diff --git a/scripts/QUICKSTART.md b/scripts/QUICKSTART.md
new file mode 100644
index 0000000..e9e525b
--- /dev/null
+++ b/scripts/QUICKSTART.md
@@ -0,0 +1,89 @@
+# 🚀 Quick Start Guide
+
+Get the Z.AI to OpenAI API proxy running in 60 seconds!
+
+## One-Command Setup
+
+```bash
+git clone https://github.com/Zeeeepa/z.ai2api_python.git
+cd z.ai2api_python
+
+# Optional: Set credentials
+export ZAI_EMAIL="developer@pixelium.uk"
+export ZAI_PASSWORD="developer123?"
+export SERVER_PORT=7322
+
+# Deploy, start, and test
+bash scripts/all.sh
+```
+
+## What You Get
+
+✅ **Server running** on http://localhost:7322 (or next available port)  
+✅ **API endpoint** at http://localhost:7322/v1  
+✅ **Automatic test** with working response  
+✅ **Ready for production** or development use
+
+## Test with cURL
+
+```bash
+curl -X POST "http://localhost:7322/v1/chat/completions" \
+  -H "Authorization: Bearer sk-any" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-5",
+    "messages": [
+      {"role": "user", "content": "Hello!"}
+    ]
+  }'
+```
+
+## Test with Python
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    api_key="sk-any",
+    base_url="http://localhost:7322/v1"
+)
+
+response = client.chat.completions.create(
+    model="gpt-5",
+    messages=[{"role": "user", "content": "Hello!"}]
+)
+
+print(response.choices[0].message.content)
+```
+
+## Common Commands
+
+```bash
+# View logs
+tail -f server.log
+
+# Stop server
+kill $(cat server.pid)
+
+# Restart server
+bash scripts/start.sh
+
+# Run test
+bash scripts/send_openai_request.sh
+```
+
+## File Locations
+
+- **Logs:** `server.log`
+- **PID:** `server.pid`
+- **Port:** `server.port`
+- **Scripts:** `scripts/`
+
+## Need Help?
+
+See [scripts/README.md](README.md) for detailed documentation.
+
+---
+
+**That's it! 🎉 Your proxy is ready to use!**
+
diff --git a/scripts/README.md b/scripts/README.md
new file mode 100644
index 0000000..87e32c0
--- /dev/null
+++ b/scripts/README.md
@@ -0,0 +1,417 @@
+# Z.AI to OpenAI API Proxy - Deployment Scripts
+
+Automated deployment and testing scripts for the z.ai2api_python proxy server.
+
+## Quick Start
+
+```bash
+# Clone the repository
+git clone https://github.com/Zeeeepa/z.ai2api_python.git
+cd z.ai2api_python
+
+# Set credentials (optional - will use anonymous mode if not set)
+export ZAI_EMAIL="your-email@example.com"
+export ZAI_PASSWORD="your-password"
+export SERVER_PORT=7322  # Optional, defaults to 7300
+
+# Run everything
+bash scripts/all.sh
+```
+
+That's it! The server will be deployed, started, and tested automatically.
+
+## Individual Scripts
+
+### 1. `deploy.sh` - Dependency Installation
+
+Installs all dependencies and sets up the virtual environment.
+
+```bash
+bash scripts/deploy.sh
+```
+
+**What it does:**
+- ✅ Checks for `uv` installation
+- ✅ Creates Python virtual environment (`.venv/`)
+- ✅ Installs project dependencies via `uv sync`
+- ✅ Installs OpenAI client library for testing
+
+**Requirements:**
+- `uv` must be installed ([installation guide](https://github.com/astral-sh/uv))
+
+**Exit Codes:**
+- `0` - Success
+- `1` - Missing required files (main.py, pyproject.toml)
+- `2` - `uv` not installed
+
+---
+
+### 2. `start.sh` - Server Startup with Port Fallback
+
+Starts the server with intelligent port selection.
+
+```bash
+bash scripts/start.sh
+```
+
+**What it does:**
+- ✅ Finds available port (tries 7300 → 7301 → 7302, etc.)
+- ✅ Starts server in background
+- ✅ Waits for server to be ready
+- ✅ Saves PID to `server.pid` and port to `server.port`
+
+**Environment Variables:**
+- `SERVER_PORT` - Starting port (default: 7300)
+- `ZAI_EMAIL` - Your Z.AI email (optional)
+- `ZAI_PASSWORD` - Your Z.AI password (optional)
+- `AUTH_TOKEN` - API key for clients (default: "sk-any")
+
+**Port Detection:**
+The script tries up to 10 ports starting from `SERVER_PORT`. If all are busy, it exits with an error.
