div>
+              <div class="context-value">{{ scenarioData.description }}</div>
+            </div>
+            <div class="context-item">
+              <div class="context-label">Challenge</div>
+              <div class="context-value">{{ scenarioData.challenge }}</div>
+            </div>
+          </div>
+        </div>
+
+        <div class="helpful-phrases" v-if="scenarioData?.helpful_phrases">
+          <h4>💬 Helpful Phrases:</h4>
+          <div class="phrases-list">
+            <div 
+              v-for="phrase in scenarioData.helpful_phrases" 
+              :key="phrase.indonesian"
+              class="phrase-item"
+            >
+              <div class="phrase-indonesian">{{ phrase.indonesian }}</div>
+              <div class="phrase-english">{{ phrase.english }}</div>
+            </div>
+          </div>
+        </div>
+      </div>
+    </div>
+  </div>
+</template>
+
+<script>
+import SpeechInterface from './SpeechInterface.vue'
+
+export default {
+  name: 'ScenarioView',
+  components: {
+    SpeechInterface
+  },
+  props: {
+    type: {
+      type: String,
+      required: true
+    }
+  },
+  data() {
+    return {
+      scenarioData: null
+    }
+  },
+  async mounted() {
+    await this.loadScenarioData()
+  },
+  watch: {
+    type: {
+      immediate: true,
+      async handler(newType) {
+        if (newType) {
+          await this.loadScenarioData()
+        }
+      }
+    }
+  },
+  methods: {
+    async loadScenarioData() {
+      try {
+        console.log('Loading scenario data for type:', this.type)
+        const response = await fetch('/api/scenarios/indonesian')
+        const scenarios = await response.json()
+        console.log('All scenarios:', scenarios)
+        this.scenarioData = scenarios[this.type]
+        console.log('Selected scenario data:', this.scenarioData)
+      } catch (error) {
+        console.error('Failed to load scenario data:', error)
+      }
+    },
+    getScenarioEmoji(type) {
+      const emojiMap = {
+        'warung': '🍜',
+        'ojek': '🏍️',
+        'alfamart': '🏪',
+        'coffee_shop': '☕'
+      }
+      return emojiMap[type] || '📍'
+    },
+    getCharacterAvatar(type) {
+      const avatarMap = {
+        'warung': '👨‍🍳',
+        'ojek': '👩‍🏋️',
+        'alfamart': '👩‍💼',
+        'coffee_shop': '👨‍💼'
+      }
+      return avatarMap[type] || '👤'
+    }
+  }
+}
+</script>
+
+<style scoped>
+.scenario-container {
+  max-width: 1400px;
+  margin: 0 auto;
+  width: 100%;
+  padding: 0 2rem; /* Add horizontal padding to prevent border touching */
+}
+
+.scenario-header {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 2rem;
+  margin-bottom: 2rem;
+  box-shadow: var(--shadow-sm);
+}
+
+.scenario-header h2 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 1.75rem;
+  font-weight: 600;
+  color: var(--text);
+  margin-bottom: 0.5rem;
+  letter-spacing: -0.01em;
+}
+
+.scenario-goal {
+  color: var(--text-light);
+  font-size: 1rem;
+  font-weight: 400;
+}
+
+.scenario-goal strong {
+  color: var(--primary);
+  font-weight: 500;
+}
+
+.conversation-area {
+  display: grid;
+  grid-template-columns: 1fr 320px;
+  gap: 2rem;
+  min-height: calc(100vh - 300px);
+}
+
+.left-panel {
+  display: flex;
+  flex-direction: column;
+  gap: 1.5rem;
+}
+
+.character-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+}
+
+.character-header {
+  display: flex;
+  align-items: center;
+  gap: 1rem;
+  margin-bottom: 1rem;
+}
+
+.character-avatar {
+  width: 60px;
+  height: 60px;
+  background: var(--primary);
+  border-radius: 50%;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+  font-size: 1.75rem;
+  box-shadow: var(--shadow);
+  position: relative;
+}
+
+
+.character-info h3 {
+  font-family: 'Crimson Pro', serif;
+  font-size: 1.25rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0;
+  letter-spacing: -0.01em;
+}
+
+.character-description {
+  color: var(--text-light);
+  margin: 0;
+  line-height: 1.5;
+  font-size: 0.9rem;
+}
+
+.ai-chat-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  overflow: hidden;
+  box-shadow: var(--shadow-sm);
+  min-height: 500px;
+}
+
+.right-panel {
+  display: flex;
+  flex-direction: column;
+  gap: 1.5rem;
+}
+
+.context-section {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.context-section::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: var(--primary);
+}
+
+.context-section h3 {
+  font-size: 1rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0 0 1rem 0;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.context-info {
+  display: flex;
+  flex-direction: column;
+  gap: 1rem;
+}
+
+.context-item {
+  display: flex;
+  flex-direction: column;
+  gap: 0.25rem;
+}
+
+.context-label {
+  font-size: 0.8rem;
+  font-weight: 500;
+  color: var(--text-muted);
+  text-transform: uppercase;
+  letter-spacing: 0.05em;
+}
+
+.context-value {
+  color: var(--text-light);
+  line-height: 1.4;
+  font-size: 0.9rem;
+}
+
+.helpful-phrases {
+  background: var(--surface);
+  border: 1px solid var(--border);
+  border-radius: var(--radius-lg);
+  padding: 1.5rem;
+  box-shadow: var(--shadow-sm);
+  position: relative;
+  overflow: hidden;
+}
+
+.helpful-phrases::before {
+  content: '';
+  position: absolute;
+  top: 0;
+  left: 0;
+  right: 0;
+  height: 3px;
+  background: var(--accent);
+}
+
+.helpful-phrases h4 {
+  font-size: 1rem;
+  font-weight: 600;
+  color: var(--text);
+  margin: 0 0 1rem 0;
+  display: flex;
+  align-items: center;
+  gap: 0.5rem;
+}
+
+.phrases-list {
+  display: flex;
+  flex-direction: column;
+  gap: 0.75rem;
+}
+
+.phrase-item {
+  background: var(--surface-alt);
+  border: 1px solid var(--border);
+  border-radius: var(--radius);
+  padding: 1rem;
+  transition: all 0.2s cubic-bezier(0.4, 0, 0.2, 1);
+  cursor: pointer;
+  position: relative;
+}
+
+.phrase-item:hover {
+  border-color: var(--primary-light);
+  box-shadow: var(--shadow-sm);
+  transform: translateY(-1px);
+}
+
+.phrase-item::before {
+  content: '';
+  position: absolute;
+  left: 0;
+  top: 0;
+  bottom: 0;
+  width: 3px;
+  background: var(--accent);
+  border-radius: 0 2px 2px 0;
+  transform: scaleY(0);
+  transition: transform 0.2s ease;
+}
+
+
+.phrase-indonesian {
+  font-weight: 500;
+  color: var(--text);
+  margin-bottom: 0.25rem;
+  font-size: 0.9rem;
+}
+
+.phrase-english {
+  font-size: 0.8rem;
+  color: var(--text-muted);
+  font-style: italic;
+  opacity: 0.8;
+}
+
+@media (max-width: 1024px) {
+  .conversation-area {
+    grid-template-columns: 1fr;
+    gap: 1.5rem;
+  }
+  
+  .character-section {
+    padding: 1.25rem;
+  }
+  
+  .character-header {
+    justify-content: center;
+    text-align: center;
+  }
+  
+  .ai-chat-section {
+    min-height: 400px;
+  }
+}
+
+@media (max-width: 768px) {
+  .scenario-container {
+    padding: 0 1rem; /* Reduce padding on mobile */
+  }
+  
+  .scenario-header {
+    padding: 1.5rem;
+  }
+  
+  .scenario-header h2 {
+    font-size: 1.5rem;
+  }
+  
+  .character-section,
+  .context-section,
+  .helpful-phrases {
+    padding: 1rem;
+  }
+  
+  .character-avatar {
+    width: 50px;
+    height: 50px;
+    font-size: 1.5rem;
+  }
+  
+  .character-info h3 {
+    font-size: 1.1rem;
+  }
+}
+</style>

apps/indonesian-app/src/main.js

@@ -0,0 +1,16 @@
+import { createApp } from 'vue'
+import { createRouter, createWebHistory } from 'vue-router'
+import App from './App.vue'
+import ScenarioView from './components/ScenarioView.vue'
+
+const routes = [
+  { path: '/', redirect: '/scenario/warung' },
+  { path: '/scenario/:type', component: ScenarioView, props: true }
+]
+
+const router = createRouter({
+  history: createWebHistory(),
+  routes
+})
+
+createApp(App).use(router).mount('#app')

apps/indonesian-app/vite.config.js

@@ -0,0 +1,15 @@
+import { defineConfig } from 'vite'
+import vue from '@vitejs/plugin-vue'
+
+export default defineConfig({
+  plugins: [vue()],
+  server: {
+    port: 3000,
+    proxy: {
+      '/api': {
+        target: 'http://localhost:8000',
+        changeOrigin: true
+      }
+    }
+  }
+})

backend/.env.example

@@ -0,0 +1,29 @@
+# Google Cloud Configuration
+GOOGLE_APPLICATION_CREDENTIALS=path/to/your/service-account-key.json
+
+# OpenAI Configuration
+OPENAI_API_KEY=your-openai-api-key-here
+
+# Optional: OpenAI Model Configuration
+OPENAI_MODEL=gpt-4o-mini
+
+# Optional: Google Cloud Speech-to-Text Configuration
+GOOGLE_CLOUD_PROJECT=your-project-id
+SPEECH_LANGUAGE_CODE=id-ID
+SPEECH_SAMPLE_RATE=48000
+SPEECH_ENCODING=WEBM_OPUS
+
+# Optional: Google Cloud Text-to-Speech Configuration
+TTS_LANGUAGE_CODE=id-ID
+TTS_VOICE_NAME=id-ID-Standard-A
+TTS_VOICE_GENDER=FEMALE
+TTS_SPEAKING_RATE=1.0
+TTS_PITCH=0.0
+
+# Optional: Server Configuration
+HOST=0.0.0.0
+PORT=8000
+DEBUG=false
+
+# Optional: CORS Configuration
+CORS_ORIGINS=http://localhost:3000,http://localhost:5173

backend/.gitignore

@@ -0,0 +1,127 @@
+# Environment variables
+.env
+.env.local
+.env.*.local
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.python-version
+
+# pipenv
+Pipfile.lock
+
+# PEP 582
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# Google Cloud credentials
+*-key.json
+*.json

backend/Dockerfile

@@ -0,0 +1,42 @@
+FROM python:3.11-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PIP_NO_CACHE_DIR=1 \
+    PIP_DISABLE_PIP_VERSION_CHECK=1
+
+# Set work directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install UV for faster Python package management
+RUN pip install uv
+
+# Copy pyproject.toml and uv.lock
+COPY pyproject.toml uv.lock ./
+
+# Install Python dependencies
+RUN uv sync --frozen --no-dev
+
+# Copy application code
+COPY . .
+
+# Create non-root user
+RUN useradd --create-home --shell /bin/bash app
+USER app
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=30s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/api/health || exit 1
+
+# Run the application
+CMD ["uv", "run", "python", "-m", "uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

backend/config.py

@@ -0,0 +1,65 @@
+import os
+from typing import List
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+class Config:
+    """Configuration settings loaded from environment variables."""
+    
+    # Google Cloud Configuration
+    GOOGLE_APPLICATION_CREDENTIALS: str = os.getenv("GOOGLE_APPLICATION_CREDENTIALS", "")
+    GOOGLE_CLOUD_PROJECT: str = os.getenv("GOOGLE_CLOUD_PROJECT", "")
+    
+    # OpenAI Configuration
+    OPENAI_API_KEY: str = os.getenv("OPENAI_API_KEY", "")
+    OPENAI_MODEL: str = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    
+    # Speech-to-Text Configuration
+    SPEECH_LANGUAGE_CODE: str = os.getenv("SPEECH_LANGUAGE_CODE", "id-ID")
+    SPEECH_SAMPLE_RATE: int = int(os.getenv("SPEECH_SAMPLE_RATE", "48000"))
+    SPEECH_ENCODING: str = os.getenv("SPEECH_ENCODING", "WEBM_OPUS")
+    
+    # Text-to-Speech Configuration
+    TTS_LANGUAGE_CODE: str = os.getenv("TTS_LANGUAGE_CODE", "id-ID")
+    TTS_VOICE_NAME: str = os.getenv("TTS_VOICE_NAME", "id-ID-Standard-A")
+    TTS_VOICE_GENDER: str = os.getenv("TTS_VOICE_GENDER", "FEMALE")
+    TTS_SPEAKING_RATE: float = float(os.getenv("TTS_SPEAKING_RATE", "1.0"))
+    TTS_PITCH: float = float(os.getenv("TTS_PITCH", "0.0"))
+    
+    # Server Configuration
+    HOST: str = os.getenv("HOST", "0.0.0.0")
+    PORT: int = int(os.getenv("PORT", "8000"))
+    DEBUG: bool = os.getenv("DEBUG", "false").lower() == "true"
+    
+    # CORS Configuration
+    CORS_ORIGINS: List[str] = [
+        origin.strip() 
+        for origin in os.getenv("CORS_ORIGINS", "http://localhost:3000,http://localhost:5173").split(",")
+    ]
+    
+    @classmethod
+    def validate(cls) -> None:
+        """Validate required environment variables are set."""
+        required_vars = [
+            ("OPENAI_API_KEY", cls.OPENAI_API_KEY),
+        ]
+        
+        missing_vars = []
+        for var_name, var_value in required_vars:
+            if not var_value:
+                missing_vars.append(var_name)
+        
+        if missing_vars:
+            raise ValueError(f"Missing required environment variables: {', '.join(missing_vars)}")
+        
+        # Warn about optional but recommended variables
+        if not cls.GOOGLE_APPLICATION_CREDENTIALS:
+            print("Warning: GOOGLE_APPLICATION_CREDENTIALS not set. Speech features may not work.")
+        
+        if not cls.GOOGLE_CLOUD_PROJECT:
+            print("Warning: GOOGLE_CLOUD_PROJECT not set. Some Google Cloud features may not work.")
+
+# Global config instance
+config = Config()

backend/core/base_models.py

@@ -0,0 +1,127 @@
+from pydantic import BaseModel
+from typing import List, Optional, Dict
+from enum import Enum
+
+class HelpfulPhrase(BaseModel):
+    native: str
+    english: str
+
+class CharacterType(str, Enum):
+    VENDOR = "vendor"
+    DRIVER = "driver"
+    CASHIER = "cashier"
+    OFFICIAL = "official"
+    NEIGHBOR = "neighbor"
+    SERVICE_WORKER = "service_worker"
+    GENERIC = "generic"
+
+class PersonalityTone(str, Enum):
+    FRIENDLY = "friendly"
+    CASUAL = "casual"
+    FORMAL = "formal"
+    CHEERFUL = "cheerful"
+    BUSINESS_LIKE = "business_like"
+    SLEEPY = "sleepy"
+    CHATTY = "chatty"
+    GRUFF = "gruff"
+    HELPFUL = "helpful"
+
+class Gender(str, Enum):
+    MALE = "male"
+    FEMALE = "female"
+    NEUTRAL = "neutral"
+
+class GoalItem(BaseModel):
+    id: str
+    description: str
+    keywords: List[str] = []
+    completed: bool = False
+
+class BasePersonality(BaseModel):
+    character_type: CharacterType
+    name: str
+    gender: Gender
+    tone: PersonalityTone
+    age_range: str
+    background: str
+    typical_phrases: List[str]
+    response_style: str
+    location_context: str
+    
+    scenario_title: str
+    scenario_description: str
+    scenario_challenge: str
+    scenario_goal: str
+    goal_items: List[GoalItem]
+    helpful_phrases: List[HelpfulPhrase]
+    
+    is_impatient: bool = False
+    is_helpful: bool = True
+    is_talkative: bool = True
+    uses_slang: bool = False
+    
+    # Language-specific settings
+    language_code: str
+    country_code: str
+    
+    def get_system_prompt(self, scenario_context: str = "", language_specific_instructions: str = "") -> str:
+        """Generate a system prompt based on this personality."""
+        casualness_note = f"""
+SPEAKING STYLE - BE VERY CASUAL AND NATURAL:
+- Use everyday {self.language_code.upper()} like real people do
+- Drop formal words when people actually don't use them
+- Use contractions and casual speech patterns
+- Speak like you're talking to a friend or regular customer
+- Don't be overly polite or formal - be natural and relaxed
+- Sound like real street conversation
+{language_specific_instructions}
+"""
+        
+        interaction_guide = self._get_interaction_guide()
+        
+        base_prompt = f"""You are {self.name}, a real {self.character_type.value.replace('_', ' ')} in {self.country_code}. You talk like a normal person - casual, natural, and relaxed.
+
+SCENARIO CONTEXT:
+📍 {self.scenario_title}
+🎯 What's happening: {self.scenario_description}
+⚡ Challenge: {self.scenario_challenge}
+🏆 Goal: {self.scenario_goal}
+
+{casualness_note}
+
+CHARACTER:
+- {self.name} ({self.age_range} {self.character_type.value.replace('_', ' ')})
+- {self.background}
+- Works at: {self.location_context}
+- Personality: {self.tone.value}, {'talkative' if self.is_talkative else 'quiet'}, {'helpful' if self.is_helpful else 'business-focused'}
+
+YOUR TYPICAL PHRASES (use these naturally):
+{chr(10).join(f'- {phrase}' for phrase in self.typical_phrases)}
+
+CRITICAL RULES - READ CONVERSATION HISTORY CAREFULLY:
+1. You are {self.name} - NOT a teacher, NOT formal, just a real person in this scenario
+2. Speak casual {self.language_code.upper()} like in real life - very relaxed and natural
+3. Keep responses SHORT (5-10 words max, like real conversation)
+4. READ THE CONVERSATION HISTORY ABOVE - remember what was already asked and answered
+5. NEVER repeat questions you already asked - check what was said before
+6. TRACK the interaction progress - move naturally through the process based on what's been discussed
+7. Stay relevant to your role and what customers need from you in this scenario
+8. If customer already answered a question, move to the NEXT step in the process
+9. Help the customer achieve their goal: {self.scenario_goal}
+
+{interaction_guide}
+
+ADDITIONAL CONTEXT: {scenario_context}
+
+IMPORTANT: Look at the conversation history above before responding! Don't ask questions that were already answered. Continue naturally from where the conversation left off! Help them complete their goal in this scenario."""
+
+        return base_prompt
+
+    def _get_interaction_guide(self) -> str:
+        """Override in language-specific implementations"""
+        return """
+INTERACTION FLOW:
+- Respond naturally to customer needs
+- Help them with whatever service you provide
+- Keep conversation relevant to your role
+"""

backend/core/speech_service.py

@@ -0,0 +1,443 @@
+import asyncio
+import json
+import os
+import logging
+from typing import AsyncGenerator, Dict, Any, Optional, List
+import base64
+
+from google.cloud import speech
+from google.cloud import texttospeech
+from google.api_core import exceptions
+import openai
+
+from config import config
+
+logger = logging.getLogger(__name__)
+
+class SpeechToTextService:
+    def __init__(self, language_code: str = "en-US"):
+        self.client = speech.SpeechClient()
+        self.language_code = language_code
+        
+        encoding_map = {
+            "WEBM_OPUS": speech.RecognitionConfig.AudioEncoding.WEBM_OPUS,
+            "LINEAR16": speech.RecognitionConfig.AudioEncoding.LINEAR16,
+            "FLAC": speech.RecognitionConfig.AudioEncoding.FLAC,
+            "MULAW": speech.RecognitionConfig.AudioEncoding.MULAW,
+            "AMR": speech.RecognitionConfig.AudioEncoding.AMR,
+            "AMR_WB": speech.RecognitionConfig.AudioEncoding.AMR_WB,
+            "OGG_OPUS": speech.RecognitionConfig.AudioEncoding.OGG_OPUS,
+            "MP3": speech.RecognitionConfig.AudioEncoding.MP3,
+        }
+        
+        self.recognition_config = speech.RecognitionConfig(
+            encoding=encoding_map.get(config.SPEECH_ENCODING, speech.RecognitionConfig.AudioEncoding.WEBM_OPUS),
+            sample_rate_hertz=config.SPEECH_SAMPLE_RATE,
+            language_code=self.language_code,
+            enable_automatic_punctuation=True,
+            use_enhanced=True,
+            model="latest_long",
+        )
+        
+        self.streaming_config = speech.StreamingRecognitionConfig(
+            config=self.recognition_config,
+            interim_results=True,
+            single_utterance=False,
+        )
+
+    async def transcribe_streaming(self, audio_generator: AsyncGenerator[bytes, None]) -> AsyncGenerator[Dict[str, Any], None]:
+        """Stream audio data to Google Cloud Speech-to-Text and yield transcription results."""
+        try:
+            async def request_generator():
+                yield speech.StreamingRecognizeRequest(streaming_config=self.streaming_config)
+                
+                async for chunk in audio_generator:
+                    yield speech.StreamingRecognizeRequest(audio_content=chunk)
+            
+            responses = self.client.streaming_recognize(request_generator())
+            
+            for response in responses:
+                for result in response.results:
+                    transcript = result.alternatives[0].transcript
+                    is_final = result.is_final
+                    
+                    yield {
+                        "type": "transcription",
+                        "transcript": transcript,
+                        "is_final": is_final,
+                        "confidence": result.alternatives[0].confidence if is_final else 0.0
+                    }
+        except exceptions.GoogleAPICallError as e:
+            yield {
+                "type": "error",
+                "message": f"Speech recognition error: {str(e)}"
+            }
+
+class TextToSpeechService:
+    def __init__(self, language_code: str = "en-US"):
+        self.client = texttospeech.TextToSpeechClient()
+        self.language_code = language_code
+        
+        self.gender_map = {
+            "FEMALE": texttospeech.SsmlVoiceGender.FEMALE,
+            "MALE": texttospeech.SsmlVoiceGender.MALE,
+            "NEUTRAL": texttospeech.SsmlVoiceGender.NEUTRAL,
+            "male": texttospeech.SsmlVoiceGender.MALE,
+            "female": texttospeech.SsmlVoiceGender.FEMALE,
+        }
+    
+    def _get_voice_config(self, gender: str, character_name: str = None) -> Dict[str, Any]:
+        """Override this method in language-specific implementations"""
+        tts_gender = self.gender_map.get(gender, texttospeech.SsmlVoiceGender.FEMALE)
+        
+        return {
+            "name": f"{self.language_code}-Standard-A",
+            "speaking_rate": 1.0,
+            "pitch": None,
+            "ssml_gender": tts_gender,
+        }
+    
+    def _get_voice_and_audio_config(self, gender: str, character_name: str = None) -> tuple:
+        """Get appropriate voice and audio configuration based on gender."""
+        config_set = self._get_voice_config(gender, character_name)
+        
+        voice = texttospeech.VoiceSelectionParams(
+            language_code=self.language_code,
+            name=config_set["name"],
+            ssml_gender=config_set["ssml_gender"],
+        )
+        
+        audio_config_params = {
+            "audio_encoding": texttospeech.AudioEncoding.MP3,  # MP3 for faster processing
+            "speaking_rate": config_set["speaking_rate"],
+            # Remove effects profile for faster generation
+        }
+        
+        if config_set["pitch"] is not None:
+            audio_config_params["pitch"] = config_set["pitch"]
+            
+        audio_config = texttospeech.AudioConfig(**audio_config_params)
+        
+        return voice, audio_config
+
+    async def synthesize_speech(self, text: str, gender: str = "female", character_name: str = None) -> bytes:
+        """Convert text to speech using Google Cloud Text-to-Speech."""
+        try:
+            logger.info(f"TTS synthesize_speech called with text: '{text}', gender: '{gender}', character: '{character_name}'")
+            
+            voice, audio_config = self._get_voice_and_audio_config(gender, character_name)
+            logger.info(f"Using voice: {voice.name}, language: {self.language_code}")
+            
+            synthesis_input = texttospeech.SynthesisInput(text=text)
+            
+            response = self.client.synthesize_speech(
+                input=synthesis_input,
+                voice=voice,
+                audio_config=audio_config,
+            )
+            
+            logger.info(f"TTS successful, audio length: {len(response.audio_content)} bytes")
+            return response.audio_content
+                
+        except exceptions.GoogleAPICallError as e:
+            logger.error(f"Text-to-speech error: {str(e)}")
+            raise Exception(f"Text-to-speech error: {str(e)}")
+
+class BaseAIConversationService:
+    def __init__(self, language_code: str = "en"):
+        self.client = openai.OpenAI(api_key=config.OPENAI_API_KEY)
+        self.model = config.OPENAI_MODEL
+        self.language_code = language_code
+        self.current_personality = None
+        self.conversation_history: List[Dict[str, str]] = []
+        self.goal_progress: List = []
+
+    def set_personality(self, personality):
+        """Set the current personality for the conversation."""
+        self.current_personality = personality
+        self.conversation_history = []
+        if hasattr(personality, 'goal_items'):
+            self.goal_progress = [item.dict() for item in personality.goal_items]
+
+    def reset_conversation(self):
+        """Reset the conversation history."""
+        self.conversation_history = []
+        if self.current_personality and hasattr(self.current_personality, 'goal_items'):
+            self.goal_progress = [item.dict() for item in self.current_personality.goal_items]
+
+    def get_personality_for_scenario(self, scenario: str, character_name: str = None):
+        """Override in language-specific implementations"""
+        raise NotImplementedError("Must be implemented by language-specific service")
+
+    async def check_goal_completion(self, user_message: str, ai_response: str) -> bool:
+        """Check if any goals are completed using LLM judge."""
+        if not self.goal_progress:
+            return False
+            
+        goals_completed = False
+        incomplete_goals = [g for g in self.goal_progress if not g.get('completed', False)]
+        if not incomplete_goals:
+            return False
+            
+        logger.info(f"Checking goal completion for user message: '{user_message}'")
+        
+        conversation_context = ""
+        for exchange in self.conversation_history[-3:]:
+            conversation_context += f"User: {exchange['user']}\nAI: {exchange['assistant']}\n"
+        
+        for goal in incomplete_goals:
+            completion_check = await self._judge_goal_completion(
+                goal, 
+                user_message, 
+                ai_response, 
+                conversation_context
+            )
+            
+            if completion_check:
+                goal['completed'] = True
+                goals_completed = True
+                logger.info(f"✅ Goal completed: {goal['description']}")
+        
+        return goals_completed
+    
+    async def _judge_goal_completion(self, goal, user_message: str, ai_response: str, conversation_context: str) -> bool:
+        """Use LLM to judge if a specific goal was completed."""
+        try:
+            if "order" in goal['description'].lower() or "buy" in goal['description'].lower():
+                judge_prompt = f"""You are a strict judge determining if a specific goal was FULLY completed in a conversation.
+
+GOAL TO CHECK: {goal['description']}
+
+RECENT CONVERSATION CONTEXT:
+{conversation_context}
+
+LATEST EXCHANGE:
+User: {user_message}
+AI: {ai_response}
+
+CRITICAL RULES FOR ORDERING GOALS:
+1. ONLY return "YES" if the user has COMPLETELY finished this exact goal
+2. Return "NO" if the goal is partial, incomplete, or just being discussed
+3. For "Order [item]" goals: user must explicitly say they want/order that EXACT item
+4. Don't mark as complete just because the AI is asking about it
+
+Answer ONLY "YES" or "NO":"""
+            else:
+                judge_prompt = f"""You are judging if a conversational goal was completed in a natural conversation scenario.
+
+GOAL TO CHECK: {goal['description']}
+
+RECENT CONVERSATION CONTEXT:
+{conversation_context}
+
+LATEST EXCHANGE:
+User: {user_message}
+AI: {ai_response}
+
+RULES FOR CONVERSATION GOALS:
+1. Return "YES" if the user has naturally accomplished this conversational goal
+2. Goals can be completed through natural conversation flow
+3. Check the FULL conversation context, not just the latest exchange
+
+Answer ONLY "YES" or "NO":"""
+
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[{"role": "user", "content": judge_prompt}],
+                max_tokens=5,
+                temperature=0.1,
+            )
+            
+            result = response.choices[0].message.content.strip().upper()
+            return result == "YES"
+            
+        except Exception as e:
+            logger.error(f"Error in goal completion judge: {str(e)}")
+            return False
+    
+    def are_all_goals_completed(self) -> bool:
+        """Check if all goals are completed."""
+        return all(goal.get('completed', False) for goal in self.goal_progress)
+    
+    def get_goal_status(self) -> Dict[str, Any]:
+        """Get current goal status."""
+        return {
+            "scenario_goal": self.current_personality.scenario_goal if self.current_personality else "",
+            "goal_items": [
+                {
+                    "id": goal.get('id'),
+                    "description": goal.get('description'),
+                    "completed": goal.get('completed', False)
+                } for goal in self.goal_progress
+            ],
+            "all_completed": self.are_all_goals_completed()
+        }
+
+    async def get_goal_status_async(self) -> Dict[str, Any]:
+        """Async version of get_goal_status for parallel processing."""
+        return self.get_goal_status()
+
+    async def get_response(self, user_message: str, context: str = "") -> str:
+        """Get AI response to user message using current personality."""
+        try:
+            if not self.current_personality:
+                raise Exception("No personality set")
+            
+            system_prompt = self.current_personality.get_system_prompt(context)
+            
+            messages = [{"role": "system", "content": system_prompt}]
+            
+            recent_history = self.conversation_history[-8:] if len(self.conversation_history) > 8 else self.conversation_history
+            for exchange in recent_history:
+                messages.append({"role": "user", "content": exchange["user"]})
+                messages.append({"role": "assistant", "content": exchange["assistant"]})
+            
+            messages.append({"role": "user", "content": user_message})
+            
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=messages,
+                max_tokens=250,
+                temperature=0.7,
+            )
+            
+            ai_response = response.choices[0].message.content
+            
+            self.conversation_history.append({
+                "user": user_message,
+                "assistant": ai_response
+            })
+            
+            await self.check_goal_completion(user_message, ai_response)
+            
+            return ai_response
+        except Exception as e:
+            return f"Sorry, there was an error: {str(e)}"
+
+class BaseConversationFlowService:
+    def __init__(self, language_code: str = "en-US"):
+        self.language_code = language_code
+        self.stt_service = SpeechToTextService(language_code)
+        self.tts_service = TextToSpeechService(language_code)
+        self.ai_service = BaseAIConversationService(language_code.split('-')[0])
+
+    def set_scenario_personality(self, scenario: str, character_name: str = None):
+        """Set the personality based on scenario and character."""
+        personality = self.ai_service.get_personality_for_scenario(scenario, character_name)
+        if not self.ai_service.current_personality or self.ai_service.current_personality.name != personality.name:
+            logger.info(f"Setting new personality: {personality.name}")
+            self.ai_service.set_personality(personality)
+
+    async def generate_initial_greeting(self, scenario_context: str = "") -> Dict[str, Any]:
+        """Generate initial greeting from character."""
+        try:
+            scenario = self.extract_scenario_from_context(scenario_context)
+            if scenario:
+                self.set_scenario_personality(scenario)
+            
+            # Generate greeting based on personality
+            personality = self.ai_service.current_personality
+            if personality and personality.typical_phrases:
+                greeting = personality.typical_phrases[0]  # Use first typical phrase
+            else:
+                greeting = "Hello!"
+            
+            # Generate audio
+            gender = personality.gender.value if personality else "female"
+            personality_name = personality.name if personality else "Character"
+            
+            audio_content = await self.tts_service.synthesize_speech(greeting, gender, personality_name)
+            audio_base64 = base64.b64encode(audio_content).decode('utf-8')
+            
+            return {
+                "type": "ai_response",
+                "text": greeting,
+                "audio": audio_base64,
+                "audio_format": "mp3",
+                "character": personality_name,
+                "is_initial_greeting": True
+            }
+        except Exception as e:
+            return {
+                "type": "error",
+                "message": f"Initial greeting error: {str(e)}"
+            }
+
+    async def process_conversation_flow_fast(self, transcribed_text: str, scenario_context: str = "") -> Dict[str, Any]:
+        """Fast conversation flow with parallel processing."""
+        try:
+            scenario = self.extract_scenario_from_context(scenario_context)
+            if scenario:
+                self.set_scenario_personality(scenario)
+            
+            # Get personality info early
+            gender = self.ai_service.current_personality.gender.value if self.ai_service.current_personality else "female"
+            personality_name = self.ai_service.current_personality.name if self.ai_service.current_personality else "Unknown"
+            
+            # Start AI response generation and goal checking in parallel
+            ai_task = asyncio.create_task(self.ai_service.get_response(transcribed_text, scenario_context))
+            goal_task = asyncio.create_task(self.ai_service.get_goal_status_async())
+            
+            # Wait for AI response
+            ai_response = await ai_task
+            
+            # Start TTS immediately while goal processing might still be running
+            tts_task = asyncio.create_task(self.tts_service.synthesize_speech(ai_response, gender, personality_name))
+            
+            # Get goal status (might already be done)
+            goal_status = await goal_task
+            
+            # Wait for TTS to complete
+            audio_content = await tts_task
+            audio_base64 = base64.b64encode(audio_content).decode('utf-8')
+            
+            return {
+                "type": "ai_response",
+                "text": ai_response,
+                "audio": audio_base64,
+                "audio_format": "mp3",
+                "character": personality_name,
+                "goal_status": goal_status,
+                "conversation_complete": goal_status.get("all_completed", False)
+            }
+        except Exception as e:
+            return {
+                "type": "error",
+                "message": f"Conversation flow error: {str(e)}"
+            }
+
+    async def process_conversation_flow(self, transcribed_text: str, scenario_context: str = "") -> Dict[str, Any]:
+        """Process the complete conversation flow: Text → AI → Speech."""
+        try:
+            scenario = self.extract_scenario_from_context(scenario_context)
+            if scenario:
+                self.set_scenario_personality(scenario)
+            
+            ai_response = await self.ai_service.get_response(transcribed_text, scenario_context)
+            
+            gender = self.ai_service.current_personality.gender.value if self.ai_service.current_personality else "female"
+            personality_name = self.ai_service.current_personality.name if self.ai_service.current_personality else "Unknown"
+            
+            audio_content = await self.tts_service.synthesize_speech(ai_response, gender, personality_name)
+            audio_base64 = base64.b64encode(audio_content).decode('utf-8')
+            
+            goal_status = self.ai_service.get_goal_status()
+            
+            return {
+                "type": "ai_response",
+                "text": ai_response,
+                "audio": audio_base64,
+                "audio_format": "mp3",
+                "character": personality_name,
+                "goal_status": goal_status,
+                "conversation_complete": goal_status.get("all_completed", False)
+            }
+        except Exception as e:
+            return {
+                "type": "error",
+                "message": f"Conversation flow error: {str(e)}"
+            }
+
+    def extract_scenario_from_context(self, context: str) -> str:
+        """Override in language-specific implementations"""
+        return "default"

