Annotate mode measures rationale coverage instead of mandating it
Per review: requiring a reason on every edit was untested policy. Genre safety already comes from the path (revise output is tracked changes by construction); rationale-per-edit is now an A/B variable - unreasoned edits apply without a comment and the receipt reports edits_without_reason. Plan doc updated with the same framing plus the mid-build addendum (reuse map, TFP resolver port, generalization assets, measurement battery). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_018bhP89cYSdEEjHNPnxacns
| Repository | eliziff/Beaver |
|---|---|
| Author | Eli Ziff <eliasziff@gmail.com> |
| Authored | |
| Parents | 95e53f17 |
| Stats | 4 files changed , +101 , -41 |
| Part of | SourceDoc / DOCX engine: redlines, tracked changes, editing benchmark |
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-69ab6b5f.md
from inside the repo you want the change in.