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'
  )
  AND NOT EXISTS (
    SELECT 1 FROM lidarr_quarantine q
    WHERE q.user_id = $1 AND q.track_id = t.id
  );

-- 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_artist AS (
    SELECT artist_id
    FROM tracks
    WHERE tracks.id = $2
),
seed_tags AS (
    SELECT trim(g) 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'
    UNION ALL
    SELECT q.track_id AS id
    FROM lidarr_quarantine q
    WHERE q.user_id = $1
),
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 seed_artist 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(*) FROM seed_tags), 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_tags)
      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_tags)
      )
    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;

-- name: SuggestArtistsForUser :many
-- M5c: per-user artist suggestions ranked by signal x similarity. The
-- seeds CTE collects the user's likes (x5) plus recency-decayed plays
-- (exp(-age_days / $2)). The contributions CTE joins those seeds against
-- artist_similarity_unmatched and filters out candidates already in
-- library or already in a non-terminal lidarr_request. The outer SELECT
-- aggregates per candidate, returning the top-3 contributing seeds for
-- attribution. $1=user_id, $2=half_life_days, $3=limit.
WITH seeds AS (
    SELECT a.id AS artist_id,
           5.0 * (CASE WHEN gla.artist_id IS NOT NULL THEN 1 ELSE 0 END)
           + COALESCE(SUM(EXP(- EXTRACT(epoch FROM now() - pe.started_at) / ($2::float8 * 86400.0))), 0)
           AS signal,
           (gla.artist_id IS NOT NULL) AS is_liked,
           COUNT(pe.id)::bigint AS play_count
    FROM artists a
    LEFT JOIN general_likes_artists gla ON gla.artist_id = a.id AND gla.user_id = $1
    LEFT JOIN tracks t ON t.artist_id = a.id
    LEFT JOIN play_events pe ON pe.track_id = t.id AND pe.user_id = $1
    WHERE gla.artist_id IS NOT NULL OR pe.id IS NOT NULL
    GROUP BY a.id, gla.artist_id
),
contributions AS (
    SELECT u.candidate_mbid,
           u.candidate_name,
           seeds.artist_id AS seed_id,
           seeds.is_liked,
           seeds.play_count,
           seeds.signal * u.score AS contribution
    FROM artist_similarity_unmatched u
    JOIN seeds ON seeds.artist_id = u.seed_artist_id
    WHERE NOT EXISTS (SELECT 1 FROM artists WHERE mbid = u.candidate_mbid)
      AND NOT EXISTS (
          SELECT 1 FROM lidarr_requests r
           WHERE r.user_id = $1
             AND r.lidarr_artist_mbid = u.candidate_mbid
             AND r.status NOT IN ('rejected', 'failed')
      )
)
SELECT candidate_mbid,
       candidate_name,
       SUM(contribution)::float8 AS total_score,
       ((array_agg(seed_id      ORDER BY contribution DESC))[1:3])::uuid[]    AS top_seed_ids,
       ((array_agg(contribution ORDER BY contribution DESC))[1:3])::float8[]  AS top_contributions,
       ((array_agg(is_liked     ORDER BY contribution DESC))[1:3])::boolean[] AS top_is_liked,
       ((array_agg(play_count   ORDER BY contribution DESC))[1:3])::bigint[]  AS top_play_counts
FROM contributions
GROUP BY candidate_mbid, candidate_name
ORDER BY total_score DESC
LIMIT $3;

-- name: ListMostPlayedTracksForUser :many
-- M6a: top-N tracks by completed-play count for the user. was_skipped
-- excludes skips so a user spamming next doesn't fabricate a top track.
-- Quarantined tracks (per-user soft-hide from M5b) are filtered out.
--
-- Aggregate play_events first (uses play_events_user_track_idx) and
-- join through tracks/albums/artists only for the survivors. Earlier
-- shape did the join across every play_event row before grouping —
-- O(plays) instead of O(distinct tracks).
WITH plays AS (
    SELECT track_id, count(*) AS cnt
    FROM play_events
    WHERE user_id = $1 AND was_skipped = false
    GROUP BY track_id
)
SELECT sqlc.embed(t),
       albums.title AS album_title,
       artists.name AS artist_name
FROM plays p
JOIN tracks t   ON t.id = p.track_id
JOIN albums     ON albums.id  = t.album_id
JOIN artists    ON artists.id = t.artist_id
WHERE NOT EXISTS (
    SELECT 1 FROM lidarr_quarantine q
    WHERE q.user_id = $1 AND q.track_id = t.id
)
ORDER BY p.cnt DESC, t.id
LIMIT $2;