+
+**Output Files:**
+- `server.log` - Server logs
+- `server.pid` - Server process ID
+- `server.port` - Selected port number
+
+**Exit Codes:**
+- `0` - Success
+- `1` - Virtual environment not found
+- `3` - No available port found
+- `4` - Server failed to start
+
+---
+
+### 3. `send_openai_request.sh` - API Testing
+
+Sends a test OpenAI API request to verify the server is working.
+
+```bash
+bash scripts/send_openai_request.sh
+```
+
+**What it does:**
+- ✅ Reads server port from `server.port`
+- ✅ Verifies server is running (checks PID)
+- ✅ Sends chat completion request
+- ✅ Displays response and timing
+
+**Test Request:**
+```python
+{
+  "model": "gpt-5",
+  "messages": [
+    {"role": "user", "content": "Write a haiku about code."}
+  ]
+}
+```
+
+**Exit Codes:**
+- `0` - Success
+- `1` - Virtual environment not found
+- `4` - Server not running
+- `5` - API request failed
+
+---
+
+### 4. `all.sh` - Complete Setup (Recommended)
+
+Runs all scripts in sequence with nice formatting.
+
+```bash
+bash scripts/all.sh
+```
+
+**Execution Order:**
+1. `deploy.sh` - Install dependencies
+2. `start.sh` - Start server
+3. `send_openai_request.sh` - Test API
+
+**Features:**
+- 🎨 Colored output
+- 📊 Environment display
+- ❌ Fail-fast behavior (stops on first error)
+- ✅ Success summary with useful commands
+
+---
+
+## Usage Examples
+
+### Example 1: Basic Setup (Anonymous Mode)
+
+```bash
+cd z.ai2api_python
+bash scripts/all.sh
+```
+
+Server will run in anonymous mode without Z.AI credentials.
+
+### Example 2: With Z.AI Credentials
+
+```bash
+export ZAI_EMAIL="developer@pixelium.uk"
+export ZAI_PASSWORD="developer123?"
+export SERVER_PORT=7322
+
+cd z.ai2api_python
+bash scripts/all.sh
+```
+
+Server will authenticate with Z.AI using provided credentials.
+
+### Example 3: Custom Port
+
+```bash
+export SERVER_PORT=8080
+bash scripts/all.sh
+```
+
+Server will try port 8080 first, then 8081, 8082, etc. if busy.
+
+### Example 4: Step-by-Step Execution
+
+```bash
+# Step 1: Deploy
+bash scripts/deploy.sh
+
+# Step 2: Start server
+export ZAI_EMAIL="your@email.com"
+export ZAI_PASSWORD="yourpass"
+bash scripts/start.sh
+
+# Step 3: Test API
+bash scripts/send_openai_request.sh
+```
+
+---
+
+## Server Management
+
+### View Logs
+
+```bash
+tail -f server.log
+```
+
+### Stop Server
+
+```bash
+kill $(cat server.pid)
+```
+
+### Restart Server
+
+```bash
+# Stop current server
+kill $(cat server.pid)
+
+# Start new server
+bash scripts/start.sh
+```
+
+### Check Server Status
+
+```bash
+# Check if process is running
+ps -p $(cat server.pid)
+
+# Get server port
+cat server.port
+
+# Test server endpoint
+curl http://localhost:$(cat server.port)/v1/models
+```
+
+---
+
+## Troubleshooting
+
+### Error: "uv is not installed"
+
+**Solution:**
+```bash
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+
+### Error: "No available port found"
+
+**Solution:**
+- Check what's using ports: `lsof -ti:7300-7310`
+- Kill processes or set different `SERVER_PORT`
+- Example: `export SERVER_PORT=8000`
+
+### Error: "Server failed to start"
+
+**Solution:**
+```bash
+# Check logs
+cat server.log
+
+# Common issues:
+# 1. Port already in use
+# 2. Missing dependencies
+# 3. Python version mismatch
+
+# Try manual start for debugging
+PYTHONPATH= ./.venv/bin/python main.py
+```
+
+### Error: "Virtual environment not found"
+
+**Solution:**
+```bash
+# Run deploy script first
+bash scripts/deploy.sh
+```
+
+### API Request Fails
+
+**Solution:**
+```bash
+# 1. Verify server is running
+ps aux | grep "python main.py"
+
+# 2. Check port
+cat server.port
+
+# 3. Test with curl
+PORT=$(cat server.port)
+curl -X POST "http://localhost:$PORT/v1/chat/completions" \
+  -H "Authorization: Bearer sk-any" \
+  -H "Content-Type: application/json" \
+  -d '{"model":"gpt-5","messages":[{"role":"user","content":"test"}]}'
+
+# 4. Check logs
+tail -50 server.log
+```
+
+### Error: "Z.AI API 错误: 405" or "匿名模式下获取访客令牌失败"
+
+This error indicates that Z.AI's authentication API has changed or is temporarily unavailable.
