Have noticed this problem also. Would be interesting to test it and get opinions from new joiners in an open source repo. Definitely you don't want to discourage people to use Coding Agents.
Yes! You are right that with turbopuffer you eliminate the need for manual compression and pruning and you get ultra-fast response times out of the box. I tried to stay at a higher system-design level and I think the optimal choice depends heavily on an organization’s scale and maturity: startups vs large enterprises.