-- name: ListMostPlayedTracksForArtist :many
-- Top tracks for one artist by this user's completed-play count (skips
-- excluded, quarantine filtered). Same projection as
-- ListMostPlayedTracksForUser plus an artist_id filter, so the handler
-- reuses trackRefFrom(row.Track, row.AlbumTitle, row.ArtistName).
WITH plays AS (
    SELECT track_id, count(*) AS cnt
    FROM play_events
    WHERE user_id = sqlc.arg(user_id) AND was_skipped = false
    GROUP BY track_id
)
SELECT sqlc.embed(t),
       albums.title AS album_title,
       artists.name AS artist_name
FROM plays p
JOIN tracks t   ON t.id = p.track_id
JOIN albums     ON albums.id  = t.album_id
JOIN artists    ON artists.id = t.artist_id
WHERE t.artist_id = sqlc.arg(artist_id)
  AND NOT EXISTS (
      SELECT 1 FROM lidarr_quarantine q
      WHERE q.user_id = sqlc.arg(user_id) AND q.track_id = t.id
  )
ORDER BY p.cnt DESC, t.id
LIMIT sqlc.arg(result_limit);

-- name: ListLastPlayedArtistsForUser :many
-- M6a: artists ranked by max(play_events.started_at) for the user, with
-- a derived cover_album_id via a representative-album lateral join (most
-- recent album that has cover_art_path set). album_count joined for the
-- ArtistRef wire shape.
--
-- Earlier shape iterated `FROM artists a` and ran a LATERAL play_events
-- subquery per artist — O(total_artists) plan even for users with a
-- handful of plays. New shape aggregates the user's plays by artist
-- via the play_events → tracks join up front (uses
-- play_events_user_track_idx + tracks pkey lookups), then attaches
-- the artist row and lateral cover/count subqueries only for the
-- artists that actually appear. Distinct-artists set is small for a
-- typical user, so cost is bounded by play history not library size.
WITH user_plays AS (
    SELECT t.artist_id, max(pe.started_at) AS last_started
    FROM play_events pe
    JOIN tracks t ON t.id = pe.track_id
    WHERE pe.user_id = $1
    GROUP BY t.artist_id
)
SELECT sqlc.embed(a),
       cov.id AS cover_album_id,
       cnt.album_count::bigint AS album_count,
       up.last_started::timestamptz AS last_played_at
FROM user_plays up
JOIN artists a ON a.id = up.artist_id
LEFT JOIN LATERAL (
    SELECT id FROM albums
    WHERE artist_id = a.id AND cover_art_path IS NOT NULL
    ORDER BY created_at DESC LIMIT 1
) cov ON true
LEFT JOIN LATERAL (
    SELECT count(*) AS album_count
    FROM albums WHERE artist_id = a.id
) cnt ON true
ORDER BY up.last_started DESC, a.id
LIMIT $2;

-- name: ListRediscoverAlbumsForUser :many
-- Albums eligible for Rediscover via either signal:
--   (a) explicit album-like (general_likes_albums) liked >30 days ago, OR
--   (b) >=2 liked tracks from the album (general_likes), where the
--       earliest such track-like is >30 days ago.
-- AND not played in the last 14 days. The HAVING epoch sentinel keeps
-- albums with NO play history eligible (treated as last-played in 1970).
-- Ordering is daily-stable random (md5 of album+user+date hashes),
-- so the row rotates at midnight local without re-running per request.
-- Final cap + diversity + cross-section dedup land in the Go layer
-- (internal/recommendation/home.go).
WITH liked_signal AS (
    -- Path (a): explicit album-likes >30 days old.
    SELECT al.id AS album_id, gla.liked_at AS like_at
    FROM general_likes_albums gla
    JOIN albums al ON al.id = gla.album_id
    WHERE gla.user_id = $1
      AND gla.liked_at < now() - interval '30 days'
    UNION ALL
    -- Path (b): >=2 liked tracks per album, earliest like >30 days old.
    SELECT t.album_id, MIN(gl.liked_at) AS like_at
    FROM general_likes gl
    JOIN tracks t ON t.id = gl.track_id
    WHERE gl.user_id = $1
    GROUP BY t.album_id
    HAVING COUNT(*) >= 2
       AND MIN(gl.liked_at) < now() - interval '30 days'
),
eligible AS (
    SELECT ls.album_id,
           MIN(ls.like_at) AS like_at,
           max(pe.started_at) AS last_played
    FROM liked_signal ls
    LEFT JOIN tracks t       ON t.album_id = ls.album_id
    LEFT JOIN play_events pe ON pe.track_id = t.id AND pe.user_id = $1
    GROUP BY ls.album_id
    HAVING COALESCE(max(pe.started_at), '1970-01-01'::timestamptz)
           < now() - interval '14 days'
)
SELECT sqlc.embed(albums), artists.name AS artist_name
FROM eligible e
JOIN albums  ON albums.id = e.album_id
JOIN artists ON artists.id = albums.artist_id
ORDER BY md5(albums.id::text || current_date::text)
LIMIT $2;

