Thank you for sharing. I was surprised Strata wasn’t mentioned. It’s all I’ve been hearing about recently.

The image doesn’t mean anything to me though. Without the capybara, it could be for anything.

I’ve used pi.dev’s default compaction (this was a few months ago, it may have improved) and it lobotomized the model, so I kept if off, and made my model do a handoff for the next session. However, Deepseek harness’s compaction is very good. Unfortunately, if you use under 264K context, you have to modify its settings because its point of compaction is TOTAL - max_tokens - 16k reserve, and max_tokens is 64k. I had to modify the settings down to 16K (using Qwen 3.8, because there’s a bug in how DSH reads settings and it wasn’t working when I did it), and I still compact at 73% (88K) on 120K context (ie: 120 - 16k - 16K). But it’s really good. I’ve gone to 2M output tokens (100M cached) until I thought it was getting too dumb for the task and started a new session.

So yes, compaction can work well. Make sure your prefill speed is 1000tk/s+ or else it will be painful.