Files
minstrel/internal/playlists/system.go
T
bvandeusen fb4431207d
test-go / test (push) Successful in 31s
test-web / test (push) Successful in 37s
test-go / integration (push) Successful in 4m37s
feat(recommendation): For You exploration attribution — taste vs fresh picks
Milestone #127 step 2 (#1249). For You deliberately blends two
populations — a head of top-scored taste picks and a tail sampled from
deeper ranking (the freshness injection) — but the metrics judged it as
one blob, so its skip rate couldn't distinguish "the taste engine is
missing" from "the freshness tax is too high". That number decides the
exploration share before we tune it.

- Migration 0038: nullable pick_kind ('taste'|'fresh') on both
  playlist_tracks (stamped at snapshot build) and play_events (frozen at
  play-ingestion — the snapshot rebuilds daily, so attribution cannot be
  reconstructed at read time).
- Builder: pickHeadAndTail marks head=taste / tail=fresh; the small-pool
  fallback is all taste (top-N-by-score IS the taste mechanism). Other
  variants persist NULL.
- Ingestion: for_you plays (live + offline replay) look the track up in
  the user's current snapshot; not found → unattributed, never guessed.
- Metrics: For You's row gains a breakdown (taste / fresh / earlier
  unattributed plays), parent row stays the sum; web card renders the
  sub-rows indented with the same baseline deltas + low-data dimming.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6
2026-07-02 20:39:41 -04:00

774 lines
29 KiB
Go

// Package playlists' system.go implements the system-generated mix
// builder (M7 #352 slice 2). The cron loop and lazy fallback both call
// BuildSystemPlaylists; the helpers in this file (pickSeedArtists,
// pickRepresentativeTrack, tieBreakHash) are the pure parts.
package playlists
import (
"bytes"
"context"
"crypto/sha256"
"encoding/binary"
"errors"
"fmt"
"log/slog"
"math/rand"
"sort"
"time"
"github.com/jackc/pgx/v5"
"github.com/jackc/pgx/v5/pgtype"
"github.com/jackc/pgx/v5/pgxpool"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
"git.fabledsword.com/bvandeusen/minstrel/internal/recommendation"
)
// seedArtistRow mirrors the sqlc-generated PickSeedArtistsRow shape.
// Defined locally so unit tests don't need a real DB.
type seedArtistRow struct {
ArtistID pgtype.UUID
Score int64
}
// pickSeedArtistsFromRows projects sqlc rows into the seed list. The
// SQL already orders by score DESC + artist_id and LIMIT 3, so this is
// just a column projection — but pulling it into a function keeps the
// call-site readable and makes the post-fetch path testable without
// a database.
func pickSeedArtistsFromRows(rows []seedArtistRow) []pgtype.UUID {
out := make([]pgtype.UUID, 0, len(rows))
for _, r := range rows {
out = append(out, r.ArtistID)
}
return out
}
// tieBreakHash returns a deterministic 64-bit hash of (track_id, date_str).
// Used to break score ties and to drive the For-You tail sample's
// daily-deterministic ordering. Same inputs always produce the same
// output; different inputs almost always differ.
//
// Switched from FNV-1a (May 2026) because two date strings differing
// only in the last character (e.g. "2026-05-07" vs "2026-05-08") gave
// hash values whose RELATIVE ORDERING across our small candidate pools
// was identical — the dateStr-driven divergence concentrated in low
// bits that lost out to high-bit ordering during sort. SHA-256
// truncated to 8 bytes has full avalanche, so any single-byte input
// change roughly half-flips the output bits and reorders meaningfully.
// The hash isn't security-load-bearing; we just want strong avalanche
// for tiny input deltas.
func tieBreakHash(trackID pgtype.UUID, dateStr string) uint64 {
h := sha256.New()
if trackID.Valid {
_, _ = h.Write(trackID.Bytes[:])
}
_, _ = h.Write([]byte(dateStr))
sum := h.Sum(nil)
return binary.BigEndian.Uint64(sum[:8])
}
// userIDHash returns a deterministic 64-bit hash of (user_id, dateStr).
