fix: move char-confusion fix to correction step, add spell + page-ref corrections

- Remove _fix_character_confusion() from words endpoint (now only in Phase 0)
- Extend spell checker to find real OCR errors via spell.correction()
- Add field-aware dictionary selection (EN/DE) for spell corrections
- Add _normalize_page_ref() for page_ref column (p-60 → p.60)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

klausur-service/backend/ocr_pipeline_api.py

@@ -1348,7 +1348,6 @@ async def detect_words(
     # No content shuffling — each cell stays at its detected position.
     if is_vocab:
         entries = _cells_to_vocab_entries(cells, columns_meta)
-        entries = _fix_character_confusion(entries)
         entries = _fix_phonetic_brackets(entries, pronunciation=pronunciation)
         word_result["vocab_entries"] = entries
         word_result["entries"] = entries
@@ -1487,7 +1486,6 @@ async def _word_batch_stream_generator(
     vocab_entries = None
     if is_vocab:
         entries = _cells_to_vocab_entries(cells, columns_meta)
-        entries = _fix_character_confusion(entries)
         entries = _fix_phonetic_brackets(entries, pronunciation=pronunciation)
         word_result["vocab_entries"] = entries
         word_result["entries"] = entries