[Feature Request] Implement User Quotas and Token Limits for Enterprise Deployment

## Describe the solution you'd like

We'd like to have a way to control and limit the user interactions.
Some solutions could be: Token limits/quotas, hourly/daily/monthly token or cost limitations, definition of user quotas based on user group.

## Why the solution needed

If the solution has to be deployed for a medium/large organization, we think that a user-based cost/usage control is a good thing to have.

## Additional context

For each user we should monitor the current token consumption, and show the status to th user.

## Implementation feasibility

Are you willing to collaborate with us to discuss the solution, decide on the approach, and assist with the implementation?

- [ ] Yes, I am able to implement the feature and create a pull request.
- [X] No, I am unable to implement the feature, but I am open to discussing the solution.

The issue names no files, tests, or entry points; begin by mapping the existing user, token-consumption, and deployment paths. Done requires an agreed design covering per-user monitoring, group-based quotas, hourly/daily/monthly token or cost limits, and status visibility before implementation and tests can be planned.

Written by the indexing model from the issue text.