// Same family as tieBreakHash, just keyed on user_id instead of
// track_id. Used to drive daily-deterministic seed picks and to seed
// the per-build scoring RNG: same (user, day) → same hash; different
// days → different hashes.
func userIDHash(userID pgtype.UUID, dateStr string) uint64 {
h := sha256.New()
if userID.Valid {
_, _ = h.Write(userID.Bytes[:])
}
_, _ = h.Write([]byte(dateStr))
sum := h.Sum(nil)
return binary.BigEndian.Uint64(sum[:8])
}
// pickForYouSeedForDay picks one of the user's top-played candidate
// tracks as today's For-You seed. With 5 candidates and SHA-256-based
// rotation, each candidate gets picked roughly 1 day in 5; the chosen
// seed drives the similarity candidate pool, so the resulting mix is
// substantially different across days for a user with diverse top-N
// plays.
//
// Degrades gracefully: 1 candidate → returns it; 0 → returns zero UUID
// (caller treats as "no seed available" and skips For-You).
func pickForYouSeedForDay(seeds []pgtype.UUID, userID pgtype.UUID, dateStr string) pgtype.UUID {
if len(seeds) == 0 {
return pgtype.UUID{}
}
idx := int(userIDHash(userID, dateStr) % uint64(len(seeds)))
return seeds[idx]
}
// pickSeedArtistsForDay takes a candidate pool of up to N artists and
// returns up to 3 of them, daily-deterministically shuffled. Each day
// gets a different ordering / selection, but within-day stability is
// preserved (same inputs always produce the same output).
//
// Uses Fisher-Yates over a copy of the input, seeded by userIDHash.
// Degrades gracefully: <3 candidates returns whatever is available in
// shuffled order.
func pickSeedArtistsForDay(pool []pgtype.UUID, userID pgtype.UUID, dateStr string) []pgtype.UUID {
if len(pool) == 0 {
return nil
}
shuffled := make([]pgtype.UUID, len(pool))
copy(shuffled, pool)
rng := rand.New(rand.NewSource(int64(userIDHash(userID, dateStr))))
rng.Shuffle(len(shuffled), func(i, j int) {
shuffled[i], shuffled[j] = shuffled[j], shuffled[i]
})
n := 3
if len(shuffled) < n {
n = len(shuffled)
}
return shuffled[:n]
}
// rankedCandidate is a (track_id, score) pair used during in-memory
// sorting before insert into playlist_tracks. T5 fills these from
// recommendation.Candidate scores. PickKind is set only by For-You's
// head/tail composition (#1249); empty persists as NULL.
type rankedCandidate struct {
TrackID pgtype.UUID
Score float64
PickKind string
}
// For-You pick kinds, persisted on playlist_tracks.pick_kind so plays
// can attribute skips to "the taste engine missing" vs "the freshness
// tax" (#1249). Values mirror the CHECK in migration 0038.
const (
pickKindTaste = "taste"
pickKindFresh = "fresh"
)
const systemMixLength = 25
// systemMixWeights are the fixed scoring weights used by the cron worker.
// JitterMagnitude is small (0.1) and combined with a userIDHash-seeded
// RNG (see scoreAndSortCandidates) — same (user, day) produces same
// scores within a day, but near-tied candidates reshuffle across days
// so the playlist doesn't feel frozen.
var systemMixWeights = recommendation.ScoringWeights{
BaseWeight: 1.0,
LikeBoost: 2.0,
RecencyWeight: 1.0,
SkipPenalty: 2.0,
JitterMagnitude: 0.1,
ContextWeight: 0.5,
SimilarityWeight: 1.5,
// Taste profile (#796 phase 2): the daily mixes are the primary
// taste-driven surface, so they lean on it. TasteMatchScore is in
// [-1,+1], so 1.5 makes a strong taste fit comparable to a like boost
// while passive avoidance (negative) gently demotes.
TasteWeight: 1.5,
}
// forYouHeadN is the number of top-scored tracks that anchor the For-You
// playlist; forYouTailN is the number sampled from positions 2*headN
// onward, daily-deterministic via tieBreakHash. The 50 + 50 split
// (~50% from the tail) gives the user a substantially different mix
// day-to-day while preserving a recognizable anchor of strong
// similarity matches.
