Configure code execution
The Code execution settings let you control whether requests from a workspace can run generated code in a sandbox. You can follow the deployment defaults or apply more restrictive settings to individual workspaces.
To configure code execution for a workspace:
Select the workspace in the top-left corner.
Go to Tools → Code execution.
Under Code execution, choose whether it should:
Follow the deployment default.
Be Allowed for requests in this workspace.
Be Blocked, preventing requests from using code execution.
Optionally, add a Prompt hint to guide how code execution should be used when a request doesn’t provide its own instructions.
Set Max tool-loop iterations to limit the number of model-to-tool rounds allowed.
Set an Execution timeout to limit how long a single code execution can run.
Configure Who runs provider code tools to control whether supported provider-native code tools or the Otari sandbox handle execution.
Where available, select the Sandbox image used to run code from the options approved for your deployment.
Configure which code-execution tools the workspace can use.
Workspace settings can restrict what is allowed at the deployment level, but they cannot enable code execution if no sandbox has been configured for the deployment.
Last updated
Was this helpful?