backend/languages/german/config.py

@@ -0,0 +1,56 @@
+"""German language configuration for Street Lingo"""
+
+# German TTS Configuration
+TTS_LANGUAGE_CODE = "de-DE"
+SPEECH_LANGUAGE_CODE = "de-DE"
+
+# German-specific settings
+DEFAULT_SCENARIO = "spati"
+COUNTRY_NAME = "Germany"
+LANGUAGE_NAME = "German"
+LOCALE = "de_DE"
+
+# Currency and units
+CURRENCY_SYMBOL = "€"
+DISTANCE_UNIT = "km"
+
+# Cultural settings
+FORMAL_ADDRESS = True  # Use Sie/du distinction
+TIME_FORMAT = "24h"
+DATE_FORMAT = "DD.MM.YYYY"
+
+# Berlin-specific settings
+CITY_NAME = "Berlin"
+TRANSPORT_SYSTEM = "BVG"
+COMMON_DISTRICTS = [
+    "Mitte",
+    "Kreuzberg", 
+    "Friedrichshain",
+    "Prenzlauer Berg",
+    "Charlottenburg",
+    "Neukölln",
+    "Schöneberg"
+]
+
+# Common German expressions for the AI to understand
+COMMON_EXPRESSIONS = {
+    "greeting": ["Hallo", "Guten Tag", "Moin", "Servus"],
+    "goodbye": ["Tschüss", "Auf Wiedersehen", "Bis bald", "Ciao"],
+    "please": ["Bitte", "Bitte schön"],
+    "thank_you": ["Danke", "Danke schön", "Vielen Dank"],
+    "excuse_me": ["Entschuldigung", "Entschuldigen Sie"],
+    "yes": ["Ja", "Jawohl", "Genau"],
+    "no": ["Nein", "Nö", "Nicht"],
+    "maybe": ["Vielleicht", "Kann sein", "Möglich"]
+}
+
+# Berlin slang and expressions
+BERLIN_SLANG = {
+    "cool": ["krass", "geil", "nice"],
+    "annoying": ["ätzend", "nervig"],
+    "money": ["Kohle", "Kröten", "Moos"],
+    "food": ["Futter", "Grub"],
+    "party": ["feiern", "abgehen"],
+    "work": ["malochen", "schaffen"],
+    "tired": ["platt", "fertig"]
+}

backend/languages/german/models.py

@@ -0,0 +1,287 @@
+from core.base_models import BasePersonality, CharacterType, PersonalityTone, Gender, GoalItem, HelpfulPhrase
+
+class GermanPersonality(BasePersonality):
+    def __init__(self, **data):
+        data['language_code'] = "de"
+        data['country_code'] = "Germany"
+        super().__init__(**data)
+    
+    def get_system_prompt(self, scenario_context: str = "") -> str:
+        """Generate a system prompt for German conversations."""
+        german_instructions = """
+- Use informal "du" unless it's a formal bureaucratic setting
+- Use common German contractions like "ich hab" instead of "ich habe"
+- Include Berlin slang and expressions when appropriate
+- Sound like a real Berliner - direct but friendly
+- Use "ne?" for confirmation questions
+- Include typical Berlin expressions
+"""
+        
+        return super().get_system_prompt(scenario_context, german_instructions)
+
+# Berlin-specific scenarios
+SPATI_PERSONALITIES = {
+    "mehmet": GermanPersonality(
+        character_type=CharacterType.VENDOR,
+        name="Mehmet",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="middle-aged",
+        background="Turkish-German Späti owner who's been in Berlin for 20 years",
+        typical_phrases=[
+            "Hallo, was brauchst du?",
+            "Alles klar?",
+            "Geht klar",
+            "Machst du",
+            "Schönen Abend noch",
+            "Bis später",
+            "Kein Problem",
+            "Läuft"
+        ],
+        response_style="Friendly but direct, knows his regulars",
+        location_context="24/7 Späti in Kreuzberg",
+        scenario_title="At a Späti",
+        scenario_description="You're at a Berlin Späti (convenience store) buying late-night essentials. Practice ordering drinks, snacks, and everyday items in German.",
+        scenario_challenge="Understanding Berlin street German, dealing with informal language, and navigating the unique Späti culture.",
+        scenario_goal="Buy a beer and some snacks",
+        goal_items=[
+            GoalItem(
+                id="buy_beer",
+                description="Buy a beer (Bier kaufen)"
+            ),
+            GoalItem(
+                id="buy_snacks",
+                description="Buy some snacks (Snacks kaufen)"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(native="Ich hätte gern...", english="I would like..."),
+            HelpfulPhrase(native="Was kostet das?", english="How much does this cost?"),
+            HelpfulPhrase(native="Haben Sie...?", english="Do you have...?"),
+            HelpfulPhrase(native="Ein Bier, bitte", english="A beer, please"),
+            HelpfulPhrase(native="Danke schön", english="Thank you"),
+            HelpfulPhrase(native="Chips", english="Chips"),
+            HelpfulPhrase(native="Bezahlen", english="To pay")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+WG_PERSONALITIES = {
+    "lisa": GermanPersonality(
+        character_type=CharacterType.NEIGHBOR,
+        name="Lisa",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.FRIENDLY,
+        age_range="young",
+        background="Berlin student showing her WG room to potential flatmates",
+        typical_phrases=[
+            "Hallo! Du bist wegen des Zimmers hier?",
+            "Komm rein!",
+            "Das ist unser Wohnzimmer",
+            "Die Küche teilen wir alle",
+            "Wir sind eine entspannte WG",
+            "Hast du Fragen?",
+            "Das würde monatlich kosten...",
+            "Wir melden uns bei dir"
+        ],
+        response_style="Friendly but assessing compatibility for shared living",
+        location_context="Shared apartment in Prenzlauer Berg",
+        scenario_title="WG Room Viewing",
+        scenario_description="You're viewing a room in a Berlin shared apartment (WG). Practice asking about living arrangements, rent, and house rules in German.",
+        scenario_challenge="Understanding housing terminology, asking appropriate questions about shared living, and presenting yourself as a good flatmate.",
+        scenario_goal="Ask about rent, house rules, and express interest",
+        goal_items=[
+            GoalItem(
+                id="ask_rent",
+                description="Ask about monthly rent (Nach der Miete fragen)"
+            ),
+            GoalItem(
+                id="ask_house_rules",
+                description="Ask about house rules (Nach Hausregeln fragen)"
+            ),
+            GoalItem(
+                id="express_interest",
+                description="Express interest in the room (Interesse zeigen)"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(native="Wie viel kostet das Zimmer?", english="How much does the room cost?"),
+            HelpfulPhrase(native="Sind Nebenkosten inklusive?", english="Are utilities included?"),
+            HelpfulPhrase(native="Wie ist die Hausordnung?", english="What are the house rules?"),
+            HelpfulPhrase(native="Wann kann ich einziehen?", english="When can I move in?"),
+            HelpfulPhrase(native="Das gefällt mir", english="I like it"),
+            HelpfulPhrase(native="Ich würde gerne hier wohnen", english="I would like to live here"),
+            HelpfulPhrase(native="Kaltmiete", english="Base rent"),
+            HelpfulPhrase(native="Warmmiete", english="Rent including utilities")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+BURGERAMT_PERSONALITIES = {
+    "frau_schmidt": GermanPersonality(
+        character_type=CharacterType.OFFICIAL,
+        name="Frau Schmidt",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.FORMAL,
+        age_range="middle-aged",
+        background="Experienced civil servant at Berlin Bürgeramt",
+        typical_phrases=[
+            "Guten Tag, womit kann ich Ihnen helfen?",
+            "Haben Sie einen Termin?",
+            "Welche Dokumente haben Sie dabei?",
+            "Das müssen Sie ausfüllen",
+            "Unterschreiben Sie bitte hier",
+            "Das kostet 28 Euro",
+            "In 2-3 Wochen bekommen Sie Post",
+            "Auf Wiedersehen"
+        ],
+        response_style="Professional, formal, efficient but can be helpful",
+        location_context="Berlin Bürgeramt office",
+        scenario_title="At the Bürgeramt",
+        scenario_description="You're at the Berlin Bürgeramt (civil services office) to register your address. Practice dealing with German bureaucracy and formal language.",
+        scenario_challenge="Understanding formal German, bureaucratic terminology, and navigating the registration process.",
+        scenario_goal="Complete address registration (Anmeldung)",
+        goal_items=[
+            GoalItem(
+                id="explain_purpose",
+                description="Explain you need to register your address (Anmeldung erklären)"
+            ),
+            GoalItem(
+                id="provide_documents",
+                description="Provide required documents (Dokumente vorlegen)"
+            ),
+            GoalItem(
+                id="complete_form",
+                description="Complete the registration form (Formular ausfüllen)"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(native="Ich möchte mich anmelden", english="I want to register my address"),
+            HelpfulPhrase(native="Ich bin neu in Berlin", english="I'm new to Berlin"),
+            HelpfulPhrase(native="Welche Dokumente brauche ich?", english="What documents do I need?"),
+            HelpfulPhrase(native="Personalausweis", english="Identity card"),
+            HelpfulPhrase(native="Mietvertrag", english="Rental contract"),
+            HelpfulPhrase(native="Wohnungsgeberbestätigung", english="Landlord confirmation"),
+            HelpfulPhrase(native="Wie lange dauert das?", english="How long does it take?"),
+            HelpfulPhrase(native="Anmeldung", english="Address registration")
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=False
+    )
+}
+
+BIERGARTEN_PERSONALITIES = {
+    "klaus": GermanPersonality(
+        character_type=CharacterType.SERVICE_WORKER,
+        name="Klaus",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CHEERFUL,
+        age_range="middle-aged",
+        background="Experienced Biergarten server who loves his job",
+        typical_phrases=[
+            "Hallo! Habt ihr schon gewählt?",
+            "Was darf's denn sein?",
+            "Möchtet ihr was zu essen dazu?",
+            "Eine Maß Bier?",
+            "Kommt sofort!",
+            "Prost!",
+            "Schmeckt's euch?",
+            "Zahlen zusammen oder getrennt?"
+        ],
+        response_style="Cheerful and traditional, enjoys chatting with customers",
+        location_context="Traditional Biergarten in Tiergarten",
+        scenario_title="At a Biergarten",
+        scenario_description="You're at a Berlin Biergarten ordering food and drinks. Practice ordering in German and understanding traditional beer garden culture.",
+        scenario_challenge="Understanding German beer terminology, food options, and traditional Biergarten etiquette.",
+        scenario_goal="Order a beer and traditional German food",
+        goal_items=[
+            GoalItem(
+                id="order_beer",
+                description="Order a beer (Bier bestellen)"
+            ),
+            GoalItem(
+                id="order_food",
+                description="Order traditional German food (Deutsches Essen bestellen)"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(native="Eine Maß Bier, bitte", english="A liter of beer, please"),
+            HelpfulPhrase(native="Was empfehlen Sie?", english="What do you recommend?"),
+            HelpfulPhrase(native="Ich hätte gern...", english="I would like..."),
+            HelpfulPhrase(native="Schweinebraten", english="Roast pork"),
+            HelpfulPhrase(native="Schnitzel", english="Schnitzel"),
+            HelpfulPhrase(native="Sauerkraut", english="Sauerkraut"),
+            HelpfulPhrase(native="Die Rechnung, bitte", english="The bill, please"),
+            HelpfulPhrase(native="Prost!", english="Cheers!")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+UBAHN_PERSONALITIES = {
+    "bvg_info": GermanPersonality(
+        character_type=CharacterType.SERVICE_WORKER,
+        name="BVG Mitarbeiter",
+        gender=Gender.MALE,
+        tone=PersonalityTone.HELPFUL,
+        age_range="young",
+        background="Helpful BVG information staff at U-Bahn station",
+        typical_phrases=[
+            "Kann ich Ihnen helfen?",
+            "Wohin möchten Sie denn?",
+            "Nehmen Sie die U6 Richtung...",
+            "Steigen Sie an... um",
+            "Das sind drei Stationen",
+            "Brauchen Sie eine Fahrkarte?",
+            "Zone AB reicht",
+            "Gute Fahrt!"
+        ],
+        response_style="Professional and helpful with public transport",
+        location_context="U-Bahn station information desk",
+        scenario_title="U-Bahn Help",
+        scenario_description="You're at a Berlin U-Bahn station asking for directions and transport information. Practice asking about public transport in German.",
+        scenario_challenge="Understanding German public transport terminology, directions, and ticket system.",
+        scenario_goal="Get directions and buy appropriate ticket",
+        goal_items=[
+            GoalItem(
+                id="ask_directions",
+                description="Ask for directions (Nach dem Weg fragen)"
+            ),
+            GoalItem(
+                id="buy_ticket",
+                description="Buy appropriate ticket (Passende Fahrkarte kaufen)"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(native="Wie komme ich nach...?", english="How do I get to...?"),
+            HelpfulPhrase(native="Welche Linie muss ich nehmen?", english="Which line do I need to take?"),
+            HelpfulPhrase(native="Wo muss ich umsteigen?", english="Where do I need to change?"),
+            HelpfulPhrase(native="Wie viele Stationen?", english="How many stations?"),
+            HelpfulPhrase(native="Welche Fahrkarte brauche ich?", english="Which ticket do I need?"),
+            HelpfulPhrase(native="Einzelfahrkarte", english="Single ticket"),
+            HelpfulPhrase(native="Tageskarte", english="Day ticket"),
+            HelpfulPhrase(native="Richtung", english="Direction")
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=False
+    )
+}
+
+# Dictionary to easily access personalities by scenario
+SCENARIO_PERSONALITIES = {
+    "spati": SPATI_PERSONALITIES,
+    "wg_viewing": WG_PERSONALITIES,
+    "burgeramt": BURGERAMT_PERSONALITIES,
+    "biergarten": BIERGARTEN_PERSONALITIES,
+    "ubahn": UBAHN_PERSONALITIES
+}

backend/languages/german/services.py

@@ -0,0 +1,138 @@
+import logging
+from typing import Dict, Any
+from google.cloud import texttospeech
+
+from core.speech_service import TextToSpeechService, BaseAIConversationService, BaseConversationFlowService
+from .models import SCENARIO_PERSONALITIES, GermanPersonality
+
+logger = logging.getLogger(__name__)
+
+class GermanTextToSpeechService(TextToSpeechService):
+    def __init__(self):
+        super().__init__(language_code="de-DE")
+    
+    def _get_voice_config(self, gender: str, character_name: str = None) -> Dict[str, Any]:
+        """Get German-specific voice configuration."""
+        tts_gender = self.gender_map.get(gender, texttospeech.SsmlVoiceGender.FEMALE)
+        
+        # Character-specific German voices using Chirp3-HD models
+        character_voice_map = {
+            "Mehmet": {
+                "name": "de-DE-Chirp3-HD-Charon",  # Male voice with slight accent
+                "speaking_rate": 0.95,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            "Lisa": {
+                "name": "de-DE-Chirp3-HD-Kore",  # Young female voice
+                "speaking_rate": 1.05,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Frau Schmidt": {
+                "name": "de-DE-Chirp3-HD-Zephyr",  # Formal female voice
+                "speaking_rate": 0.9,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Klaus": {
+                "name": "de-DE-Chirp3-HD-Puck",  # Cheerful male voice
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            "BVG Mitarbeiter": {
+                "name": "de-DE-Chirp3-HD-Fenrir",  # Professional male voice
+                "speaking_rate": 0.95,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            }
+        }
+        
+        # Generic German voices by gender using Chirp3-HD models
+        gender_voice_fallback = {
+            texttospeech.SsmlVoiceGender.MALE: {
+                "name": "de-DE-Chirp3-HD-Charon",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            texttospeech.SsmlVoiceGender.FEMALE: {
+                "name": "de-DE-Chirp3-HD-Kore",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            }
+        }
+        
+        if character_name and character_name in character_voice_map:
+            config_set = character_voice_map[character_name]
+            logger.info(f"Using character-specific German voice for '{character_name}': {config_set['name']}")
+            return config_set
+        
+        config_set = gender_voice_fallback.get(tts_gender, gender_voice_fallback[texttospeech.SsmlVoiceGender.FEMALE])
+        logger.info(f"Using German gender fallback voice for {tts_gender}: {config_set['name']}")
+        return config_set
+
+class GermanAIConversationService(BaseAIConversationService):
+    def __init__(self):
+        super().__init__(language_code="de")
+
+    def get_personality_for_scenario(self, scenario: str, character_name: str = None) -> GermanPersonality:
+        """Get German personality based on scenario and character name."""
+        if scenario in SCENARIO_PERSONALITIES:
+            personalities = SCENARIO_PERSONALITIES[scenario]
+            if character_name and character_name in personalities:
+                return personalities[character_name]
+            else:
+                return list(personalities.values())[0]
+        
+        # Return default personality if scenario not found
+        from .models import GermanPersonality, CharacterType, Gender, PersonalityTone, GoalItem, HelpfulPhrase
+        return GermanPersonality(
+            character_type=CharacterType.GENERIC,
+            name="Herr/Frau Müller",
+            gender=Gender.FEMALE,
+            tone=PersonalityTone.FRIENDLY,
+            age_range="middle-aged",
+            background="Helpful Berlin resident",
+            typical_phrases=["Hallo!", "Wie geht's?", "Kann ich helfen?"],
+            response_style="Friendly and helpful",
+            location_context="Berlin",
+            scenario_title="General Conversation",
+            scenario_description="General German conversation practice",
+            scenario_challenge="Practice basic German conversation",
+            scenario_goal="Have a natural conversation in German",
+            goal_items=[],
+            helpful_phrases=[],
+            is_helpful=True,
+            is_talkative=True
+        )
+
+class GermanConversationFlowService(BaseConversationFlowService):
+    def __init__(self):
+        super().__init__(language_code="de-DE")
+        self.tts_service = GermanTextToSpeechService()
+        self.ai_service = GermanAIConversationService()
+
+    def extract_scenario_from_context(self, context: str) -> str:
+        """Extract scenario type from context string."""
+        logger.info(f"Extracting German scenario from context: '{context}'")
+        context_lower = context.lower()
+        
+        detected_scenario = None
+        if "spati" in context_lower or "späti" in context_lower or "convenience" in context_lower:
+            detected_scenario = "spati"
+        elif "wg" in context_lower or "room" in context_lower or "apartment" in context_lower:
+            detected_scenario = "wg_viewing"
+        elif "bürgeramt" in context_lower or "burgeramt" in context_lower or "registration" in context_lower:
+            detected_scenario = "burgeramt"
+        elif "biergarten" in context_lower or "beer" in context_lower or "restaurant" in context_lower:
+            detected_scenario = "biergarten"
+        elif "ubahn" in context_lower or "u-bahn" in context_lower or "transport" in context_lower:
+            detected_scenario = "ubahn"
+        else:
+            detected_scenario = "spati"  # Default to späti
+            
+        logger.info(f"Detected German scenario: '{detected_scenario}'")
+        return detected_scenario

backend/languages/indonesian/config.py

@@ -0,0 +1,65 @@
+import os
+from typing import List
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+class Config:
+    """Configuration settings loaded from environment variables."""
+    
+    # Google Cloud Configuration
+    GOOGLE_APPLICATION_CREDENTIALS: str = os.getenv("GOOGLE_APPLICATION_CREDENTIALS", "")
+    GOOGLE_CLOUD_PROJECT: str = os.getenv("GOOGLE_CLOUD_PROJECT", "")
+    
+    # OpenAI Configuration
+    OPENAI_API_KEY: str = os.getenv("OPENAI_API_KEY", "")
+    OPENAI_MODEL: str = os.getenv("OPENAI_MODEL", "gpt-4o-mini")
+    
+    # Speech-to-Text Configuration
+    SPEECH_LANGUAGE_CODE: str = os.getenv("SPEECH_LANGUAGE_CODE", "id-ID")
+    SPEECH_SAMPLE_RATE: int = int(os.getenv("SPEECH_SAMPLE_RATE", "48000"))
+    SPEECH_ENCODING: str = os.getenv("SPEECH_ENCODING", "WEBM_OPUS")
+    
+    # Text-to-Speech Configuration
+    TTS_LANGUAGE_CODE: str = os.getenv("TTS_LANGUAGE_CODE", "id-ID")
+    TTS_VOICE_NAME: str = os.getenv("TTS_VOICE_NAME", "id-ID-Standard-A")
+    TTS_VOICE_GENDER: str = os.getenv("TTS_VOICE_GENDER", "FEMALE")
+    TTS_SPEAKING_RATE: float = float(os.getenv("TTS_SPEAKING_RATE", "1.0"))
+    TTS_PITCH: float = float(os.getenv("TTS_PITCH", "0.0"))
+    
+    # Server Configuration
+    HOST: str = os.getenv("HOST", "0.0.0.0")
+    PORT: int = int(os.getenv("PORT", "8000"))
+    DEBUG: bool = os.getenv("DEBUG", "false").lower() == "true"
+    
+    # CORS Configuration
+    CORS_ORIGINS: List[str] = [
+        origin.strip() 
+        for origin in os.getenv("CORS_ORIGINS", "http://localhost:3000,http://localhost:5173").split(",")
+    ]
+    
+    @classmethod
+    def validate(cls) -> None:
+        """Validate required environment variables are set."""
+        required_vars = [
+            ("OPENAI_API_KEY", cls.OPENAI_API_KEY),
+        ]
+        
+        missing_vars = []
+        for var_name, var_value in required_vars:
+            if not var_value:
+                missing_vars.append(var_name)
+        
+        if missing_vars:
+            raise ValueError(f"Missing required environment variables: {', '.join(missing_vars)}")
+        
+        # Warn about optional but recommended variables
+        if not cls.GOOGLE_APPLICATION_CREDENTIALS:
+            print("Warning: GOOGLE_APPLICATION_CREDENTIALS not set. Speech features may not work.")
+        
+        if not cls.GOOGLE_CLOUD_PROJECT:
+            print("Warning: GOOGLE_CLOUD_PROJECT not set. Some Google Cloud features may not work.")
+
+# Global config instance
+config = Config()

backend/languages/indonesian/models.py

@@ -0,0 +1,354 @@
+from enum import Enum
+from typing import List
+from core.base_models import BasePersonality, CharacterType, PersonalityTone, Gender, GoalItem, HelpfulPhrase
+
+class IndonesianPersonality(BasePersonality):
+    def __init__(self, **data):
+        data['language_code'] = "id"
+        data['country_code'] = "Indonesia"
+        super().__init__(**data)
+    
+    def get_system_prompt(self, scenario_context: str = "") -> str:
+        """Generate a system prompt for Indonesian conversations."""
+        indonesian_instructions = """
+- Use "gak" instead of "tidak", "udah" instead of "sudah", etc.
+- Sound like real Indonesian street conversation
+- Be casual and natural like real Indonesian people
+- Use common Indonesian contractions and informal speech
+"""
+        
+        return super().get_system_prompt(scenario_context, indonesian_instructions)
+
+# Convert existing models to use new structure  
+from pydantic import BaseModel
+
+
+
+
+class Personality(BaseModel):
+    character_type: CharacterType
+    name: str
+    gender: Gender
+    tone: PersonalityTone
+    age_range: str
+    background: str
+    typical_phrases: List[str]
+    response_style: str
+    location_context: str
+    
+    scenario_title: str
+    scenario_description: str
+    scenario_challenge: str
+    scenario_goal: str
+    goal_items: List[GoalItem]
+    helpful_phrases: List[HelpfulPhrase]
+    is_impatient: bool = False
+    is_helpful: bool = True
+    is_talkative: bool = True
+    uses_slang: bool = False
+    
+    def get_system_prompt(self, scenario_context: str = "") -> str:
+        """Generate a system prompt based on this personality."""
+        casualness_note = """
+SPEAKING STYLE - BE VERY CASUAL AND NATURAL:
+- Use everyday Indonesian like real people do
+- Drop formal words when people actually don't use them
+- Use contractions and casual speech patterns
+- Speak like you're talking to a friend or regular customer
+- Don't be overly polite or formal - be natural and relaxed
+- Use "gak" instead of "tidak", "udah" instead of "sudah", etc.
+- Sound like real Indonesian street conversation
+"""
+        
+        interaction_guide = ""
+        if self.character_type == CharacterType.VENDOR:
+            interaction_guide = """
+INTERACTION FLOW:
+- Greet → Ask what they want → Ask details (spice, egg, etc.) → Ask for drink → Give total → Finish
+- Remember what they've already ordered - don't repeat questions
+"""
+        elif self.character_type == CharacterType.DRIVER:
+            interaction_guide = """
+INTERACTION FLOW:
+- Ask destination → Negotiate price → Mention traffic/conditions → Agree on price → Give ride instructions
+- Focus on practical transport concerns
+"""
+        elif self.character_type == CharacterType.CASHIER:
+            interaction_guide = """
+INTERACTION FLOW:
+- Greet → Ask what they're buying → Scan items → Give total → Ask about bags → Complete transaction
+- Keep it efficient and friendly
+"""
+        else:
+            interaction_guide = """
+INTERACTION FLOW:
+- Respond naturally to customer needs
+- Help them with whatever service you provide
+- Keep conversation relevant to your role
+"""
+        
+        base_prompt = f"""You are {self.name}, a real {self.character_type.value.replace('_', ' ')} in Indonesia. You talk like a normal Indonesian person - casual, natural, and relaxed.
+
+SCENARIO CONTEXT:
+📍 {self.scenario_title}
+🎯 What's happening: {self.scenario_description}
+⚡ Challenge: {self.scenario_challenge}
+🏆 Goal: {self.scenario_goal}
+
+{casualness_note}
+
+CHARACTER:
+- {self.name} ({self.age_range} {self.character_type.value.replace('_', ' ')})
+- {self.background}
+- Works at: {self.location_context}
+- Personality: {self.tone.value}, {'talkative' if self.is_talkative else 'quiet'}, {'helpful' if self.is_helpful else 'business-focused'}
+
+YOUR TYPICAL PHRASES (use these naturally):
+{chr(10).join(f'- {phrase}' for phrase in self.typical_phrases)}
+
+CRITICAL RULES - READ CONVERSATION HISTORY CAREFULLY:
+1. You are {self.name} - NOT a teacher, NOT formal, just a real person in this scenario
+2. Speak casual Indonesian like in real life - very relaxed and natural
+3. Keep responses SHORT (5-10 words max, like real conversation)
+4. READ THE CONVERSATION HISTORY ABOVE - remember what was already asked and answered
+5. NEVER repeat questions you already asked - check what was said before
+6. TRACK the interaction progress - move naturally through the process based on what's been discussed
+7. Use informal language: "gak" not "tidak", "udah" not "sudah", "gimana" not "bagaimana"
+8. Stay relevant to your role and what customers need from you in this scenario
+9. If customer already answered a question, move to the NEXT step in the process
+10. Help the customer achieve their goal: {self.scenario_goal}
+
+{interaction_guide}
+
+ADDITIONAL CONTEXT: {scenario_context}
+
+IMPORTANT: Look at the conversation history above before responding! Don't ask questions that were already answered. Continue naturally from where the conversation left off! Help them complete their goal in this scenario."""
+
+        return base_prompt
+
+WARUNG_PERSONALITIES = {
+    "pak_budi": IndonesianPersonality(
+        character_type=CharacterType.VENDOR,
+        name="Pak Budi",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="middle-aged",
+        background="Chill warung owner who knows his regular customers",
+        typical_phrases=[
+            "Mau apa?",
+            "Pedes gak?",
+            "Telur ditambahin?",
+            "Minum apa?",
+            "Tunggu ya",
+            "Udah jadi nih",
+            "Berapa ribu ya...",
+            "Makasih Bos"
+        ],
+        response_style="Quick and casual, gets straight to the point",
+        location_context="Small warung near campus",
+        scenario_title="At a Warung",
+        scenario_description="You're at a local Indonesian warung (small restaurant) trying to order food and drinks. Practice ordering in Indonesian and navigating the casual dining experience.",
+        scenario_challenge="Understanding local food terminology, spice levels, and casual Indonesian conversation patterns. The owner speaks quickly and uses informal language.",
+        scenario_goal="Order nasi goreng pedas and teh manis",
+        goal_items=[
+            {"id": "order_nasi_goreng", "description": "Order nasi goreng pedas"},
+            {"id": "order_drink", "description": "Order teh manis"}
+        ],
+        helpful_phrases=[
+            {"native": "Saya mau...", "english": "I want..."},
+            {"native": "Berapa harganya?", "english": "How much?"},
+            {"native": "Terima kasih", "english": "Thank you"},
+            {"native": "Pedas", "english": "Spicy"},
+            {"native": "Teh manis", "english": "Sweet tea"},
+            {"native": "Nasi goreng", "english": "Fried rice"}
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=True
+    ),
+    
+    "ibu_sari": IndonesianPersonality(
+        character_type=CharacterType.VENDOR,
+        name="Ibu Sari",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CHEERFUL,
+        age_range="middle-aged",
+        background="Friendly warung owner who likes to chat with customers",
+        typical_phrases=[
+            "Eh, mau apa Dek?",
+            "Udah laper ya?",
+            "Pedes level berapa?",
+            "Es teh manis?",
+            "Sebentar ya Dek",
+            "Nih, masih panas",
+            "Hati-hati ya"
+        ],
+        response_style="Friendly but not overly formal, treats customers warmly",
+        location_context="Busy warung in residential area",
+        scenario_title="At a Warung",
+        scenario_description="You're at a local Indonesian warung (small restaurant) trying to order food and drinks. Practice ordering in Indonesian and navigating the casual dining experience.",
+        scenario_challenge="Understanding local food terminology, spice levels, and casual Indonesian conversation patterns. The owner is chatty and may engage in small talk.",
+        scenario_goal="Order nasi goreng pedas and teh manis",
+        goal_items=[
+            {"id": "order_nasi_goreng", "description": "Order nasi goreng pedas"},
+            {"id": "order_drink", "description": "Order teh manis"}
+        ],
+        helpful_phrases=[
+            {"native": "Saya mau...", "english": "I want..."},
+            {"native": "Berapa harganya?", "english": "How much?"},
+            {"native": "Terima kasih", "english": "Thank you"},
+            {"native": "Pedas", "english": "Spicy"},
+            {"native": "Teh manis", "english": "Sweet tea"},
+            {"native": "Nasi goreng", "english": "Fried rice"}
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+OJEK_PERSONALITIES = {
+    "mbak_sari": IndonesianPersonality(
+        character_type=CharacterType.DRIVER,
+        name="Mbak Sari",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="young",
+        background="Smart ojek driver who knows how to negotiate",
+        typical_phrases=[
+            "Kemana Mas?",
+            "Wah macet nih",
+            "Bensin naik lagi",
+            "Udah deket kok",
+            "Pegang yang kuat",
+            "Sampai deh",
+            "Ati-ati ya",
+            "Jangan bilang-bilang"
+        ],
+        response_style="Direct and business-minded, mentions practical concerns",
+        location_context="Busy street corner",
+        scenario_title="Taking an Ojek",
+        scenario_description="You need to get a motorcycle taxi (ojek) to take you to the mall. Practice negotiating destination and price in Indonesian.",
+        scenario_challenge="Learning transportation vocabulary, price negotiation, and understanding Jakarta traffic concerns. The driver may try to charge tourist prices.",
+        scenario_goal="Negotiate ride to mall and agree on price",
+        goal_items=[
+            {"id": "state_destination", "description": "Tell destination (mall)"},
+            {"id": "agree_price", "description": "Agree on price"}
+        ],
+        helpful_phrases=[
+            {"native": "Ke mall berapa?", "english": "How much to the mall?"},
+            {"native": "Mahal banget!", "english": "That's too expensive!"},
+            {"native": "Lima belas ribu boleh?", "english": "Is 15 thousand OK?"},
+            {"native": "Ayo!", "english": "Let's go!"},
+            {"native": "Ke mall", "english": "To the mall"},
+            {"native": "Berapa ongkosnya?", "english": "How much is the fare?"}
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+CASHIER_PERSONALITIES = {
+    "adik_kasir": IndonesianPersonality(
+        character_type=CharacterType.CASHIER,
+        name="Adik Kasir",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="young",
+        background="Young cashier who's chill and helpful",
+        typical_phrases=[
+            "Malam Kak",
+            "Beli apa?",
+            "Yang lain?",
+            "Pake kantong?",
+            "Total sekian",
+            "Kembaliannya",
+            "Makasih ya",
+            "Ati-ati"
+        ],
+        response_style="Quick and efficient, gets the job done",
+        location_context="Alfamart convenience store",
+        scenario_title="At Alfamart",
+        scenario_description="You're shopping at Alfamart, a popular Indonesian convenience store chain. Practice buying everyday items and completing a transaction in Indonesian.",
+        scenario_challenge="Understanding convenience store vocabulary, payment interactions, and polite customer service language. Learn about Indonesian instant noodle brands and local products.",
+        scenario_goal="Buy Indomie and mineral water",
+        goal_items=[
+            {"id": "buy_indomie", "description": "Buy Indomie"},
+            {"id": "buy_water", "description": "Buy mineral water"}
+        ],
+        helpful_phrases=[
+            {"native": "Saya mau beli...", "english": "I want to buy..."},
+            {"native": "Berapa totalnya?", "english": "How much is the total?"},
+            {"native": "Pake kantong", "english": "With a bag"},
+            {"native": "Bayar cash", "english": "Pay with cash"},
+            {"native": "Indomie", "english": "Indomie (instant noodles)"},
+            {"native": "Air mineral", "english": "Mineral water"}
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=True
+    )
+}
+
+COFFEE_SHOP_PERSONALITIES = {
+    "tetangga_ali": IndonesianPersonality(
+        character_type=CharacterType.GENERIC,
+        name="Tetangga Ali",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CHATTY,
+        age_range="middle-aged",
+        background="Friendly neighborhood guy who loves chatting with everyone about everything",
+        typical_phrases=[
+            "Eh, apa kabar?",
+            "Lagi ngapain nih?",
+            "Cuacanya panas banget ya hari ini",
+            "Udah makan belum?",
+            "Gimana kabar keluarga?",
+            "Kerja dimana sekarang?",
+            "Udah lama gak ketemu",
+            "Wah, sibuk banget ya",
+            "Ngomong-ngomong...",
+            "Oh iya, tau gak...",
+            "Kemarin aku ke...",
+            "Eh, kamu pernah ke...?"
+        ],
+        response_style="Very talkative, asks lots of questions, shares stories, makes connections to random topics",
+        location_context="Local coffee shop in residential area",
+        scenario_title="Coffee Shop Small Talk",
+        scenario_description="You're at a local coffee shop and meet a very friendly neighbor who loves to chat. Practice making small talk in Indonesian - discussing weather, family, work, hobbies, and daily life.",
+        scenario_challenge="Learn natural small talk patterns, question-asking, and how to keep conversations flowing in Indonesian. Practice responding to personal questions and sharing about yourself.",
+        scenario_goal="Have a natural small talk conversation covering at least 3 different topics",
+        goal_items=[
+            {"id": "greet_and_respond", "description": "Exchange greetings and ask how each other is doing"},
+            {"id": "discuss_weather_daily_life", "description": "Talk about weather, daily activities, or current situation"},
+            {"id": "share_personal_info", "description": "Share something about yourself (work, family, hobbies, etc.)"},
+            {"id": "ask_followup_questions", "description": "Ask follow-up questions to keep the conversation going"}
+        ],
+        helpful_phrases=[
+            {"native": "Apa kabar?", "english": "How are you?"},
+            {"native": "Baik-baik aja", "english": "I'm doing fine"},
+            {"native": "Lagi ngapain?", "english": "What are you up to?"},
+            {"native": "Cuacanya panas ya", "english": "The weather is hot, isn't it?"},
+            {"native": "Udah makan belum?", "english": "Have you eaten yet?"},
+            {"native": "Gimana kabar keluarga?", "english": "How's the family?"},
+            {"native": "Kerja dimana?", "english": "Where do you work?"},
+            {"native": "Ngomong-ngomong...", "english": "By the way..."},
+            {"native": "Oh iya...", "english": "Oh yes..."},
+            {"native": "Wah, menarik!", "english": "Wow, interesting!"},
+            {"native": "Bener juga ya", "english": "That's true"},
+            {"native": "Udah lama gak ketemu", "english": "Haven't seen you in a while"}
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        is_impatient=False,
+        uses_slang=True
+    )
+}
+
+SCENARIO_PERSONALITIES = {
+    "warung": WARUNG_PERSONALITIES,
+    "ojek": OJEK_PERSONALITIES,
+    "alfamart": CASHIER_PERSONALITIES,
+    "coffee_shop": COFFEE_SHOP_PERSONALITIES
+}

