feat(autotag): answer whether an album has a confident match

`MatchForAlbum(albumID)` is the question the album detail page needs to
ask on open: does the autotagger already have something confident to
say about this album, and what would applying it do.

**It costs no MusicBrainz request.** Everything it needs is on disk —
`tagging_items` carries the top score and release from the background
prefetch, `tagging_candidates` durably holds the scored list. The rate
limiters here are shared with every page the user can open, so a lookup
that fires on page load must not join that queue; a folder nobody has
scored yet answers "nothing", rather than scoring it now.

**The tier is computed, not read.** `tagging_items.score` is the raw
number and `Recommend` is what turns it into a claim, capping it for an
ambiguous runner-up, an incomplete alignment or a folder too small to
corroborate itself. Filtering on the stored score would promise
confidence the scorer had explicitly withheld — which the two-track
test pins.

**Nothing is said about an album the user has already answered for.**
Only a `pending` group qualifies: `confirmed` covers both a finished
apply and an explicit "leave as is", and arguing with the second would
be actively wrong.

The join is `audio_files.group_key`, not a key derived from the folder
path, because a group carved out of a mixed-bag folder is keyed on its
tags — so a path-derived key would find nothing for exactly the
messiest libraries this helps. `GroupCount` is returned because a
multi-disc album is one group per disc: a caller that applied to "the
album" from a single button would retag one disc of three.
This commit is contained in:
2026-08-19 02:34:11 -04:00
parent fe67849e57
commit 9118c16fe3
7 changed files with 662 additions and 0 deletions
+145
View File
@@ -0,0 +1,145 @@
package autotagservice
import (
"database/sql"
"fmt"
"yellowjacket/backend/autotag"
)
// AlbumMatchView is "the autotagger already has a confident match for
// the album you are looking at".
//
// It is deliberately not a score. The album page renders a suggestion,
// and a suggestion has to be actionable: which release, what it is
// called, and whether acting on it here would do the whole album or
// only part of it.
type AlbumMatchView struct {
// GroupKey is the tagging group the actions operate on.
GroupKey string `json:"groupKey"`
// Recommendation is the tier, as a string, for a caller that
// wants to render the strength rather than trust the filter.
Recommendation string `json:"recommendation"`
// Score is the top candidate's raw score, 0..1.
Score float64 `json:"score"`
// ReleaseMBID is the release Apply would write.
ReleaseMBID string `json:"releaseMbid"`
// Title and ArtistCredit name that release, so the banner can say
// what it is offering rather than "a match".
Title string `json:"title"`
ArtistCredit string `json:"artistCredit"`
// TrackCount is the group's local track count.
TrackCount int64 `json:"trackCount"`
// GroupCount is how many tagging groups this album spans.
//
// More than one means a multi-disc album (one group per disc), and
// it is the reason this is a field rather than an implementation
// detail: applying "the album" from a single button would retag
// one disc of three and leave the folder holding a mix of old and
// new tags. The caller offers review instead.
GroupCount int `json:"groupCount"`
}
// MatchForAlbum answers "does the autotagger have something confident
// to say about this album", for the album detail page.
//
// Three things about it are load-bearing.
//
// **It costs no MusicBrainz request.** Everything it needs is already
// on disk: `tagging_items` carries the top score and release from the
// background prefetch, and `tagging_candidates` durably holds the
// scored list. The rate limiters here are shared with every page the
// user can open, so a lookup that fires on page load must not join
// that queue — which also means this returns nothing for a folder
// nobody has scored yet, rather than scoring it now. That is the
// right trade: the prefetch will get to it, and a page that silently
// spends a minute of somebody's MusicBrainz budget to draw a banner
// is worse than a page that says nothing.
//
// **The tier is computed, not read.** `tagging_items.score` is the raw
// number and `Recommend` is what turns it into a claim — capping it
// for an ambiguous runner-up, an incomplete alignment or a folder too
// small to corroborate itself. Filtering on the raw score would
// promise confidence the scorer had explicitly withheld.
//
// **Nothing is said about an album the user has already answered
// for.** Only a `pending` group qualifies: `confirmed` covers both a
// finished apply and an explicit "leave as is", and `skipped` is the
// user saying not now. Re-offering either is nagging, and "leave as
// is" would be actively wrong to argue with.
func (s *Service) MatchForAlbum(albumID int64) (*AlbumMatchView, error) {
if albumID <= 0 {
return nil, nil //nolint:nilnil // "no album" is not an error.
