bvandeusen/minstrel
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 38 Wiki Activity

fix(recommendation): Rediscover no longer ships a one-song playlist (#1246)
test-go / test (push) Successful in 29s
Details
test-go / integration (push) Successful in 4m35s
Details

Browse Source 
Confirmed against prod: exactly one track (17 plays, cold since May 21)
met the c>=5 + 30d-cold bar, and three process defects turned that into
a 1-track playlist instead of the locked placeholder.

- ListRediscoverTracks: collapse the two-tier UNION into one blended
  pool. The old shallow-tier gate (WHERE NOT EXISTS deep) was
  all-or-nothing — one 6-month row suppressed the entire 30-day tier —
  and deep was a strict subset of shallow anyway. Eligibility drops to
  >=3 non-skip plays (on a weeks-old history the >=5-play tracks are
  precisely the ones still in rotation); ordering prefers >=6mo cold,
  then >=5 plays, then raw count.
- Minimum viable mix floor for all five discovery mixes: below
  minLen (15; 5 for the album-coherent NewForYou/FirstListens) the
  variant is withheld so Home renders the 'listen more to unlock'
  placeholder instead of a mix that reads as built-wrong.
- /api/events: clamp client-supplied 'at' to [user.created_at,
  now+5m]. Unbounded client clocks could write arbitrarily old plays
  and poison the 6-month ordering (prod data verified clean — no
  scrub needed).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6
This commit is contained in:
Bryan Van Deusen
2026-07-02 17:29:41 -04:00
parent 7628330f72
commit 4b150a277e
4 changed files with 95 additions and 74 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/api/events.go
+21 -1
View File
@@ -31,6 +31,26 @@ type playStartedResponse struct {
SessionID string `json:"session_id"`
}
// eventFutureSkew is the tolerated client-clock drift into the future
// before a timestamp is treated as bogus and replaced with now.
const eventFutureSkew = 5 * time.Minute
// clampEventTime bounds a client-supplied event timestamp to sanity:
// no earlier than the account's creation (offline replays can
// legitimately be days old, but no play can predate the user) and no
// later than now + a small skew allowance. Unbounded client clocks
// previously let a skewed device write arbitrarily old plays, which
// poisoned Rediscover's "not played in 6 months" ordering (#1246).
func clampEventTime(at, userCreatedAt, now time.Time) time.Time {
if at.Before(userCreatedAt) {
return userCreatedAt
}
if at.After(now.Add(eventFutureSkew)) {
return now
}
return at
}
type okResponse struct {
OK bool `json:"ok"`
}
@@ -52,7 +72,7 @@ func (h *handlers) handleEvents(w http.ResponseWriter, r *http.Request) {
writeErr(w, apierror.BadRequest("bad_request", "invalid `at` timestamp"))
return
}
at = parsed
at = clampEventTime(parsed.UTC(), user.CreatedAt.Time, time.Now().UTC())
}
clientID := ""
if req.ClientID != nil {
internal/db/dbq/system_mixes.sql.go
+23 -37
View File
@@ -262,37 +262,19 @@ WITH stats AS (
FROM play_events pe
WHERE pe.user_id = $1 AND pe.was_skipped = false
GROUP BY pe.track_id
),
deep AS (
SELECT t.id, t.album_id, t.artist_id, s.c, 0 AS tier
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 5
AND s.last_at <= now() - interval '6 months'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
),
shallow AS (
SELECT t.id, t.album_id, t.artist_id, s.c, 1 AS tier
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 5
AND s.last_at <= now() - interval '30 days'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
)
SELECT id, album_id, artist_id
FROM (
SELECT id, album_id, artist_id, c, tier FROM deep
UNION ALL
SELECT id, album_id, artist_id, c, tier FROM shallow
WHERE NOT EXISTS (SELECT 1 FROM deep)
) u
ORDER BY tier, c DESC, id
SELECT t.id, t.album_id, t.artist_id
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 3
AND s.last_at <= now() - interval '30 days'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
ORDER BY (s.last_at <= now() - interval '6 months') DESC,
(s.c >= 5) DESC,
s.c DESC, t.id
LIMIT 200
`
@@ -302,13 +284,17 @@ type ListRediscoverTracksRow struct {
ArtistID pgtype.UUID
}
// #420 Rediscover: tracks the user played a lot (>=5 non-skip) but
// has drifted away from. Tiered so a young library still gets a mix:
//
// tier 0 not played in the last 6 months (true rediscovery)
// tier 1 (only if tier 0 empty) not played in the last 30 days
//
// Ordered by historical affection. $1 user_id.
