admission control

Track request admission through a concrete page-reservation example, then connect scheduling, growth and stream cleanup to measured service limits.

Divide one token budget across gateways instead of copying it. Follow output reservation and settlement, then handle grants, retries and outages without inventing extra burst capacity.

Work a 200 ms request budget, distinguish stage allowances from percentiles, and price the capacity needed to meet the measured latency contract.

Find concrete failure paths in a small serving architecture. Rank correctness, admission and placement fixes before proposing additional infrastructure.