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).
-- Tracks the user has skipped twice or more don't qualify (#1257):
-- eligibility used to count only unskipped plays, so the most actively
-- rejected tracks read as "barely heard" and kept being re-offered.
-- Threshold 2 so a single accidental skip doesn't banish a track;
-- passive-signal only (no dislike UI, rule #101).
-- $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
),
skip_counts AS (
    SELECT track_id, COUNT(*) AS c
      FROM play_events
     WHERE user_id = $1 AND was_skipped = true
     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
  LEFT JOIN skip_counts sc ON sc.track_id = t.id
 WHERE t.missing_since IS NULL   -- #2523: never offer a file that is gone
   AND COALESCE(pc.c, 0) <= 2
   AND COALESCE(sc.c, 0) < 2
   AND NOT EXISTS (
       SELECT 1 FROM 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 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
)
SELECT t.id, t.album_id, t.artist_id
  FROM tracks t
  JOIN stats s ON s.track_id = t.id
 WHERE t.missing_since IS NULL   -- #2523: never offer a file that is gone
   AND s.c >= 3
   AND s.last_at <= now() - interval '30 days'
   AND NOT EXISTS (
       SELECT 1 FROM quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
   -- Declined-resurfacing cooldown (#1258): a skip on a
   -- rediscover-sourced play is the user explicitly saying "I've moved
   -- on" to the exact invitation this mix extends — such tracks sit
   -- out ~90 days instead of re-qualifying the next day. Passive
   -- signal only (rule #101).
   AND NOT EXISTS (
       SELECT 1 FROM play_events rp
        WHERE rp.user_id = $1
          AND rp.track_id = t.id
          AND rp.source = 'rediscover'
          AND rp.was_skipped = true
          AND rp.started_at > now() - interval '90 days'
   )
 ORDER BY (s.last_at <= now() - interval '6 months') DESC,
          (s.c >= 5) DESC,
          s.c DESC, t.id
 LIMIT 200;

-- name: ListNewForYouTracks :many
-- #421 New for you, tiered per project rule #131 (#1267). The old
-- single hard rule (added <30d AND direct affinity) had two failure
-- modes with one root: no notion of consumption — the album you
-- devoured in week one crowded the mix for three more weeks, and
-- after a quiet month nothing qualified at all.
--
-- "Consumed" = any track attempted for >=30s (the First Listens
-- threshold, #1268): once you've meaningfully engaged, the album is
-- no longer news. Applies to every tier — played albums leave the
-- mix the next build.
--
--   tier 1  the exact desire: unconsumed albums added <30d by
--           direct-affinity artists (liked, or >=3 attempted plays)
--   tier 2  step back a little: unconsumed affinity albums from the
--           wider 30-90d window — added while you weren't looking
--   tier 3  step back more: any unconsumed album added <90d
--           regardless of affinity, newest first
--
-- Album-coherent within tiers (newest album first, then disc/track);
-- the producer fills top-down and rotates within tier blocks. The
-- tier lands on playlist_tracks.pick_kind so metrics can price what
-- each step-back trades away. $1 user_id.
WITH attempted AS (
    SELECT DISTINCT pe.track_id
      FROM play_events pe
     WHERE pe.user_id = $1 AND pe.duration_played_ms >= 30000
),
consumed_albums AS (
    SELECT DISTINCT t.album_id
      FROM attempted a JOIN tracks t ON t.id = a.track_id
),
affinity_artists AS (
    SELECT gla.artist_id FROM general_likes_artists gla WHERE gla.user_id = $1
    UNION
    SELECT t.artist_id
      FROM attempted a JOIN tracks t ON t.id = a.track_id
     GROUP BY t.artist_id
    HAVING COUNT(*) >= 3
),
albums_tiered AS (
    SELECT al.id AS album_id, al.created_at,
           CASE
             WHEN al.created_at >= now() - interval '30 days'
                  AND al.artist_id IN (SELECT artist_id FROM affinity_artists) THEN 1
             WHEN al.artist_id IN (SELECT artist_id FROM affinity_artists) THEN 2
             ELSE 3
           END AS tier
      FROM albums al
     WHERE al.created_at >= now() - interval '90 days'
       AND al.id NOT IN (SELECT album_id FROM consumed_albums)
)
SELECT t.id, t.album_id, t.artist_id, alt.tier::int AS tier
  FROM tracks t
  JOIN albums_tiered alt ON alt.album_id = t.album_id
 WHERE t.missing_since IS NULL   -- #2523: never offer a file that is gone
   AND NOT EXISTS (
       SELECT 1 FROM quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
 ORDER BY alt.tier, alt.created_at DESC, t.album_id,
          t.disc_number NULLS FIRST, t.track_number NULLS FIRST
 LIMIT 300;

-- name: ListOnThisDayTracks :many
-- #422 On This Day: tracks the user played around this calendar date
-- (±10 day-of-year) in the past, excluding the very recent (>30 days
-- ago) so it's nostalgic, not just "last week". Weighted by how much
-- they were played in those windows. Floor relaxed from 60→30 days
-- and window ±7→±10 so it surfaces on a months-old library instead
-- of needing a full year of history; still skips cleanly (no rows →
-- no playlist) when there's no qualifying history yet.
