Files
hermes-agent/tests
Teknium 89c14aeb9e fix(read_file): warn when PDF pages yield no text (scanned-image coverage gap)
anydoc converts the PDF text layer only and emits no image placeholders
or page markers, so a mostly-scanned PDF extracts 'successfully' into
section headers with empty bodies — silent data loss the model cannot
detect. Count per-page text via poppler pdftotext and prepend an
EXTRACTION COVERAGE WARNING naming the empty pages and the recovery
path (pdftoppm + vision_analyze, or the ocr-and-documents skill).

Found on a 311-page HOA resale package where 198 scanned pages
(CC&Rs, Bylaws, Articles, insurance certs) vanished without a trace.
2026-08-08 04:25:27 -07:00
..