hint_extractor: _ocr_back_cover() sends back/inlay images to Ollama Vision
when no tracklist .txt/.htm/.nfo is present. Model priority:
qwen3-vl:latest → minicpm-v:latest → deepseek-ocr:latest (configurable
via OLLAMA_OCR_MODEL env var). Timeout 180s. OCR text is fed into the
same _parse_tracklist() pipeline as regular text files.
music_enricher: extract_hints(use_ocr=not args.no_api) — OCR is skipped
with --no-api to allow fully offline/fast runs.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Filename schema now: TT - AlbumArtist - TrackArtist - Title when albumartist
differs from track artist (e.g. pianist vs. composer). Identical artist → old
two-part format unchanged.
metadata_resolver: removed Claude API fallback entirely from _claude_resolve.
Chain is now Ollama (local, free) → OpenRouter (DeepSeek V3, cheap) only.
music_enricher: updated status line and use_claude flag accordingly.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
AI-powered per-album pipeline: scan → local hints → MusicBrainz/Discogs/Claude
resolve → cover art → interactive or auto review → tag write + rename + report.
All external dependencies optional; 17/17 unit tests passing.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