+
+**Solutions:**
+
+1. **Use authenticated mode with credentials:**
+   ```bash
+   export ZAI_EMAIL="your-email@example.com"
+   export ZAI_PASSWORD="your-password"
+   bash scripts/start.sh
+   ```
+
+2. **Check Z.AI service status:**
+   - Visit https://chat.z.ai/ to verify the service is operational
+   - The anonymous token endpoint may have changed
+
+3. **Wait and retry:**
+   - Z.AI may be experiencing temporary issues
+   - The service typically recovers within a few minutes
+
+---
+
+## Environment Variables Reference
+
+| Variable | Default | Description |
+|----------|---------|-------------|
+| `SERVER_PORT` | `7300` | Starting port for server |
+| `ZAI_EMAIL` | (none) | Z.AI account email |
+| `ZAI_PASSWORD` | (none) | Z.AI account password |
+| `AUTH_TOKEN` | `"sk-any"` | API key for client requests |
+| `LISTEN_PORT` | Auto | Actual port selected by start.sh |
+
+---
+
+## File Structure
+
+```
+z.ai2api_python/
+├── scripts/
+│   ├── deploy.sh              # Install dependencies
+│   ├── start.sh               # Start server
+│   ├── send_openai_request.sh # Test API
+│   ├── all.sh                 # Run all scripts
+│   └── README.md              # This file
+├── server.log                 # Server logs (generated)
+├── server.pid                 # Server PID (generated)
+└── server.port                # Server port (generated)
+```
+
+---
+
+## Advanced Usage
+
+### Run in Docker
+
+**Note:** A Dockerfile is not currently included in this repository. To run with Docker, you'll need to create a Dockerfile first. Example:
+
+```dockerfile
+FROM python:3.11-slim
+WORKDIR /app
+COPY . .
+RUN pip install uv && uv venv && uv sync
+CMD ["bash", "scripts/start.sh"]
+```
+
+Then build and run:
+
+```bash
+# Build image
+docker build -t z-ai2api .
+
+# Run container
+docker run -d \
+  -p 7300:7300 \
+  -e ZAI_EMAIL="your@email.com" \
+  -e ZAI_PASSWORD="yourpass" \
+  --name z-ai2api \
+  z-ai2api
+```
+
+### Use with systemd
+
+Create `/etc/systemd/system/z-ai2api.service`:
+
+```ini
+[Unit]
+Description=Z.AI to OpenAI API Proxy
+After=network.target
+
+[Service]
+Type=forking
+User=youruser
+WorkingDirectory=/path/to/z.ai2api_python
+Environment="ZAI_EMAIL=your@email.com"
+Environment="ZAI_PASSWORD=yourpass"
+Environment="SERVER_PORT=7300"
+ExecStart=/path/to/z.ai2api_python/scripts/start.sh
+PIDFile=/path/to/z.ai2api_python/server.pid
+
+[Install]
+WantedBy=multi-user.target
+```
+
+Then:
+```bash
+sudo systemctl enable z-ai2api
+sudo systemctl start z-ai2api
+```
+
+---
+
+## Contributing
+
+When modifying scripts:
+1. Test with `bash -n script.sh` (syntax check)
+2. Test with `shellcheck script.sh` (linting)
+3. Test all exit codes
+4. Update this README
+
+---
+
+## Support
+
+- **Repository:** https://github.com/Zeeeepa/z.ai2api_python
+- **Issues:** https://github.com/Zeeeepa/z.ai2api_python/issues
+
+---
+
+**Made with ❤️ for simplified Z.AI proxy deployment**
diff --git a/scripts/all.sh b/scripts/all.sh
new file mode 100755
index 0000000..159132b
--- /dev/null
+++ b/scripts/all.sh
@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+# all.sh - Run complete deployment, start server, and test
+
+set -e  # Exit on any error
+