//
// Sized to 100 to match Discover so the shuffle-on-play default
// (system playlists shuffle when launched from a tile) has a deep
// enough pool that re-plays within a day feel varied. Libraries with
// a thin For-You candidate pool degrade gracefully: pickHeadAndTail
// returns top-N-by-score when the capped pool can't support a full
// head/tail split, exactly as Discover returns fewer than 100 when
// its buckets are thin. Songs-like-X keeps simple pickTopN (the
// seed-artist context already frames the "you'll like this" promise).
const (
forYouHeadN = 50
forYouTailN = 50
)
// scoreAndSortCandidates scores every candidate with recommendation.Score
// and returns a new slice sorted by score DESC (ties broken by
// tieBreakHash). The scoring RNG is seeded by userIDHash so jitter is
// deterministic per (user, day) but rotates across days. Pure — no
// truncation, no cap.
func scoreAndSortCandidates(cands []recommendation.Candidate, userID pgtype.UUID, dateStr string, now time.Time) []recommendation.Candidate {
rng := rand.New(rand.NewSource(int64(userIDHash(userID, dateStr))))
type scored struct {
c recommendation.Candidate
score float64
}
// Pin candidate order by track id before drawing jitter. The candidate
// query (LoadRadioCandidatesV2) has ORDER BY random() arms and no
// stable outer ordering, so DB row order varies call-to-call. Since
// the i-th candidate gets the i-th seeded jitter draw, an unstable
// input order would assign different jitter to the same track across
// same-day rebuilds and reorder near-ties — breaking the daily
// determinism this function promises. Sorting by id first makes the
// jitter assignment a function of (track, day) alone.
ordered := make([]recommendation.Candidate, len(cands))
copy(ordered, cands)
sort.SliceStable(ordered, func(i, j int) bool {
return uuidLessPL(ordered[i].Track.ID, ordered[j].Track.ID)
})
pairs := make([]scored, len(ordered))
for i, c := range ordered {
pairs[i] = scored{c: c, score: recommendation.Score(c.Inputs, systemMixWeights, now, rng.Float64)}
}
sort.SliceStable(pairs, func(i, j int) bool {
if pairs[i].score != pairs[j].score {
return pairs[i].score > pairs[j].score
}
return tieBreakHash(pairs[i].c.Track.ID, dateStr) < tieBreakHash(pairs[j].c.Track.ID, dateStr)
})
out := make([]recommendation.Candidate, len(pairs))
for i, p := range pairs {
out[i] = p.c
}
return out
}
// capCandidatesByAlbumAndArtist trims a candidate list so no single
// album appears more than discoverMaxTracksPerAlbum times and no
// single artist appears more than discoverMaxTracksPerArtist times.
// Mirrors capByAlbumAndArtist (which operates on []discoverTrack);
// here the input/output is []recommendation.Candidate so For-You and
// Songs-like-X can apply the same diversity caps as Discover.
//
// Preserves input order. Reuses the discoverMax* constants —
// playlists across all three system variants get consistent
// diversity behavior.
func capCandidatesByAlbumAndArtist(cands []recommendation.Candidate) []recommendation.Candidate {
albumCount := map[pgtype.UUID]int{}
artistCount := map[pgtype.UUID]int{}
out := make([]recommendation.Candidate, 0, len(cands))
for _, c := range cands {
if albumCount[c.Track.AlbumID] >= discoverMaxTracksPerAlbum {
continue
}
if artistCount[c.Track.ArtistID] >= discoverMaxTracksPerArtist {
continue
}
albumCount[c.Track.AlbumID]++
artistCount[c.Track.ArtistID]++
out = append(out, c)
}
return out
}
// builtPlaylist is what a producer hands back: one playlist to
// materialize. A producer may return zero (no eligible tracks),
// one (For-You / Discover / each new kind), or many (Songs-like-X,
// one per seed artist) of these.
