mrbeandev 32a4b3d4b1 Fix codebook loading error when .npz path is passed to extractor ...

The extractor's load_codebook() was called with the .npz bypass codebook
path, but it only handles .pkl files. pickle.load() on an .npz file throws
a cryptic "persistent IDs" error, causing the extractor to silently fail.
This meant users got no before/after watermark verification during bypass.

Changes:
- load_codebook() now auto-discovers the .pkl codebook when given a .npz path
- Pickle save now uses protocol=4 for wider Python version compatibility

Fixes #10, #9, #11

2026-04-10 16:03:38 +05:30

..

analysis

codebook analysis

2025-12-15 22:11:23 +05:30

extraction

Fix codebook loading error when .npz path is passed to extractor

2026-04-10 16:03:38 +05:30