After reading the agent-design core source I finally understand the trade-offs
It took me two weeks of on-and-off digging and plenty of wrong turns. Writing the process down as it happened so the next person spends less time.
What genuinely surprised me was the tail. The average looked great while P99 jumped by an order of magnitude past some threshold. The cause was not agent-design itself but our upstream connection reuse — the load test traffic was too clean and hid the long-tail requests.
-- The query that broke: a full scan over 20M rows. -- A composite index took P99 from 1.8s down to 42ms. SELECT id, title, created_at FROM posts WHERE community_id = ? AND status = 1 ORDER BY score DESC LIMIT 20;
We also fixed monitoring along the way: replaced average-based alerts with percentiles and split them per endpoint. False alerts dropped by about seventy percent and the on-call rotation visibly cheered up.
The first thing was to collapse the variables. We were changing config and upgrading the version at the same time, and afterwards nobody could say which change caused what. We rolled back to moving one variable at a time, re-ran three times, and only then did the curve settle. Tedious, but not skippable.
Worth noting: the official docs do cover this, just in a very inconspicuous spot. I only found it reading the source comments, where the author explains the reasoning — roughly "so that it degrades into predictable behaviour in extreme cases".