You can now interrupt long-running queries and add new context without restarting or losing progress.
This is especially useful for refining deep research or GPT-5 Pro queries as the model will adjust its response with your new requirements.
Just hit update in the sidebar and type in any additional details or clarifications.
Context injection mid run basically turns long chains into editable workflows.
It's going to be great for research + agent reliability. But it will definitely annoy the LLM ๐
Nov 5, 2025 ยท 10:41 PM UTC

