Files
minstrel/internal/recommendation/candidates_v2_test.go
T
bvandeusenandClaude Opus 5 eff3d88931
test-go / test (push) Successful in 1m18s
test-go / integration (push) Successful in 4m52s
release / Build signed APK (releases and dev) (push) Successful in 6m9s
release / Build + push container image (push) Successful in 2m5s
release / Verify release artifacts (tag releases only) (push) Skipped
fix(recommendation): make the candidate draw reproducible, not accidentally so
Four arms of the candidate query ended in a bare `ORDER BY random()` with no
seed: similar_artists, likes_overlap, coplay_artists and random_fill.

Such an arm returns a STABLE set only while its LIMIT exceeds the rows
eligible for it — at that point it returns all of them and the order stops
mattering, because scoreAndSortCandidates sorts by track id before drawing
jitter. Below that threshold it returns a random SUBSET, and two builds on
the same day draw different ones.

So daily determinism held BY ACCIDENT, and only for libraries smaller than
the limits. Any real library is larger, which means same-day rebuilds have
been producing different mixes since those arms were written — invisible,
because a mix that changes after a refresh looks like a feature rather than
a broken promise.

Found by breaking it: cutting RandomFill to 10 while tuning Songs-like
turned TestBuildSystemPlaylists_DailyNonceDeterminism red. That test seeds
~20 tracks against a default RandomFill of 30, so its determinism came from
the limit exceeding the library, not from the code being right. It is now a
real guard.

The arms order by md5(id || $12) instead. The CALLER decides what that
means, which is the point: system mixes pass a per-(user, day) seed and get
the determinism they promise, radio passes a fresh value per request and
keeps varying, which is what a radio should do. Same shape the browse
queries in this file already use (`md5(id::text || current_date::text)`) —
existing idiom, not a new one.

This also unblocks the trim that #3881 wanted and could not have. Shrinking
a randomly-ordered arm was what broke membership; a seeded one takes a
smaller but REPRODUCIBLE slice. Songs-like's seed-independent share drops
from 29% to 12%, which was the original intent before determinism forced it
back to 20%.

TestSongsLikeLimits_DoNotShrinkTheUnseededRandomArms is DELETED rather than
kept passing. It existed to stop anyone trimming those arms while the
ordering was broken; the ordering is fixed, so the constraint is gone and a
guard enforcing it would now forbid correct code.

Was filed as blocked on tooling. It was not: `make generate-go` runs sqlc as
a pinned Go tool and is the same path CI takes.

One thing worth knowing for next time: three files in internal/db/dbq are
owned by root, left by `make generate` running sqlc in Docker. sqlc errored
on the first it could not write. They are untouched by this change and the
regeneration of recommendation.sql.go completed, but `make generate` will
keep failing until they are chowned.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SQ31KQpYbStyK5y58UmPLH
2026-09-11 08:44:33 -04:00