backend/languages/indonesian/services.py

@@ -0,0 +1,136 @@
+import logging
+from typing import Dict, Any
+from google.cloud import texttospeech
+
+from core.speech_service import TextToSpeechService, BaseAIConversationService, BaseConversationFlowService
+from .models import SCENARIO_PERSONALITIES, Personality
+
+logger = logging.getLogger(__name__)
+
+class IndonesianTextToSpeechService(TextToSpeechService):
+    def __init__(self):
+        super().__init__(language_code="id-ID")
+    
+    def _get_voice_config(self, gender: str, character_name: str = None) -> Dict[str, Any]:
+        """Get Indonesian-specific voice configuration."""
+        tts_gender = self.gender_map.get(gender, texttospeech.SsmlVoiceGender.FEMALE)
+        
+        character_voice_map = {
+            "Pak Budi": {
+                "name": "id-ID-Chirp3-HD-Charon",
+                "speaking_rate": 0.95,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            "Ibu Sari": {
+                "name": "id-ID-Chirp3-HD-Kore",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Mbak Sari": {
+                "name": "id-ID-Chirp3-HD-Zephyr",
+                "speaking_rate": 1.1,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Adik Kasir": {
+                "name": "id-ID-Chirp3-HD-Aoede",
+                "speaking_rate": 1.05,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Tetangga Ali": {
+                "name": "id-ID-Chirp3-HD-Puck",
+                "speaking_rate": 1.05,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            }
+        }
+        
+        gender_voice_fallback = {
+            texttospeech.SsmlVoiceGender.MALE: {
+                "name": "id-ID-Chirp3-HD-Fenrir",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            texttospeech.SsmlVoiceGender.FEMALE: {
+                "name": "id-ID-Chirp3-HD-Leda",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            }
+        }
+        
+        if character_name and character_name in character_voice_map:
+            config_set = character_voice_map[character_name]
+            logger.info(f"Using character-specific voice for '{character_name}': {config_set['name']}")
+            return config_set
+        
+        config_set = gender_voice_fallback.get(tts_gender, gender_voice_fallback[texttospeech.SsmlVoiceGender.FEMALE])
+        logger.info(f"Using gender fallback voice for {tts_gender}: {config_set['name']}")
+        return config_set
+
+class IndonesianAIConversationService(BaseAIConversationService):
+    def __init__(self):
+        super().__init__(language_code="id")
+
+    def get_personality_for_scenario(self, scenario: str, character_name: str = None) -> Personality:
+        """Get Indonesian personality based on scenario and character name."""
+        if scenario in SCENARIO_PERSONALITIES:
+            personalities = SCENARIO_PERSONALITIES[scenario]
+            if character_name and character_name in personalities:
+                return personalities[character_name]
+            else:
+                return list(personalities.values())[0]
+        
+        # Return default personality if scenario not found
+        from .models import Personality, CharacterType, Gender, PersonalityTone, GoalItem, HelpfulPhrase
+        return Personality(
+            character_type=CharacterType.GENERIC,
+            name="Pak/Bu",
+            gender=Gender.FEMALE,
+            tone=PersonalityTone.FRIENDLY,
+            age_range="middle-aged",
+            background="Helpful Indonesian person",
+            typical_phrases=["Halo!", "Apa kabar?", "Bisa saya bantu?"],
+            response_style="Friendly and helpful",
+            location_context="Indonesia",
+            scenario_title="General Conversation",
+            scenario_description="General Indonesian conversation practice",
+            scenario_challenge="Practice basic Indonesian conversation",
+            scenario_goal="Have a natural conversation",
+            goal_items=[],
+            helpful_phrases=[],
+            language_code="id",
+            country_code="Indonesia",
+            is_helpful=True,
+            is_talkative=True
+        )
+
+class IndonesianConversationFlowService(BaseConversationFlowService):
+    def __init__(self):
+        super().__init__(language_code="id-ID")
+        self.tts_service = IndonesianTextToSpeechService()
+        self.ai_service = IndonesianAIConversationService()
+
+    def extract_scenario_from_context(self, context: str) -> str:
+        """Extract scenario type from context string."""
+        logger.info(f"Extracting scenario from context: '{context}'")
+        context_lower = context.lower()
+        
+        detected_scenario = None
+        if "coffee_shop" in context_lower or "coffee" in context_lower:
+            detected_scenario = "coffee_shop"
+        elif "warung" in context_lower or "nasi goreng" in context_lower:
+            detected_scenario = "warung"
+        elif "ojek" in context_lower or "mall" in context_lower:
+            detected_scenario = "ojek"
+        elif "alfamart" in context_lower or "indomie" in context_lower:
+            detected_scenario = "alfamart"
+        else:
+            detected_scenario = "warung"  # Default to warung
+            
+        logger.info(f"Detected scenario: '{detected_scenario}'")
+        return detected_scenario

backend/main.py

@@ -0,0 +1,818 @@
+import difflib
+import re
+import json
+import base64
+import logging
+import time
+from typing import Dict, Any, List
+
+from fastapi import FastAPI, HTTPException, WebSocket, WebSocketDisconnect
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+from google.cloud import speech
+import openai
+
+from languages.indonesian.services import IndonesianConversationFlowService
+from languages.german.services import GermanConversationFlowService
+from config import config
+
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+app = FastAPI()
+
+config.validate()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Temporarily allow all origins for debugging
+    allow_credentials=False,  # Set to False when using allow_origins=["*"]
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# Language-specific services
+language_services = {
+    "indonesian": IndonesianConversationFlowService(),
+    "german": GermanConversationFlowService()
+}
+
+class ResponseCheck(BaseModel):
+    user_response: str
+    expected_response: str
+    scenario: str
+
+
+class ResponseResult(BaseModel):
+    is_correct: bool
+    feedback: str
+    similarity: float
+
+class TranslationRequest(BaseModel):
+    text: str
+    source_language: str
+    target_language: str
+
+class TranslationResult(BaseModel):
+    translation: str
+    source_text: str
+
+class SuggestionRequest(BaseModel):
+    language: str
+    scenario: str
+    conversation_history: List[Dict[str, str]]
+
+class SuggestionResponse(BaseModel):
+    intro: str
+    suggestions: List[Dict[str, str]]
+
+class ConversationFeedbackRequest(BaseModel):
+    language: str
+    scenario: str
+    conversation_history: List[Dict[str, str]]
+
+class ConversationFeedbackResponse(BaseModel):
+    encouragement: str
+    suggestions: List[Dict[str, str]]
+    examples: List[Dict[str, str]]
+
+def normalize_text(text: str) -> str:
+    text = text.lower().strip()
+    text = re.sub(r"[^\w\s]", "", text)
+    text = re.sub(r"\s+", " ", text)
+    return text
+
+def calculate_similarity(text1: str, text2: str) -> float:
+    normalized1 = normalize_text(text1)
+    normalized2 = normalize_text(text2)
+    return difflib.SequenceMatcher(None, normalized1, normalized2).ratio()
+
+def generate_feedback(
+    user_response: str, expected_response: str, similarity: float, scenario: str
+) -> str:
+    if similarity >= 0.9:
+        return "Perfect! Excellent Indonesian!"
+    elif similarity >= 0.7:
+        return "Great job! That's correct!"
+    elif similarity >= 0.5:
+        return f"Good attempt! Try: '{expected_response}'"
+    elif similarity >= 0.3:
+        return f"Close, but try again. Expected: '{expected_response}'"
+    else:
+        return f"Not quite right. The correct answer is: '{expected_response}'"
+
+@app.post("/api/check-response", response_model=ResponseResult)
+async def check_response(request: ResponseCheck) -> ResponseResult:
+    """Check user response against expected response."""
+    try:
+        similarity = calculate_similarity(request.user_response, request.expected_response)
+        is_correct = similarity >= 0.7
+        feedback = generate_feedback(
+            request.user_response,
+            request.expected_response,
+            similarity,
+            request.scenario,
+        )
+
+        return ResponseResult(
+            is_correct=is_correct,
+            feedback=feedback,
+            similarity=similarity,
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e)) from e
+
+@app.get("/api/scenarios/{language}")
+async def get_scenarios(language: str) -> dict:
+    """Get scenarios for a specific language (indonesian or german)"""
+    if language == "indonesian":
+        from languages.indonesian.models import SCENARIO_PERSONALITIES
+        native_key = "indonesian"
+    elif language == "german":
+        from languages.german.models import SCENARIO_PERSONALITIES
+        native_key = "native"
+    else:
+        raise HTTPException(status_code=400, detail="Unsupported language")
+    
+    scenarios = {}
+    
+    for scenario_id, personalities in SCENARIO_PERSONALITIES.items():
+        default_personality = list(personalities.values())[0]
+        
+        scenarios[scenario_id] = {
+            "id": scenario_id,
+            "title": default_personality.scenario_title,
+            "description": default_personality.scenario_description,
+            "challenge": default_personality.scenario_challenge,
+            "goal": default_personality.scenario_goal,
+            "character": default_personality.name,
+            "character_background": default_personality.background,
+            "character_gender": default_personality.gender.value,
+            "location": default_personality.location_context,
+            "language": language,
+            "goal_items": [
+                {
+                    "id": item.id,
+                    "description": item.description,
+                    "completed": False
+                } for item in default_personality.goal_items
+            ],
+            "helpful_phrases": [
+                {
+                    native_key: phrase.native if hasattr(phrase, 'native') else phrase.indonesian,
+                    "english": phrase.english
+                } for phrase in default_personality.helpful_phrases
+            ],
+            "available_characters": [
+                {
+                    "id": char_id,
+                    "name": char.name,
+                    "background": char.background,
+                    "tone": char.tone.value,
+                    "gender": char.gender.value
+                } for char_id, char in personalities.items()
+            ]
+        }
+    
+    return scenarios
+
+@app.get("/api/scenarios")
+async def get_all_scenarios() -> dict:
+    """Get all available scenarios for all languages"""
+    all_scenarios = {}
+    
+    # Get Indonesian scenarios
+    indonesian_scenarios = await get_scenarios("indonesian")
+    all_scenarios["indonesian"] = indonesian_scenarios
+    
+    # Get German scenarios
+    german_scenarios = await get_scenarios("german")
+    all_scenarios["german"] = german_scenarios
+    
+    return all_scenarios
+
+
+@app.post("/api/suggestions", response_model=SuggestionResponse)
+async def generate_suggestions(request: SuggestionRequest) -> SuggestionResponse:
+    """Generate contextual language suggestions based on conversation history."""
+    logger.info(f"Received suggestions request: language={request.language}, scenario={request.scenario}")
+    try:
+        client = openai.OpenAI(api_key=config.OPENAI_API_KEY)
+        
+        # Get recent conversation context
+        conversation_context = ""
+        for i, msg in enumerate(request.conversation_history[-4:]):
+            conversation_context += f"{msg['type'].capitalize()}: {msg['text']}\n"
+        
+        # Determine target language and context
+        if request.language == "german":
+            target_language = "German"
+            native_language = "English"
+            scenario_prompt = f"in a {request.scenario} scenario in Germany"
+        else:
+            target_language = "Indonesian"
+            native_language = "English" 
+            scenario_prompt = f"in a {request.scenario} scenario in Indonesia"
+        
+        suggestion_prompt = f"""You are a helpful language learning assistant. Based on the conversation history below, suggest 3 useful phrases the user might want to say next in {target_language}.
+
+Conversation context {scenario_prompt}:
+{conversation_context}
+
+Provide suggestions as a JSON object with:
+- "intro": A brief encouraging message about what they might want to say next
+- "suggestions": Array of 3 objects, each with:
+  - "{target_language.lower()}_text": The phrase in {target_language}
+  - "english_meaning": The English translation/meaning
+
+Make the suggestions contextual, natural, and progressively helpful for the conversation. Focus on practical phrases they might actually need.
+
+Example format:
+{{
+  "intro": "Here are some phrases you might find useful:",
+  "suggestions": [
+    {{
+      "{target_language.lower()}_text": "Example phrase",
+      "english_meaning": "English translation"
+    }}
+  ]
+}}"""
+        
+        response = client.chat.completions.create(
+            model=config.OPENAI_MODEL,
+            messages=[
+                {"role": "system", "content": f"You are a helpful {target_language} language learning assistant. Always respond with valid JSON."},
+                {"role": "user", "content": suggestion_prompt}
+            ],
+            max_tokens=500,
+            temperature=0.7
+        )
+        
+        suggestion_json = response.choices[0].message.content.strip()
+        logger.info(f"AI suggestion response: {suggestion_json}")
+        
+        # Parse JSON response
+        import json
+        try:
+            # Clean up the JSON response to handle potential formatting issues
+            cleaned_json = suggestion_json.strip()
+            if cleaned_json.startswith('```json'):
+                cleaned_json = cleaned_json[7:-3].strip()
+            elif cleaned_json.startswith('```'):
+                cleaned_json = cleaned_json[3:-3].strip()
+            
+            suggestion_data = json.loads(cleaned_json)
+            return SuggestionResponse(
+                intro=suggestion_data.get("intro", "Here are some helpful phrases:"),
+                suggestions=suggestion_data.get("suggestions", [])
+            )
+        except json.JSONDecodeError as e:
+            logger.error(f"JSON decode error: {str(e)} for content: {cleaned_json}")
+            # Fallback if JSON parsing fails
+            text_key = f"{target_language.lower()}_text"
+            fallback_suggestions = [
+                {
+                    text_key: "Excuse me, can you help me?",
+                    "english_meaning": "A polite way to ask for assistance"
+                },
+                {
+                    text_key: "Thank you very much",
+                    "english_meaning": "Express gratitude"
+                },
+                {
+                    text_key: "I don't understand",
+                    "english_meaning": "When you need clarification"
+                }
+            ]
+            return SuggestionResponse(
+                intro="Here are some helpful phrases:",
+                suggestions=fallback_suggestions
+            )
+        
+    except Exception as e:
+        logger.error(f"Suggestion generation error: {str(e)}")
+        # Return fallback suggestions instead of raising an error
+        return SuggestionResponse(
+            intro="Here are some helpful phrases:",
+            suggestions=[
+                {
+                    "german_text" if request.language == "german" else "indonesian_text": "Hello",
+                    "english_meaning": "A basic greeting"
+                },
+                {
+                    "german_text" if request.language == "german" else "indonesian_text": "Thank you",
+                    "english_meaning": "Express gratitude"
+                },
+                {
+                    "german_text" if request.language == "german" else "indonesian_text": "Please",
+                    "english_meaning": "Polite request"
+                }
+            ]
+        )
+
+@app.post("/api/translate", response_model=TranslationResult)
+async def translate_text(request: TranslationRequest) -> TranslationResult:
+    try:
+        client = openai.OpenAI(api_key=config.OPENAI_API_KEY)
+        
+        translation_prompt = f"""Translate the following Indonesian text to natural, conversational English. 
+Keep the tone and style appropriate for casual conversation.
+
+Indonesian text: "{request.text}"
+
+Provide only the English translation, nothing else."""
+
+        response = client.chat.completions.create(
+            model=config.OPENAI_MODEL,
+            messages=[
+                {"role": "system", "content": "You are a professional Indonesian to English translator. Provide natural, conversational translations."},
+                {"role": "user", "content": translation_prompt}
+            ],
+            max_tokens=200,
+            temperature=0.3
+        )
+        
+        translation = response.choices[0].message.content.strip()
+        
+        return TranslationResult(
+            translation=translation,
+            source_text=request.text
+        )
+        
+    except Exception as e:
+        logger.error(f"Translation error: {str(e)}")
+        raise HTTPException(status_code=500, detail=f"Translation failed: {str(e)}")
+
+@app.post("/api/conversation-feedback", response_model=ConversationFeedbackResponse)
+async def generate_conversation_feedback(request: ConversationFeedbackRequest) -> ConversationFeedbackResponse:
+    """Generate encouraging feedback and suggestions for completed conversation."""
+    logger.info(f"Received feedback request: language={request.language}, scenario={request.scenario}")
+    try:
+        client = openai.OpenAI(api_key=config.OPENAI_API_KEY)
+        
+        # Build conversation history
+        conversation_context = ""
+        user_messages = []
+        for msg in request.conversation_history:
+            if msg.get('type') == 'user':
+                user_messages.append(msg['text'])
+            conversation_context += f"{msg.get('type', 'unknown').capitalize()}: {msg.get('text', '')}\n"
+        
+        # Determine target language and feedback context
+        if request.language == "german":
+            target_language = "German"
+            language_specific_feedback = """
+Focus on common German language learning areas:
+- Article usage (der, die, das)
+- Verb conjugation and word order
+- Formal vs informal language (Sie vs du)
+- Separable verbs
+- Common German expressions and idioms
+"""
+        else:
+            target_language = "Indonesian"
+            language_specific_feedback = """
+Focus on common Indonesian language learning areas:
+- Formal vs informal language (using proper pronouns)
+- Sentence structure and word order
+- Common Indonesian expressions
+- Politeness levels and cultural context
+"""
+        
+        feedback_prompt = f"""You are an encouraging {target_language} language teacher. A student has just finished a conversation practice session in a {request.scenario} scenario. 
+
+Here's their conversation:
+{conversation_context}
+
+{language_specific_feedback}
+
+Provide helpful, encouraging feedback as a JSON object with:
+- "encouragement": A positive, motivating message about their effort (2-3 sentences)
+- "suggestions": Array of 2-3 objects with:
+  - "category": Area of improvement (e.g., "Pronunciation", "Grammar", "Vocabulary")
+  - "tip": Specific, actionable advice
+- "examples": Array of 1-2 objects with:
+  - "original": Something they actually said (from the conversation)
+  - "improved": A better way to say it
+  - "reason": Brief explanation of why it's better
+
+Make it encouraging and supportive, focusing on growth rather than criticism. If they did well, focus on areas to sound more natural or confident.
+
+Example format:
+{{
+  "encouragement": "You did a great job engaging in this conversation! Your effort to communicate is really paying off.",
+  "suggestions": [
+    {{
+      "category": "Vocabulary",
+      "tip": "Try using more common everyday words to sound more natural"
+    }}
+  ],
+  "examples": [
+    {{
+      "original": "I want to purchase this item",
+      "improved": "I'd like to buy this",
+      "reason": "Sounds more natural and conversational"
+    }}
+  ]
+}}"""
+        
+        response = client.chat.completions.create(
+            model=config.OPENAI_MODEL,
+            messages=[
+                {"role": "system", "content": f"You are an encouraging {target_language} language teacher. Always respond with valid JSON and be supportive."},
+                {"role": "user", "content": feedback_prompt}
+            ],
+            max_tokens=600,
+            temperature=0.7
+        )
+        
+        feedback_json = response.choices[0].message.content.strip()
+        logger.info(f"AI feedback response: {feedback_json}")
+        
+        # Parse JSON response
+        try:
+            # Clean up the JSON response
+            cleaned_json = feedback_json.strip()
+            if cleaned_json.startswith('```json'):
+                cleaned_json = cleaned_json[7:-3].strip()
+            elif cleaned_json.startswith('```'):
+                cleaned_json = cleaned_json[3:-3].strip()
+            
+            feedback_data = json.loads(cleaned_json)
+            return ConversationFeedbackResponse(
+                encouragement=feedback_data.get("encouragement", "Great job practicing! Every conversation helps you improve."),
+                suggestions=feedback_data.get("suggestions", []),
+                examples=feedback_data.get("examples", [])
+            )
+            
+        except json.JSONDecodeError as e:
+            logger.error(f"JSON decode error: {str(e)} for content: {cleaned_json}")
+            # Fallback response
+            return ConversationFeedbackResponse(
+                encouragement="Great job practicing! Every conversation helps you improve.",
+                suggestions=[
+                    {
+                        "category": "Practice",
+                        "tip": "Keep practicing regular conversations to build confidence"
+                    }
+                ],
+                examples=[]
+            )
+            
+    except Exception as e:
+        logger.error(f"Feedback generation error: {str(e)}")
+        # Return encouraging fallback
+        return ConversationFeedbackResponse(
+            encouragement="Great job practicing! Every conversation helps you improve.",
+            suggestions=[
+                {
+                    "category": "Practice",
+                    "tip": "Keep practicing regular conversations to build confidence"
+                }
+            ],
+            examples=[]
+        )
+
+@app.get("/api/health")
+async def health_check() -> dict:
+    return {"status": "healthy"}
+
+session_services: Dict[str, Any] = {}
+
+
+@app.websocket("/ws/speech/{language}")
+async def websocket_speech_endpoint(websocket: WebSocket, language: str):
+    await websocket.accept()
+    logger.info(f"WebSocket client connected for language: {language}")
+    
+    # Validate language
+    if language not in language_services:
+        await websocket.close(code=1008, reason="Unsupported language")
+        return
+    
+    audio_buffer = bytearray()
+    min_audio_length = 48000
+    is_recording = False
+    chunk_count = 0
+    latest_transcript = ""
+    recording_start_time = None
+    max_recording_duration = 60  # 60 seconds max (increased to give more time after suggestions)
+    transcript_repeat_count = 0
+    last_transcript = ""
+    high_confidence_count = 0
+    
+    import uuid
+    session_id = str(uuid.uuid4())
+    session_conversation_service = language_services[language].__class__()  # Create new instance
+    session_services[session_id] = session_conversation_service
+    
+    try:
+        while True:
+            data = await websocket.receive_text()
+            message = json.loads(data)
+            logger.info(f"Received message type: {message['type']}")
+            
+            if message["type"] == "audio_start":
+                is_recording = True
+                audio_buffer.clear()
+                chunk_count = 0
+                latest_transcript = ""
+                recording_start_time = time.time()
+                logger.info("Started recording session")
+                
+            elif message["type"] == "conversation_reset":
+                session_conversation_service.ai_service.reset_conversation()
+                logger.info("Conversation history reset")
+                
+            elif message["type"] == "audio_chunk":
+                if is_recording:
+                    # Check for recording timeout
+                    if recording_start_time and time.time() - recording_start_time > max_recording_duration:
+                        logger.warning("Recording timeout reached, auto-stopping")
+                        # Send timeout notification to frontend
+                        timeout_notification = {
+                            "type": "recording_timeout",
+                            "message": "Recording stopped due to timeout"
+                        }
+                        await websocket.send_text(json.dumps(timeout_notification))
+                        # Force audio_end processing
+                        message = {"type": "audio_end", "scenario_context": message.get("scenario_context", "")}
+                        # Don't return, let it fall through to audio_end processing
+                    else:
+                        audio_data = base64.b64decode(message["audio"])
+                        logger.info(f"Received audio chunk: {len(audio_data)} bytes")
+                        
+                        audio_buffer.extend(audio_data)
+                        logger.info(f"Audio buffer size: {len(audio_buffer)} bytes")
+                        
+                        # Process chunk for real-time transcription
+                        chunk_count += 1
+                        try:
+                            # Only process every 8th chunk to reduce log spam and API calls
+                            if chunk_count % 8 == 0 and len(audio_buffer) >= 19200:  # ~0.4 seconds of audio at 48kHz
+                                recognition_audio = speech.RecognitionAudio(content=bytes(audio_buffer))
+                                response = session_conversation_service.stt_service.client.recognize(
+                                    config=session_conversation_service.stt_service.recognition_config,
+                                    audio=recognition_audio
+                                )
+                                
+                                if response.results:
+                                    transcript = response.results[0].alternatives[0].transcript
+                                    confidence = response.results[0].alternatives[0].confidence
+                                    
+                                    # Store transcript if confidence is reasonable (lowered for speed)
+                                    if confidence > 0.6:
+                                        latest_transcript = transcript  # Store latest transcript
+                                        
+                                        # Check for repeated high-confidence transcripts
+                                        if confidence > 0.9:
+                                            if transcript == last_transcript:
+                                                high_confidence_count += 1
+                                                logger.info(f"Repeated high confidence transcript #{high_confidence_count}: '{transcript}' (confidence: {confidence})")
+                                                
+                                                # If we've seen the same high-confidence transcript 4+ times, auto-stop
+                                                if high_confidence_count >= 4:
+                                                    logger.info("Auto-stopping recording due to repeated high-confidence transcript")
+                                                    is_recording = False
+                                                    # Send final processing message
+                                                    final_message = {"type": "audio_end", "scenario_context": message.get("scenario_context", "")}
+                                                    # Process immediately without waiting for more chunks
+                                                    await websocket.send_text(json.dumps({
+                                                        "type": "transcription",
+                                                        "transcript": transcript,
+                                                        "is_final": True,
+                                                        "confidence": confidence
+                                                    }))
+                                                    
+                                                    # Process AI response
+                                                    logger.info("Getting AI response...")
+                                                    ai_response = await session_conversation_service.process_conversation_flow_fast(
+                                                        transcript, 
+                                                        message.get("scenario_context", "")
+                                                    )
+                                                    logger.info(f"AI response: {ai_response.get('text', 'No text')}")
+                                                    await websocket.send_text(json.dumps(ai_response))
+                                                    
+                                                    audio_buffer.clear()
+                                                    logger.info("Recording session ended due to repeated transcript")
+                                                    continue  # Continue to next message
+                                            else:
+                                                high_confidence_count = 1
+                                                last_transcript = transcript
+                                                logger.info(f"High confidence transcript ready: '{transcript}' (confidence: {confidence})")
+                                        else:
+                                            high_confidence_count = 0
+                                            last_transcript = ""
+                                    
+                                    transcription_result = {
+                                        "type": "transcription",
+                                        "transcript": transcript,
+                                        "is_final": False,
+                                        "confidence": confidence
+                                    }
+                                    await websocket.send_text(json.dumps(transcription_result))
+                                    # Only log interim transcriptions occasionally to reduce spam
+                                    if chunk_count % 16 == 0:
+                                        logger.info(f"Interim transcription: '{transcript}' (confidence: {confidence})")
+                                else:
+                                    transcription_result = {
+                                        "type": "transcription",
+                                        "transcript": "Listening...",
+                                        "is_final": False,
+                                        "confidence": 0.0
+                                    }
+                                    await websocket.send_text(json.dumps(transcription_result))
+                        except Exception as e:
+                            # Only log transcription errors occasionally to reduce spam
+                            if chunk_count % 16 == 0:
+                                logger.error(f"Real-time transcription error: {str(e)}")
+                            transcription_result = {
+                                "type": "transcription",
+                                "transcript": "Listening...",
+                                "is_final": False,
+                                "confidence": 0.0
+                            }
+                            await websocket.send_text(json.dumps(transcription_result))
+                else:
+                    # Reduce logging for non-recording chunks
+                    if chunk_count % 32 == 0:
+                        logger.info("Received audio chunk but not in recording mode")
+            
+            elif message["type"] == "audio_end":
+                is_recording = False
+                final_transcript = ""
+                
+                # Use latest interim transcript if available for faster response
+                logger.info(f"Checking latest_transcript: '{latest_transcript}'")
+                if latest_transcript.strip():
+                    final_transcript = latest_transcript
+                    logger.info(f"Using latest interim transcript: '{final_transcript}'")
+                    
+                    # Send final transcription immediately
+                    transcription_result = {
+                        "type": "transcription",
+                        "transcript": final_transcript,
+                        "is_final": True,
+                        "confidence": 0.8  # Reasonable confidence for interim result
+                    }
+                    await websocket.send_text(json.dumps(transcription_result))
+                    
+                    # Process AI response with faster flow
+                    logger.info("Getting AI response...")
+                    ai_response = await session_conversation_service.process_conversation_flow_fast(
+                        final_transcript, 
+                        message.get("scenario_context", "")
+                    )
+                    logger.info(f"AI response: {ai_response.get('text', 'No text')}")
+                    await websocket.send_text(json.dumps(ai_response))
+                    
+                    # Clear buffer
+                    audio_buffer.clear()
+                    logger.info("Recording session ended, ready for next session")
+                    
+                elif len(audio_buffer) > 0:
+                    # Fallback to full transcription if no interim results
+                    logger.info(f"Processing final audio buffer: {len(audio_buffer)} bytes")
+                    try:
+                        recognition_audio = speech.RecognitionAudio(content=bytes(audio_buffer))
+                        response = session_conversation_service.stt_service.client.recognize(
+                            config=session_conversation_service.stt_service.recognition_config,
+                            audio=recognition_audio
+                        )
+                        
+                        if response.results:
+                            transcript = response.results[0].alternatives[0].transcript
+                            confidence = response.results[0].alternatives[0].confidence
+                            
+                            logger.info(f"Final transcription: '{transcript}' (confidence: {confidence})")
+                            
+                            transcription_result = {
+                                "type": "transcription",
+                                "transcript": transcript,
+                                "is_final": True,
+                                "confidence": confidence
+                            }
+                            await websocket.send_text(json.dumps(transcription_result))
+                            
+                            logger.info("Getting AI response...")
+                            ai_response = await session_conversation_service.process_conversation_flow(
+                                transcript, 
+                                message.get("scenario_context", "")
+                            )
+                            logger.info(f"AI response: {ai_response.get('text', 'No text')}")
+                            await websocket.send_text(json.dumps(ai_response))
+                        else:
+                            logger.info("No transcription results from Google Speech")
+                            # Send empty final transcription so UI knows recording ended
+                            transcription_result = {
+                                "type": "transcription",
+                                "transcript": "",
+                                "is_final": True,
+                                "confidence": 0.0
+                            }
+                            await websocket.send_text(json.dumps(transcription_result))
+                        
+                        audio_buffer.clear()
+                        logger.info("Recording session ended, ready for next session")
+                        
+                    except Exception as e:
+                        logger.error(f"Final speech recognition error: {str(e)}")
+                        
+                        # Send empty final transcription so UI knows recording ended
+                        transcription_result = {
+                            "type": "transcription",
+                            "transcript": "",
+                            "is_final": True,
+                            "confidence": 0.0
+                        }
+                        await websocket.send_text(json.dumps(transcription_result))
+                        
+                        error_result = {
+                            "type": "error",
+                            "message": f"Speech recognition error: {str(e)}"
+                        }
+                        await websocket.send_text(json.dumps(error_result))
+                        audio_buffer.clear()
+                else:
+                    logger.info("No audio data to process")
+                    # Send empty final transcription so UI knows recording ended
+                    transcription_result = {
+                        "type": "transcription",
+                        "transcript": "",
+                        "is_final": True,
+                        "confidence": 0.0
+                    }
+                    await websocket.send_text(json.dumps(transcription_result))
+            
+            elif message["type"] == "text_message":
+                logger.info(f"Processing text message: '{message['text']}'")
+                ai_response = await session_conversation_service.process_conversation_flow(
+                    message["text"], 
+                    message.get("scenario_context", "")
+                )
+                logger.info(f"AI response: {ai_response.get('text', 'No text')}")
+                await websocket.send_text(json.dumps(ai_response))
+                
+            elif message["type"] == "initial_greeting":
+                logger.info("Processing initial greeting request")
+                ai_response = await session_conversation_service.generate_initial_greeting(
+                    message.get("scenario_context", "")
+                )
+                logger.info(f"Initial greeting: {ai_response.get('text', 'No text')}")
+                await websocket.send_text(json.dumps(ai_response))
+                
+    except WebSocketDisconnect:
+        logger.info("WebSocket client disconnected")
+    except Exception as e:
+        logger.error(f"WebSocket error: {str(e)}")
+        error_message = {
+            "type": "error",
+            "message": f"WebSocket error: {str(e)}"
+        }
+        await websocket.send_text(json.dumps(error_message))
+
+
+@app.websocket("/ws/tts")
+async def websocket_tts_endpoint(websocket: WebSocket):
+    """WebSocket endpoint for text-to-speech streaming."""
+    await websocket.accept()
+    
+    try:
+        while True:
+            data = await websocket.receive_text()
+            message = json.loads(data)
+            
+            if message["type"] == "synthesize":
+                try:
+                    # Use the default TTS service for this endpoint
+                    tts_service = language_services["indonesian"].tts_service
+                    audio_content = await tts_service.synthesize_speech(message["text"])
+                    audio_base64 = base64.b64encode(audio_content).decode('utf-8')
+                    
+                    response = {
+                        "type": "audio",
+                        "audio": audio_base64,
+                        "format": "mp3"
+                    }
+                    await websocket.send_text(json.dumps(response))
+                except Exception as e:
+                    error_response = {
+                        "type": "error",
+                        "message": f"TTS error: {str(e)}"
+                    }
+                    await websocket.send_text(json.dumps(error_response))
+                    
+    except WebSocketDisconnect:
+        print("TTS client disconnected")
+    except Exception as e:
+        error_message = {
+            "type": "error",
+            "message": f"TTS WebSocket error: {str(e)}"
+        }
+        await websocket.send_text(json.dumps(error_message))
+
+
+if __name__ == "__main__":
+    import uvicorn
+
+    uvicorn.run(app, host=config.HOST, port=config.PORT, log_level="debug" if config.DEBUG else "info")

