Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.dartantic.ai/llms.txt

Use this file to discover all available pages before exploring further.

Google’s code execution tool runs Python in a sandboxed environment. State persists across turns, allowing multi-step computations and file generation.

​
Enable Code Execution

final agent = Agent(
  'google',
  chatModelOptions: const GoogleChatModelOptions(
    serverSideTools: {GoogleServerSideTool.codeExecution},
  ),
);

​
Multi-Turn Execution

State persists across conversation turns, enabling iterative workflows: 
final history = <ChatMessage>[];

// Step 1: Calculate data
await for (final chunk in agent.sendStream(
  'Calculate the first 10 Fibonacci numbers and store them in a variable '
  'called "fib_sequence".',
)) {
  stdout.write(chunk.output);
  history.addAll(chunk.messages);
}

// Step 2: Use the data from step 1
await for (final chunk in agent.sendStream(
  'Using fib_sequence, create a plot showing the golden ratio convergence. '
  'Save it as "golden_ratio.png".',
  history: history,
)) {
  stdout.write(chunk.output);
  history.addAll(chunk.messages);
}

​
Generated Files

Files created during code execution (images, CSVs, etc.) are attached as DataPart instances on the assistant message: 
for (final msg in history) {
  for (final part in msg.parts) {
    if (part is DataPart) {
      print('Generated: ${part.name} (${part.mimeType})');
      File('output/${part.name}').writeAsBytesSync(part.bytes);
    }
  }
}

​
Combined Tools

Enable both search and code execution for research + computation workflows: 
final agent = Agent(
  'google',
  chatModelOptions: const GoogleChatModelOptions(
    serverSideTools: {
      GoogleServerSideTool.googleSearch,
      GoogleServerSideTool.codeExecution,
    },
  ),
);

​
Example