432 lines
15 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package recommendation
import (
"context"
"fmt"
"reflect"
"sort"
"strings"
"testing"
"github.com/jackc/pgx/v5/pgtype"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
)
// helperLBSimilarity inserts a track_similarity row.
func helperLBSimilarity(t *testing.T, f fixture, a, b pgtype.UUID, score float64) {
t.Helper()
if _, err := f.pool.Exec(context.Background(),
`INSERT INTO track_similarity (track_a_id, track_b_id, score, source) VALUES ($1, $2, $3, 'listenbrainz')`,
a, b, score); err != nil {
t.Fatalf("insert track_similarity: %v", err)
}
}
// helperArtistSimilarity inserts an artist_similarity row.
func helperArtistSimilarity(t *testing.T, f fixture, a, b pgtype.UUID, score float64) {
t.Helper()
if _, err := f.pool.Exec(context.Background(),
`INSERT INTO artist_similarity (artist_a_id, artist_b_id, score, source) VALUES ($1, $2, $3, 'listenbrainz')`,
a, b, score); err != nil {
t.Fatalf("insert artist_similarity: %v", err)
}
}
// helperSetTrackGenre updates a track's genre column. Used to retrofit
// genres onto the fixture's auto-created tracks (fixture creates tracks
// with NULL genre).
func helperSetTrackGenre(t *testing.T, f fixture, trackID pgtype.UUID, genre string) {
t.Helper()
if _, err := f.pool.Exec(context.Background(),
`UPDATE tracks SET genre = $1 WHERE id = $2`, genre, trackID); err != nil {
t.Fatalf("set genre: %v", err)
}
}
func defaultLimits() CandidateSourceLimits {
return DefaultCandidateSourceLimits()
}
func TestLoadCandidatesFromSimilarity_LBSimilarSourceContributes(t *testing.T) {
f := newFixture(t, 5)
seed := f.tracks[0]
target := f.tracks[1]
helperLBSimilarity(t, f, seed.ID, target.ID, 0.85)
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
var found *Candidate
for i := range got {
if got[i].Track.ID == target.ID {
found = &got[i]
break
}
}
if found == nil {
t.Fatal("LB-similar target missing from candidates")
}
if found.Inputs.SimilarityScore < 0.84 || found.Inputs.SimilarityScore > 0.86 {
t.Errorf("LB-similar SimilarityScore = %v, want ~0.85", found.Inputs.SimilarityScore)
}
}
func TestLoadCandidatesFromSimilarity_SimilarArtistTracksContribute(t *testing.T) {
f := newFixture(t, 1) // creates 1 artist + 1 album + 1 track (the seed)
seed := f.tracks[0]
// Add a SECOND artist + track in that artist; relate the two artists via artist_similarity.
otherArtist, _ := f.q.UpsertArtist(context.Background(), dbq.UpsertArtistParams{Name: "OtherArtist", SortName: "OtherArtist"})
otherAlbum, _ := f.q.UpsertAlbum(context.Background(), dbq.UpsertAlbumParams{Title: "OtherAlbum", SortTitle: "OtherAlbum", ArtistID: otherArtist.ID})
otherTrack, _ := f.q.UpsertTrack(context.Background(), dbq.UpsertTrackParams{
Title: "OtherTrack", AlbumID: otherAlbum.ID, ArtistID: otherArtist.ID,
FilePath: "/tmp/other.flac", DurationMs: 180_000,
})
helperArtistSimilarity(t, f, seed.ArtistID, otherArtist.ID, 0.8)
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == otherTrack.ID {
// 0.8 × 0.5 = 0.4
if c.Inputs.SimilarityScore < 0.39 || c.Inputs.SimilarityScore > 0.41 {
t.Errorf("similar-artist SimilarityScore = %v, want ~0.4 (0.8 × 0.5)", c.Inputs.SimilarityScore)
}
return
}
}
t.Error("similar-artist track missing from candidates")
}
func TestLoadCandidatesFromSimilarity_TagOverlapContributes(t *testing.T) {
f := newFixture(t, 2)
seed := f.tracks[0]
target := f.tracks[1]
helperSetTrackGenre(t, f, seed.ID, "Rock; Pop")
helperSetTrackGenre(t, f, target.ID, "Rock")
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == target.ID {
// Seed has 2 tags; target shares 1 → jaccard 1/2 = 0.5.
if c.Inputs.SimilarityScore < 0.49 || c.Inputs.SimilarityScore > 0.51 {
t.Errorf("tag-overlap SimilarityScore = %v, want ~0.5", c.Inputs.SimilarityScore)
}
return
}
}
t.Error("tag-overlap target missing from candidates")
}
func TestLoadCandidatesFromSimilarity_LikesOverlapContributes(t *testing.T) {
f := newFixture(t, 2)
seed := f.tracks[0]
liked := f.tracks[1]
helperSetTrackGenre(t, f, seed.ID, "Rock")
helperSetTrackGenre(t, f, liked.ID, "Rock")
if _, err := f.q.LikeTrack(context.Background(), dbq.LikeTrackParams{UserID: f.user, TrackID: liked.ID}); err != nil {
t.Fatalf("like: %v", err)
}