}
rows, err := s.db.Queries.GetTaggingItemsForAlbum(
s.ctx, sql.NullInt64{Int64: albumID, Valid: true},
)
if err != nil {
return nil, fmt.Errorf("tagging items for album: %w", err)
}
pending := rows[:0:0]
for _, row := range rows {
if row.Status == "pending" {
pending = append(pending, row)
}
}
if len(pending) == 0 {
return nil, nil //nolint:nilnil // nothing to say is not an error.
}
// Rows arrive best-score-first, so the first pending one is the
// group worth describing. On a multi-disc album that is one disc
// of several and GroupCount says so.
best := pending[0]
cands := s.lookupCachedCandidates(best.GroupKey)
if len(cands) == 0 {
return nil, nil //nolint:nilnil // not scored yet; see the doc comment.
}
locals, err := s.scorer.LocalTracksForGroup(s.ctx, best.GroupKey)
if err != nil {
return nil, fmt.Errorf("local tracks for group: %w", err)
}
group := autotag.Group{
AlbumName: best.AlbumName,
AlbumArtist: best.AlbumArtist,
Tracks: locals,
Synthetic: best.Synthetic != 0,
}
rec := autotag.Recommend(group, cands)
if !autotag.Confident(rec) {
return nil, nil //nolint:nilnil // not confident enough to interrupt.
}
top := cands[0]
// The release the banner names must be the release Apply would
// write. Apply with an empty MBID takes the top cached candidate,
// which is what this reads — but it is passed explicitly anyway,
// so a rescore between the page rendering and the user clicking
// cannot swap the album out from under a button they have already
// read.
return &AlbumMatchView{
GroupKey: best.GroupKey,
Recommendation: string(rec),
Score: top.Score,
ReleaseMBID: top.ReleaseMBID,
Title: top.Title,
ArtistCredit: top.ArtistCredit,
TrackCount: best.TrackCount,
GroupCount: len(pending),
}, nil
}
+320
View File
@@ -0,0 +1,320 @@
package autotagservice
import (
"encoding/json"
"testing"
"yellowjacket/backend/autotag"
"yellowjacket/backend/database"
)
// seedAlbumGroup writes one album's files, its tagging item and the
// durable candidate blob the prefetch would have left behind.
//
// The candidate list is what a real one looks like in the two ways
// that decide the tier: a per-track alignment for every local track,
// and a runner-up far enough away not to count as ambiguity.
func seedAlbumGroup(
t *testing.T,
db *database.DB,
groupKey string,
tracks int,
status string,
score float64,
) int64 {
t.Helper()
for i := 1; i <= tracks; i++ {
database.InsertTestTrack(t, db, database.TestTrack{
FilePath: filePathFor(groupKey, i),
Title: titleFor(i),
Artist: "Tideline",
Album: "Glass Harbour",
AlbumArtist: "Tideline",
TrackNumber: int64(i),
LengthMs: 200000,
LibraryID: 0,
GroupKey: groupKey,
})
}
if _, err := db.ExecContext(`
INSERT INTO tagging_items
(group_key, library_id, track_count, album_name, album_artist,
disc_number, status, score, best_match_release_mbid)
VALUES (?, 0, ?, 'Glass Harbour', 'Tideline', 0, ?, ?, 'rel-1')
`, groupKey, tracks, status, score); err != nil {
t.Fatalf("insert tagging item: %v", err)
}
var albumID int64
if err := db.QueryRowWriter(
`SELECT album_id FROM audio_files WHERE group_key = ? LIMIT 1`, groupKey,
).Scan(&albumID); err != nil {
t.Fatalf("read album id: %v", err)
}
return albumID
}
func filePathFor(groupKey string, n int) string {
return "/music/" + groupKey + "/0" + string(rune('0'+n)) + ".mp3"
}
func titleFor(n int) string {
return "Track " + string(rune('0'+n))
}
// storeCandidates writes the durable blob GetCandidates would have
// cached, with `top` as the winning score.
