alt Hacker NewsThat is really the biggest beef I have with agy over others, the forced auto compaction at the 250k token threshold (3.8-flash), while the model itself (via API) would be fine with a 1M context window. Even if the model is great, restricting context to 250k tokens (and auto compacting no matter what) limits certain applications and workflows somewhat.
Replies
adastra22 • yesterday at 7:01 PM
Wtf. Can you turn that off? On CC I have compaction completely turned off. I’d rather hit the hard out of context limit at 1M.
There is auto compaction at 250k? Having used agy for months with multi day sessions, I have never seen this.