type builtPlaylist struct {
Name string
Variant string
SeedArtistID pgtype.UUID // zero value for non-seeded kinds
Tracks []rankedCandidate
}
// systemPlaylistProducer computes the playlists for one kind for a
// given user/day. A returned error is fatal to the whole build
// (e.g. a required base query failed); per-item issues should be
// logged and yield fewer playlists, not an error.
type systemPlaylistProducer func(
ctx context.Context, q *dbq.Queries, logger *slog.Logger,
userID pgtype.UUID, dateStr string, now time.Time,
) ([]builtPlaylist, error)
type systemPlaylistKind struct {
Key string
// Singleton kinds produce exactly one playlist per user (For-You,
// Discover, the discovery mixes) and so can be addressed by kind:
// the generic /system/{kind}/{refresh,shuffle} endpoints + the
// per-tile refresh affordance only apply to these. Non-singleton
// kinds (songs_like_artist → up to 3 per user) are played by
// playlist id and have no by-kind endpoint.
Singleton bool
Produce systemPlaylistProducer
}
// RefreshableSystemKind reports whether `key` is a known singleton
// system-playlist kind — i.e. addressable by the generic by-kind
// refresh/shuffle endpoints and eligible for the per-tile refresh
// affordance. The API layer + clients use this so neither hardcodes
// the kind list.
func RefreshableSystemKind(key string) bool {
for _, k := range systemPlaylistRegistry {
if k.Key == key {
return k.Singleton
}
}
return false
}
// systemPlaylistRegistry is the single source of truth for which
// system playlists exist. BuildSystemPlaylists iterates it; the
// generic /api/playlists/system/{kind}/{refresh,shuffle} endpoints
// validate against it. Adding a new mix = a producer + one entry
// here (plus its candidate query). Order is the materialize order;
// it has no functional effect (atomic replace + per-playlist
// collage are order-independent).
var systemPlaylistRegistry = func() []systemPlaylistKind {
out := []systemPlaylistKind{
{Key: "for_you", Singleton: true, Produce: produceForYou},
{Key: "songs_like_artist", Singleton: false, Produce: produceSeedMixes},
{Key: "discover", Singleton: true, Produce: produceDiscover},
}
// The five discovery mixes share one Produce closure factory keyed
// by a per-mix spec; spec list + factory live in system_mixes.go.
for _, spec := range discoveryMixSpecs {
out = append(out, systemPlaylistKind{
Key: spec.variant,
Singleton: true,
Produce: produceDiscoveryMix(spec),
})
}
return out
}()
// systemForYouSourceLimits is a deeper candidate pool than the radio
// default. On a self-hosted library without ListenBrainz similarity
// data the lb_similar / similar_artists sources contribute nothing,
// so the default (~130 raw, ~40 after dedup + diversity caps) can
// never fill For-You's 100-track head/tail. The raised random/tag
// fill keeps For-You ~100 deep regardless of LB enrichment; when LB
// data IS present the larger lb/similar K just makes it richer.
func systemForYouSourceLimits() recommendation.CandidateSourceLimits {
return recommendation.CandidateSourceLimits{
LBSimilar: 80,
SimilarArtist: 80,
TagOverlap: 60,
LikesOverlap: 40,
RandomFill: 150,
// For-You / You-might-like are the taste-driven surfaces, so pull a
// deep slice of the user's top taste-profile artists into the pool
// (#796 phase 2b). Empty for cold-start users (no profile yet).
TasteOverlap: 80,
}
}
// produceForYou: today's seed from the user's top-5 played tracks
// (rotates daily via userIDHash), similarity candidate pool, head+
// tail composition. The base seed query failing is fatal; a
// candidate-load failure is logged and yields no For-You.
