v0.1.4

Added

• Extractive backend — auto-detected support for KRLabsOrg/verbatim-rag-modern-bert-v2 and other Verbatim-RAG ModernBERT span models. Same CLI, just point SQUEEZ_LOCAL_MODEL at the HF id.
• Session stats — --stats prints token/line savings per call; --summary shows accumulated savings. Logged to ~/.cache/squeez/session_stats.jsonl.

Changed

• Docs reframed around two model types (generative vs extractive) instead of internal backend names.

Install

pip install --upgrade squeez