+# Color codes for output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+BLUE='\033[0;34m'
+NC='\033[0m' # No Color
+
+echo -e "${BLUE}╔════════════════════════════════════════════════════════════╗${NC}"
+echo -e "${BLUE}║         Z.AI to OpenAI API Proxy - Full Setup             ║${NC}"
+echo -e "${BLUE}╚════════════════════════════════════════════════════════════╝${NC}"
+echo ""
+
+# Trap errors
+trap 'echo -e "${RED}❌ Setup failed at step: $CURRENT_STEP${NC}"; exit 1' ERR
+
+# Check if we're in the correct directory
+if [[ ! -f "main.py" ]]; then
+    echo -e "${RED}❌ Error: main.py not found. Please run from project root.${NC}"
+    exit 1
+fi
+
+# Display environment
+echo -e "${YELLOW}📋 Environment:${NC}"
+echo "   PWD: $(pwd)"
+echo "   Python: $(command -v python3 || echo 'not found')"
+echo "   uv: $(command -v uv || echo 'not found')"
+
+if [[ -n "$ZAI_EMAIL" ]]; then
+    echo "   ZAI_EMAIL: $ZAI_EMAIL"
+else
+    echo "   ZAI_EMAIL: (not set - will use anonymous mode)"
+fi
+
+if [[ -n "$ZAI_PASSWORD" ]]; then
+    echo "   ZAI_PASSWORD: ***"
+else
+    echo "   ZAI_PASSWORD: (not set - will use anonymous mode)"
+fi
+
+echo "   SERVER_PORT: ${SERVER_PORT:-7300 (default)}"
+echo ""
+
+# Step 1: Deploy
+CURRENT_STEP="deploy"
+echo -e "${GREEN}━━━ Step 1/3: Deployment ━━━${NC}"
+bash scripts/deploy.sh
+echo ""
+
+# Step 2: Start server
+CURRENT_STEP="start server"
+echo -e "${GREEN}━━━ Step 2/3: Starting Server ━━━${NC}"
+bash scripts/start.sh
+echo ""
+
+# Give server extra time to stabilize
+sleep 2
+
+# Step 3: Test API
+CURRENT_STEP="test API"
+echo -e "${GREEN}━━━ Step 3/3: Testing API ━━━${NC}"
+bash scripts/send_openai_request.sh
+echo ""
+
+# Success!
+echo -e "${GREEN}╔════════════════════════════════════════════════════════════╗${NC}"
+echo -e "${GREEN}║                  ✅ Setup Complete!                        ║${NC}"
+echo -e "${GREEN}╚════════════════════════════════════════════════════════════╝${NC}"
+echo ""
+echo -e "${BLUE}📊 Server Information:${NC}"
+
+if [[ -f "server.port" ]]; then
+    PORT=$(cat server.port)
+    echo "   URL: http://localhost:$PORT"
+    echo "   API: http://localhost:$PORT/v1"
+fi
+
+if [[ -f "server.pid" ]]; then
+    PID=$(cat server.pid)
+    echo "   PID: $PID"
+fi
+
+echo ""
+echo -e "${YELLOW}💡 Useful Commands:${NC}"
+echo "   View logs:  tail -f server.log"
+echo "   Stop server: kill \$(cat server.pid)"
+echo "   Restart:     bash scripts/start.sh"
+echo "   Test API:    bash scripts/send_openai_request.sh"
+echo ""
+echo -e "${GREEN}🎉 Your OpenAI-compatible API proxy is ready!${NC}"
+
diff --git a/scripts/deploy.sh b/scripts/deploy.sh
new file mode 100755
index 0000000..13d7c52
--- /dev/null
+++ b/scripts/deploy.sh
@@ -0,0 +1,48 @@
+#!/usr/bin/env bash
+# deploy.sh - Install dependencies and setup virtual environment
+
+set -e  # Exit on any error
+
+echo "🚀 Starting deployment of z.ai2api_python..."
+
+# Check if uv is installed
+if ! command -v uv &> /dev/null; then
+    echo "❌ Error: 'uv' is not installed."
+    echo "📦 Install it with: curl -LsSf https://astral.sh/uv/install.sh | sh"
+    exit 2
+fi
+
+echo "✅ uv found: $(uv --version)"
+
+# Check for required files
+if [[ ! -f "main.py" ]]; then
+    echo "❌ Error: main.py not found. Are you in the project root?"