func storeCandidates(
t *testing.T, db *database.DB, groupKey string, tracks int, top float64,
) {
t.Helper()
aligns := make([]autotag.TrackAlignment, 0, tracks)
for i := range tracks {
aligns = append(aligns, autotag.TrackAlignment{
Status: autotag.AlignmentMatched,
LocalIndex: i,
})
}
cands := []autotag.Candidate{
{
ReleaseMBID: "rel-1",
ReleaseGroupMBID: "rg-1",
Title: "Glass Harbour",
ArtistCredit: "Tideline",
TrackCount: tracks,
Alignments: aligns,
Score: top,
},
{
ReleaseMBID: "rel-2",
ReleaseGroupMBID: "rg-2",
Title: "Something Else",
ArtistCredit: "Another Band",
TrackCount: tracks,
Score: 0.40,
},
}
blob, err := json.Marshal(cands)
if err != nil {
t.Fatalf("marshal candidates: %v", err)
}
if _, err := db.ExecContext(
`INSERT INTO tagging_candidates (group_key, candidates) VALUES (?, ?)`,
groupKey, string(blob),
); err != nil {
t.Fatalf("insert candidates: %v", err)
}
}
// A confident match is what the album page exists to surface.
func TestMatchForAlbumSurfacesAConfidentMatch(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
albumID := seedAlbumGroup(t, db, "grp-1", 8, "pending", 0.95)
storeCandidates(t, db, "grp-1", 8, 0.95)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got == nil {
t.Fatal("no match returned for a strong candidate")
}
if got.Recommendation != string(autotag.RecommendationStrong) {
t.Errorf("recommendation = %q, want strong", got.Recommendation)
}
// The release named is the release Apply would write — the page
// must not offer one album and tag another.
if got.ReleaseMBID != "rel-1" || got.Title != "Glass Harbour" {
t.Errorf("named %q/%q, want rel-1/Glass Harbour", got.ReleaseMBID, got.Title)
}
if got.GroupCount != 1 {
t.Errorf("groupCount = %d, want 1", got.GroupCount)
}
}
// The tier is computed from the candidates, not read off the raw
// score — a high number the scorer would have capped must not reach
// the page as confidence it withheld.
func TestMatchForAlbumDoesNotTrustTheStoredScore(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
// Two tracks: below the evidence floor, so `Recommend` caps this
// at medium however well it scores.
albumID := seedAlbumGroup(t, db, "grp-2", 2, "pending", 0.99)
storeCandidates(t, db, "grp-2", 2, 0.99)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got != nil {
t.Errorf("surfaced %+v for a two-track folder, want nothing", got)
}
}
// A weak match is not worth interrupting for.
func TestMatchForAlbumStaysQuietBelowTheTier(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
albumID := seedAlbumGroup(t, db, "grp-3", 8, "pending", 0.60)
storeCandidates(t, db, "grp-3", 8, 0.60)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got != nil {
t.Errorf("surfaced %+v for a 0.60 match, want nothing", got)
}
}
// An album the user has already answered for is not re-offered.
//
// `confirmed` covers both a finished apply and an explicit "leave as
// is", and arguing with the second would be actively wrong.
func TestMatchForAlbumRespectsAnAnswerAlreadyGiven(t *testing.T) {
t.Parallel()
for _, status := range []string{"confirmed", "skipped", "matched"} {
t.Run(status, func(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
albumID := seedAlbumGroup(t, db, "grp-"+status, 8, status, 0.95)
storeCandidates(t, db, "grp-"+status, 8, 0.95)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got != nil {
t.Errorf("surfaced %+v for a %s group, want nothing", got, status)
}
})
}
}
// A folder nobody has scored yet says nothing, rather than scoring it
// now: the MusicBrainz limiter is shared with every page the user can
// open, and this runs on page load.
func TestMatchForAlbumMakesNoNetworkCallForAnUnscoredFolder(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
// No storeCandidates: the prefetch has not reached this folder.
albumID := seedAlbumGroup(t, db, "grp-4", 8, "pending", 0.95)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got != nil {
t.Errorf("surfaced %+v with no cached candidates, want nothing", got)
}
}
// A multi-disc album is several groups, and the count is what stops
// the page offering one button that would retag one disc of two.
func TestMatchForAlbumCountsEveryGroupOfTheAlbum(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
albumID := seedAlbumGroup(t, db, "grp-d1", 8, "pending", 0.95)
storeCandidates(t, db, "grp-d1", 8, 0.95)
// Disc two: same album row, its own folder and tagging group.
