Skip to main content

​
Overview

Execute Python code in a secure sandboxed environment directly from chat. The sandbox runs on Vercel infrastructure with a 5-minute timeout and 2 vCPUs.

​
Quick Start

Enable code execution in chat.config.ts: 
integrations: {
  sandbox: true, // Vercel-native, no key needed
}

​
Pre-installed Packages

The following packages are available out of the box:
  • matplotlib - Plotting and visualization
  • pandas - Data analysis
  • numpy - Numerical computing
  • sympy - Symbolic mathematics
  • yfinance - Yahoo Finance market data

​
Installing Additional Packages

Add !pip install lines at the top of your code. They are automatically stripped before execution: 
!pip install requests beautifulsoup4

import requests
from bs4 import BeautifulSoup

response = requests.get("https://example.com")
print(response.status_code)

​
Output

There are two ways to return output: 1. Use print() 
import pandas as pd
df = pd.DataFrame({"a": [1, 2], "b": [3, 4]})
print(df.head())
2. Assign to result or results The sandbox automatically prints these variables if they exist: 
import numpy as np
result = np.mean([1, 2, 3, 4, 5])
Implicit REPL output (last expression value) is not captured. Always use print() or assign to result.

​
Charts

The sandbox supports matplotlib charts. No need to call plt.show(). The chart is saved automatically: 
import matplotlib.pyplot as plt
import numpy as np

x = np.linspace(0, 10, 100)
y = np.sin(x)

plt.figure(figsize=(10, 6))
plt.plot(x, y)
plt.title("Sine Wave")
plt.xlabel("x")
plt.ylabel("sin(x)")
Supported chart types:
  • Line charts
  • Scatter plots
  • Bar charts
Charts are rendered as PNG images. Complex chart types beyond line, scatter, and bar may not render correctly.

​
Customization

​
Sandbox Runtime

Set the Python version via environment variable: 
VERCEL_SANDBOX_RUNTIME=python3.13

​
Non-Vercel Deployments

When deploying outside Vercel (Docker, Railway, Fly.io, etc.), you need to authenticate with an access token since VERCEL_OIDC_TOKEN is unavailable.
  1. Copy your Team ID from team settings
  2. Copy your Project ID from project settings
  3. Create a token in your Vercel account settings scoped to your team
  4. Set these environment variables:
VERCEL_TEAM_ID=team_xxx
VERCEL_PROJECT_ID=prj_xxx
VERCEL_TOKEN=your_token_here
The sandbox automatically uses these credentials when running outside Vercel infrastructure.

​
Tool Definition

The tool is defined in lib/ai/tools/code-execution.ts. You can modify the description to adjust how the AI uses it, or change the base packages installed in the sandbox.