-- Day-of-year distance is circular (#1256): plain ABS made Dec 28 vs
-- Jan 3 read as 359 days apart, silently gutting the window for ~3
-- weeks around every New Year — precisely when holiday nostalgia is
-- the point. LEAST(d, 365-d) wraps the boundary; leap-year drift of
-- ±1 is absorbed by the ±10 window. The build date ($2, already here
-- for the md5 rotation) anchors "today" instead of now() so the
-- window is testable and consistent with the mix's daily determinism.
-- $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 '30 days'
       AND LEAST(
           ABS(EXTRACT(DOY FROM started_at) - EXTRACT(DOY FROM $2::date)),
           365 - ABS(EXTRACT(DOY FROM started_at) - EXTRACT(DOY FROM $2::date))
       ) <= 10
     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 t.missing_since IS NULL   -- #2523: never offer a file that is gone
   AND NOT EXISTS (
       SELECT 1 FROM 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: songs the user has never heard or even
-- attempted. "Attempted" is track-level with a >=30s listen threshold
-- (#1268, operator decision 2026-07-03) — the old version disqualified
-- a whole album on ANY play_event, so a 2-second accidental brush
-- banished it permanently.
--
--   tier 1  the exact desire: albums with ZERO attempted tracks
--   tier 2  step back: barely-attempted albums (<=25% of tracks
--           reached 30s) — brushed, never explored. The already-
--           attempted tracks themselves are excluded; they're not
--           first listens.
--
-- Within each tier, affinity-ordered as before: liked artist, then
-- attempted-played artist (>=30s — skip-only contact isn't trust),
-- then the rest; album-coherent. The tier lands on
-- playlist_tracks.pick_kind via the producer. $1 user_id.
WITH attempted AS (
    SELECT DISTINCT pe.track_id
      FROM play_events pe
     WHERE pe.user_id = $1 AND pe.duration_played_ms >= 30000
),
album_attempts AS (
    SELECT t.album_id,
           COUNT(a.track_id) AS attempted_count,
           COUNT(*) AS track_count
      FROM tracks t
      LEFT JOIN attempted a ON a.track_id = t.id
     GROUP BY t.album_id
),
attempted_artists AS (
    SELECT DISTINCT t.artist_id
      FROM attempted a JOIN tracks t ON t.id = a.track_id
),
albums_tiered AS (
    SELECT aa.album_id,
           CASE
             WHEN aa.attempted_count = 0 THEN 1
             WHEN aa.attempted_count::float / GREATEST(aa.track_count, 1) <= 0.25 THEN 2
           END AS tier
      FROM album_attempts aa
)
SELECT t.id, t.album_id, t.artist_id, alt.tier::int AS tier
  FROM tracks t
  JOIN albums al ON al.id = t.album_id
  JOIN albums_tiered alt ON alt.album_id = al.id
 WHERE t.missing_since IS NULL   -- #2523: never offer a file that is gone
   AND alt.tier IS NOT NULL
   AND NOT EXISTS (SELECT 1 FROM attempted a WHERE a.track_id = t.id)
   AND NOT EXISTS (
       SELECT 1 FROM quarantine q
        WHERE q.user_id = $1 AND q.track_id = t.id
   )
 ORDER BY
   alt.tier,
   (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 attempted_artists) THEN 1
      ELSE 2
    END),
   al.id, t.disc_number NULLS FIRST, t.track_number NULLS FIRST
 LIMIT 300;