backend/models.py

@@ -0,0 +1,398 @@
+from pydantic import BaseModel
+from typing import List, Optional, Dict
+from enum import Enum
+
+class HelpfulPhrase(BaseModel):
+    indonesian: str
+    english: str
+
+class CharacterType(str, Enum):
+    WARUNG_OWNER = "warung_owner"
+    OJEK_DRIVER = "ojek_driver"
+    CASHIER = "cashier"
+    HOTEL_RECEPTIONIST = "hotel_receptionist"
+    MARKET_VENDOR = "market_vendor"
+    GENERIC = "generic"
+
+class PersonalityTone(str, Enum):
+    FRIENDLY = "friendly"
+    CASUAL = "casual"
+    FORMAL = "formal"
+    CHEERFUL = "cheerful"
+    BUSINESS_LIKE = "business_like"
+    SLEEPY = "sleepy"
+    CHATTY = "chatty"
+
+class Gender(str, Enum):
+    MALE = "male"
+    FEMALE = "female"
+
+class GoalItem(BaseModel):
+    id: str
+    description: str
+    keywords: List[str] = []
+    completed: bool = False
+
+class Personality(BaseModel):
+    character_type: CharacterType
+    name: str
+    gender: Gender
+    tone: PersonalityTone
+    age_range: str
+    background: str
+    typical_phrases: List[str]
+    response_style: str
+    location_context: str
+    
+    scenario_title: str
+    scenario_description: str
+    scenario_challenge: str
+    scenario_goal: str
+    goal_items: List[GoalItem]
+    helpful_phrases: List[HelpfulPhrase]
+    is_impatient: bool = False
+    is_helpful: bool = True
+    is_talkative: bool = True
+    uses_slang: bool = False
+    
+    def get_system_prompt(self, scenario_context: str = "") -> str:
+        """Generate a system prompt based on this personality."""
+        casualness_note = """
+SPEAKING STYLE - BE VERY CASUAL AND NATURAL:
+- Use everyday Indonesian like real people do
+- Drop formal words when people actually don't use them
+- Use contractions and casual speech patterns
+- Speak like you're talking to a friend or regular customer
+- Don't be overly polite or formal - be natural and relaxed
+- Use "gak" instead of "tidak", "udah" instead of "sudah", etc.
+- Sound like real Indonesian street conversation
+"""
+        
+        interaction_guide = ""
+        if self.character_type == CharacterType.WARUNG_OWNER:
+            interaction_guide = """
+INTERACTION FLOW:
+- Greet → Ask what they want → Ask details (spice, egg, etc.) → Ask for drink → Give total → Finish
+- Remember what they've already ordered - don't repeat questions
+"""
+        elif self.character_type == CharacterType.OJEK_DRIVER:
+            interaction_guide = """
+INTERACTION FLOW:
+- Ask destination → Negotiate price → Mention traffic/conditions → Agree on price → Give ride instructions
+- Focus on practical transport concerns
+"""
+        elif self.character_type == CharacterType.CASHIER:
+            interaction_guide = """
+INTERACTION FLOW:
+- Greet → Ask what they're buying → Scan items → Give total → Ask about bags → Complete transaction
+- Keep it efficient and friendly
+"""
+        else:
+            interaction_guide = """
+INTERACTION FLOW:
+- Respond naturally to customer needs
+- Help them with whatever service you provide
+- Keep conversation relevant to your role
+"""
+        
+        base_prompt = f"""You are {self.name}, a real {self.character_type.value.replace('_', ' ')} in Indonesia. You talk like a normal Indonesian person - casual, natural, and relaxed.
+
+SCENARIO CONTEXT:
+📍 {self.scenario_title}
+🎯 What's happening: {self.scenario_description}
+⚡ Challenge: {self.scenario_challenge}
+🏆 Goal: {self.scenario_goal}
+
+{casualness_note}
+
+CHARACTER:
+- {self.name} ({self.age_range} {self.character_type.value.replace('_', ' ')})
+- {self.background}
+- Works at: {self.location_context}
+- Personality: {self.tone.value}, {'talkative' if self.is_talkative else 'quiet'}, {'helpful' if self.is_helpful else 'business-focused'}
+
+YOUR TYPICAL PHRASES (use these naturally):
+{chr(10).join(f'- {phrase}' for phrase in self.typical_phrases)}
+
+CRITICAL RULES - READ CONVERSATION HISTORY CAREFULLY:
+1. You are {self.name} - NOT a teacher, NOT formal, just a real person in this scenario
+2. Speak casual Indonesian like in real life - very relaxed and natural
+3. Keep responses SHORT (5-10 words max, like real conversation)
+4. READ THE CONVERSATION HISTORY ABOVE - remember what was already asked and answered
+5. NEVER repeat questions you already asked - check what was said before
+6. TRACK the interaction progress - move naturally through the process based on what's been discussed
+7. Use informal language: "gak" not "tidak", "udah" not "sudah", "gimana" not "bagaimana"
+8. Stay relevant to your role and what customers need from you in this scenario
+9. If customer already answered a question, move to the NEXT step in the process
+10. Help the customer achieve their goal: {self.scenario_goal}
+
+{interaction_guide}
+
+ADDITIONAL CONTEXT: {scenario_context}
+
+IMPORTANT: Look at the conversation history above before responding! Don't ask questions that were already answered. Continue naturally from where the conversation left off! Help them complete their goal in this scenario."""
+
+        return base_prompt
+
+WARUNG_PERSONALITIES = {
+    "pak_budi": Personality(
+        character_type=CharacterType.WARUNG_OWNER,
+        name="Pak Budi",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="middle-aged",
+        background="Chill warung owner who knows his regular customers",
+        typical_phrases=[
+            "Mau apa?",
+            "Pedes gak?",
+            "Telur ditambahin?",
+            "Minum apa?",
+            "Tunggu ya",
+            "Udah jadi nih",
+            "Berapa ribu ya...",
+            "Makasih Bos"
+        ],
+        response_style="Quick and casual, gets straight to the point",
+        location_context="Small warung near campus",
+        scenario_title="At a Warung",
+        scenario_description="You're at a local Indonesian warung (small restaurant) trying to order food and drinks. Practice ordering in Indonesian and navigating the casual dining experience.",
+        scenario_challenge="Understanding local food terminology, spice levels, and casual Indonesian conversation patterns. The owner speaks quickly and uses informal language.",
+        scenario_goal="Order nasi goreng pedas and teh manis",
+        goal_items=[
+            GoalItem(
+                id="order_nasi_goreng",
+                description="Order nasi goreng pedas"
+            ),
+            GoalItem(
+                id="order_drink",
+                description="Order teh manis"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(indonesian="Saya mau...", english="I want..."),
+            HelpfulPhrase(indonesian="Berapa harganya?", english="How much?"),
+            HelpfulPhrase(indonesian="Terima kasih", english="Thank you"),
+            HelpfulPhrase(indonesian="Pedas", english="Spicy"),
+            HelpfulPhrase(indonesian="Teh manis", english="Sweet tea"),
+            HelpfulPhrase(indonesian="Nasi goreng", english="Fried rice")
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=True
+    ),
+    
+    "ibu_sari": Personality(
+        character_type=CharacterType.WARUNG_OWNER,
+        name="Ibu Sari",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CHEERFUL,
+        age_range="middle-aged",
+        background="Friendly warung owner who likes to chat with customers",
+        typical_phrases=[
+            "Eh, mau apa Dek?",
+            "Udah laper ya?",
+            "Pedes level berapa?",
+            "Es teh manis?",
+            "Sebentar ya Dek",
+            "Nih, masih panas",
+            "Hati-hati ya"
+        ],
+        response_style="Friendly but not overly formal, treats customers warmly",
+        location_context="Busy warung in residential area",
+        scenario_title="At a Warung",
+        scenario_description="You're at a local Indonesian warung (small restaurant) trying to order food and drinks. Practice ordering in Indonesian and navigating the casual dining experience.",
+        scenario_challenge="Understanding local food terminology, spice levels, and casual Indonesian conversation patterns. The owner is chatty and may engage in small talk.",
+        scenario_goal="Order nasi goreng pedas and teh manis",
+        goal_items=[
+            GoalItem(
+                id="order_nasi_goreng",
+                description="Order nasi goreng pedas"
+            ),
+            GoalItem(
+                id="order_drink",
+                description="Order teh manis"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(indonesian="Saya mau...", english="I want..."),
+            HelpfulPhrase(indonesian="Berapa harganya?", english="How much?"),
+            HelpfulPhrase(indonesian="Terima kasih", english="Thank you"),
+            HelpfulPhrase(indonesian="Pedas", english="Spicy"),
+            HelpfulPhrase(indonesian="Teh manis", english="Sweet tea"),
+            HelpfulPhrase(indonesian="Nasi goreng", english="Fried rice")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+OJEK_PERSONALITIES = {
+    "mbak_sari": Personality(
+        character_type=CharacterType.OJEK_DRIVER,
+        name="Mbak Sari",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="young",
+        background="Smart ojek driver who knows how to negotiate",
+        typical_phrases=[
+            "Kemana Mas?",
+            "Wah macet nih",
+            "Bensin naik lagi",
+            "Udah deket kok",
+            "Pegang yang kuat",
+            "Sampai deh",
+            "Ati-ati ya",
+            "Jangan bilang-bilang"
+        ],
+        response_style="Direct and business-minded, mentions practical concerns",
+        location_context="Busy street corner",
+        scenario_title="Taking an Ojek",
+        scenario_description="You need to get a motorcycle taxi (ojek) to take you to the mall. Practice negotiating destination and price in Indonesian.",
+        scenario_challenge="Learning transportation vocabulary, price negotiation, and understanding Jakarta traffic concerns. The driver may try to charge tourist prices.",
+        scenario_goal="Negotiate ride to mall and agree on price",
+        goal_items=[
+            GoalItem(
+                id="state_destination",
+                description="Tell destination (mall)"
+            ),
+            GoalItem(
+                id="agree_price",
+                description="Agree on price"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(indonesian="Ke mall berapa?", english="How much to the mall?"),
+            HelpfulPhrase(indonesian="Mahal banget!", english="That's too expensive!"),
+            HelpfulPhrase(indonesian="Lima belas ribu boleh?", english="Is 15 thousand OK?"),
+            HelpfulPhrase(indonesian="Ayo!", english="Let's go!"),
+            HelpfulPhrase(indonesian="Ke mall", english="To the mall"),
+            HelpfulPhrase(indonesian="Berapa ongkosnya?", english="How much is the fare?")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        uses_slang=True
+    )
+}
+
+CASHIER_PERSONALITIES = {
+    "adik_kasir": Personality(
+        character_type=CharacterType.CASHIER,
+        name="Adik Kasir",
+        gender=Gender.FEMALE,
+        tone=PersonalityTone.CASUAL,
+        age_range="young",
+        background="Young cashier who's chill and helpful",
+        typical_phrases=[
+            "Malam Kak",
+            "Beli apa?",
+            "Yang lain?",
+            "Pake kantong?",
+            "Total sekian",
+            "Kembaliannya",
+            "Makasih ya",
+            "Ati-ati"
+        ],
+        response_style="Quick and efficient, gets the job done",
+        location_context="Alfamart convenience store",
+        scenario_title="At Alfamart",
+        scenario_description="You're shopping at Alfamart, a popular Indonesian convenience store chain. Practice buying everyday items and completing a transaction in Indonesian.",
+        scenario_challenge="Understanding convenience store vocabulary, payment interactions, and polite customer service language. Learn about Indonesian instant noodle brands and local products.",
+        scenario_goal="Buy Indomie and mineral water",
+        goal_items=[
+            GoalItem(
+                id="buy_indomie",
+                description="Buy Indomie"
+            ),
+            GoalItem(
+                id="buy_water",
+                description="Buy mineral water"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(indonesian="Saya mau beli...", english="I want to buy..."),
+            HelpfulPhrase(indonesian="Berapa totalnya?", english="How much is the total?"),
+            HelpfulPhrase(indonesian="Pake kantong", english="With a bag"),
+            HelpfulPhrase(indonesian="Bayar cash", english="Pay with cash"),
+            HelpfulPhrase(indonesian="Indomie", english="Indomie (instant noodles)"),
+            HelpfulPhrase(indonesian="Air mineral", english="Mineral water")
+        ],
+        is_helpful=True,
+        is_talkative=False,
+        uses_slang=True
+    )
+}
+
+COFFEE_SHOP_PERSONALITIES = {
+    "tetangga_ali": Personality(
+        character_type=CharacterType.GENERIC,
+        name="Tetangga Ali",
+        gender=Gender.MALE,
+        tone=PersonalityTone.CHATTY,
+        age_range="middle-aged",
+        background="Friendly neighborhood guy who loves chatting with everyone about everything",
+        typical_phrases=[
+            "Eh, apa kabar?",
+            "Lagi ngapain nih?",
+            "Cuacanya panas banget ya hari ini",
+            "Udah makan belum?",
+            "Gimana kabar keluarga?",
+            "Kerja dimana sekarang?",
+            "Udah lama gak ketemu",
+            "Wah, sibuk banget ya",
+            "Ngomong-ngomong...",
+            "Oh iya, tau gak...",
+            "Kemarin aku ke...",
+            "Eh, kamu pernah ke...?"
+        ],
+        response_style="Very talkative, asks lots of questions, shares stories, makes connections to random topics",
+        location_context="Local coffee shop in residential area",
+        scenario_title="Coffee Shop Small Talk",
+        scenario_description="You're at a local coffee shop and meet a very friendly neighbor who loves to chat. Practice making small talk in Indonesian - discussing weather, family, work, hobbies, and daily life.",
+        scenario_challenge="Learn natural small talk patterns, question-asking, and how to keep conversations flowing in Indonesian. Practice responding to personal questions and sharing about yourself.",
+        scenario_goal="Have a natural small talk conversation covering at least 3 different topics",
+        goal_items=[
+            GoalItem(
+                id="greet_and_respond",
+                description="Exchange greetings and ask how each other is doing"
+            ),
+            GoalItem(
+                id="discuss_weather_daily_life",
+                description="Talk about weather, daily activities, or current situation"
+            ),
+            GoalItem(
+                id="share_personal_info",
+                description="Share something about yourself (work, family, hobbies, etc.)"
+            ),
+            GoalItem(
+                id="ask_followup_questions",
+                description="Ask follow-up questions to keep the conversation going"
+            )
+        ],
+        helpful_phrases=[
+            HelpfulPhrase(indonesian="Apa kabar?", english="How are you?"),
+            HelpfulPhrase(indonesian="Baik-baik aja", english="I'm doing fine"),
+            HelpfulPhrase(indonesian="Lagi ngapain?", english="What are you up to?"),
+            HelpfulPhrase(indonesian="Cuacanya panas ya", english="The weather is hot, isn't it?"),
+            HelpfulPhrase(indonesian="Udah makan belum?", english="Have you eaten yet?"),
+            HelpfulPhrase(indonesian="Gimana kabar keluarga?", english="How's the family?"),
+            HelpfulPhrase(indonesian="Kerja dimana?", english="Where do you work?"),
+            HelpfulPhrase(indonesian="Ngomong-ngomong...", english="By the way..."),
+            HelpfulPhrase(indonesian="Oh iya...", english="Oh yes..."),
+            HelpfulPhrase(indonesian="Wah, menarik!", english="Wow, interesting!"),
+            HelpfulPhrase(indonesian="Bener juga ya", english="That's true"),
+            HelpfulPhrase(indonesian="Udah lama gak ketemu", english="Haven't seen you in a while")
+        ],
+        is_helpful=True,
+        is_talkative=True,
+        is_impatient=False,
+        uses_slang=True
+    )
+}
+
+SCENARIO_PERSONALITIES = {
+    "warung": WARUNG_PERSONALITIES,
+    "ojek": OJEK_PERSONALITIES,
+    "alfamart": CASHIER_PERSONALITIES,
+    "coffee_shop": COFFEE_SHOP_PERSONALITIES
+}

backend/pyproject.toml

@@ -0,0 +1,65 @@
+[project]
+name = "learn-indonesian-backend"
+version = "0.1.0"
+description = "FastAPI backend for Indonesian learning app"
+authors = [
+    {name = "Your Name", email = "your.email@example.com"},
+]
+dependencies = [
+    "fastapi>=0.104.1",
+    "uvicorn>=0.24.0",
+    "pydantic>=2.5.0",
+    "python-multipart>=0.0.6",
+    "google-cloud-speech>=2.21.0",
+    "google-cloud-texttospeech>=2.14.2",
+    "openai>=1.0.0",
+    "websockets>=11.0.3",
+    "python-dotenv>=1.0.0",
+]
+requires-python = ">=3.11"
+license = {text = "MIT"}
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["."]
+
+[tool.ruff]
+target-version = "py311"
+line-length = 88
+select = [
+    "E",  # pycodestyle errors
+    "W",  # pycodestyle warnings
+    "F",  # pyflakes
+    "I",  # isort
+    "B",  # flake8-bugbear
+    "C4", # flake8-comprehensions
+    "UP", # pyupgrade
+]
+ignore = [
+    "E501",  # line too long, handled by black
+    "B008",  # do not perform function calls in argument defaults
+    "C901",  # too complex
+]
+
+[tool.ruff.per-file-ignores]
+"__init__.py" = ["F401"]
+
+[tool.ruff.isort]
+known-first-party = ["app"]
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+skip-magic-trailing-comma = false
+line-ending = "auto"
+
+[tool.uv]
+dev-dependencies = [
+    "ruff>=0.1.6",
+    "pytest>=7.4.3",
+    "pytest-asyncio>=0.21.1",
+    "httpx>=0.25.2",
+]