// #420 Rediscover: tracks the user played a lot but has drifted away
// from. One blended pool (issue #1246: the old two-tier UNION was
// all-or-nothing — a single ">=6 months cold" row suppressed the whole
// ">=30 days" tier, which is how a one-song playlist shipped; the 6mo
// tier was also a strict subset of the 30d tier). Eligibility is >=3
// non-skip plays and >=30 days cold; the bar sits at 3 rather than 5
// so a weeks-old library still fields a pool — on young histories the
// >=5-play tracks are precisely the ones still in rotation. Ordering
// prefers true rediscoveries (>=6 months cold), then strong affection
// (>=5 plays), then raw play count; the producer's minimum floor
// decides whether the pool is big enough to ship at all. $1 user_id.
func (q *Queries) ListRediscoverTracks(ctx context.Context, userID pgtype.UUID) ([]ListRediscoverTracksRow, error) {
rows, err := q.db.Query(ctx, listRediscoverTracks, userID)
if err != nil {
internal/db/queries/system_mixes.sql
+23 -35
View File
@@ -37,47 +37,35 @@ SELECT t.id, t.album_id, t.artist_id
LIMIT 200;
-- name: ListRediscoverTracks :many
-- #420 Rediscover: tracks the user played a lot (>=5 non-skip) but
-- has drifted away from. Tiered so a young library still gets a mix:
-- tier 0 not played in the last 6 months (true rediscovery)
-- tier 1 (only if tier 0 empty) not played in the last 30 days
-- Ordered by historical affection. $1 user_id.
-- #420 Rediscover: tracks the user played a lot but has drifted away
-- from. One blended pool (issue #1246: the old two-tier UNION was
-- all-or-nothing — a single ">=6 months cold" row suppressed the whole
-- ">=30 days" tier, which is how a one-song playlist shipped; the 6mo
-- tier was also a strict subset of the 30d tier). Eligibility is >=3
-- non-skip plays and >=30 days cold; the bar sits at 3 rather than 5
-- so a weeks-old library still fields a pool — on young histories the
-- >=5-play tracks are precisely the ones still in rotation. Ordering
-- prefers true rediscoveries (>=6 months cold), then strong affection
-- (>=5 plays), then raw play count; the producer's minimum floor
-- decides whether the pool is big enough to ship at all. $1 user_id.
WITH stats AS (
SELECT pe.track_id, COUNT(*) AS c, MAX(pe.started_at) AS last_at
FROM play_events pe
WHERE pe.user_id = $1 AND pe.was_skipped = false
GROUP BY pe.track_id
),
deep AS (
SELECT t.id, t.album_id, t.artist_id, s.c, 0 AS tier
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 5
AND s.last_at <= now() - interval '6 months'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
),
shallow AS (
SELECT t.id, t.album_id, t.artist_id, s.c, 1 AS tier
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 5
AND s.last_at <= now() - interval '30 days'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
)
SELECT id, album_id, artist_id
FROM (
SELECT id, album_id, artist_id, c, tier FROM deep
UNION ALL
SELECT id, album_id, artist_id, c, tier FROM shallow
WHERE NOT EXISTS (SELECT 1 FROM deep)
) u
ORDER BY tier, c DESC, id
SELECT t.id, t.album_id, t.artist_id
FROM tracks t
JOIN stats s ON s.track_id = t.id
WHERE s.c >= 3
AND s.last_at <= now() - interval '30 days'
AND NOT EXISTS (
SELECT 1 FROM lidarr_quarantine q
WHERE q.user_id = $1 AND q.track_id = t.id
)
ORDER BY (s.last_at <= now() - interval '6 months') DESC,
(s.c >= 5) DESC,
s.c DESC, t.id
LIMIT 200;
-- name: ListNewForYouTracks :many
internal/playlists/system_mixes.go
+28 -1
View File
@@ -40,6 +40,17 @@ import (
// Discover so shuffle-on-play has a varied pool within a day.
