minstrel/internal/db/queries/system_mixes.sql

-- Candidate queries for the discovery system-playlist mixes
-- (#419-423). Each returns (id, album_id, artist_id) rows; the Go
-- producer caps + truncates and converts to rankedCandidate. Daily-
-- deterministic md5(id||dateStr) ordering (where used) keeps a mix
-- stable within a day while rotating across days; shuffle-on-play
-- gives per-play variety on top.

-- name: ListDeepCutsTracks :many
-- #419 Deep Cuts: low-play tracks (<=2 plays) from artists the user
-- has liked OR played heavily (>=5 non-skip plays across the artist).
-- $1 user_id, $2 date string.
WITH affinity_artists AS (
    SELECT artist_id FROM general_likes_artists WHERE user_id = $1
    UNION
    SELECT t.artist_id
      FROM play_events pe JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = $1 AND pe.was_skipped = false
     GROUP BY t.artist_id
    HAVING COUNT(*) >= 5
),
play_counts AS (
    SELECT track_id, COUNT(*) AS c
      FROM play_events
     WHERE user_id = $1 AND was_skipped = false
     GROUP BY track_id
)
SELECT t.id, t.album_id, t.artist_id
  FROM tracks t
  JOIN affinity_artists aa ON aa.artist_id = t.artist_id
  LEFT JOIN play_counts pc ON pc.track_id = t.id
 WHERE COALESCE(pc.c, 0) <= 2
   AND NOT EXISTS (
       SELECT 1 FROM lidarr_quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
 ORDER BY md5(t.id::text || $2::text)
 LIMIT 200;

-- name: ListRediscoverTracks :many
-- #420 Rediscover: tracks the user played a lot (>=5 non-skip) but
-- not in the last 6 months. Ordered by historical affection.
-- $1 user_id.
WITH stats AS (
    SELECT track_id, COUNT(*) AS c, MAX(started_at) AS last_at
      FROM play_events
     WHERE user_id = $1 AND was_skipped = false
     GROUP BY track_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 >= 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
   )
 ORDER BY s.c DESC, t.id
 LIMIT 200;

-- name: ListNewForYouTracks :many
-- #421 New for you: tracks from albums added in the last 30 days
-- whose artist the user has liked OR played (>=3 non-skip). Album-
-- coherent (newest album first, then disc/track) — the producer does
-- NOT diversity-cap these; they're meant as whole-album discovery.
-- $1 user_id.
WITH affinity_artists AS (
    SELECT artist_id FROM general_likes_artists WHERE user_id = $1
    UNION
    SELECT t.artist_id
      FROM play_events pe JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = $1 AND pe.was_skipped = false
     GROUP BY t.artist_id
    HAVING COUNT(*) >= 3
)
SELECT t.id, t.album_id, t.artist_id
  FROM tracks t
  JOIN albums al ON al.id = t.album_id
  JOIN affinity_artists aa ON aa.artist_id = al.artist_id
 WHERE al.created_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 al.created_at DESC, t.disc_number NULLS FIRST, t.track_number NULLS FIRST
 LIMIT 200;

-- name: ListOnThisDayTracks :many
-- #422 On This Day: tracks the user played around this calendar date
-- (±7 day-of-year) in the past, excluding the very recent (>60 days
-- ago) so it's nostalgic, not just "last week". Weighted by how much
-- they were played in those windows.
-- $1 user_id, $2 date string.
WITH windowed AS (
    SELECT track_id, COUNT(*) AS c
      FROM play_events
     WHERE user_id = $1 AND was_skipped = false
       AND started_at < now() - interval '60 days'
       AND ABS(EXTRACT(DOY FROM started_at) - EXTRACT(DOY FROM now())) <= 7
     GROUP BY track_id
)
SELECT t.id, t.album_id, t.artist_id
  FROM tracks t
  JOIN windowed w ON w.track_id = t.id
 WHERE NOT EXISTS (
       SELECT 1 FROM lidarr_quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
 ORDER BY w.c DESC, md5(t.id::text || $2::text)
 LIMIT 200;

-- name: ListFirstListensTracks :many
-- #423 First Listens: albums the user has never played any track of.
-- Tiered: liked-artist albums first, then played-artist albums, then
-- the rest — album-coherent within each tier. Not diversity-capped
-- (whole-album discovery). $1 user_id.
WITH heard_albums AS (
    SELECT DISTINCT t.album_id
      FROM play_events pe JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = $1
),
played_artists AS (
    SELECT DISTINCT t.artist_id
      FROM play_events pe JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = $1
)
SELECT t.id, t.album_id, t.artist_id
  FROM tracks t
  JOIN albums al ON al.id = t.album_id
 WHERE NOT EXISTS (SELECT 1 FROM heard_albums h WHERE h.album_id = al.id)
   AND NOT EXISTS (
       SELECT 1 FROM lidarr_quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
 ORDER BY
   (CASE
      WHEN EXISTS (
        SELECT 1 FROM general_likes_artists gla
         WHERE gla.user_id = $1 AND gla.artist_id = al.artist_id
      ) THEN 0
      WHEN al.artist_id IN (SELECT artist_id FROM played_artists) THEN 1
      ELSE 2
    END),
   al.id, t.disc_number NULLS FIRST, t.track_number NULLS FIRST
 LIMIT 300;