for i := 1; i <= 6; i++ {
database.InsertTestTrack(t, db, database.TestTrack{
FilePath: filePathFor("grp-d2", i),
Title: titleFor(i),
Artist: "Tideline",
Album: "Glass Harbour",
AlbumArtist: "Tideline",
TrackNumber: int64(i),
DiscNumber: 2,
LengthMs: 200000,
LibraryID: 0,
GroupKey: "grp-d2",
})
}
if _, err := db.ExecContext(`
INSERT INTO tagging_items
(group_key, library_id, track_count, album_name, album_artist,
disc_number, status, score)
VALUES ('grp-d2', 0, 6, 'Glass Harbour', 'Tideline', 2, 'pending', 0.93)
`); err != nil {
t.Fatalf("insert disc two: %v", err)
}
storeCandidates(t, db, "grp-d2", 6, 0.93)
got, err := svc.MatchForAlbum(albumID)
if err != nil {
t.Fatalf("MatchForAlbum: %v", err)
}
if got == nil {
t.Fatal("no match returned")
}
if got.GroupCount != 2 {
t.Errorf("groupCount = %d, want 2", got.GroupCount)
}
// Best-first: the 0.95 disc is the one described.
if got.GroupKey != "grp-d1" {
t.Errorf("described %q, want the higher-scoring grp-d1", got.GroupKey)
}
}
// An album with no local files at all — a pure catalog page — is not
// a question this can answer.
func TestMatchForAlbumSaysNothingWithoutAnAlbum(t *testing.T) {
t.Parallel()
db := database.NewTestDB(t)
svc := newTestService(t, db)
for _, id := range []int64{0, -1, 4242} {
got, err := svc.MatchForAlbum(id)
if err != nil {
t.Fatalf("MatchForAlbum(%d): %v", id, err)
}
if got != nil {
t.Errorf("MatchForAlbum(%d) = %+v, want nil", id, got)
}
}
}
@@ -342,3 +342,35 @@ WHERE ti.status = 'pending'
)
ORDER BY ti.group_key
LIMIT 1;
-- name: GetTaggingItemsForAlbum :many
-- Every tagging group holding a file of this album.
--
-- The join is `audio_files.group_key`, not a key derived from the
-- album's folder path: a group carved out of a mixed-bag folder by
-- SplitMixedFolder is keyed on its tags rather than on a directory,
-- so a path-derived key finds nothing for exactly the messiest
-- libraries this is meant to help.
--
-- Usually one row. A multi-disc album is one group per disc, which
-- the caller has to know about rather than average over -- applying
-- to "the album" would silently retag one disc of three.
SELECT
ti.group_key,
ti.status,
ti.score,
ti.best_match_release_mbid,
ti.track_count,
ti.album_name,
ti.album_artist,
ti.synthetic
FROM tagging_items ti
WHERE ti.group_key IN (
SELECT DISTINCT af.group_key
FROM audio_files af
WHERE af.album_id = sqlc.arg(album_id) AND af.group_key != ''
)
AND ti.cleared_at IS NULL
-- Best first, with an unscored group last rather than first: NULL
-- sorts low in SQLite and DESC would put it at the top.
ORDER BY ti.score IS NULL, ti.score DESC, ti.group_key;
@@ -231,6 +231,82 @@ func (q *Queries) GetTaggingItem(ctx context.Context, groupKey string) (TaggingI
return i, err
}
const getTaggingItemsForAlbum = `-- name: GetTaggingItemsForAlbum :many
SELECT
ti.group_key,
ti.status,
ti.score,
ti.best_match_release_mbid,
ti.track_count,
ti.album_name,
ti.album_artist,
ti.synthetic
FROM tagging_items ti
WHERE ti.group_key IN (
SELECT DISTINCT af.group_key
FROM audio_files af
WHERE af.album_id = ?1 AND af.group_key != ''
)
AND ti.cleared_at IS NULL
ORDER BY ti.score IS NULL, ti.score DESC, ti.group_key
`
type GetTaggingItemsForAlbumRow struct {
GroupKey string
Status string
Score sql.NullFloat64
BestMatchReleaseMbid sql.NullString
TrackCount int64
AlbumName string
AlbumArtist string
Synthetic int64
}
// Every tagging group holding a file of this album.
//
// The join is `audio_files.group_key`, not a key derived from the
// album's folder path: a group carved out of a mixed-bag folder by
// SplitMixedFolder is keyed on its tags rather than on a directory,
// so a path-derived key finds nothing for exactly the messiest
// libraries this is meant to help.
//
// Usually one row. A multi-disc album is one group per disc, which
// the caller has to know about rather than average over -- applying
// to "the album" would silently retag one disc of three.
