mARTin-B78
a78dac98fa
Some checks are pending
Test and SonarQube / quality (push) Waiting to run
Confirmed live: re-ingesting c't KI Wissen 2026 with a local Qwen VL engine, page 18's chart transcription degenerated into "das Produkt, das Produkt, das Produkt, ..." repeated hundreds of times, filling the whole response budget -- and was accepted as real region text, which would have been narrated verbatim. The codebase already had two narrow signatures for specific observed failures (a formatting-instruction echo, a fabricated LaTeX loop), both scoped to the plain-text fallback path only. Added a general detector (_looks_like_repetition_loop): any short phrase containing a real word, repeated 8+ times immediately back-to-back. Deliberately excludes patterns with no letters -- a dot-leader contents line, a repeated number sequence -- which are legitimate and must not be flagged. Applied at both call sites: vision_ocr_page (the labelled-region path most engines use) and _whole_page_region (the plain-text fallback). Treated as a failed call in both, so vision_ocr_page_chain's existing fallback (secondary engine, then tesseract) gets a real chance instead of garbage being accepted as the page's transcription. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
1 line
6 B
Plaintext
1 line
6 B
Plaintext
1.27.4 |