func produceForYou(
ctx context.Context, q *dbq.Queries, logger *slog.Logger,
userID pgtype.UUID, dateStr string, now time.Time,
) ([]builtPlaylist, error) {
forYouSeeds, err := q.PickTopPlayedTracksForUser(ctx, userID)
if err != nil {
return nil, fmt.Errorf("pick for-you seed candidates: %w", err)
}
forYouSeed := pickForYouSeedForDay(forYouSeeds, userID, dateStr)
if !forYouSeed.Valid {
return nil, nil
}
zeroVec := recommendation.SessionVector{Seed: true}
cands, cerr := recommendation.LoadCandidatesFromSimilarity(
ctx, q, userID, forYouSeed,
1, // recentlyPlayedHours — small to avoid filtering the seed's recent neighbourhood
zeroVec,
[]pgtype.UUID{forYouSeed},
systemForYouSourceLimits(),
)
if cerr != nil {
logger.Warn("system playlist: for-you candidates load failed; skipping",
"user_id", uuidStringPL(userID), "err", cerr)
return nil, nil
}
tracks := pickHeadAndTail(cands, userID, dateStr, now, forYouHeadN, forYouTailN)
if len(tracks) == 0 {
return nil, nil
}
return []builtPlaylist{{Name: "For You", Variant: "for_you", Tracks: tracks}}, nil
}
// produceSeedMixes: up to 3 "Songs like {artist}" mixes. Seed
// artists rotate daily-deterministically. The base seed-artist
// query failing is fatal; per-artist failures are logged + skipped.
func produceSeedMixes(
ctx context.Context, q *dbq.Queries, logger *slog.Logger,
userID pgtype.UUID, dateStr string, now time.Time,
) ([]builtPlaylist, error) {
seedRows, err := q.PickSeedArtists(ctx, userID)
if err != nil {
return nil, fmt.Errorf("pick seed artists: %w", err)
}
seedRowsLocal := make([]seedArtistRow, 0, len(seedRows))
for _, r := range seedRows {
seedRowsLocal = append(seedRowsLocal, seedArtistRow{
ArtistID: r.ArtistID, Score: r.Score,
})
}
seedPool := pickSeedArtistsFromRows(seedRowsLocal)
seeds := pickSeedArtistsForDay(seedPool, userID, dateStr)
out := make([]builtPlaylist, 0, len(seeds))
for _, artistID := range seeds {
artistRow, aerr := q.GetArtistByID(ctx, artistID)
if aerr != nil {
logger.Warn("system playlist: seed artist load failed; skipping",
"artist_id", uuidStringPL(artistID), "err", aerr)
continue
}
seedTrack, terr := q.PickTopPlayedTrackForArtistByUser(ctx, dbq.PickTopPlayedTrackForArtistByUserParams{
UserID: userID, ArtistID: artistID,
})
if terr != nil || !seedTrack.Valid {
continue
}
zeroVec := recommendation.SessionVector{Seed: true}
cands, cerr := recommendation.LoadCandidatesFromSimilarity(
ctx, q, userID, seedTrack, 1, zeroVec, []pgtype.UUID{seedTrack},
recommendation.DefaultCandidateSourceLimits(),
)
if cerr != nil {
logger.Warn("system playlist: seed candidates load failed; skipping",
"artist_id", uuidStringPL(artistID), "err", cerr)
continue
}
// "Songs like X" excludes X's own songs.
filtered := make([]recommendation.Candidate, 0, len(cands))
for _, c := range cands {
if !pgtypeUUIDEqual(c.Track.ArtistID, artistID) {
filtered = append(filtered, c)
}
}
tracks := pickTopN(filtered, userID, dateStr, now, systemMixLength)
if len(tracks) == 0 {
continue
}
out = append(out, builtPlaylist{
Name: fmt.Sprintf("Songs like %s", artistRow.Name),
Variant: "songs_like_artist",
SeedArtistID: artistID,
Tracks: tracks,
})
}
return out, nil
}
// produceDiscover: unheard tracks biased toward dormant artists.
// Bucket failures are handled inside buildDiscoverCandidates and
// redistribute as deficit; a returned error is non-fatal here
// (logged, yields no Discover) to match the prior behavior.
func produceDiscover(
ctx context.Context, q *dbq.Queries, logger *slog.Logger,
userID pgtype.UUID, dateStr string, _ time.Time,
) ([]builtPlaylist, error) {
tracks, derr := buildDiscoverCandidates(ctx, q, logger, userID, dateStr)
if derr != nil {
logger.Warn("system playlist: discover candidates load failed; skipping",
"user_id", uuidStringPL(userID), "err", derr)
return nil, nil
}
if len(tracks) == 0 {
return nil, nil
}
return []builtPlaylist{{Name: "Discover", Variant: "discover", Tracks: tracks}}, nil
}
// BuildSystemPlaylists builds the user's daily system mixes (one For-You +
// up to 3 Songs-like-{seed} mixes). Atomic-replace inside one tx;
// concurrency-guarded via system_playlist_runs.in_flight; deterministic
// within a day via tieBreakHash(track_id, now.UTC().Format("2006-01-02")).
