# 0.2.41

## Features

- **Compaction completion message** now shows the before → after token reduction instead of only the final count.

## Bug Fixes

- **Fixed token count after compaction** so the displayed number no longer jumps back up on the next model response.
- **Fixed plugin skill loading** when a manifest lists skill directories directly instead of a parent skills/ folder.

## Performance

- **Fixed memory context injection** on resume so the prompt prefix stays byte-stable and KV cache is preserved.