- Implement robustSentenceSplit across reader.js and backend (miner.py, cefr.py) to prevent false cutoffs on honorifics (Mr., Mrs., Dr.), single-letter initials (John F. Kennedy), decimals, acronyms (U.S., U.K.), and abbreviations (No. 4, etc.)
- Upgrade translation prompt to professional literary Russian, eliminating literal word-for-word translation and preserving titles/honorifics
- Inject surrounding paragraph context into translation API to avoid out-of-context translations
- Inject offline dictionary hints into LLM prompt for accurate contextual word meaning
- Prefer qwen2.5:3b for higher translation fluency and fidelity
- Purge truncated cache entries from sentence_translations and restore Card 30 (briefcase) with authentic full sentence
- Bump Service Worker cache to notes-v6.0
- Add unit tests for robust sentence splitting, prompt formatting, and translation API
- Add resolve_context_sentence_for_term to replace placeholder blanks and lookup authentic sentences from cefr_questions or books
- Fix dual mistake ingestion in process_cefr_answer to assign distinct context to target and chosen distractor
- Provide authentic context_sentence in options_breakdown and pass it via data-context in cefr.js
- Add repair_mismatched_cefr_contexts in database.py to automatically repair cards with placeholder blanks
- Bump Service Worker cache to notes-v5.9
- Add test_cefr_context_resolution_and_repair covering resolution, dual ingestion, manual add, and DB repair
Antigravity