//
// Callable from both the cron loop (system_cron.go) and the lazy fallback.
// Returns nil when the user has no library activity to build from. Errors
// are captured in system_playlist_runs.last_error before returning.
func BuildSystemPlaylists(ctx context.Context, pool *pgxpool.Pool, logger *slog.Logger, userID pgtype.UUID, now time.Time, dataDir string) error {
q := dbq.New(pool)
dateStr := now.UTC().Format("2006-01-02")
dateOnly := pgtype.Date{Time: now.UTC(), Valid: true}
// Concurrency guard: try to claim the run row.
if _, err := q.TryClaimSystemPlaylistRun(ctx, userID); err != nil {
if errors.Is(err, pgx.ErrNoRows) {
logger.Debug("system playlist build: another run is in flight",
"user_id", uuidStringPL(userID))
return nil
}
return fmt.Errorf("claim run: %w", err)
}
// On any return path, mark the run finished. Failure capture is
// best-effort; success is updated in the happy path.
var buildErr error
defer func() {
if buildErr == nil {
if err := q.FinishSystemPlaylistRun(ctx, dbq.FinishSystemPlaylistRunParams{
UserID: userID,
LastRunAt: pgtype.Timestamptz{Time: now.UTC(), Valid: true},
LastRunDate: dateOnly,
}); err != nil {
logger.Warn("system playlist: failed to mark run finished; in_flight may be stuck",
"user_id", uuidStringPL(userID), "err", err)
}
} else {
errStr := buildErr.Error()
if err := q.FailSystemPlaylistRun(ctx, dbq.FailSystemPlaylistRunParams{
UserID: userID,
LastError: &errStr,
}); err != nil {
logger.Warn("system playlist: failed to record build failure",
"user_id", uuidStringPL(userID), "err", err)
}
}
}()
// Run every registered system-playlist producer. Each returns the
// playlists it wants materialized for this user/day (zero or more);
// a returned error is fatal to the whole build (matches the prior
// behavior where a seed-query failure aborted). Per-item issues are
// logged inside the producer and just yield fewer playlists.
var built []builtPlaylist
for _, kind := range systemPlaylistRegistry {
out, perr := kind.Produce(ctx, q, logger, userID, dateStr, now)
if perr != nil {
buildErr = fmt.Errorf("produce %s: %w", kind.Key, perr)
return buildErr
}
built = append(built, out...)
}
// "You might like" Home rows reuse the same similarity engine but
// persist to dedicated album/artist tables (not playlist_tracks).
// Computed here (reads only) and atomic-replaced inside the tx below,
// alongside the system playlists. A failed/gated computation is
// handled by yml.built (leave prior rows vs. clear) — never fatal.
yml := buildYouMightLike(ctx, q, logger, userID, dateStr, now)
// Atomic replace inside a transaction.
tx, err := pool.Begin(ctx)
if err != nil {
buildErr = fmt.Errorf("begin tx: %w", err)
return buildErr
}
defer func() { _ = tx.Rollback(ctx) }()
qtx := dbq.New(tx)
if err := qtx.DeleteSystemPlaylistsForUser(ctx, userID); err != nil {
buildErr = fmt.Errorf("delete old system playlists: %w", err)
return buildErr
}
// Track the playlist IDs we create so we can generate collage covers
// for each one after the transaction commits. Collage generation
// reads the playlist's tracks via a separate query that won't see
// uncommitted rows, so the work happens post-commit.
