Please read this first

• Have you read the docs?Agents SDK docs
• Have you searched for related issues? Others may have had similar requesrs

Describe the feature

Description:
I would like to request a feature that allows users to manually interrupt/halt an OpenAI agent's operation while it's running. Currently, once an agent starts executing a task, there doesn't appear to be a straightforward way to stop the process mid-execution.

This capability would be particularly valuable for:

Long-running operations where users might want to abort

Cases where the agent is going down an undesired path

Situations requiring immediate termination for cost or resource management

Could the team consider implementing either:

A programmatic way to send an interrupt signal, or

A user interface control (in applicable environments) to stop execution?

Thank you for considering this enhancement to the agent functionality.