Hacker News new | ask | show | jobs
by kevin8704 335 days ago
Awesome! It looks like you’re building a “reasoning tree” approach with runtime-level context engineering and pruning.

Quick question — how does the context-pruning mechanism decide which KV states to discard vs. retain? Just trying to understand how it balances memory efficiency with reasoning depth.

I’ll sign up and try out the API — excited to try it out!