+    exit 1
+fi
+
+if [[ ! -f "pyproject.toml" ]]; then
+    echo "❌ Error: pyproject.toml not found. Are you in the project root?"
+    exit 1
+fi
+
+# Create/sync virtual environment
+echo "📦 Creating virtual environment and syncing dependencies..."
+uv venv
+
+echo "📥 Installing project dependencies..."
+uv sync
+
+# Install OpenAI client for testing
+echo "🔧 Installing OpenAI client for API testing..."
+uv pip install "openai>=1.0.0,<2"
+
+echo ""
+echo "✅ Deployment complete!"
+echo "📁 Virtual environment: .venv/"
+echo "🐍 Python: $(./.venv/bin/python --version)"
+echo ""
+echo "Next steps:"
+echo "  1. Export credentials: export ZAI_EMAIL='your@email.com' ZAI_PASSWORD='yourpass'"
+echo "  2. Start server: bash scripts/start.sh"
+echo "  3. Or run all: bash scripts/all.sh"
+
diff --git a/scripts/send_openai_request.sh b/scripts/send_openai_request.sh
new file mode 100755
index 0000000..70e2197
--- /dev/null
+++ b/scripts/send_openai_request.sh
@@ -0,0 +1,94 @@
+#!/usr/bin/env bash
+# send_openai_request.sh - Send test OpenAI API request to the server
+
+set -e
+
+echo "🧪 Sending OpenAI API test request..."
+
+# Check if virtual environment exists
+if [[ ! -d ".venv" ]]; then
+    echo "❌ Error: Virtual environment not found. Run: bash scripts/deploy.sh"
+    exit 1
+fi
+
+# Get server port
+if [[ -f "server.port" ]]; then
+    SERVER_PORT=$(cat server.port)
+else
+    SERVER_PORT=${SERVER_PORT:-7300}
+    echo "⚠️  server.port not found, using SERVER_PORT=${SERVER_PORT}"
+fi
+
+# Check if server is running
+if [[ -f "server.pid" ]]; then
+    SERVER_PID=$(cat server.pid)
+    if ! ps -p $SERVER_PID > /dev/null 2>&1; then
+        echo "❌ Error: Server process (PID: $SERVER_PID) is not running"
+        exit 4
+    fi
+else
+    echo "⚠️  server.pid not found, cannot verify server is running"
+fi
+
+# Get AUTH_TOKEN
+AUTH_TOKEN=${AUTH_TOKEN:-"sk-any"}
+
+echo "📡 Request details:"
+echo "   URL: http://localhost:$SERVER_PORT/v1"
+echo "   Model: gpt-5"
+echo "   AUTH_TOKEN: ${AUTH_TOKEN:0:8}... (masked for security)"
+echo ""
+
+# Create and run test script
+echo "🔄 Executing request..."
+PYTHONPATH= ./.venv/bin/python - <<PYEOF
+import sys
+import time
+from openai import OpenAI
+
+try:
+    start_time = time.time()
+    
+    client = OpenAI(
+        api_key="${AUTH_TOKEN}",
+        base_url="http://localhost:${SERVER_PORT}/v1"
+    )
+    
+    response = client.chat.completions.create(
+        model="gpt-5",
+        messages=[
+            {"role": "user", "content": "Write a haiku about code."}
+        ]
+    )
+    
+    elapsed_time = time.time() - start_time
+    
+    print("✅ Request successful!")
+    print(f"⏱️  Response time: {elapsed_time:.2f}s")
+    print("")
+    print("📝 Response:")
+    print("=" * 60)
+    print(response.choices[0].message.content)
+    print("=" * 60)
+    print("")
+    print(f"🔧 Model used: {response.model}")
+    print(f"📊 Tokens: {response.usage.total_tokens if hasattr(response, 'usage') and response.usage else 'N/A'}")
+    
+except Exception as e:
+    print(f"❌ Request failed: {str(e)}")
+    print("")
+    print("💡 Troubleshooting:")
+    print("   1. Check if server is running: ps aux | grep 'python main.py'")
+    print("   2. Check server logs: tail -50 server.log")
+    print(f"   3. Test port: curl http://localhost:${SERVER_PORT}/v1/models")
+    sys.exit(5)
+PYEOF
+
+EXIT_CODE=$?
+
+if [[ $EXIT_CODE -eq 0 ]]; then
+    echo "✅ Test completed successfully!"