backend/speech_service.py

@@ -0,0 +1,507 @@
+import asyncio
+import json
+import os
+import logging
+from typing import AsyncGenerator, Dict, Any, Optional, List
+import base64
+
+from google.cloud import speech
+from google.cloud import texttospeech
+from google.api_core import exceptions
+import openai
+
+from config import config
+from models import Personality, SCENARIO_PERSONALITIES, GoalItem, Gender
+
+logger = logging.getLogger(__name__)
+
+
+class SpeechToTextService:
+    def __init__(self):
+        self.client = speech.SpeechClient()
+        
+        # Get encoding from config
+        encoding_map = {
+            "WEBM_OPUS": speech.RecognitionConfig.AudioEncoding.WEBM_OPUS,
+            "LINEAR16": speech.RecognitionConfig.AudioEncoding.LINEAR16,
+            "FLAC": speech.RecognitionConfig.AudioEncoding.FLAC,
+            "MULAW": speech.RecognitionConfig.AudioEncoding.MULAW,
+            "AMR": speech.RecognitionConfig.AudioEncoding.AMR,
+            "AMR_WB": speech.RecognitionConfig.AudioEncoding.AMR_WB,
+            "OGG_OPUS": speech.RecognitionConfig.AudioEncoding.OGG_OPUS,
+            "MP3": speech.RecognitionConfig.AudioEncoding.MP3,
+        }
+        
+        self.recognition_config = speech.RecognitionConfig(
+            encoding=encoding_map.get(config.SPEECH_ENCODING, speech.RecognitionConfig.AudioEncoding.WEBM_OPUS),
+            sample_rate_hertz=config.SPEECH_SAMPLE_RATE,
+            language_code=config.SPEECH_LANGUAGE_CODE,
+            enable_automatic_punctuation=True,
+            use_enhanced=True,
+            model="latest_long",
+        )
+        self.streaming_config = speech.StreamingRecognitionConfig(
+            config=self.recognition_config,
+            interim_results=True,
+            single_utterance=False,
+        )
+
+    async def transcribe_streaming(self, audio_generator: AsyncGenerator[bytes, None]) -> AsyncGenerator[Dict[str, Any], None]:
+        """Stream audio data to Google Cloud Speech-to-Text and yield transcription results."""
+        try:
+            async def request_generator():
+                # First request with config
+                yield speech.StreamingRecognizeRequest(streaming_config=self.streaming_config)
+                
+                # Then audio requests
+                async for chunk in audio_generator:
+                    yield speech.StreamingRecognizeRequest(audio_content=chunk)
+            
+            responses = self.client.streaming_recognize(request_generator())
+            
+            for response in responses:
+                for result in response.results:
+                    transcript = result.alternatives[0].transcript
+                    is_final = result.is_final
+                    
+                    yield {
+                        "type": "transcription",
+                        "transcript": transcript,
+                        "is_final": is_final,
+                        "confidence": result.alternatives[0].confidence if is_final else 0.0
+                    }
+        except exceptions.GoogleAPICallError as e:
+            yield {
+                "type": "error",
+                "message": f"Speech recognition error: {str(e)}"
+            }
+
+
+class TextToSpeechService:
+    def __init__(self):
+        self.client = texttospeech.TextToSpeechClient()
+        
+        # Gender mapping for Google TTS
+        self.gender_map = {
+            "FEMALE": texttospeech.SsmlVoiceGender.FEMALE,
+            "MALE": texttospeech.SsmlVoiceGender.MALE,
+            "NEUTRAL": texttospeech.SsmlVoiceGender.NEUTRAL,
+            "male": texttospeech.SsmlVoiceGender.MALE,
+            "female": texttospeech.SsmlVoiceGender.FEMALE,
+        }
+        
+    
+    def _get_voice_and_audio_config(self, gender: str, character_name: str = None) -> tuple:
+        """Get appropriate voice and audio configuration based on gender."""
+        tts_gender = self.gender_map.get(gender, texttospeech.SsmlVoiceGender.FEMALE)
+        
+        character_voice_map = {
+            "Pak Budi": {
+                "name": "id-ID-Chirp3-HD-Charon",
+                "speaking_rate": 0.95,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            "Ibu Sari": {
+                "name": "id-ID-Chirp3-HD-Kore",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Mbak Sari": {
+                "name": "id-ID-Chirp3-HD-Zephyr",
+                "speaking_rate": 1.1,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Adik Kasir": {
+                "name": "id-ID-Chirp3-HD-Aoede",
+                "speaking_rate": 1.05,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            },
+            "Tetangga Ali": {
+                "name": "id-ID-Chirp3-HD-Puck",
+                "speaking_rate": 1.05,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            }
+        }
+        
+        gender_voice_fallback = {
+            texttospeech.SsmlVoiceGender.MALE: {
+                "name": "id-ID-Chirp3-HD-Fenrir",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.MALE,
+            },
+            texttospeech.SsmlVoiceGender.FEMALE: {
+                "name": "id-ID-Chirp3-HD-Leda",
+                "speaking_rate": 1.0,
+                "pitch": None,
+                "ssml_gender": texttospeech.SsmlVoiceGender.FEMALE,
+            }
+        }
+        
+        config_set = None
+        
+        if character_name and character_name in character_voice_map:
+            config_set = character_voice_map[character_name]
+            logger.info(f"Using character-specific voice for '{character_name}': {config_set['name']}")
+        
+        if not config_set:
+            config_set = gender_voice_fallback.get(tts_gender, gender_voice_fallback[texttospeech.SsmlVoiceGender.FEMALE])
+            logger.info(f"Using gender fallback voice for {tts_gender}: {config_set['name']}")
+        
+        voice = texttospeech.VoiceSelectionParams(
+            language_code=config.TTS_LANGUAGE_CODE,
+            name=config_set["name"],
+            ssml_gender=config_set["ssml_gender"],
+        )
+        
+        audio_config_params = {
+            "audio_encoding": texttospeech.AudioEncoding.LINEAR16,
+            "speaking_rate": config_set["speaking_rate"],
+            "effects_profile_id": ['handset-class-device'],
+        }
+        
+        if config_set["pitch"] is not None:
+            audio_config_params["pitch"] = config_set["pitch"]
+            
+        audio_config = texttospeech.AudioConfig(**audio_config_params)
+        
+        return voice, audio_config
+
+
+    async def synthesize_speech(self, text: str, gender: str = "female", character_name: str = None) -> bytes:
+        """Convert text to speech using Google Cloud Text-to-Speech with natural, conversational voice."""
+        try:
+            logger.info(f"TTS synthesize_speech called with text: '{text}', gender: '{gender}', character: '{character_name}'")
+            
+            voice, audio_config = self._get_voice_and_audio_config(gender, character_name)
+            logger.info(f"Using voice: {voice.name}, requested gender: '{gender}', mapped TTS gender: {voice.ssml_gender}")
+            
+            synthesis_input = texttospeech.SynthesisInput(text=text)
+            
+            response = self.client.synthesize_speech(
+                input=synthesis_input,
+                voice=voice,
+                audio_config=audio_config,
+            )
+            
+            logger.info(f"TTS successful, audio length: {len(response.audio_content)} bytes")
+            return response.audio_content
+                
+        except exceptions.GoogleAPICallError as e:
+            logger.error(f"Text-to-speech error: {str(e)}")
+            raise Exception(f"Text-to-speech error: {str(e)}")
+
+
+class AIConversationService:
+    def __init__(self):
+        self.client = openai.OpenAI(api_key=config.OPENAI_API_KEY)
+        self.model = config.OPENAI_MODEL
+        self.current_personality: Optional[Personality] = None
+        self.conversation_history: List[Dict[str, str]] = []
+        self.goal_progress: List[GoalItem] = []
+
+    def set_personality(self, personality: Personality):
+        """Set the current personality for the conversation."""
+        self.current_personality = personality
+        # Reset conversation history when personality changes
+        self.conversation_history = []
+        # Initialize goal progress
+        self.goal_progress = [GoalItem(**item.dict()) for item in personality.goal_items]
+
+    def reset_conversation(self):
+        """Reset the conversation history."""
+        self.conversation_history = []
+        # Reset goal progress
+        if self.current_personality:
+            self.goal_progress = [GoalItem(**item.dict()) for item in self.current_personality.goal_items]
+
+    def get_personality_for_scenario(self, scenario: str, character_name: str = None) -> Personality:
+        """Get personality based on scenario and optional character name."""
+        if scenario in SCENARIO_PERSONALITIES:
+            personalities = SCENARIO_PERSONALITIES[scenario]
+            if character_name and character_name in personalities:
+                return personalities[character_name]
+            else:
+                # Return first personality if no specific character requested
+                return list(personalities.values())[0]
+        
+        # Return default personality if scenario not found
+        return Personality(
+            character_type="generic",
+            name="Pak/Bu",
+            tone="friendly",
+            age_range="middle-aged",
+            background="Helpful Indonesian person",
+            typical_phrases=["Halo!", "Apa kabar?", "Bisa saya bantu?"],
+            response_style="Friendly and helpful",
+            location_context="Indonesia",
+            is_helpful=True,
+            is_talkative=True
+        )
+
+    async def check_goal_completion(self, user_message: str, ai_response: str) -> bool:
+        """Check if any goals are completed using LLM judge."""
+        if not self.goal_progress:
+            return False
+            
+        goals_completed = False
+        
+        # Only check goals that aren't already completed
+        incomplete_goals = [g for g in self.goal_progress if not g.completed]
+        if not incomplete_goals:
+            return False
+            
+        logger.info(f"Checking goal completion for user message: '{user_message}'")
+        logger.info(f"Incomplete goals: {[g.description for g in incomplete_goals]}")
+        
+        conversation_context = ""
+        for exchange in self.conversation_history[-3:]:
+            conversation_context += f"User: {exchange['user']}\nAI: {exchange['assistant']}\n"
+        
+        for goal in incomplete_goals:
+            logger.info(f"Checking goal: '{goal.description}'")
+            completion_check = await self._judge_goal_completion(
+                goal, 
+                user_message, 
+                ai_response, 
+                conversation_context
+            )
+            
+            if completion_check:
+                goal.completed = True
+                goals_completed = True
+                logger.info(f"✅ Goal completed: {goal.description}")
+            else:
+                logger.info(f"❌ Goal not completed: {goal.description}")
+        
+        return goals_completed
+    
+    async def _judge_goal_completion(self, goal: GoalItem, user_message: str, ai_response: str, conversation_context: str) -> bool:
+        """Use LLM to judge if a specific goal was completed."""
+        try:
+            if "order" in goal.description.lower() or "buy" in goal.description.lower():
+                judge_prompt = f"""You are a strict judge determining if a specific goal was FULLY completed in a conversation.
+
+GOAL TO CHECK: {goal.description}
+
+RECENT CONVERSATION CONTEXT:
+{conversation_context}
+
+LATEST EXCHANGE:
+User: {user_message}
+AI: {ai_response}
+
+CRITICAL RULES FOR ORDERING GOALS:
+1. ONLY return "YES" if the user has COMPLETELY finished this exact goal
+2. Return "NO" if the goal is partial, incomplete, or just being discussed
+3. For "Order [item]" goals: user must explicitly say they want/order that EXACT item with ALL specifications
+4. For drink goals: user must specifically mention wanting/ordering a drink
+5. Don't mark as complete just because the AI is asking about it
+
+Answer ONLY "YES" or "NO":"""
+            else:
+                judge_prompt = f"""You are judging if a conversational goal was completed in a natural small talk scenario.
+
+GOAL TO CHECK: {goal.description}
+
+RECENT CONVERSATION CONTEXT:
+{conversation_context}
+
+LATEST EXCHANGE:
+User: {user_message}
+AI: {ai_response}
+
+RULES FOR SMALL TALK GOALS:
+1. Return "YES" if the user has naturally accomplished this conversational goal ANYWHERE in the conversation
+2. For "Share something about yourself" goals: Look through the ENTIRE conversation for work, family, hobbies, personal interests, financial situation, dreams, etc.
+3. For "Ask follow-up questions" goals: user asks questions to continue conversation
+4. For "Exchange greetings" goals: user greets or responds to greetings
+5. For "Discuss weather/daily life" goals: user talks about weather, daily activities, current events
+6. Goals can be completed through natural conversation flow, not just direct statements
+7. IMPORTANT: Check the FULL conversation context, not just the latest exchange
+
+EXAMPLES:
+- Goal: "Share something about yourself (work, family, hobbies, etc.)"
+  - User mentions work: "sibuk banget di kantor sering lembur" → YES (work situation)
+  - User mentions finances: "nggak punya duit" → YES (personal finance)
+  - User mentions hobbies: "sukanya ke Afrika" → YES (travel interests)
+  - User mentions dreams: "Belum pernah mimpi aja dulu sih" → YES (personal aspirations)
+  - User just greets: "Baik nih" → NO (just greeting, no personal info)
+
+- Goal: "Ask follow-up questions to keep the conversation going"
+  - User: "Mas Ali suka lari juga gak?" → YES (asking follow-up question)
+  - User: "Gimana kabar keluarga?" → YES (asking about family)
+  - User: "Iya" → NO (just responding, not asking)
+
+Be reasonable and natural - small talk goals should be completed through normal conversation. 
+SCAN THE ENTIRE CONVERSATION, not just the latest message.
+
+Answer ONLY "YES" or "NO":"""
+
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=[{"role": "user", "content": judge_prompt}],
+                max_tokens=5,
+                temperature=0.1,  # Low temperature for consistent judging
+            )
+            
+            result = response.choices[0].message.content.strip().upper()
+            logger.info(f"Goal judge result for '{goal.description}': {result}")
+            
+            return result == "YES"
+            
+        except Exception as e:
+            logger.error(f"Error in goal completion judge: {str(e)}")
+            return False
+    
+    def are_all_goals_completed(self) -> bool:
+        """Check if all goals are completed."""
+        return all(goal.completed for goal in self.goal_progress)
+    
+    def get_goal_status(self) -> Dict[str, Any]:
+        """Get current goal status."""
+        return {
+            "scenario_goal": self.current_personality.scenario_goal if self.current_personality else "",
+            "goal_items": [
+                {
+                    "id": goal.id,
+                    "description": goal.description,
+                    "completed": goal.completed
+                } for goal in self.goal_progress
+            ],
+            "all_completed": self.are_all_goals_completed()
+        }
+
+    async def get_response(self, user_message: str, context: str = "") -> str:
+        """Get AI response to user message using current personality and conversation history."""
+        try:
+            # Use current personality or default
+            if not self.current_personality:
+                default_personality = self.get_personality_for_scenario("warung", "pak_budi")
+                self.set_personality(default_personality)
+            
+            system_prompt = self.current_personality.get_system_prompt(context)
+            
+            # Build messages with conversation history
+            messages = [{"role": "system", "content": system_prompt}]
+            
+            # Add conversation history (keep last 15 exchanges for better chitchat context)
+            recent_history = self.conversation_history[-15:] if len(self.conversation_history) > 15 else self.conversation_history
+            for exchange in recent_history:
+                messages.append({"role": "user", "content": exchange["user"]})
+                messages.append({"role": "assistant", "content": exchange["assistant"]})
+            
+            # Add current user message
+            messages.append({"role": "user", "content": user_message})
+            
+            logger.info(f"Sending {len(messages)} messages to AI:")
+            for i, msg in enumerate(messages):
+                if msg["role"] == "system":
+                    logger.info(f"  {i}: SYSTEM (length: {len(msg['content'])})")
+                else:
+                    logger.info(f"  {i}: {msg['role'].upper()}: '{msg['content']}'")
+            
+            response = self.client.chat.completions.create(
+                model=self.model,
+                messages=messages,
+                max_tokens=250,
+                temperature=0.7,
+            )
+            
+            ai_response = response.choices[0].message.content
+            
+            self.conversation_history.append({
+                "user": user_message,
+                "assistant": ai_response
+            })
+            
+            await self.check_goal_completion(user_message, ai_response)
+            
+            logger.info(f"Conversation history length: {len(self.conversation_history)}")
+            if len(self.conversation_history) > 0:
+                logger.info(f"Last exchange - User: '{self.conversation_history[-1]['user']}', AI: '{self.conversation_history[-1]['assistant']}'")
+            
+            if self.goal_progress:
+                completed_goals = [g.description for g in self.goal_progress if g.completed]
+                logger.info(f"Completed goals: {completed_goals}")
+                logger.info(f"All goals completed: {self.are_all_goals_completed()}")
+            
+            return ai_response
+        except Exception as e:
+            return f"Maaf, ada error: {str(e)}"
+
+
+class ConversationFlowService:
+    def __init__(self):
+        self.stt_service = SpeechToTextService()
+        self.tts_service = TextToSpeechService()
+        self.ai_service = AIConversationService()
+
+    def set_scenario_personality(self, scenario: str, character_name: str = None):
+        """Set the personality based on scenario and character."""
+        personality = self.ai_service.get_personality_for_scenario(scenario, character_name)
+        if not self.ai_service.current_personality or self.ai_service.current_personality.name != personality.name:
+            logger.info(f"Setting new personality: {personality.name}")
+            self.ai_service.set_personality(personality)
+            logger.info("Goal progress initialized for new personality")
+        else:
+            logger.info(f"Keeping existing personality: {personality.name}")
+
+    async def process_conversation_flow(self, transcribed_text: str, scenario_context: str = "") -> Dict[str, Any]:
+        """Process the complete conversation flow: Text → AI → Speech."""
+        try:
+            scenario = self.extract_scenario_from_context(scenario_context)
+            if scenario:
+                self.set_scenario_personality(scenario)
+            
+            ai_response = await self.ai_service.get_response(transcribed_text, scenario_context)
+            
+            gender = self.ai_service.current_personality.gender.value if self.ai_service.current_personality else "female"
+            personality_name = self.ai_service.current_personality.name if self.ai_service.current_personality else "Unknown"
+            logger.info(f"Generating TTS for character '{personality_name}' with text: '{ai_response}' and gender: '{gender}'")
+            audio_content = await self.tts_service.synthesize_speech(ai_response, gender, personality_name)
+            logger.info(f"TTS generation successful, audio length: {len(audio_content)} bytes")
+            
+            audio_base64 = base64.b64encode(audio_content).decode('utf-8')
+            
+            goal_status = self.ai_service.get_goal_status()
+            
+            return {
+                "type": "ai_response",
+                "text": ai_response,
+                "audio": audio_base64,
+                "audio_format": "mp3",
+                "character": self.ai_service.current_personality.name if self.ai_service.current_personality else "Unknown",
+                "goal_status": goal_status,
+                "conversation_complete": goal_status.get("all_completed", False)
+            }
+        except Exception as e:
+            return {
+                "type": "error",
+                "message": f"Conversation flow error: {str(e)}"
+            }
+
+    def extract_scenario_from_context(self, context: str) -> str:
+        """Extract scenario type from context string."""
+        logger.info(f"Extracting scenario from context: '{context}'")
+        context_lower = context.lower()
+        
+        detected_scenario = None
+        if "coffee_shop" in context_lower or "coffee" in context_lower:
+            detected_scenario = "coffee_shop"
+        elif "warung" in context_lower or "nasi goreng" in context_lower:
+            detected_scenario = "warung"
+        elif "ojek" in context_lower or "mall" in context_lower:
+            detected_scenario = "ojek"
+        elif "alfamart" in context_lower or "indomie" in context_lower:
+            detected_scenario = "alfamart"
+        else:
+            detected_scenario = "warung"  # Default to warung
+            
+        logger.info(f"Detected scenario: '{detected_scenario}'")
+        return detected_scenario

