fix(config): pdf.ocr.request_timeout_secs default 600 → 60 per dogfood evidence (Bug #11)

metro-korea.pdf v0.20 final-dogfood (2026-05-27):
- page 8 + page 13 양쪽 모두 600s default 까지 완전 timeout
  (`ms: 600000, chars: 0, skipped: true`)
- 결과: 본문 indexed 안 됨 + page 당 20분 cost 낭비

cloud GPU Ollama 의 실측 per-page throughput 는 6-32s (parent spec 가정 105s 보다
훨씬 빠름). 60s 면 production-friendly upper-bound. dense/고해상도 page 는
config.toml override (`[pdf.ocr] request_timeout_secs = N`) 로 user 가 늘릴 수
있음 — Step 6 에서 HOTFIXES + parent spec cross-link.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-27 23:15:21 +00:00
parent 28f513795e
commit 10b0e2f4f2
2 changed files with 20 additions and 2 deletions

View File

@@ -52,7 +52,7 @@ fn pdf_ocr_defaults_off_with_qwen_3b() {
assert!(cfg.pdf.ocr.endpoint.is_none());
assert_eq!(cfg.pdf.ocr.languages, vec!["eng".to_string(), "kor".to_string()]);
assert_eq!(cfg.pdf.ocr.max_pixels, 2048);
assert_eq!(cfg.pdf.ocr.request_timeout_secs, 600);
assert_eq!(cfg.pdf.ocr.request_timeout_secs, 60); // Bug #11: default 600 → 60
assert!((cfg.pdf.ocr.valid_ratio_threshold - 0.5).abs() < 1e-6);
assert_eq!(cfg.pdf.ocr.min_char_count, 20);
assert_eq!(cfg.pdf.ocr.lang_hint.as_deref(), Some("kor"));