Feature Overview (aka. Goal Summary)

As an OpenShift Lightspeed (OLS) admin, I want the ability to define and enforce usage quota limits for each OLS user to ensure fair resource allocation and prevent system abuse.

Why is this needed?

• Noisy Neighbor Problem: Without quota limits, a single user or a small subset of users can overconsume resources, negatively impacting the experience for other users.
• Cost Management: Excessive usage by a few users can lead to increased costs, especially when integrating with external AI services that charge per query or usage volume.

Success Criteria

• Admins can set, modify, and enforce tokens/month/OLS instance via OLS config 
• When OLS user exceed the quota then user will not be able to ask any questions in OLS and display a message on OLS that quota has been met 
• quota values needs to persistent