const discoveryMixLen = 100
// Minimum viable mix sizes (issue #1246): below the floor the variant
// is withheld entirely so Home renders its "listen more to unlock"
// placeholder — a playlist with a couple of songs reads as a build
// bug, not a mix. Album-coherent mixes (NewForYou / FirstListens) get
// a lower floor because one legitimate new album (~5+ tracks) is a
// useful mix on its own; the scattered mixes need more to feel real.
const (
discoveryMixMinLen = 15
discoveryMixMinLenAlbum = 5
)
// discoveryMixSpec describes one discovery mix. The unified producer
// reads the spec and runs a single code path for all variants.
type discoveryMixSpec struct {
@@ -55,6 +66,11 @@ type discoveryMixSpec struct {
// or when day-over-day stability is the intended UX (NewForYou).
dailyRotate bool
// minLen is the minimum viable mix size: a finished pool below it
// is withheld (no playlist row) so the client renders the locked
// placeholder instead of a mix that looks built-wrong (#1246).
minLen int
// fetch returns the raw ranked rows. dateStr is supplied for
// queries that accept it (passed as the second positional arg
// historically); queries that don't accept it ignore the param.
@@ -79,7 +95,13 @@ func produceDiscoveryMix(spec discoveryMixSpec) systemPlaylistProducer {
if spec.dailyRotate {
pool = rotateForDay(pool, userID, dateStr)
}
return emit(spec.name, spec.variant, finishMix(pool, spec.diversify)), nil
tracks := finishMix(pool, spec.diversify)
if len(tracks) < spec.minLen {
logger.Info("system playlist: "+spec.variant+" below minimum viable size; withholding",
"user_id", uuidStringPL(userID), "pool", len(tracks), "min", spec.minLen)
return nil, nil
}
return emit(spec.name, spec.variant, tracks), nil
}
}
@@ -109,6 +131,7 @@ var discoveryMixSpecs = []discoveryMixSpec{
{
name: "Deep Cuts", variant: "deep_cuts",
diversify: true, dailyRotate: false, // SQL day-keys via md5(id||$2)
minLen: discoveryMixMinLen,
fetch: func(ctx context.Context, q *dbq.Queries, uid pgtype.UUID, ds string) ([]discoverTrack, error) {
rows, err := q.ListDeepCutsTracks(ctx, dbq.ListDeepCutsTracksParams{
UserID: uid, Column2: ds,
@@ -126,6 +149,7 @@ var discoveryMixSpecs = []discoveryMixSpec{
{
name: "Rediscover", variant: "rediscover",
diversify: true, dailyRotate: true, // SQL has no date arg
minLen: discoveryMixMinLen,
fetch: func(ctx context.Context, q *dbq.Queries, uid pgtype.UUID, _ string) ([]discoverTrack, error) {
rows, err := q.ListRediscoverTracks(ctx, uid)
if err != nil {
@@ -141,6 +165,7 @@ var discoveryMixSpecs = []discoveryMixSpec{
{
name: "New for you", variant: "new_for_you",
diversify: true, dailyRotate: true, // operator wants daily rotation on all deterministic mixes
minLen: discoveryMixMinLenAlbum,
fetch: func(ctx context.Context, q *dbq.Queries, uid pgtype.UUID, _ string) ([]discoverTrack, error) {
rows, err := q.ListNewForYouTracks(ctx, uid)
if err != nil {
@@ -156,6 +181,7 @@ var discoveryMixSpecs = []discoveryMixSpec{
{
name: "On this day", variant: "on_this_day",
diversify: true, dailyRotate: false, // SQL day-keys via md5(id||$2)
minLen: discoveryMixMinLen,
fetch: func(ctx context.Context, q *dbq.Queries, uid pgtype.UUID, ds string) ([]discoverTrack, error) {
rows, err := q.ListOnThisDayTracks(ctx, dbq.ListOnThisDayTracksParams{
UserID: uid, Column2: ds,
@@ -173,6 +199,7 @@ var discoveryMixSpecs = []discoveryMixSpec{
{
name: "First listens", variant: "first_listens",
diversify: true, dailyRotate: true, // SQL has no date arg; daily rotate + diversity top-up
minLen: discoveryMixMinLenAlbum,
fetch: func(ctx context.Context, q *dbq.Queries, uid pgtype.UUID, _ string) ([]discoverTrack, error) {
rows, err := q.ListFirstListensTracks(ctx, uid)
if err != nil {