backend/uv.lock

@@ -0,0 +1,819 @@
+version = 1
+requires-python = ">=3.11"
+resolution-markers = [
+    "python_full_version >= '3.13'",
+    "python_full_version < '3.13'",
+]
+
+[[package]]
+name = "annotated-types"
+version = "0.7.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ee/67/531ea369ba64dcff5ec9c3402f9f51bf748cec26dde048a2f973a4eea7f5/annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89", size = 16081 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", size = 13643 },
+]
+
+[[package]]
+name = "anyio"
+version = "4.9.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "idna" },
+    { name = "sniffio" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/95/7d/4c1bd541d4dffa1b52bd83fb8527089e097a106fc90b467a7313b105f840/anyio-4.9.0.tar.gz", hash = "sha256:673c0c244e15788651a4ff38710fea9675823028a6f08a5eda409e0c9840a028", size = 190949 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a1/ee/48ca1a7c89ffec8b6a0c5d02b89c305671d5ffd8d3c94acf8b8c408575bb/anyio-4.9.0-py3-none-any.whl", hash = "sha256:9f76d541cad6e36af7beb62e978876f3b41e3e04f2c1fbf0884604c0a9c4d93c", size = 100916 },
+]
+
+[[package]]
+name = "cachetools"
+version = "5.5.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/6c/81/3747dad6b14fa2cf53fcf10548cf5aea6913e96fab41a3c198676f8948a5/cachetools-5.5.2.tar.gz", hash = "sha256:1a661caa9175d26759571b2e19580f9d6393969e5dfca11fdb1f947a23e640d4", size = 28380 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/72/76/20fa66124dbe6be5cafeb312ece67de6b61dd91a0247d1ea13db4ebb33c2/cachetools-5.5.2-py3-none-any.whl", hash = "sha256:d26a22bcc62eb95c3beabd9f1ee5e820d3d2704fe2967cbe350e20c8ffcd3f0a", size = 10080 },
+]
+
+[[package]]
+name = "certifi"
+version = "2025.7.14"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b3/76/52c535bcebe74590f296d6c77c86dabf761c41980e1347a2422e4aa2ae41/certifi-2025.7.14.tar.gz", hash = "sha256:8ea99dbdfaaf2ba2f9bac77b9249ef62ec5218e7c2b2e903378ed5fccf765995", size = 163981 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4f/52/34c6cf5bb9285074dc3531c437b3919e825d976fde097a7a73f79e726d03/certifi-2025.7.14-py3-none-any.whl", hash = "sha256:6b31f564a415d79ee77df69d757bb49a5bb53bd9f756cbbe24394ffd6fc1f4b2", size = 162722 },
+]
+
+[[package]]
+name = "charset-normalizer"
+version = "3.4.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/e4/33/89c2ced2b67d1c2a61c19c6751aa8902d46ce3dacb23600a283619f5a12d/charset_normalizer-3.4.2.tar.gz", hash = "sha256:5baececa9ecba31eff645232d59845c07aa030f0c81ee70184a90d35099a0e63", size = 126367 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/05/85/4c40d00dcc6284a1c1ad5de5e0996b06f39d8232f1031cd23c2f5c07ee86/charset_normalizer-3.4.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:be1e352acbe3c78727a16a455126d9ff83ea2dfdcbc83148d2982305a04714c2", size = 198794 },
+    { url = "https://files.pythonhosted.org/packages/41/d9/7a6c0b9db952598e97e93cbdfcb91bacd89b9b88c7c983250a77c008703c/charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa88ca0b1932e93f2d961bf3addbb2db902198dca337d88c89e1559e066e7645", size = 142846 },
+    { url = "https://files.pythonhosted.org/packages/66/82/a37989cda2ace7e37f36c1a8ed16c58cf48965a79c2142713244bf945c89/charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d524ba3f1581b35c03cb42beebab4a13e6cdad7b36246bd22541fa585a56cccd", size = 153350 },
+    { url = "https://files.pythonhosted.org/packages/df/68/a576b31b694d07b53807269d05ec3f6f1093e9545e8607121995ba7a8313/charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28a1005facc94196e1fb3e82a3d442a9d9110b8434fc1ded7a24a2983c9888d8", size = 145657 },
+    { url = "https://files.pythonhosted.org/packages/92/9b/ad67f03d74554bed3aefd56fe836e1623a50780f7c998d00ca128924a499/charset_normalizer-3.4.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fdb20a30fe1175ecabed17cbf7812f7b804b8a315a25f24678bcdf120a90077f", size = 147260 },
+    { url = "https://files.pythonhosted.org/packages/a6/e6/8aebae25e328160b20e31a7e9929b1578bbdc7f42e66f46595a432f8539e/charset_normalizer-3.4.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0f5d9ed7f254402c9e7d35d2f5972c9bbea9040e99cd2861bd77dc68263277c7", size = 149164 },
+    { url = "https://files.pythonhosted.org/packages/8b/f2/b3c2f07dbcc248805f10e67a0262c93308cfa149a4cd3d1fe01f593e5fd2/charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:efd387a49825780ff861998cd959767800d54f8308936b21025326de4b5a42b9", size = 144571 },
+    { url = "https://files.pythonhosted.org/packages/60/5b/c3f3a94bc345bc211622ea59b4bed9ae63c00920e2e8f11824aa5708e8b7/charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:f0aa37f3c979cf2546b73e8222bbfa3dc07a641585340179d768068e3455e544", size = 151952 },
+    { url = "https://files.pythonhosted.org/packages/e2/4d/ff460c8b474122334c2fa394a3f99a04cf11c646da895f81402ae54f5c42/charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:e70e990b2137b29dc5564715de1e12701815dacc1d056308e2b17e9095372a82", size = 155959 },
+    { url = "https://files.pythonhosted.org/packages/a2/2b/b964c6a2fda88611a1fe3d4c400d39c66a42d6c169c924818c848f922415/charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:0c8c57f84ccfc871a48a47321cfa49ae1df56cd1d965a09abe84066f6853b9c0", size = 153030 },
+    { url = "https://files.pythonhosted.org/packages/59/2e/d3b9811db26a5ebf444bc0fa4f4be5aa6d76fc6e1c0fd537b16c14e849b6/charset_normalizer-3.4.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:6b66f92b17849b85cad91259efc341dce9c1af48e2173bf38a85c6329f1033e5", size = 148015 },
+    { url = "https://files.pythonhosted.org/packages/90/07/c5fd7c11eafd561bb51220d600a788f1c8d77c5eef37ee49454cc5c35575/charset_normalizer-3.4.2-cp311-cp311-win32.whl", hash = "sha256:daac4765328a919a805fa5e2720f3e94767abd632ae410a9062dff5412bae65a", size = 98106 },
+    { url = "https://files.pythonhosted.org/packages/a8/05/5e33dbef7e2f773d672b6d79f10ec633d4a71cd96db6673625838a4fd532/charset_normalizer-3.4.2-cp311-cp311-win_amd64.whl", hash = "sha256:e53efc7c7cee4c1e70661e2e112ca46a575f90ed9ae3fef200f2a25e954f4b28", size = 105402 },
+    { url = "https://files.pythonhosted.org/packages/d7/a4/37f4d6035c89cac7930395a35cc0f1b872e652eaafb76a6075943754f095/charset_normalizer-3.4.2-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0c29de6a1a95f24b9a1aa7aefd27d2487263f00dfd55a77719b530788f75cff7", size = 199936 },
+    { url = "https://files.pythonhosted.org/packages/ee/8a/1a5e33b73e0d9287274f899d967907cd0bf9c343e651755d9307e0dbf2b3/charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cddf7bd982eaa998934a91f69d182aec997c6c468898efe6679af88283b498d3", size = 143790 },
+    { url = "https://files.pythonhosted.org/packages/66/52/59521f1d8e6ab1482164fa21409c5ef44da3e9f653c13ba71becdd98dec3/charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fcbe676a55d7445b22c10967bceaaf0ee69407fbe0ece4d032b6eb8d4565982a", size = 153924 },
+    { url = "https://files.pythonhosted.org/packages/86/2d/fb55fdf41964ec782febbf33cb64be480a6b8f16ded2dbe8db27a405c09f/charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d41c4d287cfc69060fa91cae9683eacffad989f1a10811995fa309df656ec214", size = 146626 },
+    { url = "https://files.pythonhosted.org/packages/8c/73/6ede2ec59bce19b3edf4209d70004253ec5f4e319f9a2e3f2f15601ed5f7/charset_normalizer-3.4.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4e594135de17ab3866138f496755f302b72157d115086d100c3f19370839dd3a", size = 148567 },
+    { url = "https://files.pythonhosted.org/packages/09/14/957d03c6dc343c04904530b6bef4e5efae5ec7d7990a7cbb868e4595ee30/charset_normalizer-3.4.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cf713fe9a71ef6fd5adf7a79670135081cd4431c2943864757f0fa3a65b1fafd", size = 150957 },
+    { url = "https://files.pythonhosted.org/packages/0d/c8/8174d0e5c10ccebdcb1b53cc959591c4c722a3ad92461a273e86b9f5a302/charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:a370b3e078e418187da8c3674eddb9d983ec09445c99a3a263c2011993522981", size = 145408 },
+    { url = "https://files.pythonhosted.org/packages/58/aa/8904b84bc8084ac19dc52feb4f5952c6df03ffb460a887b42615ee1382e8/charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:a955b438e62efdf7e0b7b52a64dc5c3396e2634baa62471768a64bc2adb73d5c", size = 153399 },
+    { url = "https://files.pythonhosted.org/packages/c2/26/89ee1f0e264d201cb65cf054aca6038c03b1a0c6b4ae998070392a3ce605/charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:7222ffd5e4de8e57e03ce2cef95a4c43c98fcb72ad86909abdfc2c17d227fc1b", size = 156815 },
+    { url = "https://files.pythonhosted.org/packages/fd/07/68e95b4b345bad3dbbd3a8681737b4338ff2c9df29856a6d6d23ac4c73cb/charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:bee093bf902e1d8fc0ac143c88902c3dfc8941f7ea1d6a8dd2bcb786d33db03d", size = 154537 },
+    { url = "https://files.pythonhosted.org/packages/77/1a/5eefc0ce04affb98af07bc05f3bac9094513c0e23b0562d64af46a06aae4/charset_normalizer-3.4.2-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:dedb8adb91d11846ee08bec4c8236c8549ac721c245678282dcb06b221aab59f", size = 149565 },
+    { url = "https://files.pythonhosted.org/packages/37/a0/2410e5e6032a174c95e0806b1a6585eb21e12f445ebe239fac441995226a/charset_normalizer-3.4.2-cp312-cp312-win32.whl", hash = "sha256:db4c7bf0e07fc3b7d89ac2a5880a6a8062056801b83ff56d8464b70f65482b6c", size = 98357 },
+    { url = "https://files.pythonhosted.org/packages/6c/4f/c02d5c493967af3eda9c771ad4d2bbc8df6f99ddbeb37ceea6e8716a32bc/charset_normalizer-3.4.2-cp312-cp312-win_amd64.whl", hash = "sha256:5a9979887252a82fefd3d3ed2a8e3b937a7a809f65dcb1e068b090e165bbe99e", size = 105776 },
+    { url = "https://files.pythonhosted.org/packages/ea/12/a93df3366ed32db1d907d7593a94f1fe6293903e3e92967bebd6950ed12c/charset_normalizer-3.4.2-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:926ca93accd5d36ccdabd803392ddc3e03e6d4cd1cf17deff3b989ab8e9dbcf0", size = 199622 },
+    { url = "https://files.pythonhosted.org/packages/04/93/bf204e6f344c39d9937d3c13c8cd5bbfc266472e51fc8c07cb7f64fcd2de/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:eba9904b0f38a143592d9fc0e19e2df0fa2e41c3c3745554761c5f6447eedabf", size = 143435 },
+    { url = "https://files.pythonhosted.org/packages/22/2a/ea8a2095b0bafa6c5b5a55ffdc2f924455233ee7b91c69b7edfcc9e02284/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3fddb7e2c84ac87ac3a947cb4e66d143ca5863ef48e4a5ecb83bd48619e4634e", size = 153653 },
+    { url = "https://files.pythonhosted.org/packages/b6/57/1b090ff183d13cef485dfbe272e2fe57622a76694061353c59da52c9a659/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:98f862da73774290f251b9df8d11161b6cf25b599a66baf087c1ffe340e9bfd1", size = 146231 },
+    { url = "https://files.pythonhosted.org/packages/e2/28/ffc026b26f441fc67bd21ab7f03b313ab3fe46714a14b516f931abe1a2d8/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c9379d65defcab82d07b2a9dfbfc2e95bc8fe0ebb1b176a3190230a3ef0e07c", size = 148243 },
+    { url = "https://files.pythonhosted.org/packages/c0/0f/9abe9bd191629c33e69e47c6ef45ef99773320e9ad8e9cb08b8ab4a8d4cb/charset_normalizer-3.4.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e635b87f01ebc977342e2697d05b56632f5f879a4f15955dfe8cef2448b51691", size = 150442 },
+    { url = "https://files.pythonhosted.org/packages/67/7c/a123bbcedca91d5916c056407f89a7f5e8fdfce12ba825d7d6b9954a1a3c/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:1c95a1e2902a8b722868587c0e1184ad5c55631de5afc0eb96bc4b0d738092c0", size = 145147 },
+    { url = "https://files.pythonhosted.org/packages/ec/fe/1ac556fa4899d967b83e9893788e86b6af4d83e4726511eaaad035e36595/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:ef8de666d6179b009dce7bcb2ad4c4a779f113f12caf8dc77f0162c29d20490b", size = 153057 },
+    { url = "https://files.pythonhosted.org/packages/2b/ff/acfc0b0a70b19e3e54febdd5301a98b72fa07635e56f24f60502e954c461/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:32fc0341d72e0f73f80acb0a2c94216bd704f4f0bce10aedea38f30502b271ff", size = 156454 },
+    { url = "https://files.pythonhosted.org/packages/92/08/95b458ce9c740d0645feb0e96cea1f5ec946ea9c580a94adfe0b617f3573/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:289200a18fa698949d2b39c671c2cc7a24d44096784e76614899a7ccf2574b7b", size = 154174 },
+    { url = "https://files.pythonhosted.org/packages/78/be/8392efc43487ac051eee6c36d5fbd63032d78f7728cb37aebcc98191f1ff/charset_normalizer-3.4.2-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:4a476b06fbcf359ad25d34a057b7219281286ae2477cc5ff5e3f70a246971148", size = 149166 },
+    { url = "https://files.pythonhosted.org/packages/44/96/392abd49b094d30b91d9fbda6a69519e95802250b777841cf3bda8fe136c/charset_normalizer-3.4.2-cp313-cp313-win32.whl", hash = "sha256:aaeeb6a479c7667fbe1099af9617c83aaca22182d6cf8c53966491a0f1b7ffb7", size = 98064 },
+    { url = "https://files.pythonhosted.org/packages/e9/b0/0200da600134e001d91851ddc797809e2fe0ea72de90e09bec5a2fbdaccb/charset_normalizer-3.4.2-cp313-cp313-win_amd64.whl", hash = "sha256:aa6af9e7d59f9c12b33ae4e9450619cf2488e2bbe9b44030905877f0b2324980", size = 105641 },
+    { url = "https://files.pythonhosted.org/packages/20/94/c5790835a017658cbfabd07f3bfb549140c3ac458cfc196323996b10095a/charset_normalizer-3.4.2-py3-none-any.whl", hash = "sha256:7f56930ab0abd1c45cd15be65cc741c28b1c9a34876ce8c17a2fa107810c0af0", size = 52626 },
+]
+
+[[package]]
+name = "click"
+version = "8.2.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/60/6c/8ca2efa64cf75a977a0d7fac081354553ebe483345c734fb6b6515d96bbc/click-8.2.1.tar.gz", hash = "sha256:27c491cc05d968d271d5a1db13e3b5a184636d9d930f148c50b038f0d0646202", size = 286342 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/85/32/10bb5764d90a8eee674e9dc6f4db6a0ab47c8c4d0d83c27f7c39ac415a4d/click-8.2.1-py3-none-any.whl", hash = "sha256:61a3265b914e850b85317d0b3109c7f8cd35a670f963866005d6ef1d5175a12b", size = 102215 },
+]
+
+[[package]]
+name = "colorama"
+version = "0.4.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/d8/53/6f443c9a4a8358a93a6792e2acffb9d9d5cb0a5cfd8802644b7b1c9a02e4/colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44", size = 27697 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335 },
+]
+
+[[package]]
+name = "distro"
+version = "1.9.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/fc/f8/98eea607f65de6527f8a2e8885fc8015d3e6f5775df186e443e0964a11c3/distro-1.9.0.tar.gz", hash = "sha256:2fa77c6fd8940f116ee1d6b94a2f90b13b5ea8d019b98bc8bafdcabcdd9bdbed", size = 60722 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl", hash = "sha256:7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2", size = 20277 },
+]
+
+[[package]]
+name = "fastapi"
+version = "0.116.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pydantic" },
+    { name = "starlette" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/78/d7/6c8b3bfe33eeffa208183ec037fee0cce9f7f024089ab1c5d12ef04bd27c/fastapi-0.116.1.tar.gz", hash = "sha256:ed52cbf946abfd70c5a0dccb24673f0670deeb517a88b3544d03c2a6bf283143", size = 296485 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e5/47/d63c60f59a59467fda0f93f46335c9d18526d7071f025cb5b89d5353ea42/fastapi-0.116.1-py3-none-any.whl", hash = "sha256:c46ac7c312df840f0c9e220f7964bada936781bc4e2e6eb71f1c4d7553786565", size = 95631 },
+]
+
+[[package]]
+name = "google-api-core"
+version = "2.25.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-auth" },
+    { name = "googleapis-common-protos" },
+    { name = "proto-plus" },
+    { name = "protobuf" },
+    { name = "requests" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/dc/21/e9d043e88222317afdbdb567165fdbc3b0aad90064c7e0c9eb0ad9955ad8/google_api_core-2.25.1.tar.gz", hash = "sha256:d2aaa0b13c78c61cb3f4282c464c046e45fbd75755683c9c525e6e8f7ed0a5e8", size = 165443 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/14/4b/ead00905132820b623732b175d66354e9d3e69fcf2a5dcdab780664e7896/google_api_core-2.25.1-py3-none-any.whl", hash = "sha256:8a2a56c1fef82987a524371f99f3bd0143702fecc670c72e600c1cda6bf8dbb7", size = 160807 },
+]
+
+[package.optional-dependencies]
+grpc = [
+    { name = "grpcio" },
+    { name = "grpcio-status" },
+]
+
+[[package]]
+name = "google-auth"
+version = "2.40.3"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "cachetools" },
+    { name = "pyasn1-modules" },
+    { name = "rsa" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9e/9b/e92ef23b84fa10a64ce4831390b7a4c2e53c0132568d99d4ae61d04c8855/google_auth-2.40.3.tar.gz", hash = "sha256:500c3a29adedeb36ea9cf24b8d10858e152f2412e3ca37829b3fa18e33d63b77", size = 281029 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/17/63/b19553b658a1692443c62bd07e5868adaa0ad746a0751ba62c59568cd45b/google_auth-2.40.3-py2.py3-none-any.whl", hash = "sha256:1370d4593e86213563547f97a92752fc658456fe4514c809544f330fed45a7ca", size = 216137 },
+]
+
+[[package]]
+name = "google-cloud-speech"
+version = "2.33.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-api-core", extra = ["grpc"] },
+    { name = "google-auth" },
+    { name = "proto-plus" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/9a/74/9c5a556f8af19cab461058aa15e1409e7afa453ca2383473a24a12801ef7/google_cloud_speech-2.33.0.tar.gz", hash = "sha256:fd08511b5124fdaa768d71a4054e84a5d8eb02531cb6f84f311c0387ea1314ed", size = 389072 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/12/1d/880342b2541b4bad888ad8ab2ac77d4b5dad25b32a2a1c5f21140c14c8e3/google_cloud_speech-2.33.0-py3-none-any.whl", hash = "sha256:4ba16c8517c24a6abcde877289b0f40b719090504bf06b1adea248198ccd50a5", size = 335681 },
+]
+
+[[package]]
+name = "google-cloud-texttospeech"
+version = "2.27.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "google-api-core", extra = ["grpc"] },
+    { name = "google-auth" },
+    { name = "proto-plus" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/3b/65/0873b430c2ad885bde9649bfcdc9e87dca0ad400da4ff1495f62911baa36/google_cloud_texttospeech-2.27.0.tar.gz", hash = "sha256:94a382c95b7cc58efd2505a24c2968e2614fc6bdf9d76fb9a819d4ed29ae188e", size = 182332 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d8/40/1560257fb77b601c0801b370411e0b849b278a90e6232b46c5b84489fb67/google_cloud_texttospeech-2.27.0-py3-none-any.whl", hash = "sha256:0f7c5fe05281beb6d005ea191f61c913085e8439e5ffd2d5d21e29d106150b54", size = 189408 },
+]
+
+[[package]]
+name = "googleapis-common-protos"
+version = "1.70.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/39/24/33db22342cf4a2ea27c9955e6713140fedd51e8b141b5ce5260897020f1a/googleapis_common_protos-1.70.0.tar.gz", hash = "sha256:0e1b44e0ea153e6594f9f394fef15193a68aaaea2d843f83e2742717ca753257", size = 145903 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/86/f1/62a193f0227cf15a920390abe675f386dec35f7ae3ffe6da582d3ade42c7/googleapis_common_protos-1.70.0-py3-none-any.whl", hash = "sha256:b8bfcca8c25a2bb253e0e0b0adaf8c00773e5e6af6fd92397576680b807e0fd8", size = 294530 },
+]
+
+[[package]]
+name = "grpcio"
+version = "1.73.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/79/e8/b43b851537da2e2f03fa8be1aef207e5cbfb1a2e014fbb6b40d24c177cd3/grpcio-1.73.1.tar.gz", hash = "sha256:7fce2cd1c0c1116cf3850564ebfc3264fba75d3c74a7414373f1238ea365ef87", size = 12730355 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e4/41/921565815e871d84043e73e2c0e748f0318dab6fa9be872cd042778f14a9/grpcio-1.73.1-cp311-cp311-linux_armv7l.whl", hash = "sha256:ba2cea9f7ae4bc21f42015f0ec98f69ae4179848ad744b210e7685112fa507a1", size = 5363853 },
+    { url = "https://files.pythonhosted.org/packages/b0/cc/9c51109c71d068e4d474becf5f5d43c9d63038cec1b74112978000fa72f4/grpcio-1.73.1-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:d74c3f4f37b79e746271aa6cdb3a1d7e4432aea38735542b23adcabaaee0c097", size = 10621476 },
+    { url = "https://files.pythonhosted.org/packages/8f/d3/33d738a06f6dbd4943f4d377468f8299941a7c8c6ac8a385e4cef4dd3c93/grpcio-1.73.1-cp311-cp311-manylinux_2_17_aarch64.whl", hash = "sha256:5b9b1805a7d61c9e90541cbe8dfe0a593dfc8c5c3a43fe623701b6a01b01d710", size = 5807903 },
+    { url = "https://files.pythonhosted.org/packages/5d/47/36deacd3c967b74e0265f4c608983e897d8bb3254b920f8eafdf60e4ad7e/grpcio-1.73.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b3215f69a0670a8cfa2ab53236d9e8026bfb7ead5d4baabe7d7dc11d30fda967", size = 6448172 },
+    { url = "https://files.pythonhosted.org/packages/0e/64/12d6dc446021684ee1428ea56a3f3712048a18beeadbdefa06e6f8814a6e/grpcio-1.73.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc5eccfd9577a5dc7d5612b2ba90cca4ad14c6d949216c68585fdec9848befb1", size = 6044226 },
+    { url = "https://files.pythonhosted.org/packages/72/4b/6bae2d88a006000f1152d2c9c10ffd41d0131ca1198e0b661101c2e30ab9/grpcio-1.73.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:dc7d7fd520614fce2e6455ba89791458020a39716951c7c07694f9dbae28e9c0", size = 6135690 },
+    { url = "https://files.pythonhosted.org/packages/38/64/02c83b5076510784d1305025e93e0d78f53bb6a0213c8c84cfe8a00c5c48/grpcio-1.73.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:105492124828911f85127e4825d1c1234b032cb9d238567876b5515d01151379", size = 6775867 },
+    { url = "https://files.pythonhosted.org/packages/42/72/a13ff7ba6c68ccffa35dacdc06373a76c0008fd75777cba84d7491956620/grpcio-1.73.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:610e19b04f452ba6f402ac9aa94eb3d21fbc94553368008af634812c4a85a99e", size = 6308380 },
+    { url = "https://files.pythonhosted.org/packages/65/ae/d29d948021faa0070ec33245c1ae354e2aefabd97e6a9a7b6dcf0fb8ef6b/grpcio-1.73.1-cp311-cp311-win32.whl", hash = "sha256:d60588ab6ba0ac753761ee0e5b30a29398306401bfbceffe7d68ebb21193f9d4", size = 3679139 },
+    { url = "https://files.pythonhosted.org/packages/af/66/e1bbb0c95ea222947f0829b3db7692c59b59bcc531df84442e413fa983d9/grpcio-1.73.1-cp311-cp311-win_amd64.whl", hash = "sha256:6957025a4608bb0a5ff42abd75bfbb2ed99eda29d5992ef31d691ab54b753643", size = 4342558 },
+    { url = "https://files.pythonhosted.org/packages/b8/41/456caf570c55d5ac26f4c1f2db1f2ac1467d5bf3bcd660cba3e0a25b195f/grpcio-1.73.1-cp312-cp312-linux_armv7l.whl", hash = "sha256:921b25618b084e75d424a9f8e6403bfeb7abef074bb6c3174701e0f2542debcf", size = 5334621 },
+    { url = "https://files.pythonhosted.org/packages/2a/c2/9a15e179e49f235bb5e63b01590658c03747a43c9775e20c4e13ca04f4c4/grpcio-1.73.1-cp312-cp312-macosx_11_0_universal2.whl", hash = "sha256:277b426a0ed341e8447fbf6c1d6b68c952adddf585ea4685aa563de0f03df887", size = 10601131 },
+    { url = "https://files.pythonhosted.org/packages/0c/1d/1d39e90ef6348a0964caa7c5c4d05f3bae2c51ab429eb7d2e21198ac9b6d/grpcio-1.73.1-cp312-cp312-manylinux_2_17_aarch64.whl", hash = "sha256:96c112333309493c10e118d92f04594f9055774757f5d101b39f8150f8c25582", size = 5759268 },
+    { url = "https://files.pythonhosted.org/packages/8a/2b/2dfe9ae43de75616177bc576df4c36d6401e0959833b2e5b2d58d50c1f6b/grpcio-1.73.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f48e862aed925ae987eb7084409a80985de75243389dc9d9c271dd711e589918", size = 6409791 },
+    { url = "https://files.pythonhosted.org/packages/6e/66/e8fe779b23b5a26d1b6949e5c70bc0a5fd08f61a6ec5ac7760d589229511/grpcio-1.73.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:83a6c2cce218e28f5040429835fa34a29319071079e3169f9543c3fbeff166d2", size = 6003728 },
+    { url = "https://files.pythonhosted.org/packages/a9/39/57a18fcef567784108c4fc3f5441cb9938ae5a51378505aafe81e8e15ecc/grpcio-1.73.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:65b0458a10b100d815a8426b1442bd17001fdb77ea13665b2f7dc9e8587fdc6b", size = 6103364 },
+    { url = "https://files.pythonhosted.org/packages/c5/46/28919d2aa038712fc399d02fa83e998abd8c1f46c2680c5689deca06d1b2/grpcio-1.73.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:0a9f3ea8dce9eae9d7cb36827200133a72b37a63896e0e61a9d5ec7d61a59ab1", size = 6749194 },
+    { url = "https://files.pythonhosted.org/packages/3d/56/3898526f1fad588c5d19a29ea0a3a4996fb4fa7d7c02dc1be0c9fd188b62/grpcio-1.73.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:de18769aea47f18e782bf6819a37c1c528914bfd5683b8782b9da356506190c8", size = 6283902 },
+    { url = "https://files.pythonhosted.org/packages/dc/64/18b77b89c5870d8ea91818feb0c3ffb5b31b48d1b0ee3e0f0d539730fea3/grpcio-1.73.1-cp312-cp312-win32.whl", hash = "sha256:24e06a5319e33041e322d32c62b1e728f18ab8c9dbc91729a3d9f9e3ed336642", size = 3668687 },
+    { url = "https://files.pythonhosted.org/packages/3c/52/302448ca6e52f2a77166b2e2ed75f5d08feca4f2145faf75cb768cccb25b/grpcio-1.73.1-cp312-cp312-win_amd64.whl", hash = "sha256:303c8135d8ab176f8038c14cc10d698ae1db9c480f2b2823f7a987aa2a4c5646", size = 4334887 },
+    { url = "https://files.pythonhosted.org/packages/37/bf/4ca20d1acbefabcaba633ab17f4244cbbe8eca877df01517207bd6655914/grpcio-1.73.1-cp313-cp313-linux_armv7l.whl", hash = "sha256:b310824ab5092cf74750ebd8a8a8981c1810cb2b363210e70d06ef37ad80d4f9", size = 5335615 },
+    { url = "https://files.pythonhosted.org/packages/75/ed/45c345f284abec5d4f6d77cbca9c52c39b554397eb7de7d2fcf440bcd049/grpcio-1.73.1-cp313-cp313-macosx_11_0_universal2.whl", hash = "sha256:8f5a6df3fba31a3485096ac85b2e34b9666ffb0590df0cd044f58694e6a1f6b5", size = 10595497 },
+    { url = "https://files.pythonhosted.org/packages/a4/75/bff2c2728018f546d812b755455014bc718f8cdcbf5c84f1f6e5494443a8/grpcio-1.73.1-cp313-cp313-manylinux_2_17_aarch64.whl", hash = "sha256:052e28fe9c41357da42250a91926a3e2f74c046575c070b69659467ca5aa976b", size = 5765321 },
+    { url = "https://files.pythonhosted.org/packages/70/3b/14e43158d3b81a38251b1d231dfb45a9b492d872102a919fbf7ba4ac20cd/grpcio-1.73.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1c0bf15f629b1497436596b1cbddddfa3234273490229ca29561209778ebe182", size = 6415436 },
+    { url = "https://files.pythonhosted.org/packages/e5/3f/81d9650ca40b54338336fd360f36773be8cb6c07c036e751d8996eb96598/grpcio-1.73.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0ab860d5bfa788c5a021fba264802e2593688cd965d1374d31d2b1a34cacd854", size = 6007012 },
+    { url = "https://files.pythonhosted.org/packages/55/f4/59edf5af68d684d0f4f7ad9462a418ac517201c238551529098c9aa28cb0/grpcio-1.73.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:ad1d958c31cc91ab050bd8a91355480b8e0683e21176522bacea225ce51163f2", size = 6105209 },
+    { url = "https://files.pythonhosted.org/packages/e4/a8/700d034d5d0786a5ba14bfa9ce974ed4c976936c2748c2bd87aa50f69b36/grpcio-1.73.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:f43ffb3bd415c57224c7427bfb9e6c46a0b6e998754bfa0d00f408e1873dcbb5", size = 6753655 },
+    { url = "https://files.pythonhosted.org/packages/1f/29/efbd4ac837c23bc48e34bbaf32bd429f0dc9ad7f80721cdb4622144c118c/grpcio-1.73.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:686231cdd03a8a8055f798b2b54b19428cdf18fa1549bee92249b43607c42668", size = 6287288 },
+    { url = "https://files.pythonhosted.org/packages/d8/61/c6045d2ce16624bbe18b5d169c1a5ce4d6c3a47bc9d0e5c4fa6a50ed1239/grpcio-1.73.1-cp313-cp313-win32.whl", hash = "sha256:89018866a096e2ce21e05eabed1567479713ebe57b1db7cbb0f1e3b896793ba4", size = 3668151 },
+    { url = "https://files.pythonhosted.org/packages/c2/d7/77ac689216daee10de318db5aa1b88d159432dc76a130948a56b3aa671a2/grpcio-1.73.1-cp313-cp313-win_amd64.whl", hash = "sha256:4a68f8c9966b94dff693670a5cf2b54888a48a5011c5d9ce2295a1a1465ee84f", size = 4335747 },
+]
+
+[[package]]
+name = "grpcio-status"
+version = "1.73.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "googleapis-common-protos" },
+    { name = "grpcio" },
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f6/59/9350a13804f2e407d76b3962c548e023639fc1545056e342c6bad0d4fd30/grpcio_status-1.73.1.tar.gz", hash = "sha256:928f49ccf9688db5f20cd9e45c4578a1d01ccca29aeaabf066f2ac76aa886668", size = 13664 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2e/50/ee32e6073e2c3a4457be168e2bbf84d02ad9d2c18c4a578a641480c293d4/grpcio_status-1.73.1-py3-none-any.whl", hash = "sha256:538595c32a6c819c32b46a621a51e9ae4ffcd7e7e1bce35f728ef3447e9809b6", size = 14422 },
+]
+
+[[package]]
+name = "h11"
+version = "0.16.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/01/ee/02a2c011bdab74c6fb3c75474d40b3052059d95df7e73351460c8588d963/h11-0.16.0.tar.gz", hash = "sha256:4e35b956cf45792e4caa5885e69fba00bdbc6ffafbfa020300e549b208ee5ff1", size = 101250 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/04/4b/29cac41a4d98d144bf5f6d33995617b185d14b22401f75ca86f384e87ff1/h11-0.16.0-py3-none-any.whl", hash = "sha256:63cf8bbe7522de3bf65932fda1d9c2772064ffb3dae62d55932da54b31cb6c86", size = 37515 },
+]
+
+[[package]]
+name = "httpcore"
+version = "1.0.9"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/06/94/82699a10bca87a5556c9c59b5963f2d039dbd239f25bc2a63907a05a14cb/httpcore-1.0.9.tar.gz", hash = "sha256:6e34463af53fd2ab5d807f399a9b45ea31c3dfa2276f15a2c3f00afff6e176e8", size = 85484 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7e/f5/f66802a942d491edb555dd61e3a9961140fd64c90bce1eafd741609d334d/httpcore-1.0.9-py3-none-any.whl", hash = "sha256:2d400746a40668fc9dec9810239072b40b4484b640a8c38fd654a024c7a1bf55", size = 78784 },
+]
+
+[[package]]
+name = "httpx"
+version = "0.28.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "certifi" },
+    { name = "httpcore" },
+    { name = "idna" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/b1/df/48c586a5fe32a0f01324ee087459e112ebb7224f646c0b5023f5e79e9956/httpx-0.28.1.tar.gz", hash = "sha256:75e98c5f16b0f35b567856f597f06ff2270a374470a5c2392242528e3e3e42fc", size = 141406 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2a/39/e50c7c3a983047577ee07d2a9e53faf5a69493943ec3f6a384bdc792deb2/httpx-0.28.1-py3-none-any.whl", hash = "sha256:d909fcccc110f8c7faf814ca82a9a4d816bc5a6dbfea25d6591d6985b8ba59ad", size = 73517 },
+]
+
+[[package]]
+name = "idna"
+version = "3.10"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f1/70/7703c29685631f5a7590aa73f1f1d3fa9a380e654b86af429e0934a32f7d/idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9", size = 190490 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/76/c6/c88e154df9c4e1a2a66ccf0005a88dfb2650c1dffb6f5ce603dfbd452ce3/idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3", size = 70442 },
+]
+
+[[package]]
+name = "iniconfig"
+version = "2.1.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f2/97/ebf4da567aa6827c909642694d71c9fcf53e5b504f2d96afea02718862f3/iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7", size = 4793 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/2c/e1/e6716421ea10d38022b952c159d5161ca1193197fb744506875fbb87ea7b/iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760", size = 6050 },
+]
+
+[[package]]
+name = "jiter"
+version = "0.10.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ee/9d/ae7ddb4b8ab3fb1b51faf4deb36cb48a4fbbd7cb36bad6a5fca4741306f7/jiter-0.10.0.tar.gz", hash = "sha256:07a7142c38aacc85194391108dc91b5b57093c978a9932bd86a36862759d9500", size = 162759 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/1b/dd/6cefc6bd68b1c3c979cecfa7029ab582b57690a31cd2f346c4d0ce7951b6/jiter-0.10.0-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:3bebe0c558e19902c96e99217e0b8e8b17d570906e72ed8a87170bc290b1e978", size = 317473 },
+    { url = "https://files.pythonhosted.org/packages/be/cf/fc33f5159ce132be1d8dd57251a1ec7a631c7df4bd11e1cd198308c6ae32/jiter-0.10.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:558cc7e44fd8e507a236bee6a02fa17199ba752874400a0ca6cd6e2196cdb7dc", size = 321971 },
+    { url = "https://files.pythonhosted.org/packages/68/a4/da3f150cf1d51f6c472616fb7650429c7ce053e0c962b41b68557fdf6379/jiter-0.10.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4d613e4b379a07d7c8453c5712ce7014e86c6ac93d990a0b8e7377e18505e98d", size = 345574 },
+    { url = "https://files.pythonhosted.org/packages/84/34/6e8d412e60ff06b186040e77da5f83bc158e9735759fcae65b37d681f28b/jiter-0.10.0-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:f62cf8ba0618eda841b9bf61797f21c5ebd15a7a1e19daab76e4e4b498d515b2", size = 371028 },
+    { url = "https://files.pythonhosted.org/packages/fb/d9/9ee86173aae4576c35a2f50ae930d2ccb4c4c236f6cb9353267aa1d626b7/jiter-0.10.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:919d139cdfa8ae8945112398511cb7fca58a77382617d279556b344867a37e61", size = 491083 },
+    { url = "https://files.pythonhosted.org/packages/d9/2c/f955de55e74771493ac9e188b0f731524c6a995dffdcb8c255b89c6fb74b/jiter-0.10.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:13ddbc6ae311175a3b03bd8994881bc4635c923754932918e18da841632349db", size = 388821 },
+    { url = "https://files.pythonhosted.org/packages/81/5a/0e73541b6edd3f4aada586c24e50626c7815c561a7ba337d6a7eb0a915b4/jiter-0.10.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c440ea003ad10927a30521a9062ce10b5479592e8a70da27f21eeb457b4a9c5", size = 352174 },
+    { url = "https://files.pythonhosted.org/packages/1c/c0/61eeec33b8c75b31cae42be14d44f9e6fe3ac15a4e58010256ac3abf3638/jiter-0.10.0-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:dc347c87944983481e138dea467c0551080c86b9d21de6ea9306efb12ca8f606", size = 391869 },
+    { url = "https://files.pythonhosted.org/packages/41/22/5beb5ee4ad4ef7d86f5ea5b4509f680a20706c4a7659e74344777efb7739/jiter-0.10.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:13252b58c1f4d8c5b63ab103c03d909e8e1e7842d302473f482915d95fefd605", size = 523741 },
+    { url = "https://files.pythonhosted.org/packages/ea/10/768e8818538e5817c637b0df52e54366ec4cebc3346108a4457ea7a98f32/jiter-0.10.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:7d1bbf3c465de4a24ab12fb7766a0003f6f9bce48b8b6a886158c4d569452dc5", size = 514527 },
+    { url = "https://files.pythonhosted.org/packages/73/6d/29b7c2dc76ce93cbedabfd842fc9096d01a0550c52692dfc33d3cc889815/jiter-0.10.0-cp311-cp311-win32.whl", hash = "sha256:db16e4848b7e826edca4ccdd5b145939758dadf0dc06e7007ad0e9cfb5928ae7", size = 210765 },
+    { url = "https://files.pythonhosted.org/packages/c2/c9/d394706deb4c660137caf13e33d05a031d734eb99c051142e039d8ceb794/jiter-0.10.0-cp311-cp311-win_amd64.whl", hash = "sha256:9c9c1d5f10e18909e993f9641f12fe1c77b3e9b533ee94ffa970acc14ded3812", size = 209234 },
+    { url = "https://files.pythonhosted.org/packages/6d/b5/348b3313c58f5fbfb2194eb4d07e46a35748ba6e5b3b3046143f3040bafa/jiter-0.10.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:1e274728e4a5345a6dde2d343c8da018b9d4bd4350f5a472fa91f66fda44911b", size = 312262 },
+    { url = "https://files.pythonhosted.org/packages/9c/4a/6a2397096162b21645162825f058d1709a02965606e537e3304b02742e9b/jiter-0.10.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:7202ae396446c988cb2a5feb33a543ab2165b786ac97f53b59aafb803fef0744", size = 320124 },
+    { url = "https://files.pythonhosted.org/packages/2a/85/1ce02cade7516b726dd88f59a4ee46914bf79d1676d1228ef2002ed2f1c9/jiter-0.10.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:23ba7722d6748b6920ed02a8f1726fb4b33e0fd2f3f621816a8b486c66410ab2", size = 345330 },
+    { url = "https://files.pythonhosted.org/packages/75/d0/bb6b4f209a77190ce10ea8d7e50bf3725fc16d3372d0a9f11985a2b23eff/jiter-0.10.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:371eab43c0a288537d30e1f0b193bc4eca90439fc08a022dd83e5e07500ed026", size = 369670 },
+    { url = "https://files.pythonhosted.org/packages/a0/f5/a61787da9b8847a601e6827fbc42ecb12be2c925ced3252c8ffcb56afcaf/jiter-0.10.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:6c675736059020365cebc845a820214765162728b51ab1e03a1b7b3abb70f74c", size = 489057 },
+    { url = "https://files.pythonhosted.org/packages/12/e4/6f906272810a7b21406c760a53aadbe52e99ee070fc5c0cb191e316de30b/jiter-0.10.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0c5867d40ab716e4684858e4887489685968a47e3ba222e44cde6e4a2154f959", size = 389372 },
+    { url = "https://files.pythonhosted.org/packages/e2/ba/77013b0b8ba904bf3762f11e0129b8928bff7f978a81838dfcc958ad5728/jiter-0.10.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:395bb9a26111b60141757d874d27fdea01b17e8fac958b91c20128ba8f4acc8a", size = 352038 },
+    { url = "https://files.pythonhosted.org/packages/67/27/c62568e3ccb03368dbcc44a1ef3a423cb86778a4389e995125d3d1aaa0a4/jiter-0.10.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:6842184aed5cdb07e0c7e20e5bdcfafe33515ee1741a6835353bb45fe5d1bd95", size = 391538 },
+    { url = "https://files.pythonhosted.org/packages/c0/72/0d6b7e31fc17a8fdce76164884edef0698ba556b8eb0af9546ae1a06b91d/jiter-0.10.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:62755d1bcea9876770d4df713d82606c8c1a3dca88ff39046b85a048566d56ea", size = 523557 },
+    { url = "https://files.pythonhosted.org/packages/2f/09/bc1661fbbcbeb6244bd2904ff3a06f340aa77a2b94e5a7373fd165960ea3/jiter-0.10.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:533efbce2cacec78d5ba73a41756beff8431dfa1694b6346ce7af3a12c42202b", size = 514202 },
+    { url = "https://files.pythonhosted.org/packages/1b/84/5a5d5400e9d4d54b8004c9673bbe4403928a00d28529ff35b19e9d176b19/jiter-0.10.0-cp312-cp312-win32.whl", hash = "sha256:8be921f0cadd245e981b964dfbcd6fd4bc4e254cdc069490416dd7a2632ecc01", size = 211781 },
+    { url = "https://files.pythonhosted.org/packages/9b/52/7ec47455e26f2d6e5f2ea4951a0652c06e5b995c291f723973ae9e724a65/jiter-0.10.0-cp312-cp312-win_amd64.whl", hash = "sha256:a7c7d785ae9dda68c2678532a5a1581347e9c15362ae9f6e68f3fdbfb64f2e49", size = 206176 },
+    { url = "https://files.pythonhosted.org/packages/2e/b0/279597e7a270e8d22623fea6c5d4eeac328e7d95c236ed51a2b884c54f70/jiter-0.10.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:e0588107ec8e11b6f5ef0e0d656fb2803ac6cf94a96b2b9fc675c0e3ab5e8644", size = 311617 },
+    { url = "https://files.pythonhosted.org/packages/91/e3/0916334936f356d605f54cc164af4060e3e7094364add445a3bc79335d46/jiter-0.10.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:cafc4628b616dc32530c20ee53d71589816cf385dd9449633e910d596b1f5c8a", size = 318947 },
+    { url = "https://files.pythonhosted.org/packages/6a/8e/fd94e8c02d0e94539b7d669a7ebbd2776e51f329bb2c84d4385e8063a2ad/jiter-0.10.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:520ef6d981172693786a49ff5b09eda72a42e539f14788124a07530f785c3ad6", size = 344618 },
+    { url = "https://files.pythonhosted.org/packages/6f/b0/f9f0a2ec42c6e9c2e61c327824687f1e2415b767e1089c1d9135f43816bd/jiter-0.10.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:554dedfd05937f8fc45d17ebdf298fe7e0c77458232bcb73d9fbbf4c6455f5b3", size = 368829 },
+    { url = "https://files.pythonhosted.org/packages/e8/57/5bbcd5331910595ad53b9fd0c610392ac68692176f05ae48d6ce5c852967/jiter-0.10.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5bc299da7789deacf95f64052d97f75c16d4fc8c4c214a22bf8d859a4288a1c2", size = 491034 },
+    { url = "https://files.pythonhosted.org/packages/9b/be/c393df00e6e6e9e623a73551774449f2f23b6ec6a502a3297aeeece2c65a/jiter-0.10.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5161e201172de298a8a1baad95eb85db4fb90e902353b1f6a41d64ea64644e25", size = 388529 },
+    { url = "https://files.pythonhosted.org/packages/42/3e/df2235c54d365434c7f150b986a6e35f41ebdc2f95acea3036d99613025d/jiter-0.10.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e2227db6ba93cb3e2bf67c87e594adde0609f146344e8207e8730364db27041", size = 350671 },
+    { url = "https://files.pythonhosted.org/packages/c6/77/71b0b24cbcc28f55ab4dbfe029f9a5b73aeadaba677843fc6dc9ed2b1d0a/jiter-0.10.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:15acb267ea5e2c64515574b06a8bf393fbfee6a50eb1673614aa45f4613c0cca", size = 390864 },
+    { url = "https://files.pythonhosted.org/packages/6a/d3/ef774b6969b9b6178e1d1e7a89a3bd37d241f3d3ec5f8deb37bbd203714a/jiter-0.10.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:901b92f2e2947dc6dfcb52fd624453862e16665ea909a08398dde19c0731b7f4", size = 522989 },
+    { url = "https://files.pythonhosted.org/packages/0c/41/9becdb1d8dd5d854142f45a9d71949ed7e87a8e312b0bede2de849388cb9/jiter-0.10.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:d0cb9a125d5a3ec971a094a845eadde2db0de85b33c9f13eb94a0c63d463879e", size = 513495 },
+    { url = "https://files.pythonhosted.org/packages/9c/36/3468e5a18238bdedae7c4d19461265b5e9b8e288d3f86cd89d00cbb48686/jiter-0.10.0-cp313-cp313-win32.whl", hash = "sha256:48a403277ad1ee208fb930bdf91745e4d2d6e47253eedc96e2559d1e6527006d", size = 211289 },
+    { url = "https://files.pythonhosted.org/packages/7e/07/1c96b623128bcb913706e294adb5f768fb7baf8db5e1338ce7b4ee8c78ef/jiter-0.10.0-cp313-cp313-win_amd64.whl", hash = "sha256:75f9eb72ecb640619c29bf714e78c9c46c9c4eaafd644bf78577ede459f330d4", size = 205074 },
+    { url = "https://files.pythonhosted.org/packages/54/46/caa2c1342655f57d8f0f2519774c6d67132205909c65e9aa8255e1d7b4f4/jiter-0.10.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:28ed2a4c05a1f32ef0e1d24c2611330219fed727dae01789f4a335617634b1ca", size = 318225 },
+    { url = "https://files.pythonhosted.org/packages/43/84/c7d44c75767e18946219ba2d703a5a32ab37b0bc21886a97bc6062e4da42/jiter-0.10.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14a4c418b1ec86a195f1ca69da8b23e8926c752b685af665ce30777233dfe070", size = 350235 },
+    { url = "https://files.pythonhosted.org/packages/01/16/f5a0135ccd968b480daad0e6ab34b0c7c5ba3bc447e5088152696140dcb3/jiter-0.10.0-cp313-cp313t-win_amd64.whl", hash = "sha256:d7bfed2fe1fe0e4dda6ef682cee888ba444b21e7a6553e03252e4feb6cf0adca", size = 207278 },
+    { url = "https://files.pythonhosted.org/packages/1c/9b/1d646da42c3de6c2188fdaa15bce8ecb22b635904fc68be025e21249ba44/jiter-0.10.0-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:5e9251a5e83fab8d87799d3e1a46cb4b7f2919b895c6f4483629ed2446f66522", size = 310866 },
+    { url = "https://files.pythonhosted.org/packages/ad/0e/26538b158e8a7c7987e94e7aeb2999e2e82b1f9d2e1f6e9874ddf71ebda0/jiter-0.10.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:023aa0204126fe5b87ccbcd75c8a0d0261b9abdbbf46d55e7ae9f8e22424eeb8", size = 318772 },
+    { url = "https://files.pythonhosted.org/packages/7b/fb/d302893151caa1c2636d6574d213e4b34e31fd077af6050a9c5cbb42f6fb/jiter-0.10.0-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3c189c4f1779c05f75fc17c0c1267594ed918996a231593a21a5ca5438445216", size = 344534 },
+    { url = "https://files.pythonhosted.org/packages/01/d8/5780b64a149d74e347c5128d82176eb1e3241b1391ac07935693466d6219/jiter-0.10.0-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:15720084d90d1098ca0229352607cd68256c76991f6b374af96f36920eae13c4", size = 369087 },
+    { url = "https://files.pythonhosted.org/packages/e8/5b/f235a1437445160e777544f3ade57544daf96ba7e96c1a5b24a6f7ac7004/jiter-0.10.0-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e4f2fb68e5f1cfee30e2b2a09549a00683e0fde4c6a2ab88c94072fc33cb7426", size = 490694 },
+    { url = "https://files.pythonhosted.org/packages/85/a9/9c3d4617caa2ff89cf61b41e83820c27ebb3f7b5fae8a72901e8cd6ff9be/jiter-0.10.0-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ce541693355fc6da424c08b7edf39a2895f58d6ea17d92cc2b168d20907dee12", size = 388992 },
+    { url = "https://files.pythonhosted.org/packages/68/b1/344fd14049ba5c94526540af7eb661871f9c54d5f5601ff41a959b9a0bbd/jiter-0.10.0-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:31c50c40272e189d50006ad5c73883caabb73d4e9748a688b216e85a9a9ca3b9", size = 351723 },
+    { url = "https://files.pythonhosted.org/packages/41/89/4c0e345041186f82a31aee7b9d4219a910df672b9fef26f129f0cda07a29/jiter-0.10.0-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:fa3402a2ff9815960e0372a47b75c76979d74402448509ccd49a275fa983ef8a", size = 392215 },
+    { url = "https://files.pythonhosted.org/packages/55/58/ee607863e18d3f895feb802154a2177d7e823a7103f000df182e0f718b38/jiter-0.10.0-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:1956f934dca32d7bb647ea21d06d93ca40868b505c228556d3373cbd255ce853", size = 522762 },
+    { url = "https://files.pythonhosted.org/packages/15/d0/9123fb41825490d16929e73c212de9a42913d68324a8ce3c8476cae7ac9d/jiter-0.10.0-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:fcedb049bdfc555e261d6f65a6abe1d5ad68825b7202ccb9692636c70fcced86", size = 513427 },
+    { url = "https://files.pythonhosted.org/packages/d8/b3/2bd02071c5a2430d0b70403a34411fc519c2f227da7b03da9ba6a956f931/jiter-0.10.0-cp314-cp314-win32.whl", hash = "sha256:ac509f7eccca54b2a29daeb516fb95b6f0bd0d0d8084efaf8ed5dfc7b9f0b357", size = 210127 },
+    { url = "https://files.pythonhosted.org/packages/03/0c/5fe86614ea050c3ecd728ab4035534387cd41e7c1855ef6c031f1ca93e3f/jiter-0.10.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:5ed975b83a2b8639356151cef5c0d597c68376fc4922b45d0eb384ac058cfa00", size = 318527 },
+    { url = "https://files.pythonhosted.org/packages/b3/4a/4175a563579e884192ba6e81725fc0448b042024419be8d83aa8a80a3f44/jiter-0.10.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3aa96f2abba33dc77f79b4cf791840230375f9534e5fac927ccceb58c5e604a5", size = 354213 },
