feat: Add multi-LLM provider support with DeepSeek integration

Major Features:
- ✨ Multi-LLM provider support (DeepSeek, Ollama, OpenAI, Custom)
- 🤖 Admin panel LLM configuration management UI
- 🔄 Dynamic provider switching without restart
- 🧪 Built-in API connection testing
- 🔒 Secure API key management

Backend Changes:
- Add routes/llmConfig.js: Complete LLM config CRUD API
- Update routes/analyze.js: Use database LLM configuration
- Update server.js: Add LLM config routes
- Add scripts/add-deepseek-config.js: DeepSeek setup script

Frontend Changes:
- Update src/pages/AdminPage.jsx: Add LLM Config tab + modal
- Update src/services/api.js: Add LLM config API methods
- Provider presets for DeepSeek, Ollama, OpenAI
- Test connection feature in config modal

Configuration:
- Update .env.example: Add DeepSeek API configuration
- Update package.json: Add llm:add-deepseek script

Documentation:
- Add docs/LLM_CONFIGURATION_GUIDE.md: Complete guide
- Add DEEPSEEK_INTEGRATION.md: Integration summary
- Quick setup instructions for DeepSeek

API Endpoints:
- GET /api/llm-config: List all configurations
- GET /api/llm-config/active: Get active configuration
- POST /api/llm-config: Create configuration
- PUT /api/llm-config/🆔 Update configuration
- PUT /api/llm-config/:id/activate: Activate configuration
- DELETE /api/llm-config/🆔 Delete configuration
- POST /api/llm-config/test: Test API connection

Database:
- Uses existing llm_configs table
- Only one config active at a time
- Fallback to Ollama if no database config

Security:
- Admin-only access to LLM configuration
- API keys never returned in GET requests
- Audit logging for all config changes
- Cannot delete active configuration

DeepSeek Model:
- Model: deepseek-chat
- High-quality 5 Why analysis
- Excellent Chinese language support
- Cost-effective pricing

🤖 Generated with Claude Code
Co-Authored-By: Claude <noreply@anthropic.com>

server.js

@@ -12,6 +12,7 @@ import { notFoundHandler, errorHandler } from './middleware/errorHandler.js';
 import authRoutes from './routes/auth.js';
 import analyzeRoutes from './routes/analyze.js';
 import adminRoutes from './routes/admin.js';
+import llmConfigRoutes from './routes/llmConfig.js';
 
 // 載入環境變數
 dotenv.config();
@@ -104,6 +105,7 @@ app.get('/health/db', async (req, res) => {
 app.use('/api/auth', authRoutes);
 app.use('/api/analyze', analyzeRoutes);
 app.use('/api/admin', adminRoutes);
+app.use('/api/llm-config', llmConfigRoutes);
 
 // Root Endpoint
 app.get('/', (req, res) => {
@@ -128,6 +130,15 @@ app.get('/', (req, res) => {
         users: 'GET /api/admin/users',
         analyses: 'GET /api/admin/analyses',
         auditLogs: 'GET /api/admin/audit-logs'
+      },
+      llmConfig: {
+        list: 'GET /api/llm-config',
+        active: 'GET /api/llm-config/active',
+        create: 'POST /api/llm-config',
+        update: 'PUT /api/llm-config/:id',
+        activate: 'PUT /api/llm-config/:id/activate',
+        delete: 'DELETE /api/llm-config/:id',
+        test: 'POST /api/llm-config/test'
       }
     }
   });