Is your feature request related to a problem? Please describe.

Some LLM models may reason for a long time call a lot of tools. The recommended way for that is to run such requests in the background.

https://platform.openai.com/docs/guides/background

Describe the solution you'd like

Spawn requests in background.

Set store=true

Navigate to a page that has request ID in the url.

Stream the responses on the UI.

Describe alternatives you've considered

Explain any additional use-cases

If there are any use-cases that would help us understand the use/need/value please share them as they can help us decide on acceptance and prioritization.

Additional context

Add any other context or screenshots about the feature request here.