A pathological document announces itself on first read

↗ view on GitHub · Eli Ziff · 2026-07-29 · 5e188b38

The sniffer now runs at the read choke points: extractLocalDocument
(library_read/library_find/library_outline) and readDocumentContent
(read_document/fetch_documents) surface scanDocxPathology's
notes_of_caution - manual redlines, unresolved tracked changes, text
boxes, unicode traps - as additive metadata. The extracted text stays
byte-identical, held by test against extractDocxBodyText on both paths;
find_in_document opts out so hit offsets keep anchoring into pure text.

The report caches beside the text parse under its own parseCache
identity (docx-pathology v1, JSON-in-string); an unparseable entry
degrades to no notes, never a failed read. Note wording comes from the
report verbatim, capped at 8 lines per result.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012AgUm5EcRKbT3duVFMbrQD
Repository eliziff/Beaver
Author Eli Ziff <eliasziff@gmail.com>
Authored
Parents 0e792666
Stats 4 files changed , +359 , -9
Part of Legal agent-surface and context-compaction experiments

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-5e188b38.md from inside the repo you want the change in.

⬇ Download capture-commit-5e188b38.md