Commit Graph

2 Commits

Author SHA1 Message Date
iomgaa 61cace71c4 feat: add parse_document to the MonkeyOCR transport
Unrecognizable bytes are rejected before any request. The result package is downloaded as a stream with a cumulative size cap, and error statuses are classified before the size check. Parsing runs in a worker thread so cancellation and call deadlines stay effective. parse_layout shares the first protocol stage without behavior change.
2026-10-21 23:50:51 -04:00
iomgaa 3db7d9979c feat: parse document result packages from middle json only
Content comes from the middle json and its paired markdown; the content list is deliberately ignored because it escapes markdown characters. The external-data exception boundary covers both reading and structure parsing so no native exception escapes the OCR client. The layout parser is unchanged.
2026-10-21 23:35:47 -04:00