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

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:
2026-07-02 17:29:41 -04:00
parent 7628330f72
commit 4b150a277e
4 changed files with 95 additions and 74 deletions
+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 {
+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