Marcel 131ed336bc feat(ocr): count words and illegible words at the OCR call sites ...

Walks block["words"] before apply_confidence_markers strips the list, then
increments ocr_words_total by len(words) and ocr_illegible_words_total by
the count below threshold. Same pattern in both /ocr and /ocr/stream so the
ratio illegible/words is a faithful quality signal across endpoints.

Refs #652 (AC4)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-21 16:07:59 +02:00

27 KiB

Raw Blame History

View Raw