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == liked.ID {
// Both tracks tagged "Rock" → jaccard 1/1 = 1.0 from tag-overlap.
// likes-overlap = 0.6. Max wins = 1.0.
if c.Inputs.SimilarityScore < 0.59 {
t.Errorf("likes-overlap candidate SimilarityScore = %v, want ≥ 0.6", c.Inputs.SimilarityScore)
}
return
}
}
t.Error("liked track with shared tag missing from candidates")
}
func TestLoadCandidatesFromSimilarity_RandomFillReturnsTracks(t *testing.T) {
f := newFixture(t, 10) // 10 tracks; no similarity data
seed := f.tracks[0]
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
if len(got) == 0 {
t.Error("random fill returned 0 candidates; expected at least some")
}
for _, c := range got {
if c.Inputs.SimilarityScore != 0 {
t.Errorf("random-fill track %s has SimilarityScore = %v, want 0", c.Track.Title, c.Inputs.SimilarityScore)
}
}
}
func TestLoadCandidatesFromSimilarity_ExcludeListRespected(t *testing.T) {
f := newFixture(t, 5)
seed := f.tracks[0]
excluded := f.tracks[1].ID
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true},
[]pgtype.UUID{excluded}, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == excluded {
t.Error("excluded track appeared in candidates")
}
}
}
func TestLoadCandidatesFromSimilarity_SeedAlwaysExcluded(t *testing.T) {
f := newFixture(t, 5)
seed := f.tracks[0]
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == seed.ID {
t.Error("seed track appeared in candidates")
}
}
}
func TestLoadCandidatesFromSimilarity_RecentlyPlayedExcluded(t *testing.T) {
f := newFixture(t, 5)
seed := f.tracks[0]
recent := f.tracks[1].ID
var sessionID pgtype.UUID
if err := f.pool.QueryRow(context.Background(),
`INSERT INTO play_sessions (user_id, started_at, last_event_at, client_id)
VALUES ($1, now() - interval '5 minutes', now(), 'test') RETURNING id`,
f.user).Scan(&sessionID); err != nil {
t.Fatalf("session: %v", err)
}
if _, err := f.pool.Exec(context.Background(),
`INSERT INTO play_events (user_id, track_id, session_id, started_at, ended_at, duration_played_ms, completion_ratio, was_skipped)
VALUES ($1, $2, $3, now() - interval '30 minutes', now() - interval '20 minutes', 200000, 0.9, false)`,
f.user, recent, sessionID); err != nil {
t.Fatalf("play_event: %v", err)
}
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
for _, c := range got {
if c.Track.ID == recent {
t.Error("recently-played track appeared in candidates")
}
}
}
func TestLoadCandidatesFromSimilarity_DedupTakesMaxScore(t *testing.T) {
f := newFixture(t, 2)
seed := f.tracks[0]
target := f.tracks[1]
helperSetTrackGenre(t, f, seed.ID, "Rock")
helperSetTrackGenre(t, f, target.ID, "Rock") // jaccard 1/1 = 1.0 from tag-overlap
helperLBSimilarity(t, f, seed.ID, target.ID, 0.5) // weaker LB signal
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
count := 0
for _, c := range got {
if c.Track.ID == target.ID {
count++
// tag-overlap (1.0) wins over LB (0.5) per max() — expect ≥ 0.99
if c.Inputs.SimilarityScore < 0.99 {
t.Errorf("dedup max SimilarityScore = %v, want ≥ 0.99 (tag-overlap should win)", c.Inputs.SimilarityScore)
}
}
}
if count != 1 {
t.Errorf("target appeared %d times, want 1 (dedup failed)", count)
}
}
// TestLoadCandidatesFromSimilarity_TasteOverlapArm (#796 phase 2b): a track by
// a positively-weighted taste-profile artist enters the pool via taste_overlap
// even with every other arm disabled; a negatively-weighted artist's track does
// not (the WHERE weight > 0 filter).
func TestLoadCandidatesFromSimilarity_TasteOverlapArm(t *testing.T) {
f := newFixture(t, 2) // seed + 1 other, both by the fixture artist
seed := f.tracks[0]
target := f.tracks[1]
ctx := context.Background()
// Fixture artist gets a positive taste weight.
if _, err := f.pool.Exec(ctx,
`INSERT INTO taste_profile_artists (user_id, artist_id, weight) VALUES ($1, $2, 5.0)`,
f.user, seed.ArtistID); err != nil {
t.Fatalf("insert taste (positive): %v", err)
}
// A second artist with a NEGATIVE weight — its track must be excluded.
negArtist, _ := f.q.UpsertArtist(ctx, dbq.UpsertArtistParams{Name: "NegArtist", SortName: "NegArtist"})
negAlbum, _ := f.q.UpsertAlbum(ctx, dbq.UpsertAlbumParams{Title: "NegAlbum", SortTitle: "NegAlbum", ArtistID: negArtist.ID})
negTrack, _ := f.q.UpsertTrack(ctx, dbq.UpsertTrackParams{
