minstrel/internal/db/queries/recommendation.sql

-- name: LoadRadioCandidates :many
-- Returns all tracks except the seed and any played by the user within
-- the last $3 hours, joined with the stats needed for scoring:
--   is_liked     — boolean from general_likes for this user
--   last_played_at — max(play_events.started_at) for this user/track
--   play_count   — count of play_events for this user/track
--   skip_count   — play_events where was_skipped=true
SELECT
    sqlc.embed(t),
    (l.user_id IS NOT NULL)::bool AS is_liked,
    pe.last_played_at::timestamptz AS last_played_at,
    pe.play_count,
    pe.skip_count
FROM tracks t
LEFT JOIN general_likes l ON l.user_id = $1 AND l.track_id = t.id
LEFT JOIN LATERAL (
    SELECT
        max(started_at) AS last_played_at,
        count(*) AS play_count,
        count(*) FILTER (WHERE was_skipped) AS skip_count
    FROM play_events
    WHERE user_id = $1 AND track_id = t.id
) pe ON true
WHERE t.id <> $2
  AND NOT EXISTS (
    SELECT 1 FROM play_events
    WHERE user_id = $1 AND track_id = t.id
      AND started_at > now() - $3 * interval '1 hour'
  );

-- name: LoadRadioCandidatesV2 :many
-- M4c: similarity-driven candidate pool. 5-way UNION:
--   $1 user_id, $2 seed_track_id, $3 recently_played_hours,
--   $4 exclude (uuid[]), $5 lb_similar K, $6 similar_artists K,
--   $7 tag_overlap K, $8 likes_overlap K, $9 random_fill K.
-- Returns same shape as LoadRadioCandidates plus similarity_score column.

WITH
seed_info AS (
    SELECT t.artist_id,
           trim(g)::text AS tag
    FROM tracks t
    LEFT JOIN LATERAL regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g(tag) ON true
    WHERE t.id = $2 AND trim(g) <> ''
),
excluded_ids AS (
    SELECT unnest($4::uuid[]) AS id
    UNION ALL
    SELECT pe.track_id AS id
    FROM play_events pe
    WHERE pe.user_id = $1 AND pe.started_at > now() - $3 * interval '1 hour'
),
lb_similar AS (
    SELECT ts.track_b_id AS track_id, ts.score AS sim_score
    FROM track_similarity ts
    WHERE ts.track_a_id = $2
      AND ts.source = 'listenbrainz'
      AND ts.track_b_id NOT IN (SELECT id FROM excluded_ids)
    ORDER BY ts.score DESC
    LIMIT $5
),
similar_artists AS (
    SELECT t.id AS track_id, asim.score * 0.5 AS sim_score
    FROM artist_similarity asim
    JOIN tracks t ON t.artist_id = asim.artist_b_id
    JOIN (SELECT DISTINCT artist_id FROM seed_info) sa ON asim.artist_a_id = sa.artist_id
    WHERE asim.source = 'listenbrainz'
      AND t.id NOT IN (SELECT id FROM excluded_ids)
    ORDER BY asim.score DESC, random()
    LIMIT $6
),
tag_overlap AS (
    SELECT t.id AS track_id,
           (count(DISTINCT trim(g))::float8
            / GREATEST((SELECT count(DISTINCT tag) FROM seed_info), 1)) AS sim_score
    FROM tracks t
    LEFT JOIN LATERAL regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g_split(g) ON true
    WHERE trim(g_split.g) IN (SELECT tag FROM seed_info)
      AND t.id NOT IN (SELECT id FROM excluded_ids)
      AND t.id <> $2
    GROUP BY t.id
    HAVING count(DISTINCT trim(g_split.g)) > 0
    ORDER BY sim_score DESC
    LIMIT $7
),
likes_overlap AS (
    SELECT gl.track_id, 0.6::float8 AS sim_score
    FROM general_likes gl
    WHERE gl.user_id = $1
      AND gl.track_id NOT IN (SELECT id FROM excluded_ids)
      AND EXISTS (
          SELECT 1 FROM tracks t
          LEFT JOIN LATERAL regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g_overlap(g) ON true
          WHERE t.id = gl.track_id
            AND trim(g_overlap.g) IN (SELECT tag FROM seed_info)
      )
    ORDER BY random()
    LIMIT $8
),
random_fill AS (
    SELECT t.id AS track_id, 0.0::float8 AS sim_score
    FROM tracks t
    WHERE t.id NOT IN (SELECT id FROM excluded_ids)
      AND t.id <> $2
      AND t.id NOT IN (
          SELECT track_id FROM lb_similar
          UNION SELECT track_id FROM similar_artists
          UNION SELECT track_id FROM tag_overlap
          UNION SELECT track_id FROM likes_overlap
      )
    ORDER BY random()
    LIMIT $9
)
SELECT
    sqlc.embed(t),
    (l.user_id IS NOT NULL)::bool AS is_liked,
    pe.last_played_at::timestamptz AS last_played_at,
    pe.play_count,
    pe.skip_count,
    COALESCE(max(u.sim_score), 0.0) AS similarity_score
FROM (
    SELECT track_id, sim_score FROM lb_similar
    UNION ALL SELECT track_id, sim_score FROM similar_artists
    UNION ALL SELECT track_id, sim_score FROM tag_overlap
    UNION ALL SELECT track_id, sim_score FROM likes_overlap
    UNION ALL SELECT track_id, sim_score FROM random_fill
) u
JOIN tracks t ON t.id = u.track_id
LEFT JOIN general_likes l ON l.user_id = $1 AND l.track_id = t.id
LEFT JOIN LATERAL (
    SELECT max(started_at) AS last_played_at,
           count(*) AS play_count,
           count(*) FILTER (WHERE was_skipped) AS skip_count
    FROM play_events
    WHERE user_id = $1 AND track_id = t.id
) pe ON true
GROUP BY t.id, t.title, t.album_id, t.artist_id, t.duration_ms, t.file_path,
         t.file_format, t.file_size, t.bitrate, t.track_number, t.disc_number,
         t.mbid, t.genre, t.added_at, t.updated_at,
         l.user_id, pe.last_played_at, pe.play_count, pe.skip_count;