feat(lab): draft-edit-v4 - universal refinement checkpoint with honest coverage contents
v3 replicates: acq 58+60 (both above the 56-57 pre-refinement ceiling) vs tax 48+51 (edits cannot rescue partial-coverage composition). The acq gains depended on the FALSE refusal capturing the draft at full coverage - the honest gate would have removed the checkpoint from exactly those runs. v4 decouples them: the first bodied generate_docx always pauses once, saving the draft and reporting coverage honestly (true unread list when short, all-read confirmation when complete), then the next call renders. Echo-only arms (no draft-edit) keep pure shortfall-refusal semantics. Gen-7 smoke (employment, pre-v4): honest gate stayed silent at full coverage, single emission, cacheadj 67.5k = cheapest employment row of the night. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_011pfUVhNFTRvhYGXBwoKNj6
| Repository | eliziff/Beaver |
|---|---|
| Author | Eli Ziff <eliasziff@gmail.com> |
| Authored | |
| Parents | ada6e7c8 |
| Stats | 2 files changed , +49 , -37 |
| Part of | Evaluation harness: Beaver-CAN and LegalBench-RAG adapters |
Capture this commit into my fork
Download a Markdown prompt that tells Claude how to port this
exact commit into your working tree. Run it via
claude -p < capture-commit-bc57d942.md
from inside the repo you want the change in.