+]
+
+[[package]]
+name = "learn-indonesian-backend"
+version = "0.1.0"
+source = { editable = "." }
+dependencies = [
+    { name = "fastapi" },
+    { name = "google-cloud-speech" },
+    { name = "google-cloud-texttospeech" },
+    { name = "openai" },
+    { name = "pydantic" },
+    { name = "python-dotenv" },
+    { name = "python-multipart" },
+    { name = "uvicorn" },
+    { name = "websockets" },
+]
+
+[package.dev-dependencies]
+dev = [
+    { name = "httpx" },
+    { name = "pytest" },
+    { name = "pytest-asyncio" },
+    { name = "ruff" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "fastapi", specifier = ">=0.104.1" },
+    { name = "google-cloud-speech", specifier = ">=2.21.0" },
+    { name = "google-cloud-texttospeech", specifier = ">=2.14.2" },
+    { name = "openai", specifier = ">=1.0.0" },
+    { name = "pydantic", specifier = ">=2.5.0" },
+    { name = "python-dotenv", specifier = ">=1.0.0" },
+    { name = "python-multipart", specifier = ">=0.0.6" },
+    { name = "uvicorn", specifier = ">=0.24.0" },
+    { name = "websockets", specifier = ">=11.0.3" },
+]
+
+[package.metadata.requires-dev]
+dev = [
+    { name = "httpx", specifier = ">=0.25.2" },
+    { name = "pytest", specifier = ">=7.4.3" },
+    { name = "pytest-asyncio", specifier = ">=0.21.1" },
+    { name = "ruff", specifier = ">=0.1.6" },
+]
+
+[[package]]
+name = "openai"
+version = "1.95.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "distro" },
+    { name = "httpx" },
+    { name = "jiter" },
+    { name = "pydantic" },
+    { name = "sniffio" },
+    { name = "tqdm" },
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a1/a3/70cd57c7d71086c532ce90de5fdef4165dc6ae9dbf346da6737ff9ebafaa/openai-1.95.1.tar.gz", hash = "sha256:f089b605282e2a2b6776090b4b46563ac1da77f56402a222597d591e2dcc1086", size = 488271 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/02/1d/0432ea635097f4dbb34641a3650803d8a4aa29d06bafc66583bf1adcceb4/openai-1.95.1-py3-none-any.whl", hash = "sha256:8bbdfeceef231b1ddfabbc232b179d79f8b849aab5a7da131178f8d10e0f162f", size = 755613 },
+]
+
+[[package]]
+name = "packaging"
+version = "25.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a1/d4/1fc4078c65507b51b96ca8f8c3ba19e6a61c8253c72794544580a7b6c24d/packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f", size = 165727 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/20/12/38679034af332785aac8774540895e234f4d07f7545804097de4b666afd8/packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484", size = 66469 },
+]
+
+[[package]]
+name = "pluggy"
+version = "1.6.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f9/e2/3e91f31a7d2b083fe6ef3fa267035b518369d9511ffab804f839851d2779/pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3", size = 69412 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/54/20/4d324d65cc6d9205fabedc306948156824eb9f0ee1633355a8f7ec5c66bf/pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746", size = 20538 },
+]
+
+[[package]]
+name = "proto-plus"
+version = "1.26.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "protobuf" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f4/ac/87285f15f7cce6d4a008f33f1757fb5a13611ea8914eb58c3d0d26243468/proto_plus-1.26.1.tar.gz", hash = "sha256:21a515a4c4c0088a773899e23c7bbade3d18f9c66c73edd4c7ee3816bc96a012", size = 56142 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/4e/6d/280c4c2ce28b1593a19ad5239c8b826871fc6ec275c21afc8e1820108039/proto_plus-1.26.1-py3-none-any.whl", hash = "sha256:13285478c2dcf2abb829db158e1047e2f1e8d63a077d94263c2b88b043c75a66", size = 50163 },
+]
+
+[[package]]
+name = "protobuf"
+version = "6.31.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/52/f3/b9655a711b32c19720253f6f06326faf90580834e2e83f840472d752bc8b/protobuf-6.31.1.tar.gz", hash = "sha256:d8cac4c982f0b957a4dc73a80e2ea24fab08e679c0de9deb835f4a12d69aca9a", size = 441797 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f3/6f/6ab8e4bf962fd5570d3deaa2d5c38f0a363f57b4501047b5ebeb83ab1125/protobuf-6.31.1-cp310-abi3-win32.whl", hash = "sha256:7fa17d5a29c2e04b7d90e5e32388b8bfd0e7107cd8e616feef7ed3fa6bdab5c9", size = 423603 },
+    { url = "https://files.pythonhosted.org/packages/44/3a/b15c4347dd4bf3a1b0ee882f384623e2063bb5cf9fa9d57990a4f7df2fb6/protobuf-6.31.1-cp310-abi3-win_amd64.whl", hash = "sha256:426f59d2964864a1a366254fa703b8632dcec0790d8862d30034d8245e1cd447", size = 435283 },
+    { url = "https://files.pythonhosted.org/packages/6a/c9/b9689a2a250264a84e66c46d8862ba788ee7a641cdca39bccf64f59284b7/protobuf-6.31.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:6f1227473dc43d44ed644425268eb7c2e488ae245d51c6866d19fe158e207402", size = 425604 },
+    { url = "https://files.pythonhosted.org/packages/76/a1/7a5a94032c83375e4fe7e7f56e3976ea6ac90c5e85fac8576409e25c39c3/protobuf-6.31.1-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:a40fc12b84c154884d7d4c4ebd675d5b3b5283e155f324049ae396b95ddebc39", size = 322115 },
+    { url = "https://files.pythonhosted.org/packages/fa/b1/b59d405d64d31999244643d88c45c8241c58f17cc887e73bcb90602327f8/protobuf-6.31.1-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:4ee898bf66f7a8b0bd21bce523814e6fbd8c6add948045ce958b73af7e8878c6", size = 321070 },
+    { url = "https://files.pythonhosted.org/packages/f7/af/ab3c51ab7507a7325e98ffe691d9495ee3d3aa5f589afad65ec920d39821/protobuf-6.31.1-py3-none-any.whl", hash = "sha256:720a6c7e6b77288b85063569baae8536671b39f15cc22037ec7045658d80489e", size = 168724 },
+]
+
+[[package]]
+name = "pyasn1"
+version = "0.6.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/ba/e9/01f1a64245b89f039897cb0130016d79f77d52669aae6ee7b159a6c4c018/pyasn1-0.6.1.tar.gz", hash = "sha256:6f580d2bdd84365380830acf45550f2511469f673cb4a5ae3857a3170128b034", size = 145322 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c8/f1/d6a797abb14f6283c0ddff96bbdd46937f64122b8c925cab503dd37f8214/pyasn1-0.6.1-py3-none-any.whl", hash = "sha256:0d632f46f2ba09143da3a8afe9e33fb6f92fa2320ab7e886e2d0f7672af84629", size = 83135 },
+]
+
+[[package]]
+name = "pyasn1-modules"
+version = "0.4.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyasn1" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e9/e6/78ebbb10a8c8e4b61a59249394a4a594c1a7af95593dc933a349c8d00964/pyasn1_modules-0.4.2.tar.gz", hash = "sha256:677091de870a80aae844b1ca6134f54652fa2c8c5a52aa396440ac3106e941e6", size = 307892 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/47/8d/d529b5d697919ba8c11ad626e835d4039be708a35b0d22de83a269a6682c/pyasn1_modules-0.4.2-py3-none-any.whl", hash = "sha256:29253a9207ce32b64c3ac6600edc75368f98473906e8fd1043bd6b5b1de2c14a", size = 181259 },
+]
+
+[[package]]
+name = "pydantic"
+version = "2.11.7"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "annotated-types" },
+    { name = "pydantic-core" },
+    { name = "typing-extensions" },
+    { name = "typing-inspection" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/00/dd/4325abf92c39ba8623b5af936ddb36ffcfe0beae70405d456ab1fb2f5b8c/pydantic-2.11.7.tar.gz", hash = "sha256:d989c3c6cb79469287b1569f7447a17848c998458d49ebe294e975b9baf0f0db", size = 788350 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6a/c0/ec2b1c8712ca690e5d61979dee872603e92b8a32f94cc1b72d53beab008a/pydantic-2.11.7-py3-none-any.whl", hash = "sha256:dde5df002701f6de26248661f6835bbe296a47bf73990135c7d07ce741b9623b", size = 444782 },
+]
+
+[[package]]
+name = "pydantic-core"
+version = "2.33.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/ad/88/5f2260bdfae97aabf98f1778d43f69574390ad787afb646292a638c923d4/pydantic_core-2.33.2.tar.gz", hash = "sha256:7cb8bc3605c29176e1b105350d2e6474142d7c1bd1d9327c4a9bdb46bf827acc", size = 435195 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/3f/8d/71db63483d518cbbf290261a1fc2839d17ff89fce7089e08cad07ccfce67/pydantic_core-2.33.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:4c5b0a576fb381edd6d27f0a85915c6daf2f8138dc5c267a57c08a62900758c7", size = 2028584 },
+    { url = "https://files.pythonhosted.org/packages/24/2f/3cfa7244ae292dd850989f328722d2aef313f74ffc471184dc509e1e4e5a/pydantic_core-2.33.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:e799c050df38a639db758c617ec771fd8fb7a5f8eaaa4b27b101f266b216a246", size = 1855071 },
+    { url = "https://files.pythonhosted.org/packages/b3/d3/4ae42d33f5e3f50dd467761304be2fa0a9417fbf09735bc2cce003480f2a/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dc46a01bf8d62f227d5ecee74178ffc448ff4e5197c756331f71efcc66dc980f", size = 1897823 },
+    { url = "https://files.pythonhosted.org/packages/f4/f3/aa5976e8352b7695ff808599794b1fba2a9ae2ee954a3426855935799488/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a144d4f717285c6d9234a66778059f33a89096dfb9b39117663fd8413d582dcc", size = 1983792 },
+    { url = "https://files.pythonhosted.org/packages/d5/7a/cda9b5a23c552037717f2b2a5257e9b2bfe45e687386df9591eff7b46d28/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:73cf6373c21bc80b2e0dc88444f41ae60b2f070ed02095754eb5a01df12256de", size = 2136338 },
+    { url = "https://files.pythonhosted.org/packages/2b/9f/b8f9ec8dd1417eb9da784e91e1667d58a2a4a7b7b34cf4af765ef663a7e5/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3dc625f4aa79713512d1976fe9f0bc99f706a9dee21dfd1810b4bbbf228d0e8a", size = 2730998 },
+    { url = "https://files.pythonhosted.org/packages/47/bc/cd720e078576bdb8255d5032c5d63ee5c0bf4b7173dd955185a1d658c456/pydantic_core-2.33.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:881b21b5549499972441da4758d662aeea93f1923f953e9cbaff14b8b9565aef", size = 2003200 },
+    { url = "https://files.pythonhosted.org/packages/ca/22/3602b895ee2cd29d11a2b349372446ae9727c32e78a94b3d588a40fdf187/pydantic_core-2.33.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:bdc25f3681f7b78572699569514036afe3c243bc3059d3942624e936ec93450e", size = 2113890 },
+    { url = "https://files.pythonhosted.org/packages/ff/e6/e3c5908c03cf00d629eb38393a98fccc38ee0ce8ecce32f69fc7d7b558a7/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:fe5b32187cbc0c862ee201ad66c30cf218e5ed468ec8dc1cf49dec66e160cc4d", size = 2073359 },
+    { url = "https://files.pythonhosted.org/packages/12/e7/6a36a07c59ebefc8777d1ffdaf5ae71b06b21952582e4b07eba88a421c79/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_armv7l.whl", hash = "sha256:bc7aee6f634a6f4a95676fcb5d6559a2c2a390330098dba5e5a5f28a2e4ada30", size = 2245883 },
+    { url = "https://files.pythonhosted.org/packages/16/3f/59b3187aaa6cc0c1e6616e8045b284de2b6a87b027cce2ffcea073adf1d2/pydantic_core-2.33.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:235f45e5dbcccf6bd99f9f472858849f73d11120d76ea8707115415f8e5ebebf", size = 2241074 },
+    { url = "https://files.pythonhosted.org/packages/e0/ed/55532bb88f674d5d8f67ab121a2a13c385df382de2a1677f30ad385f7438/pydantic_core-2.33.2-cp311-cp311-win32.whl", hash = "sha256:6368900c2d3ef09b69cb0b913f9f8263b03786e5b2a387706c5afb66800efd51", size = 1910538 },
+    { url = "https://files.pythonhosted.org/packages/fe/1b/25b7cccd4519c0b23c2dd636ad39d381abf113085ce4f7bec2b0dc755eb1/pydantic_core-2.33.2-cp311-cp311-win_amd64.whl", hash = "sha256:1e063337ef9e9820c77acc768546325ebe04ee38b08703244c1309cccc4f1bab", size = 1952909 },
+    { url = "https://files.pythonhosted.org/packages/49/a9/d809358e49126438055884c4366a1f6227f0f84f635a9014e2deb9b9de54/pydantic_core-2.33.2-cp311-cp311-win_arm64.whl", hash = "sha256:6b99022f1d19bc32a4c2a0d544fc9a76e3be90f0b3f4af413f87d38749300e65", size = 1897786 },
+    { url = "https://files.pythonhosted.org/packages/18/8a/2b41c97f554ec8c71f2a8a5f85cb56a8b0956addfe8b0efb5b3d77e8bdc3/pydantic_core-2.33.2-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:a7ec89dc587667f22b6a0b6579c249fca9026ce7c333fc142ba42411fa243cdc", size = 2009000 },
+    { url = "https://files.pythonhosted.org/packages/a1/02/6224312aacb3c8ecbaa959897af57181fb6cf3a3d7917fd44d0f2917e6f2/pydantic_core-2.33.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:3c6db6e52c6d70aa0d00d45cdb9b40f0433b96380071ea80b09277dba021ddf7", size = 1847996 },
+    { url = "https://files.pythonhosted.org/packages/d6/46/6dcdf084a523dbe0a0be59d054734b86a981726f221f4562aed313dbcb49/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e61206137cbc65e6d5256e1166f88331d3b6238e082d9f74613b9b765fb9025", size = 1880957 },
+    { url = "https://files.pythonhosted.org/packages/ec/6b/1ec2c03837ac00886ba8160ce041ce4e325b41d06a034adbef11339ae422/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:eb8c529b2819c37140eb51b914153063d27ed88e3bdc31b71198a198e921e011", size = 1964199 },
+    { url = "https://files.pythonhosted.org/packages/2d/1d/6bf34d6adb9debd9136bd197ca72642203ce9aaaa85cfcbfcf20f9696e83/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c52b02ad8b4e2cf14ca7b3d918f3eb0ee91e63b3167c32591e57c4317e134f8f", size = 2120296 },
+    { url = "https://files.pythonhosted.org/packages/e0/94/2bd0aaf5a591e974b32a9f7123f16637776c304471a0ab33cf263cf5591a/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:96081f1605125ba0855dfda83f6f3df5ec90c61195421ba72223de35ccfb2f88", size = 2676109 },
+    { url = "https://files.pythonhosted.org/packages/f9/41/4b043778cf9c4285d59742281a769eac371b9e47e35f98ad321349cc5d61/pydantic_core-2.33.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f57a69461af2a5fa6e6bbd7a5f60d3b7e6cebb687f55106933188e79ad155c1", size = 2002028 },
+    { url = "https://files.pythonhosted.org/packages/cb/d5/7bb781bf2748ce3d03af04d5c969fa1308880e1dca35a9bd94e1a96a922e/pydantic_core-2.33.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:572c7e6c8bb4774d2ac88929e3d1f12bc45714ae5ee6d9a788a9fb35e60bb04b", size = 2100044 },
+    { url = "https://files.pythonhosted.org/packages/fe/36/def5e53e1eb0ad896785702a5bbfd25eed546cdcf4087ad285021a90ed53/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:db4b41f9bd95fbe5acd76d89920336ba96f03e149097365afe1cb092fceb89a1", size = 2058881 },
+    { url = "https://files.pythonhosted.org/packages/01/6c/57f8d70b2ee57fc3dc8b9610315949837fa8c11d86927b9bb044f8705419/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:fa854f5cf7e33842a892e5c73f45327760bc7bc516339fda888c75ae60edaeb6", size = 2227034 },
+    { url = "https://files.pythonhosted.org/packages/27/b9/9c17f0396a82b3d5cbea4c24d742083422639e7bb1d5bf600e12cb176a13/pydantic_core-2.33.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:5f483cfb75ff703095c59e365360cb73e00185e01aaea067cd19acffd2ab20ea", size = 2234187 },
+    { url = "https://files.pythonhosted.org/packages/b0/6a/adf5734ffd52bf86d865093ad70b2ce543415e0e356f6cacabbc0d9ad910/pydantic_core-2.33.2-cp312-cp312-win32.whl", hash = "sha256:9cb1da0f5a471435a7bc7e439b8a728e8b61e59784b2af70d7c169f8dd8ae290", size = 1892628 },
+    { url = "https://files.pythonhosted.org/packages/43/e4/5479fecb3606c1368d496a825d8411e126133c41224c1e7238be58b87d7e/pydantic_core-2.33.2-cp312-cp312-win_amd64.whl", hash = "sha256:f941635f2a3d96b2973e867144fde513665c87f13fe0e193c158ac51bfaaa7b2", size = 1955866 },
+    { url = "https://files.pythonhosted.org/packages/0d/24/8b11e8b3e2be9dd82df4b11408a67c61bb4dc4f8e11b5b0fc888b38118b5/pydantic_core-2.33.2-cp312-cp312-win_arm64.whl", hash = "sha256:cca3868ddfaccfbc4bfb1d608e2ccaaebe0ae628e1416aeb9c4d88c001bb45ab", size = 1888894 },
+    { url = "https://files.pythonhosted.org/packages/46/8c/99040727b41f56616573a28771b1bfa08a3d3fe74d3d513f01251f79f172/pydantic_core-2.33.2-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:1082dd3e2d7109ad8b7da48e1d4710c8d06c253cbc4a27c1cff4fbcaa97a9e3f", size = 2015688 },
+    { url = "https://files.pythonhosted.org/packages/3a/cc/5999d1eb705a6cefc31f0b4a90e9f7fc400539b1a1030529700cc1b51838/pydantic_core-2.33.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:f517ca031dfc037a9c07e748cefd8d96235088b83b4f4ba8939105d20fa1dcd6", size = 1844808 },
+    { url = "https://files.pythonhosted.org/packages/6f/5e/a0a7b8885c98889a18b6e376f344da1ef323d270b44edf8174d6bce4d622/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0a9f2c9dd19656823cb8250b0724ee9c60a82f3cdf68a080979d13092a3b0fef", size = 1885580 },
+    { url = "https://files.pythonhosted.org/packages/3b/2a/953581f343c7d11a304581156618c3f592435523dd9d79865903272c256a/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:2b0a451c263b01acebe51895bfb0e1cc842a5c666efe06cdf13846c7418caa9a", size = 1973859 },
+    { url = "https://files.pythonhosted.org/packages/e6/55/f1a813904771c03a3f97f676c62cca0c0a4138654107c1b61f19c644868b/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ea40a64d23faa25e62a70ad163571c0b342b8bf66d5fa612ac0dec4f069d916", size = 2120810 },
+    { url = "https://files.pythonhosted.org/packages/aa/c3/053389835a996e18853ba107a63caae0b9deb4a276c6b472931ea9ae6e48/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:0fb2d542b4d66f9470e8065c5469ec676978d625a8b7a363f07d9a501a9cb36a", size = 2676498 },
+    { url = "https://files.pythonhosted.org/packages/eb/3c/f4abd740877a35abade05e437245b192f9d0ffb48bbbbd708df33d3cda37/pydantic_core-2.33.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9fdac5d6ffa1b5a83bca06ffe7583f5576555e6c8b3a91fbd25ea7780f825f7d", size = 2000611 },
+    { url = "https://files.pythonhosted.org/packages/59/a7/63ef2fed1837d1121a894d0ce88439fe3e3b3e48c7543b2a4479eb99c2bd/pydantic_core-2.33.2-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:04a1a413977ab517154eebb2d326da71638271477d6ad87a769102f7c2488c56", size = 2107924 },
+    { url = "https://files.pythonhosted.org/packages/04/8f/2551964ef045669801675f1cfc3b0d74147f4901c3ffa42be2ddb1f0efc4/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:c8e7af2f4e0194c22b5b37205bfb293d166a7344a5b0d0eaccebc376546d77d5", size = 2063196 },
+    { url = "https://files.pythonhosted.org/packages/26/bd/d9602777e77fc6dbb0c7db9ad356e9a985825547dce5ad1d30ee04903918/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:5c92edd15cd58b3c2d34873597a1e20f13094f59cf88068adb18947df5455b4e", size = 2236389 },
+    { url = "https://files.pythonhosted.org/packages/42/db/0e950daa7e2230423ab342ae918a794964b053bec24ba8af013fc7c94846/pydantic_core-2.33.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:65132b7b4a1c0beded5e057324b7e16e10910c106d43675d9bd87d4f38dde162", size = 2239223 },
+    { url = "https://files.pythonhosted.org/packages/58/4d/4f937099c545a8a17eb52cb67fe0447fd9a373b348ccfa9a87f141eeb00f/pydantic_core-2.33.2-cp313-cp313-win32.whl", hash = "sha256:52fb90784e0a242bb96ec53f42196a17278855b0f31ac7c3cc6f5c1ec4811849", size = 1900473 },
+    { url = "https://files.pythonhosted.org/packages/a0/75/4a0a9bac998d78d889def5e4ef2b065acba8cae8c93696906c3a91f310ca/pydantic_core-2.33.2-cp313-cp313-win_amd64.whl", hash = "sha256:c083a3bdd5a93dfe480f1125926afcdbf2917ae714bdb80b36d34318b2bec5d9", size = 1955269 },
+    { url = "https://files.pythonhosted.org/packages/f9/86/1beda0576969592f1497b4ce8e7bc8cbdf614c352426271b1b10d5f0aa64/pydantic_core-2.33.2-cp313-cp313-win_arm64.whl", hash = "sha256:e80b087132752f6b3d714f041ccf74403799d3b23a72722ea2e6ba2e892555b9", size = 1893921 },
+    { url = "https://files.pythonhosted.org/packages/a4/7d/e09391c2eebeab681df2b74bfe6c43422fffede8dc74187b2b0bf6fd7571/pydantic_core-2.33.2-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:61c18fba8e5e9db3ab908620af374db0ac1baa69f0f32df4f61ae23f15e586ac", size = 1806162 },
+    { url = "https://files.pythonhosted.org/packages/f1/3d/847b6b1fed9f8ed3bb95a9ad04fbd0b212e832d4f0f50ff4d9ee5a9f15cf/pydantic_core-2.33.2-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95237e53bb015f67b63c91af7518a62a8660376a6a0db19b89acc77a4d6199f5", size = 1981560 },
+    { url = "https://files.pythonhosted.org/packages/6f/9a/e73262f6c6656262b5fdd723ad90f518f579b7bc8622e43a942eec53c938/pydantic_core-2.33.2-cp313-cp313t-win_amd64.whl", hash = "sha256:c2fc0a768ef76c15ab9238afa6da7f69895bb5d1ee83aeea2e3509af4472d0b9", size = 1935777 },
+    { url = "https://files.pythonhosted.org/packages/7b/27/d4ae6487d73948d6f20dddcd94be4ea43e74349b56eba82e9bdee2d7494c/pydantic_core-2.33.2-pp311-pypy311_pp73-macosx_10_12_x86_64.whl", hash = "sha256:dd14041875d09cc0f9308e37a6f8b65f5585cf2598a53aa0123df8b129d481f8", size = 2025200 },
+    { url = "https://files.pythonhosted.org/packages/f1/b8/b3cb95375f05d33801024079b9392a5ab45267a63400bf1866e7ce0f0de4/pydantic_core-2.33.2-pp311-pypy311_pp73-macosx_11_0_arm64.whl", hash = "sha256:d87c561733f66531dced0da6e864f44ebf89a8fba55f31407b00c2f7f9449593", size = 1859123 },
+    { url = "https://files.pythonhosted.org/packages/05/bc/0d0b5adeda59a261cd30a1235a445bf55c7e46ae44aea28f7bd6ed46e091/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2f82865531efd18d6e07a04a17331af02cb7a651583c418df8266f17a63c6612", size = 1892852 },
+    { url = "https://files.pythonhosted.org/packages/3e/11/d37bdebbda2e449cb3f519f6ce950927b56d62f0b84fd9cb9e372a26a3d5/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2bfb5112df54209d820d7bf9317c7a6c9025ea52e49f46b6a2060104bba37de7", size = 2067484 },
+    { url = "https://files.pythonhosted.org/packages/8c/55/1f95f0a05ce72ecb02a8a8a1c3be0579bbc29b1d5ab68f1378b7bebc5057/pydantic_core-2.33.2-pp311-pypy311_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:64632ff9d614e5eecfb495796ad51b0ed98c453e447a76bcbeeb69615079fc7e", size = 2108896 },
+    { url = "https://files.pythonhosted.org/packages/53/89/2b2de6c81fa131f423246a9109d7b2a375e83968ad0800d6e57d0574629b/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f889f7a40498cc077332c7ab6b4608d296d852182211787d4f3ee377aaae66e8", size = 2069475 },
+    { url = "https://files.pythonhosted.org/packages/b8/e9/1f7efbe20d0b2b10f6718944b5d8ece9152390904f29a78e68d4e7961159/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_armv7l.whl", hash = "sha256:de4b83bb311557e439b9e186f733f6c645b9417c84e2eb8203f3f820a4b988bf", size = 2239013 },
+    { url = "https://files.pythonhosted.org/packages/3c/b2/5309c905a93811524a49b4e031e9851a6b00ff0fb668794472ea7746b448/pydantic_core-2.33.2-pp311-pypy311_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:82f68293f055f51b51ea42fafc74b6aad03e70e191799430b90c13d643059ebb", size = 2238715 },
+    { url = "https://files.pythonhosted.org/packages/32/56/8a7ca5d2cd2cda1d245d34b1c9a942920a718082ae8e54e5f3e5a58b7add/pydantic_core-2.33.2-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:329467cecfb529c925cf2bbd4d60d2c509bc2fb52a20c1045bf09bb70971a9c1", size = 2066757 },
+]
+
+[[package]]
+name = "pygments"
+version = "2.19.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/b0/77/a5b8c569bf593b0140bde72ea885a803b82086995367bf2037de0159d924/pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887", size = 4968631 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/c7/21/705964c7812476f378728bdf590ca4b771ec72385c533964653c68e86bdc/pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b", size = 1225217 },
+]
+
+[[package]]
+name = "pytest"
+version = "8.4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+    { name = "iniconfig" },
+    { name = "packaging" },
+    { name = "pluggy" },
+    { name = "pygments" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/08/ba/45911d754e8eba3d5a841a5ce61a65a685ff1798421ac054f85aa8747dfb/pytest-8.4.1.tar.gz", hash = "sha256:7c67fd69174877359ed9371ec3af8a3d2b04741818c51e5e99cc1742251fa93c", size = 1517714 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/29/16/c8a903f4c4dffe7a12843191437d7cd8e32751d5de349d45d3fe69544e87/pytest-8.4.1-py3-none-any.whl", hash = "sha256:539c70ba6fcead8e78eebbf1115e8b589e7565830d7d006a8723f19ac8a0afb7", size = 365474 },
+]
+
+[[package]]
+name = "pytest-asyncio"
+version = "1.0.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/d0/d4/14f53324cb1a6381bef29d698987625d80052bb33932d8e7cbf9b337b17c/pytest_asyncio-1.0.0.tar.gz", hash = "sha256:d15463d13f4456e1ead2594520216b225a16f781e144f8fdf6c5bb4667c48b3f", size = 46960 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/30/05/ce271016e351fddc8399e546f6e23761967ee09c8c568bbfbecb0c150171/pytest_asyncio-1.0.0-py3-none-any.whl", hash = "sha256:4f024da9f1ef945e680dc68610b52550e36590a67fd31bb3b4943979a1f90ef3", size = 15976 },
+]
+
+[[package]]
+name = "python-dotenv"
+version = "1.1.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/b0/4bc07ccd3572a2f9df7e6782f52b0c6c90dcbb803ac4a167702d7d0dfe1e/python_dotenv-1.1.1.tar.gz", hash = "sha256:a8a6399716257f45be6a007360200409fce5cda2661e3dec71d23dc15f6189ab", size = 41978 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/5f/ed/539768cf28c661b5b068d66d96a2f155c4971a5d55684a514c1a0e0dec2f/python_dotenv-1.1.1-py3-none-any.whl", hash = "sha256:31f23644fe2602f88ff55e1f5c79ba497e01224ee7737937930c448e4d0e24dc", size = 20556 },
+]
+
+[[package]]
+name = "python-multipart"
+version = "0.0.20"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/f3/87/f44d7c9f274c7ee665a29b885ec97089ec5dc034c7f3fafa03da9e39a09e/python_multipart-0.0.20.tar.gz", hash = "sha256:8dd0cab45b8e23064ae09147625994d090fa46f5b0d1e13af944c331a7fa9d13", size = 37158 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/45/58/38b5afbc1a800eeea951b9285d3912613f2603bdf897a4ab0f4bd7f405fc/python_multipart-0.0.20-py3-none-any.whl", hash = "sha256:8a62d3a8335e06589fe01f2a3e178cdcc632f3fbe0d492ad9ee0ec35aab1f104", size = 24546 },
+]
+
+[[package]]
+name = "requests"
+version = "2.32.4"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "certifi" },
+    { name = "charset-normalizer" },
+    { name = "idna" },
+    { name = "urllib3" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/e1/0a/929373653770d8a0d7ea76c37de6e41f11eb07559b103b1c02cafb3f7cf8/requests-2.32.4.tar.gz", hash = "sha256:27d0316682c8a29834d3264820024b62a36942083d52caf2f14c0591336d3422", size = 135258 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7c/e4/56027c4a6b4ae70ca9de302488c5ca95ad4a39e190093d6c1a8ace08341b/requests-2.32.4-py3-none-any.whl", hash = "sha256:27babd3cda2a6d50b30443204ee89830707d396671944c998b5975b031ac2b2c", size = 64847 },
+]
+
+[[package]]
+name = "rsa"
+version = "4.9.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "pyasn1" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/da/8a/22b7beea3ee0d44b1916c0c1cb0ee3af23b700b6da9f04991899d0c555d4/rsa-4.9.1.tar.gz", hash = "sha256:e7bdbfdb5497da4c07dfd35530e1a902659db6ff241e39d9953cad06ebd0ae75", size = 29034 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/64/8d/0133e4eb4beed9e425d9a98ed6e081a55d195481b7632472be1af08d2f6b/rsa-4.9.1-py3-none-any.whl", hash = "sha256:68635866661c6836b8d39430f97a996acbd61bfa49406748ea243539fe239762", size = 34696 },
+]
+
+[[package]]
+name = "ruff"
+version = "0.12.3"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/c3/2a/43955b530c49684d3c38fcda18c43caf91e99204c2a065552528e0552d4f/ruff-0.12.3.tar.gz", hash = "sha256:f1b5a4b6668fd7b7ea3697d8d98857390b40c1320a63a178eee6be0899ea2d77", size = 4459341 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e2/fd/b44c5115539de0d598d75232a1cc7201430b6891808df111b8b0506aae43/ruff-0.12.3-py3-none-linux_armv6l.whl", hash = "sha256:47552138f7206454eaf0c4fe827e546e9ddac62c2a3d2585ca54d29a890137a2", size = 10430499 },
+    { url = "https://files.pythonhosted.org/packages/43/c5/9eba4f337970d7f639a37077be067e4ec80a2ad359e4cc6c5b56805cbc66/ruff-0.12.3-py3-none-macosx_10_12_x86_64.whl", hash = "sha256:0a9153b000c6fe169bb307f5bd1b691221c4286c133407b8827c406a55282041", size = 11213413 },
+    { url = "https://files.pythonhosted.org/packages/e2/2c/fac3016236cf1fe0bdc8e5de4f24c76ce53c6dd9b5f350d902549b7719b2/ruff-0.12.3-py3-none-macosx_11_0_arm64.whl", hash = "sha256:fa6b24600cf3b750e48ddb6057e901dd5b9aa426e316addb2a1af185a7509882", size = 10586941 },
+    { url = "https://files.pythonhosted.org/packages/c5/0f/41fec224e9dfa49a139f0b402ad6f5d53696ba1800e0f77b279d55210ca9/ruff-0.12.3-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e2506961bf6ead54887ba3562604d69cb430f59b42133d36976421bc8bd45901", size = 10783001 },
+    { url = "https://files.pythonhosted.org/packages/0d/ca/dd64a9ce56d9ed6cad109606ac014860b1c217c883e93bf61536400ba107/ruff-0.12.3-py3-none-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c4faaff1f90cea9d3033cbbcdf1acf5d7fb11d8180758feb31337391691f3df0", size = 10269641 },
+    { url = "https://files.pythonhosted.org/packages/63/5c/2be545034c6bd5ce5bb740ced3e7014d7916f4c445974be11d2a406d5088/ruff-0.12.3-py3-none-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:40dced4a79d7c264389de1c59467d5d5cefd79e7e06d1dfa2c75497b5269a5a6", size = 11875059 },
+    { url = "https://files.pythonhosted.org/packages/8e/d4/a74ef1e801ceb5855e9527dae105eaff136afcb9cc4d2056d44feb0e4792/ruff-0.12.3-py3-none-manylinux_2_17_ppc64.manylinux2014_ppc64.whl", hash = "sha256:0262d50ba2767ed0fe212aa7e62112a1dcbfd46b858c5bf7bbd11f326998bafc", size = 12658890 },
+    { url = "https://files.pythonhosted.org/packages/13/c8/1057916416de02e6d7c9bcd550868a49b72df94e3cca0aeb77457dcd9644/ruff-0.12.3-py3-none-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:12371aec33e1a3758597c5c631bae9a5286f3c963bdfb4d17acdd2d395406687", size = 12232008 },
+    { url = "https://files.pythonhosted.org/packages/f5/59/4f7c130cc25220392051fadfe15f63ed70001487eca21d1796db46cbcc04/ruff-0.12.3-py3-none-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:560f13b6baa49785665276c963edc363f8ad4b4fc910a883e2625bdb14a83a9e", size = 11499096 },
+    { url = "https://files.pythonhosted.org/packages/d4/01/a0ad24a5d2ed6be03a312e30d32d4e3904bfdbc1cdbe63c47be9d0e82c79/ruff-0.12.3-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:023040a3499f6f974ae9091bcdd0385dd9e9eb4942f231c23c57708147b06311", size = 11688307 },
+    { url = "https://files.pythonhosted.org/packages/93/72/08f9e826085b1f57c9a0226e48acb27643ff19b61516a34c6cab9d6ff3fa/ruff-0.12.3-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:883d844967bffff5ab28bba1a4d246c1a1b2933f48cb9840f3fdc5111c603b07", size = 10661020 },
+    { url = "https://files.pythonhosted.org/packages/80/a0/68da1250d12893466c78e54b4a0ff381370a33d848804bb51279367fc688/ruff-0.12.3-py3-none-musllinux_1_2_armv7l.whl", hash = "sha256:2120d3aa855ff385e0e562fdee14d564c9675edbe41625c87eeab744a7830d12", size = 10246300 },
+    { url = "https://files.pythonhosted.org/packages/6a/22/5f0093d556403e04b6fd0984fc0fb32fbb6f6ce116828fd54306a946f444/ruff-0.12.3-py3-none-musllinux_1_2_i686.whl", hash = "sha256:6b16647cbb470eaf4750d27dddc6ebf7758b918887b56d39e9c22cce2049082b", size = 11263119 },
+    { url = "https://files.pythonhosted.org/packages/92/c9/f4c0b69bdaffb9968ba40dd5fa7df354ae0c73d01f988601d8fac0c639b1/ruff-0.12.3-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:e1417051edb436230023575b149e8ff843a324557fe0a265863b7602df86722f", size = 11746990 },
+    { url = "https://files.pythonhosted.org/packages/fe/84/7cc7bd73924ee6be4724be0db5414a4a2ed82d06b30827342315a1be9e9c/ruff-0.12.3-py3-none-win32.whl", hash = "sha256:dfd45e6e926deb6409d0616078a666ebce93e55e07f0fb0228d4b2608b2c248d", size = 10589263 },
+    { url = "https://files.pythonhosted.org/packages/07/87/c070f5f027bd81f3efee7d14cb4d84067ecf67a3a8efb43aadfc72aa79a6/ruff-0.12.3-py3-none-win_amd64.whl", hash = "sha256:a946cf1e7ba3209bdef039eb97647f1c77f6f540e5845ec9c114d3af8df873e7", size = 11695072 },
+    { url = "https://files.pythonhosted.org/packages/e0/30/f3eaf6563c637b6e66238ed6535f6775480db973c836336e4122161986fc/ruff-0.12.3-py3-none-win_arm64.whl", hash = "sha256:5f9c7c9c8f84c2d7f27e93674d27136fbf489720251544c4da7fb3d742e011b1", size = 10805855 },
+]
+
+[[package]]
+name = "sniffio"
+version = "1.3.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/a2/87/a6771e1546d97e7e041b6ae58d80074f81b7d5121207425c964ddf5cfdbd/sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc", size = 20372 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/e9/44/75a9c9421471a6c4805dbf2356f7c181a29c1879239abab1ea2cc8f38b40/sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2", size = 10235 },
+]
+
+[[package]]
+name = "starlette"
+version = "0.47.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "anyio" },
+    { name = "typing-extensions", marker = "python_full_version < '3.13'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0a/69/662169fdb92fb96ec3eaee218cf540a629d629c86d7993d9651226a6789b/starlette-0.47.1.tar.gz", hash = "sha256:aef012dd2b6be325ffa16698f9dc533614fb1cebd593a906b90dc1025529a79b", size = 2583072 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/82/95/38ef0cd7fa11eaba6a99b3c4f5ac948d8bc6ff199aabd327a29cc000840c/starlette-0.47.1-py3-none-any.whl", hash = "sha256:5e11c9f5c7c3f24959edbf2dffdc01bba860228acf657129467d8a7468591527", size = 72747 },
+]
+
+[[package]]
+name = "tqdm"
+version = "4.67.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "colorama", marker = "sys_platform == 'win32'" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/a8/4b/29b4ef32e036bb34e4ab51796dd745cdba7ed47ad142a9f4a1eb8e0c744d/tqdm-4.67.1.tar.gz", hash = "sha256:f8aef9c52c08c13a65f30ea34f4e5aac3fd1a34959879d7e59e63027286627f2", size = 169737 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d0/30/dc54f88dd4a2b5dc8a0279bdd7270e735851848b762aeb1c1184ed1f6b14/tqdm-4.67.1-py3-none-any.whl", hash = "sha256:26445eca388f82e72884e0d580d5464cd801a3ea01e63e5601bdff9ba6a48de2", size = 78540 },
+]
+
+[[package]]
+name = "typing-extensions"
+version = "4.14.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/98/5a/da40306b885cc8c09109dc2e1abd358d5684b1425678151cdaed4731c822/typing_extensions-4.14.1.tar.gz", hash = "sha256:38b39f4aeeab64884ce9f74c94263ef78f3c22467c8724005483154c26648d36", size = 107673 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/b5/00/d631e67a838026495268c2f6884f3711a15a9a2a96cd244fdaea53b823fb/typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76", size = 43906 },
+]
+
+[[package]]
+name = "typing-inspection"
+version = "0.4.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "typing-extensions" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f8/b1/0c11f5058406b3af7609f121aaa6b609744687f1d158b3c3a5bf4cc94238/typing_inspection-0.4.1.tar.gz", hash = "sha256:6ae134cc0203c33377d43188d4064e9b357dba58cff3185f22924610e70a9d28", size = 75726 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/17/69/cd203477f944c353c31bade965f880aa1061fd6bf05ded0726ca845b6ff7/typing_inspection-0.4.1-py3-none-any.whl", hash = "sha256:389055682238f53b04f7badcb49b989835495a96700ced5dab2d8feae4b26f51", size = 14552 },
+]
+
+[[package]]
+name = "urllib3"
+version = "2.5.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795 },
+]
+
+[[package]]
+name = "uvicorn"
+version = "0.35.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "click" },
+    { name = "h11" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/5e/42/e0e305207bb88c6b8d3061399c6a961ffe5fbb7e2aa63c9234df7259e9cd/uvicorn-0.35.0.tar.gz", hash = "sha256:bc662f087f7cf2ce11a1d7fd70b90c9f98ef2e2831556dd078d131b96cc94a01", size = 78473 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/d2/e2/dc81b1bd1dcfe91735810265e9d26bc8ec5da45b4c0f6237e286819194c3/uvicorn-0.35.0-py3-none-any.whl", hash = "sha256:197535216b25ff9b785e29a0b79199f55222193d47f820816e7da751e9bc8d4a", size = 66406 },
+]
+
+[[package]]
+name = "websockets"
+version = "15.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/21/e6/26d09fab466b7ca9c7737474c52be4f76a40301b08362eb2dbc19dcc16c1/websockets-15.0.1.tar.gz", hash = "sha256:82544de02076bafba038ce055ee6412d68da13ab47f0c60cab827346de828dee", size = 177016 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9f/32/18fcd5919c293a398db67443acd33fde142f283853076049824fc58e6f75/websockets-15.0.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:823c248b690b2fd9303ba00c4f66cd5e2d8c3ba4aa968b2779be9532a4dad431", size = 175423 },
+    { url = "https://files.pythonhosted.org/packages/76/70/ba1ad96b07869275ef42e2ce21f07a5b0148936688c2baf7e4a1f60d5058/websockets-15.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678999709e68425ae2593acf2e3ebcbcf2e69885a5ee78f9eb80e6e371f1bf57", size = 173082 },
+    { url = "https://files.pythonhosted.org/packages/86/f2/10b55821dd40eb696ce4704a87d57774696f9451108cff0d2824c97e0f97/websockets-15.0.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:d50fd1ee42388dcfb2b3676132c78116490976f1300da28eb629272d5d93e905", size = 173330 },
+    { url = "https://files.pythonhosted.org/packages/a5/90/1c37ae8b8a113d3daf1065222b6af61cc44102da95388ac0018fcb7d93d9/websockets-15.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d99e5546bf73dbad5bf3547174cd6cb8ba7273062a23808ffea025ecb1cf8562", size = 182878 },
+    { url = "https://files.pythonhosted.org/packages/8e/8d/96e8e288b2a41dffafb78e8904ea7367ee4f891dafc2ab8d87e2124cb3d3/websockets-15.0.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:66dd88c918e3287efc22409d426c8f729688d89a0c587c88971a0faa2c2f3792", size = 181883 },
+    { url = "https://files.pythonhosted.org/packages/93/1f/5d6dbf551766308f6f50f8baf8e9860be6182911e8106da7a7f73785f4c4/websockets-15.0.1-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8dd8327c795b3e3f219760fa603dcae1dcc148172290a8ab15158cf85a953413", size = 182252 },
+    { url = "https://files.pythonhosted.org/packages/d4/78/2d4fed9123e6620cbf1706c0de8a1632e1a28e7774d94346d7de1bba2ca3/websockets-15.0.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8fdc51055e6ff4adeb88d58a11042ec9a5eae317a0a53d12c062c8a8865909e8", size = 182521 },
+    { url = "https://files.pythonhosted.org/packages/e7/3b/66d4c1b444dd1a9823c4a81f50231b921bab54eee2f69e70319b4e21f1ca/websockets-15.0.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:693f0192126df6c2327cce3baa7c06f2a117575e32ab2308f7f8216c29d9e2e3", size = 181958 },
+    { url = "https://files.pythonhosted.org/packages/08/ff/e9eed2ee5fed6f76fdd6032ca5cd38c57ca9661430bb3d5fb2872dc8703c/websockets-15.0.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:54479983bd5fb469c38f2f5c7e3a24f9a4e70594cd68cd1fa6b9340dadaff7cf", size = 181918 },
+    { url = "https://files.pythonhosted.org/packages/d8/75/994634a49b7e12532be6a42103597b71098fd25900f7437d6055ed39930a/websockets-15.0.1-cp311-cp311-win32.whl", hash = "sha256:16b6c1b3e57799b9d38427dda63edcbe4926352c47cf88588c0be4ace18dac85", size = 176388 },
+    { url = "https://files.pythonhosted.org/packages/98/93/e36c73f78400a65f5e236cd376713c34182e6663f6889cd45a4a04d8f203/websockets-15.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:27ccee0071a0e75d22cb35849b1db43f2ecd3e161041ac1ee9d2352ddf72f065", size = 176828 },
+    { url = "https://files.pythonhosted.org/packages/51/6b/4545a0d843594f5d0771e86463606a3988b5a09ca5123136f8a76580dd63/websockets-15.0.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:3e90baa811a5d73f3ca0bcbf32064d663ed81318ab225ee4f427ad4e26e5aff3", size = 175437 },
+    { url = "https://files.pythonhosted.org/packages/f4/71/809a0f5f6a06522af902e0f2ea2757f71ead94610010cf570ab5c98e99ed/websockets-15.0.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:592f1a9fe869c778694f0aa806ba0374e97648ab57936f092fd9d87f8bc03665", size = 173096 },
+    { url = "https://files.pythonhosted.org/packages/3d/69/1a681dd6f02180916f116894181eab8b2e25b31e484c5d0eae637ec01f7c/websockets-15.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:0701bc3cfcb9164d04a14b149fd74be7347a530ad3bbf15ab2c678a2cd3dd9a2", size = 173332 },
+    { url = "https://files.pythonhosted.org/packages/a6/02/0073b3952f5bce97eafbb35757f8d0d54812b6174ed8dd952aa08429bcc3/websockets-15.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e8b56bdcdb4505c8078cb6c7157d9811a85790f2f2b3632c7d1462ab5783d215", size = 183152 },
+    { url = "https://files.pythonhosted.org/packages/74/45/c205c8480eafd114b428284840da0b1be9ffd0e4f87338dc95dc6ff961a1/websockets-15.0.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0af68c55afbd5f07986df82831c7bff04846928ea8d1fd7f30052638788bc9b5", size = 182096 },
+    { url = "https://files.pythonhosted.org/packages/14/8f/aa61f528fba38578ec553c145857a181384c72b98156f858ca5c8e82d9d3/websockets-15.0.1-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64dee438fed052b52e4f98f76c5790513235efaa1ef7f3f2192c392cd7c91b65", size = 182523 },
+    { url = "https://files.pythonhosted.org/packages/ec/6d/0267396610add5bc0d0d3e77f546d4cd287200804fe02323797de77dbce9/websockets-15.0.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:d5f6b181bb38171a8ad1d6aa58a67a6aa9d4b38d0f8c5f496b9e42561dfc62fe", size = 182790 },
+    { url = "https://files.pythonhosted.org/packages/02/05/c68c5adbf679cf610ae2f74a9b871ae84564462955d991178f95a1ddb7dd/websockets-15.0.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:5d54b09eba2bada6011aea5375542a157637b91029687eb4fdb2dab11059c1b4", size = 182165 },
+    { url = "https://files.pythonhosted.org/packages/29/93/bb672df7b2f5faac89761cb5fa34f5cec45a4026c383a4b5761c6cea5c16/websockets-15.0.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:3be571a8b5afed347da347bfcf27ba12b069d9d7f42cb8c7028b5e98bbb12597", size = 182160 },
+    { url = "https://files.pythonhosted.org/packages/ff/83/de1f7709376dc3ca9b7eeb4b9a07b4526b14876b6d372a4dc62312bebee0/websockets-15.0.1-cp312-cp312-win32.whl", hash = "sha256:c338ffa0520bdb12fbc527265235639fb76e7bc7faafbb93f6ba80d9c06578a9", size = 176395 },
+    { url = "https://files.pythonhosted.org/packages/7d/71/abf2ebc3bbfa40f391ce1428c7168fb20582d0ff57019b69ea20fa698043/websockets-15.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:fcd5cf9e305d7b8338754470cf69cf81f420459dbae8a3b40cee57417f4614a7", size = 176841 },
+    { url = "https://files.pythonhosted.org/packages/cb/9f/51f0cf64471a9d2b4d0fc6c534f323b664e7095640c34562f5182e5a7195/websockets-15.0.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:ee443ef070bb3b6ed74514f5efaa37a252af57c90eb33b956d35c8e9c10a1931", size = 175440 },
+    { url = "https://files.pythonhosted.org/packages/8a/05/aa116ec9943c718905997412c5989f7ed671bc0188ee2ba89520e8765d7b/websockets-15.0.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:5a939de6b7b4e18ca683218320fc67ea886038265fd1ed30173f5ce3f8e85675", size = 173098 },
+    { url = "https://files.pythonhosted.org/packages/ff/0b/33cef55ff24f2d92924923c99926dcce78e7bd922d649467f0eda8368923/websockets-15.0.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:746ee8dba912cd6fc889a8147168991d50ed70447bf18bcda7039f7d2e3d9151", size = 173329 },
+    { url = "https://files.pythonhosted.org/packages/31/1d/063b25dcc01faa8fada1469bdf769de3768b7044eac9d41f734fd7b6ad6d/websockets-15.0.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:595b6c3969023ecf9041b2936ac3827e4623bfa3ccf007575f04c5a6aa318c22", size = 183111 },
+    { url = "https://files.pythonhosted.org/packages/93/53/9a87ee494a51bf63e4ec9241c1ccc4f7c2f45fff85d5bde2ff74fcb68b9e/websockets-15.0.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3c714d2fc58b5ca3e285461a4cc0c9a66bd0e24c5da9911e30158286c9b5be7f", size = 182054 },
+    { url = "https://files.pythonhosted.org/packages/ff/b2/83a6ddf56cdcbad4e3d841fcc55d6ba7d19aeb89c50f24dd7e859ec0805f/websockets-15.0.1-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0f3c1e2ab208db911594ae5b4f79addeb3501604a165019dd221c0bdcabe4db8", size = 182496 },
+    { url = "https://files.pythonhosted.org/packages/98/41/e7038944ed0abf34c45aa4635ba28136f06052e08fc2168520bb8b25149f/websockets-15.0.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:229cf1d3ca6c1804400b0a9790dc66528e08a6a1feec0d5040e8b9eb14422375", size = 182829 },
+    { url = "https://files.pythonhosted.org/packages/e0/17/de15b6158680c7623c6ef0db361da965ab25d813ae54fcfeae2e5b9ef910/websockets-15.0.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:756c56e867a90fb00177d530dca4b097dd753cde348448a1012ed6c5131f8b7d", size = 182217 },
+    { url = "https://files.pythonhosted.org/packages/33/2b/1f168cb6041853eef0362fb9554c3824367c5560cbdaad89ac40f8c2edfc/websockets-15.0.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:558d023b3df0bffe50a04e710bc87742de35060580a293c2a984299ed83bc4e4", size = 182195 },
+    { url = "https://files.pythonhosted.org/packages/86/eb/20b6cdf273913d0ad05a6a14aed4b9a85591c18a987a3d47f20fa13dcc47/websockets-15.0.1-cp313-cp313-win32.whl", hash = "sha256:ba9e56e8ceeeedb2e080147ba85ffcd5cd0711b89576b83784d8605a7df455fa", size = 176393 },
+    { url = "https://files.pythonhosted.org/packages/1b/6c/c65773d6cab416a64d191d6ee8a8b1c68a09970ea6909d16965d26bfed1e/websockets-15.0.1-cp313-cp313-win_amd64.whl", hash = "sha256:e09473f095a819042ecb2ab9465aee615bd9c2028e4ef7d933600a8401c79561", size = 176837 },
+    { url = "https://files.pythonhosted.org/packages/fa/a8/5b41e0da817d64113292ab1f8247140aac61cbf6cfd085d6a0fa77f4984f/websockets-15.0.1-py3-none-any.whl", hash = "sha256:f7a866fbc1e97b5c617ee4116daaa09b722101d4a3c170c787450ba409f9736f", size = 169743 },
+]

