Skip to content

0.2.3

Choose a tag to compare

View all tags
@BYK BYK released this 24 Feb 22:46
· 112 commits to main since this release
0.2.3
This tag was signed with the committer’s verified signature.
BYK Burak Yigit Kaya
SSH Key Fingerprint: VDubqw7WU8f0pORSLylahzz5hbeXS0ZMUgfKZF7MT6o
Verified
Learn about vigilant mode.
1cb90cc
This commit was signed with the committer’s verified signature.
BYK Burak Yigit Kaya
SSH Key Fingerprint: VDubqw7WU8f0pORSLylahzz5hbeXS0ZMUgfKZF7MT6o
Verified
Learn about vigilant mode.

Fix

Calibration using wrong message count after compressed turns

After a gradient-compressed turn (layers 1-4), calibrate() was called with the total DB message count instead of the compressed window size. On the next turn, newMsgCount ≈ 0 (dbCount − dbCount), so expectedInput ≈ lastKnownInput (the compressed prompt, e.g. 114K tokens). Since 114K < maxInput (168K), layer 0 fired and sent all messages uncompressed → 405K overflow on a 200K-limit model.

Fix: transform() now records the compressed message count in lastTransformedCount. The calibration call uses getLastTransformedCount() so the delta on the next turn is computed relative to the actual compressed window, not the DB snapshot.

Assets 2
Loading