createdIDs := make([]pgtype.UUID, 0, len(built))
for _, bp := range built {
if len(bp.Tracks) == 0 {
continue
}
id, err := insertSystemPlaylist(ctx, qtx, userID, bp.Name, bp.Variant,
bp.SeedArtistID, bp.Tracks)
if err != nil {
buildErr = fmt.Errorf("insert %s (%s): %w", bp.Variant, bp.Name, err)
return buildErr
}
createdIDs = append(createdIDs, id)
}
if yml.built {
if err := persistYouMightLike(ctx, qtx, userID, yml); err != nil {
buildErr = fmt.Errorf("persist you-might-like: %w", err)
return buildErr
}
}
if err := tx.Commit(ctx); err != nil {
buildErr = fmt.Errorf("commit tx: %w", err)
return buildErr
}
// Post-commit: generate a 4-cell collage cover for each system
// playlist from the contributing tracks' album covers. The collage
// gracefully falls back to the FabledSword glyph in cells whose
// album lacks cover art, so a partially-covered library still
// produces a sensible visual rather than an empty placeholder.
// Errors are non-fatal — the playlist is already committed; a
// missing collage just leaves cover_path NULL until next build.
if dataDir != "" {
for _, plID := range createdIDs {
if _, cerr := GenerateCollage(ctx, pool, plID, dataDir); cerr != nil {
logger.Warn("system playlist: collage generation failed",
"playlist_id", uuidStringPL(plID), "err", cerr)
}
}
}
return nil
}
// pickTopN sorts candidates by score DESC, applies per-album (<=2) /
// per-artist (<=3) diversity caps matching Discover's behavior, then
// truncates to n. Used by Songs-like-X (and as the fallback inside
// pickHeadAndTail for small pools).
func pickTopN(cands []recommendation.Candidate, userID pgtype.UUID, dateStr string, now time.Time, n int) []rankedCandidate {
sorted := scoreAndSortCandidates(cands, userID, dateStr, now)
capped := capCandidatesByAlbumAndArtist(sorted)
if len(capped) > n {
capped = capped[:n]
}
rng := rand.New(rand.NewSource(int64(userIDHash(userID, dateStr))))
out := make([]rankedCandidate, len(capped))
for i, c := range capped {
out[i] = rankedCandidate{
TrackID: c.Track.ID,
Score: recommendation.Score(c.Inputs, systemMixWeights, now, rng.Float64),
}
}
return out
}
// pickHeadAndTail picks headN from the score-sorted head plus tailN from
// positions 2*headN onward (the tail), with the tail sampled
// daily-deterministically via tieBreakHash. Caps applied before the
// head/tail split. Used by For-You only.
//
// The "tail" — candidates ranked beyond 2*headN — is still similarity-
// related (every candidate passed the similarity filter) but isn't among
// the obvious top hits. Sampling from there gives the user variety they'll
// probably enjoy without resorting to genuinely random unrelated tracks.
//
// Falls back to standard pickTopN behavior when the candidate pool is too
// small to support a meaningful head/tail split (capped pool <=
// headN+tailN, or no candidates at or beyond position 2*headN).
func pickHeadAndTail(cands []recommendation.Candidate, userID pgtype.UUID, dateStr string, now time.Time, headN, tailN int) []rankedCandidate {
sorted := scoreAndSortCandidates(cands, userID, dateStr, now)
capped := capCandidatesByAlbumAndArtist(sorted)
rng := rand.New(rand.NewSource(int64(userIDHash(userID, dateStr))))
total := headN + tailN
if len(capped) <= total {
// Pool too small for a head/tail split — return up to total entries.
// All marked taste: top-N-by-score IS the taste mechanism; no
// exploration sampling happens on this path.
if len(capped) < total {
total = len(capped)
}
out := make([]rankedCandidate, total)
for i := 0; i < total; i++ {
out[i] = rankedCandidate{
TrackID: capped[i].Track.ID,
Score: recommendation.Score(capped[i].Inputs, systemMixWeights, now, rng.Float64),
PickKind: pickKindTaste,
}
}
return out
}
head := capped[:headN]
tailStart := 2 * headN
if tailStart >= len(capped) {
tailStart = headN
}
// Defensive copy so that sorting the tail pool does not mutate capped.
tailPool := append([]recommendation.Candidate{}, capped[tailStart:]...)
