Commit History
-
docs: non-Latin OCR findings — ja scams fixed to warning, hi documented
Prompt-fix probe simulated through full triage: ja gift-card scams 3/3 warning (original-script quotes + multilingual heuristics), ja bills stay low; Devanagari remains under-read (1.3B limit) -> honest README limitation. sim_probe_levels.py re-scores probe dumps offline. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>ac5db64
