Commit Graph
5 Commits
Author SHA1 Message Date
weichen 15b388fc86 docs(ops): salvage task docs and mineru gofmt in closeout batch 2026-09-23 12:49:33 +00:00
weichenandCursor c026ad7160 test(mineru): dump parsed markdown for live content proof
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-21 11:10:42 +00:00
weichenandCursor db76a28689 feat(mineru): chunk Agent parse by page_range past 20-page cap
The free Agent lightweight API rejects files over 20 pages (-30003)
and the precision token is expired, so a real 28-page PDF could not
parse at all. On -30003, parse in 20-page windows and renumber chunk
anchors to global pages; report engine mode agent_chunked.

Also log skipped assets in ResolveMaterials and return a bool from
EnqueueAsync so parse_state is only set when a job is enqueued.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-21 10:11:08 +00:00
weichenandCursor 2c6b41a5ac feat(mineru): fall back to Agent lightweight API on token failure
When precision API key is missing or expired (A0202/A0211), parse
via the no-token Agent API so document understanding still works.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-21 08:36:24 +00:00
weichenandCursor 32cda4486c feat(mineru): add MinerU precision parse client
Implement signed batch upload, poll, zip extract, and real page
anchor rebuild from content_list.json.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-21 08:29:10 +00:00