// Sort tail pool by tieBreakHash (daily-deterministic), take tailN.
// Sample is stable across requests within a day but varies across days.
sort.SliceStable(tailPool, func(i, j int) bool {
return tieBreakHash(tailPool[i].Track.ID, dateStr) < tieBreakHash(tailPool[j].Track.ID, dateStr)
})
tail := tailPool
if len(tail) > tailN {
tail = tail[:tailN]
}
// Combine: head order preserved (score-sorted), tail in tieBreakHash
// order. "First similar, then surprise" reads naturally in playback.
// Head entries are the taste picks; tail entries are the freshness
// injection (#1249) — the split the metrics page attributes skips to.
combined := make([]recommendation.Candidate, 0, len(head)+len(tail))
combined = append(combined, head...)
combined = append(combined, tail...)
out := make([]rankedCandidate, len(combined))
for i, c := range combined {
kind := pickKindTaste
if i >= len(head) {
kind = pickKindFresh
}
out[i] = rankedCandidate{
TrackID: c.Track.ID,
Score: recommendation.Score(c.Inputs, systemMixWeights, now, rng.Float64),
PickKind: kind,
}
}
return out
}
// insertSystemPlaylist inserts a kind='system' playlists row plus its
// playlist_tracks via AppendPlaylistTrack (slice 1's existing query, which
// does the snapshot lookup from tracks/albums/artists). Then recomputes
// rollups. Returns the new playlist's ID so the caller can drive
// post-commit collage generation.
//
// Pass seed_artist_id with Valid=false (zero pgtype.UUID) for the For-You
// variant; the CreateSystemPlaylist query persists NULL.
//
// cover_path is always inserted as NULL — the post-commit collage step
// in BuildSystemPlaylists overrides it with a 4-cell composite of the
// contributing tracks' album art.
func insertSystemPlaylist(ctx context.Context, qtx *dbq.Queries, userID pgtype.UUID,
name, variant string, seedArtistID pgtype.UUID,
tracks []rankedCandidate) (pgtype.UUID, error) {
variantStr := variant
p, err := qtx.CreateSystemPlaylist(ctx, dbq.CreateSystemPlaylistParams{
UserID: userID,
Name: name,
SystemVariant: &variantStr,
SeedArtistID: seedArtistID,
CoverPath: nil,
})
if err != nil {
return pgtype.UUID{}, fmt.Errorf("insert playlist row: %w", err)
}
for _, t := range tracks {
var pickKind *string
if t.PickKind != "" {
k := t.PickKind
pickKind = &k
}
if _, err := qtx.AppendPlaylistTrack(ctx, dbq.AppendPlaylistTrackParams{
PlaylistID: p.ID,
TrackID: t.TrackID,
PickKind: pickKind,
}); err != nil {
// Track may have been deleted between candidate-load and insert;
// skip silently rather than failing the whole build.
if errors.Is(err, pgx.ErrNoRows) {
continue
}
return pgtype.UUID{}, fmt.Errorf("append track %s: %w", uuidStringPL(t.TrackID), err)
}
}
if err := qtx.UpdatePlaylistRollups(ctx, p.ID); err != nil {
return pgtype.UUID{}, fmt.Errorf("update rollups: %w", err)
}
return p.ID, nil
}
// uuidStringPL renders a pgtype.UUID as the canonical 8-4-4-4-12 form.
// (pgtype.UUID's String method exists on some pgx versions but not others;
// also the playlists package needs this independent of test helpers.)
// Suffix `PL` distinguishes it from any test helper named uuidString.
// uuidLessPL reports whether a sorts before b by raw 16-byte value. Used
// to pin candidate order deterministically before jitter assignment.
func uuidLessPL(a, b pgtype.UUID) bool {
return bytes.Compare(a.Bytes[:], b.Bytes[:]) < 0
}
func uuidStringPL(u pgtype.UUID) string {
if !u.Valid {
return "<nil>"
}
return fmt.Sprintf("%x-%x-%x-%x-%x",
u.Bytes[0:4], u.Bytes[4:6], u.Bytes[6:8], u.Bytes[8:10], u.Bytes[10:16])
}