-- name: ListRediscoverAlbumsFallbackForUser :many
-- Daily-stable random sample of liked albums for the user. The Go
-- service uses this to top up the rediscover row when the primary
-- eligibility query returns fewer than the inner limit. Same daily
-- hash ordering as the primary so the fallback rows stay stable
-- through the day instead of reshuffling on every refresh. Hash
-- omits user_id so sqlc can keep the user_id parameter UUID-typed
-- (a $1::text cast would force the param to string); eligibility
-- already differs per user, so output sets differ regardless.
SELECT sqlc.embed(albums), artists.name AS artist_name
FROM general_likes_albums gla
JOIN albums  ON albums.id = gla.album_id
JOIN artists ON artists.id = albums.artist_id
WHERE gla.user_id = $1
ORDER BY md5(albums.id::text || current_date::text)
LIMIT $2;

-- name: ListRediscoverArtistsForUser :many
-- Artists eligible for Rediscover via either signal:
--   (a) explicit artist-like (general_likes_artists) liked >30 days ago, OR
--   (b) >=3 liked tracks from the artist (general_likes), where the
--       earliest such track-like is >30 days ago.
-- AND none of their tracks played in the last 14 days. Higher track
-- threshold than the album path (3 vs 2) because artists span many
-- releases, so the bar is higher to avoid surfacing one-hit-wonder
-- affinities. Ordering is daily-stable random (md5 of artist+user+date
-- hashes). cover_album_id derived from a representative album (most
-- recently created album with cover_art_path set).
WITH liked_signal AS (
    SELECT a.id AS artist_id, gla.liked_at AS like_at
    FROM general_likes_artists gla
    JOIN artists a ON a.id = gla.artist_id
    WHERE gla.user_id = $1
      AND gla.liked_at < now() - interval '30 days'
    UNION ALL
    SELECT t.artist_id, MIN(gl.liked_at) AS like_at
    FROM general_likes gl
    JOIN tracks t ON t.id = gl.track_id
    WHERE gl.user_id = $1
    GROUP BY t.artist_id
    HAVING COUNT(*) >= 3
       AND MIN(gl.liked_at) < now() - interval '30 days'
),
eligible AS (
    SELECT ls.artist_id,
           MIN(ls.like_at) AS like_at,
           max(pe.started_at) AS last_played
    FROM liked_signal ls
    LEFT JOIN tracks t       ON t.artist_id = ls.artist_id
    LEFT JOIN play_events pe ON pe.track_id = t.id AND pe.user_id = $1
    GROUP BY ls.artist_id
    HAVING COALESCE(max(pe.started_at), '1970-01-01'::timestamptz)
           < now() - interval '14 days'
)
SELECT sqlc.embed(artists),
       cov.id AS cover_album_id,
       cnt.album_count::bigint AS album_count
FROM eligible e
JOIN artists ON artists.id = e.artist_id
LEFT JOIN LATERAL (
    SELECT id FROM albums
    WHERE artist_id = artists.id AND cover_art_path IS NOT NULL
    ORDER BY created_at DESC LIMIT 1
) cov ON true
LEFT JOIN LATERAL (
    SELECT count(*) AS album_count
    FROM albums WHERE artist_id = artists.id
) cnt ON true
ORDER BY md5(artists.id::text || current_date::text)
LIMIT $2;

-- name: ListRediscoverArtistsFallbackForUser :many
-- Daily-stable random sample of liked artists, paired with the Go
-- top-up logic in HomeData when the primary eligibility query returns
-- fewer than the inner limit. Daily hash ordering matches the primary
-- (omitting user_id from the hash for the same sqlc-typing reason).
SELECT sqlc.embed(artists),
       cov.id AS cover_album_id,
       cnt.album_count::bigint AS album_count
FROM general_likes_artists gla
JOIN artists ON artists.id = gla.artist_id
LEFT JOIN LATERAL (
    SELECT id FROM albums
    WHERE artist_id = artists.id AND cover_art_path IS NOT NULL
    ORDER BY created_at DESC LIMIT 1
) cov ON true
LEFT JOIN LATERAL (
    SELECT count(*) AS album_count
    FROM albums WHERE artist_id = artists.id
) cnt ON true
WHERE gla.user_id = $1
ORDER BY md5(artists.id::text || current_date::text)
LIMIT $2;