+else
+    echo "❌ Test failed with exit code: $EXIT_CODE"
+    exit $EXIT_CODE
+fi
diff --git a/scripts/start.sh b/scripts/start.sh
new file mode 100755
index 0000000..38ead18
--- /dev/null
+++ b/scripts/start.sh
@@ -0,0 +1,109 @@
+#!/usr/bin/env bash
+# start.sh - Start the server with port fallback logic
+
+set -e
+
+echo "🔧 Starting z.ai2api server..."
+
+# Check if virtual environment exists
+if [[ ! -d ".venv" ]]; then
+    echo "❌ Error: Virtual environment not found. Run: bash scripts/deploy.sh"
+    exit 1
+fi
+
+# Function to check if a port is in use
+is_port_in_use() {
+    local port=$1
+    if command -v lsof &> /dev/null; then
+        lsof -ti:$port &> /dev/null
+    elif command -v nc &> /dev/null; then
+        nc -z localhost $port &> /dev/null
+    else
+        # Fallback: try to bind with Python
+        # If bind succeeds, port is FREE (return 1), if it fails, port is IN USE (return 0)
+        if ./.venv/bin/python -c "import socket; s=socket.socket(); s.bind(('', $port)); s.close()" 2>/dev/null; then
+            return 1  # Port is free
+        else
+            return 0  # Port is in use
+        fi
+    fi
+}
+
+# Find available port starting from SERVER_PORT (default 7300)
+START_PORT=${SERVER_PORT:-7300}
+MAX_ATTEMPTS=10
+SELECTED_PORT=""
+
+echo "🔍 Searching for available port starting from $START_PORT..."
+
+for ((i=0; i<$MAX_ATTEMPTS; i++)); do
+    TEST_PORT=$((START_PORT + i))
+    if ! is_port_in_use $TEST_PORT; then
+        SELECTED_PORT=$TEST_PORT
+        echo "✅ Found available port: $SELECTED_PORT"
+        break
+    else
+        echo "   Port $TEST_PORT is busy, trying next..."
+    fi
+done
+
+if [[ -z "$SELECTED_PORT" ]]; then
+    echo "❌ Error: Could not find available port after $MAX_ATTEMPTS attempts"
+    echo "   Tried ports: $START_PORT-$((START_PORT + MAX_ATTEMPTS - 1))"
+    exit 3
+fi
+
+# Set environment variables
+export LISTEN_PORT=$SELECTED_PORT
+export PYTHONPATH=
+export AUTH_TOKEN=${AUTH_TOKEN:-"sk-any"}
+
+# Optional: Use ZAI credentials if provided
+if [[ -n "$ZAI_EMAIL" && -n "$ZAI_PASSWORD" ]]; then
+    echo "🔐 Using ZAI credentials: $ZAI_EMAIL"
+    export ZAI_EMAIL
+    export ZAI_PASSWORD
+else
+    echo "⚠️  ZAI_EMAIL and ZAI_PASSWORD not set - running in anonymous mode"
+fi
+
+# Clean up old logs and PID files
+rm -f server.log server.pid
+
+# Start server in background
+echo "🚀 Starting server on port $SELECTED_PORT..."
+nohup ./.venv/bin/python main.py > server.log 2>&1 &
+SERVER_PID=$!
+
+# Save PID and port
+echo $SERVER_PID > server.pid
+echo $SELECTED_PORT > server.port
+
+echo "✅ Server started!"
+echo "   PID: $SERVER_PID"
+echo "   Port: $SELECTED_PORT"
+echo "   Logs: server.log"
+
+# Wait for server to be ready
+echo "⏳ Waiting for server to be ready..."
+MAX_WAIT=15
+for ((i=1; i<=$MAX_WAIT; i++)); do
+    if is_port_in_use $SELECTED_PORT; then
+        echo "✅ Server is ready after ${i}s!"
+        echo ""
+        echo "📊 Server Info:"
+        echo "   Base URL: http://localhost:$SELECTED_PORT"
+        echo "   API URL: http://localhost:$SELECTED_PORT/v1"
+        echo "   AUTH_TOKEN: $AUTH_TOKEN"
+        echo ""
+        echo "To stop server: kill $SERVER_PID"
+        echo "To view logs: tail -f server.log"
+        exit 0
+    fi
+    sleep 1
+done
+
+echo "❌ Error: Server failed to start within ${MAX_WAIT}s"
+echo "📋 Last 20 lines of server.log:"
+tail -20 server.log
+exit 4