docker-compose.yml

@@ -0,0 +1,70 @@
+services:
+  backend:
+    build: 
+      context: ./backend
+      dockerfile: Dockerfile
+    restart: always
+    env_file:
+      - ./.env
+    volumes:
+      - ./credentials:/app/credentials:ro
+    networks:
+      - default
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.learn-api.rule=Host(`learn-indonesian.velouria.dev`,`learn-german.velouria.dev`) && PathPrefix(`/api/`,`/ws/`)"
+      - "traefik.http.routers.learn-api.entrypoints=websecure"
+      - "traefik.http.routers.learn-api.tls.certresolver=myresolver"
+      - "traefik.http.services.learn-api.loadbalancer.server.port=8000"
+      - "traefik.docker.network=traefik_network"
+      - "homepage.group=Education"
+      - "homepage.name=Learn API"
+      - "homepage.description=Language Learning API"
+
+  indonesian-app:
+    build:
+      context: ./apps/indonesian-app
+      dockerfile: Dockerfile
+    restart: always
+    depends_on:
+      - backend
+    networks:
+      - default
+      - traefik_network
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.learn-indonesian.rule=Host(`learn-indonesian.velouria.dev`)"
+      - "traefik.http.routers.learn-indonesian.entrypoints=websecure"
+      - "traefik.http.routers.learn-indonesian.tls.certresolver=myresolver"
+      - "traefik.http.services.learn-indonesian.loadbalancer.server.port=80"
+      - "traefik.docker.network=traefik_network"
+      - "homepage.group=Education"
+      - "homepage.name=Learn Indonesian"
+      - "homepage.description=Indonesian Language Learning"
+
+  german-app:
+    build:
+      context: ./apps/german-app
+      dockerfile: Dockerfile
+    restart: always
+    depends_on:
+      - backend
+    networks:
+      - default
+      - traefik_network
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.learn-german.rule=Host(`learn-german.velouria.dev`)"
+      - "traefik.http.routers.learn-german.entrypoints=websecure"
+      - "traefik.http.routers.learn-german.tls.certresolver=myresolver"
+      - "traefik.http.services.learn-german.loadbalancer.server.port=80"
+      - "traefik.docker.network=traefik_network"
+      - "homepage.group=Education"
+      - "homepage.name=Learn German"
+      - "homepage.description=German Language Learning"
+
+networks:
+  default:
+    name: learn-languages_default
+  traefik_network:
+    external: true

package.json

@@ -0,0 +1,25 @@
+{
+  "name": "learn-indo-workspace",
+  "version": "1.0.0",
+  "description": "Language learning platform with Indonesian and German apps",
+  "private": true,
+  "scripts": {
+    "dev:indonesian": "cd apps/indonesian-app && npm run dev",
+    "dev:german": "cd apps/german-app && npm run dev",
+    "dev:backend": "cd backend && python -m uvicorn main:app --reload --host 0.0.0.0 --port 8000",
+    "dev:all": "concurrently \"npm run dev:backend\" \"npm run dev:indonesian\" \"npm run dev:german\"",
+    "build:indonesian": "cd apps/indonesian-app && npm run build",
+    "build:german": "cd apps/german-app && npm run build",
+    "build:all": "npm run build:indonesian && npm run build:german",
+    "install:indonesian": "cd apps/indonesian-app && npm install",
+    "install:german": "cd apps/german-app && npm install",
+    "install:all": "npm run install:indonesian && npm run install:german",
+    "start:backend": "cd backend && python -m uvicorn main:app --host 0.0.0.0 --port 8000"
+  },
+  "devDependencies": {
+    "concurrently": "^8.2.0"
+  },
+  "workspaces": [
+    "apps/*"
+  ]
+}

start-street-lingo.sh

@@ -0,0 +1,102 @@
+#!/bin/bash
+
+# Street Lingo Development Startup Script
+echo "🌍 Starting Street Lingo Platform..."
+echo ""
+
+# Colors for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+# Function to print colored output
+print_status() {
+    echo -e "${GREEN}[INFO]${NC} $1"
+}
+
+print_warning() {
+    echo -e "${YELLOW}[WARN]${NC} $1"
+}
+
+print_error() {
+    echo -e "${RED}[ERROR]${NC} $1"
+}
+
+print_info() {
+    echo -e "${BLUE}[INFO]${NC} $1"
+}
+
+# Check if we're in the right directory
+if [ ! -f "backend/main.py" ]; then
+    print_error "Please run this script from the root directory of the project"
+    exit 1
+fi
+
+# Start backend
+print_status "Starting backend server on port 8000..."
+cd backend
+uv run python main.py &
+BACKEND_PID=$!
+cd ..
+
+# Wait a moment for backend to start
+sleep 3
+
+# Start Indonesian app
+print_status "Starting Indonesian app (Street Lingo Indo) on port 3000..."
+cd apps/indonesian-app
+npm install
+npm run dev &
+INDO_PID=$!
+cd ../..
+
+# Start German app
+print_status "Starting German app (Street Lingo Berlin) on port 3001..."
+cd apps/german-app
+npm install
+npm run dev &
+GERMAN_PID=$!
+cd ../..
+
+# Wait a moment for apps to start
+sleep 5
+
+echo ""
+print_info "🎉 Street Lingo Platform is now running!"
+echo ""
+echo "📱 Applications:"
+echo "  🇮🇩 Indonesian App:  http://localhost:3000"
+echo "  🇩🇪 German App:      http://localhost:3001"
+echo ""
+echo "🔧 Backend API:"
+echo "  📡 Main API:         http://localhost:8000"
+echo "  📊 API Docs:         http://localhost:8000/docs"
+echo ""
+echo "🌐 WebSocket Endpoints:"
+echo "  🇮🇩 Indonesian WS:   ws://localhost:8000/ws/speech/indonesian"
+echo "  🇩🇪 German WS:       ws://localhost:8000/ws/speech/german"
+echo ""
+echo "🎯 API Routes:"
+echo "  🇮🇩 Indonesian API:  http://localhost:8000/api/scenarios/indonesian"
+echo "  🇩🇪 German API:      http://localhost:8000/api/scenarios/german"
+echo ""
+print_warning "Press Ctrl+C to stop all services"
+echo ""
+
+# Function to cleanup processes
+cleanup() {
+    print_status "Stopping all Street Lingo services..."
+    kill $BACKEND_PID 2>/dev/null
+    kill $INDO_PID 2>/dev/null
+    kill $GERMAN_PID 2>/dev/null
+    print_status "All services stopped. Goodbye!"
+    exit 0
+}
+
+# Set up signal handlers
+trap cleanup SIGINT SIGTERM
+
+# Wait for user to stop
+wait

test-setup.py

@@ -0,0 +1,157 @@
+#!/usr/bin/env python3
+"""
+Street Lingo Platform Setup Test
+Tests backend functionality and API endpoints
+"""
+
+import requests
+import json
+import sys
+from typing import Dict, Any
+
+def test_backend_health():
+    """Test if backend is running and healthy"""
+    try:
+        response = requests.get("http://localhost:8000/api/health", timeout=5)
+        if response.status_code == 200:
+            print("✅ Backend health check passed")
+            return True
+        else:
+            print(f"❌ Backend health check failed: {response.status_code}")
+            return False
+    except Exception as e:
+        print(f"❌ Backend not reachable: {e}")
+        return False
+
+def test_scenarios_api():
+    """Test scenarios API endpoints"""
+    print("\n🧪 Testing Scenarios API...")
+    
+    # Test Indonesian scenarios
+    try:
+        response = requests.get("http://localhost:8000/api/scenarios/indonesian", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            scenarios = list(data.keys())
+            print(f"✅ Indonesian scenarios: {scenarios}")
+        else:
+            print(f"❌ Indonesian scenarios failed: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Indonesian scenarios error: {e}")
+    
+    # Test German scenarios
+    try:
+        response = requests.get("http://localhost:8000/api/scenarios/german", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            scenarios = list(data.keys())
+            print(f"✅ German scenarios: {scenarios}")
+        else:
+            print(f"❌ German scenarios failed: {response.status_code}")
+    except Exception as e:
+        print(f"❌ German scenarios error: {e}")
+    
+    # Test all scenarios
+    try:
+        response = requests.get("http://localhost:8000/api/scenarios", timeout=5)
+        if response.status_code == 200:
+            data = response.json()
+            languages = list(data.keys())
+            print(f"✅ All scenarios endpoint: {languages}")
+        else:
+            print(f"❌ All scenarios failed: {response.status_code}")
+    except Exception as e:
+        print(f"❌ All scenarios error: {e}")
+
+def test_translation_api():
+    """Test translation API"""
+    print("\n🧪 Testing Translation API...")
+    
+    test_data = {
+        "text": "Hallo, wie geht es dir?",
+        "source_language": "de",
+        "target_language": "en"
+    }
+    
+    try:
+        response = requests.post(
+            "http://localhost:8000/api/translate",
+            json=test_data,
+            timeout=10
+        )
+        if response.status_code == 200:
+            result = response.json()
+            print(f"✅ Translation API works: '{test_data['text']}' → '{result['translation']}'")
+        else:
+            print(f"❌ Translation API failed: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Translation API error: {e}")
+
+def test_frontend_accessibility():
+    """Test if frontend apps are accessible"""
+    print("\n🧪 Testing Frontend Accessibility...")
+    
+    # Test Indonesian app
+    try:
+        response = requests.get("http://localhost:3000", timeout=5)
+        if response.status_code == 200:
+            print("✅ Indonesian app (port 3000) is accessible")
+        else:
+            print(f"❌ Indonesian app failed: {response.status_code}")
+    except Exception as e:
+        print(f"⚠️ Indonesian app not accessible: {e}")
+    
+    # Test German app  
+    try:
+        response = requests.get("http://localhost:3001", timeout=5)
+        if response.status_code == 200:
+            print("✅ German app (port 3001) is accessible")
+        else:
+            print(f"❌ German app failed: {response.status_code}")
+    except Exception as e:
+        print(f"⚠️ German app not accessible: {e}")
+
+def print_summary():
+    """Print setup summary"""
+    print("\n" + "="*50)
+    print("🌍 STREET LINGO PLATFORM SETUP SUMMARY")
+    print("="*50)
+    print("\n📱 Access Your Apps:")
+    print("  🇮🇩 Indonesian: http://localhost:3000")
+    print("  🇩🇪 German:     http://localhost:3001")
+    print("\n🔧 Backend API:")
+    print("  📡 Main API:    http://localhost:8000")
+    print("  📊 API Docs:    http://localhost:8000/docs")
+    print("\n🎯 Test Scenarios:")
+    print("  🇮🇩 Indonesian: http://localhost:8000/api/scenarios/indonesian")
+    print("  🇩🇪 German:     http://localhost:8000/api/scenarios/german")
+    print("\n💡 Next Steps:")
+    print("  1. Open the apps in your browser")
+    print("  2. Grant microphone permissions")
+    print("  3. Try a conversation scenario")
+    print("  4. Check the API docs for more endpoints")
+    print("\n🚀 Happy Learning!")
+
+def main():
+    """Main test function"""
+    print("🧪 STREET LINGO PLATFORM TEST")
+    print("=" * 40)
+    
+    # Test backend health
+    if not test_backend_health():
+        print("\n❌ Backend is not running. Please start it first:")
+        print("   cd backend && python main.py")
+        sys.exit(1)
+    
+    # Test API endpoints
+    test_scenarios_api()
+    test_translation_api()
+    
+    # Test frontend accessibility
+    test_frontend_accessibility()
+    
+    # Print summary
+    print_summary()
+
+if __name__ == "__main__":
+    main()