// Best first, with an unscored group last rather than first: NULL
// sorts low in SQLite and DESC would put it at the top.
func (q *Queries) GetTaggingItemsForAlbum(ctx context.Context, albumID sql.NullInt64) ([]GetTaggingItemsForAlbumRow, error) {
rows, err := q.db.QueryContext(ctx, getTaggingItemsForAlbum, albumID)
if err != nil {
return nil, err
}
defer rows.Close()
var items []GetTaggingItemsForAlbumRow
for rows.Next() {
var i GetTaggingItemsForAlbumRow
if err := rows.Scan(
&i.GroupKey,
&i.Status,
&i.Score,
&i.BestMatchReleaseMbid,
&i.TrackCount,
&i.AlbumName,
&i.AlbumArtist,
&i.Synthetic,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Close(); err != nil {
return nil, err
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const listAudioFilesInTaggingGroup = `-- name: ListAudioFilesInTaggingGroup :many
SELECT
af.id,
@@ -7,6 +7,7 @@ export {
};
export type {
AlbumMatchView,
AlignmentView,
ApplyResultView,
CandidateView,
@@ -1,6 +1,61 @@
// Cynhyrchwyd y ffeil hon yn awtomatig. PEIDIWCH Â MODIWL
// This file is automatically generated. DO NOT EDIT
/**
* AlbumMatchView is "the autotagger already has a confident match for
* the album you are looking at".
*
* It is deliberately not a score. The album page renders a suggestion,
* and a suggestion has to be actionable: which release, what it is
* called, and whether acting on it here would do the whole album or
* only part of it.
*/
export interface AlbumMatchView {
/**
* GroupKey is the tagging group the actions operate on.
*/
"groupKey": string;
/**
* Recommendation is the tier, as a string, for a caller that
* wants to render the strength rather than trust the filter.
*/
"recommendation": string;
/**
* Score is the top candidate's raw score, 0..1.
*/
"score": number;
/**
* ReleaseMBID is the release Apply would write.
*/
"releaseMbid": string;
/**
* Title and ArtistCredit name that release, so the banner can say
* what it is offering rather than "a match".
*/
"title": string;
"artistCredit": string;
/**
* TrackCount is the group's local track count.
*/
"trackCount": number;
/**
* GroupCount is how many tagging groups this album spans.
*
* More than one means a multi-disc album (one group per disc), and
* it is the reason this is a field rather than an implementation
* detail: applying "the album" from a single button would retag
* one disc of three and leave the folder holding a mix of old and
* new tags. The caller offers review instead.
*/
"groupCount": number;
}
/**
* AlignmentView mirrors autotag.TrackAlignment. LocalIndex of -1
* means "candidate has this track, folder doesn't" (status=missing).
@@ -160,6 +160,39 @@ export function ListPendingFolders(libraryID: number): $CancellablePromise<$mode
return $Call.ByID(617511590, libraryID);
}
/**
* MatchForAlbum answers "does the autotagger have something confident
* to say about this album", for the album detail page.
*
* Three things about it are load-bearing.
*
* **It costs no MusicBrainz request.** Everything it needs is already
* on disk: `tagging_items` carries the top score and release from the
* background prefetch, and `tagging_candidates` durably holds the
* scored list. The rate limiters here are shared with every page the
* user can open, so a lookup that fires on page load must not join
* that queue — which also means this returns nothing for a folder
* nobody has scored yet, rather than scoring it now. That is the
* right trade: the prefetch will get to it, and a page that silently
* spends a minute of somebody's MusicBrainz budget to draw a banner
* is worse than a page that says nothing.
*
* **The tier is computed, not read.** `tagging_items.score` is the raw
* number and `Recommend` is what turns it into a claim — capping it
* for an ambiguous runner-up, an incomplete alignment or a folder too
* small to corroborate itself. Filtering on the raw score would
* promise confidence the scorer had explicitly withheld.
*
* **Nothing is said about an album the user has already answered
* for.** Only a `pending` group qualifies: `confirmed` covers both a
* finished apply and an explicit "leave as is", and `skipped` is the
* user saying not now. Re-offering either is nagging, and "leave as
* is" would be actively wrong to argue with.
*/
export function MatchForAlbum(albumID: number): $CancellablePromise<$models.AlbumMatchView | null> {
return $Call.ByID(514173221, albumID);
}
/**
* RetagGroup flips a group back to 'pending' so the user can
* re-review after an apply or skip. Drops the durably-cached