v0.16.0: the file already told you

Two real failures from the first hour of round 45, both fixed by treating
the file itself as evidence.

"B. Clem - Zuuso [1025657891]" fingerprinted fine and matched nothing.
Checked before building: AcoustID returns zero results, a MusicBrainz text
search for "Zuuso" returns zero, iTunes returns zero. The track is in no
metadata service on earth, so no smarter lookup could have answered it —
but its filename said exactly what it was. New filename_tags.py reads that,
validated against all 474 files in the untagged folder rather than invented
examples: it strips yt-dlp ids, drops "(Official Video)" noise, splits
Artist - Title, reads a leading 1-04, and falls back to the iTunes tree.
It is careful about what it removes — an 11-char trailing token counts as a
YouTube id only if it carries a digit, an underscore or flipping case, or
"Cold Draft-Underground" loses a word, and a hyphen only splits when it has
spaces around it so Jay-Z survives.

A guess says it is one: candidates carry a source, and the dialog quotes a
confidence only for real fingerprint matches.

The file now ranks lookup results too, which fixes the Alhambra case: token
overlap (words double, bare numbers single), a duration bucket against the
recording lengths AcoustID returns, and a filename year that predates what
the database knows. Live also stops counting as a demerit — it was lumped in
with Compilation and buried a live album for a file whose name said "Live At
The Alhambra". That track now proposes the right album with year 1961
instead of a compilation with 2002.

The year genuinely needed the filename: MusicBrainz's own first-release-date
for "Ahmad Jamal's Alhambra" is 2002, because its three original 1961
pressings are stored undated. The obvious fix of a second MusicBrainz call
returns the same wrong answer.

Not done on purpose: trav rejected "never propose a shorter title" —
truncating is wanted, since the garbage is usually the part being dropped.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01NsiFHdyVg1UhBSxDJfTNRm

tasks-done.md

@@ -1,5 +1,51 @@
 ## Done
 
+### Round 46 (2026-09-02) — The file already told you (v0.16.0)
+
+Round 45 shipped and trav broke it in two places within the hour, both real.
+"B. Clem - Zuuso [1025657891]" fingerprinted fine and matched **nothing**, and
+"Snowfall (Live At The Alhambra_1961)" matched but proposed a 2002 reissue year
+and ranked a compilation above the album its own filename named.
+
+- [x] **The limit is the database, not the fingerprint.** Verified before
+      building anything: that Zuuso fingerprint returns zero AcoustID results,
+      a MusicBrainz text search for "Zuuso" returns zero, and iTunes returns
+      zero (and irrelevant fuzz for "B. Clem"). The track exists in no metadata
+      service on earth. So no smarter lookup — LLM or otherwise — could have
+      answered it, because there was nothing to answer with.
+- [x] **But the filename knew.** New `lintunes/filename_tags.py` reads tags out
+      of the name yt-dlp gave the file. "B. Clem - Zuuso [1025657891]" → artist
+      "B. Clem", name "Zuuso", which is exactly what trav said it was. Checked
+      against all 474 files in the untagged folder, not against invented
+      examples.
+- [x] **Careful about what it strips.** An 11-character trailing token is only
+      a YouTube id if it carries a digit, an underscore, or case that flips
+      repeatedly — otherwise "Cold Draft-Underground" loses a word. A hyphen
+      only splits artist from title when it has spaces around it, so "Jay-Z"
+      and "350-440-DialTone" survive. A 4-digit year is never a numeric id.
+- [x] **A guess is labelled a guess.** `IdentifyCandidate.source` is
+      "acoustid" or "filename"; the dialog quotes a match confidence only for
+      the former and says "No database knows this — read from the file's name"
+      for the latter, rather than inventing a percentage.
+- [x] **The file now ranks the results too.** `hint_for(track)` feeds tag +
+      filename tokens into `parse_lookup`: overlap scoring (words count double,
+      bare numbers single — "alhambra" identifies a release, "1961" appears in
+      every compilation spanning it), a coarse duration bucket against the
+      recording lengths AcoustID returns, and a filename year that predates
+      what the database knows. Alhambra now ranks the right album first with
+      year 1961 instead of a compilation with 2002.
+- [x] **Live is no longer a demerit.** It was lumped in with Compilation, which
+      buried a live album for a file whose name said "Live At The Alhambra".
+      Only compilations, remixes, interviews and the like are demoted now.
+- [x] **Why the year needed the filename at all:** MusicBrainz's own
+      `first-release-date` for "Ahmad Jamal's Alhambra" is *2002* — its three
+      original 1961 pressings are in the database undated. A second MusicBrainz
+      call, the obvious fix, returns the same wrong answer. 1961 exists only in
+      trav's filename.
+- [x] Not done, deliberately: trav rejected "never propose a shorter title" —
+      truncating is *wanted*, because the garbage in a title is usually the
+      part being dropped.
+
 ### Round 45 (2026-09-02) — Ask the song what it is (v0.15.0)
 
 Some files arrive with the title right and everything else missing or wrong,