Title: "NegTrack", AlbumID: negAlbum.ID, ArtistID: negArtist.ID,
FilePath: "/tmp/neg.flac", DurationMs: 180_000,
})
if _, err := f.pool.Exec(ctx,
`INSERT INTO taste_profile_artists (user_id, artist_id, weight) VALUES ($1, $2, -3.0)`,
f.user, negArtist.ID); err != nil {
t.Fatalf("insert taste (negative): %v", err)
}
// Only the taste_overlap arm is enabled.
limits := CandidateSourceLimits{TasteOverlap: 10}
got, err := LoadCandidatesFromSimilarity(
ctx, f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, limits, "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
var sawTarget, sawNeg bool
for _, c := range got {
switch c.Track.ID {
case target.ID:
sawTarget = true
case negTrack.ID:
sawNeg = true
}
}
if !sawTarget {
t.Error("positive-taste-artist track missing (taste_overlap arm didn't contribute)")
}
if sawNeg {
t.Error("negative-taste-artist track present (weight > 0 filter failed)")
}
}
func TestLoadCandidatesFromSimilarity_EmptyLibrary_NoError(t *testing.T) {
f := newFixture(t, 1) // just the seed
seed := f.tracks[0]
got, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, defaultLimits(), "test-seed",
)
if err != nil {
t.Fatalf("load: %v", err)
}
// Only the seed exists; it's excluded → 0 candidates.
if len(got) != 0 {
t.Errorf("got %d candidates from seed-only library, want 0", len(got))
}
}
// The randomised arms must draw REPRODUCIBLY for a given seed (#3889).
//
// Four arms used to end in a bare `ORDER BY random()`. That returned a stable
// set only while the arm's LIMIT exceeded the rows eligible for it — at that
// point it returned all of them and the order stopped mattering, because the
// caller sorts by track id before scoring. Below that threshold it returned a
// random SUBSET, so two calls drew different candidates.
//
// It therefore held by ACCIDENT, and only for libraries smaller than the
// limits. Any real library is larger, so same-day rebuilds had been drawing
// different mixes since the arm was written — invisible, because a mix that
// changes after a refresh looks like a feature.
//
// Limits deliberately smaller than the fixture, because that is the only
// regime where the bug existed at all: with limits above the eligible count
// the old code passes this too.
func TestLoadCandidatesFromSimilarity_SameSeedDrawsTheSameSet(t *testing.T) {
f := newFixture(t, 12)
seed := f.tracks[0]
tight := CandidateSourceLimits{
LBSimilar: 2, SimilarArtist: 2, TagOverlap: 2,
LikesOverlap: 2, RandomFill: 3, TasteOverlap: 2, UserCoplay: 2,
}
ids := func(cs []Candidate) []string {
out := make([]string, 0, len(cs))
for _, c := range cs {
out = append(out, fmt.Sprintf("%x", c.Track.ID.Bytes))
}
sort.Strings(out) // membership, not order — order is settled downstream
return out
}
first, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, tight, "day-one",
)
if err != nil {
t.Fatalf("load: %v", err)
}
if len(first) == 0 {
t.Fatal("no candidates, so this test asserts nothing")
}
for i := 0; i < 3; i++ {
again, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, tight, "day-one",
)
if err != nil {
t.Fatalf("load %d: %v", i, err)
}
if !reflect.DeepEqual(ids(first), ids(again)) {
t.Fatalf("same seed drew a different set on call %d:\n first %v\n again %v",
i, ids(first), ids(again))
}
}
}
// ...and a different seed is free to draw differently, or the ordering would
// be fixed rather than seeded and every day would serve the same mix.
//
// Asserted as "not pinned to one answer" rather than "always differs": with a
// small fixture two seeds can legitimately collide, so requiring a difference
// on any single pair would be flaky. Several seeds producing exactly one
// distinct set is the real regression — that is what a constant ORDER BY
// looks like.
func TestLoadCandidatesFromSimilarity_DifferentSeedsCanDrawDifferently(t *testing.T) {
f := newFixture(t, 12)
seed := f.tracks[0]
tight := CandidateSourceLimits{
LBSimilar: 2, SimilarArtist: 2, TagOverlap: 2,
LikesOverlap: 2, RandomFill: 3, TasteOverlap: 2, UserCoplay: 2,
}
seen := map[string]bool{}
for _, orderSeed := range []string{"a", "b", "c", "d", "e", "f"} {
cs, err := LoadCandidatesFromSimilarity(
context.Background(), f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, tight, orderSeed,
)
if err != nil {
t.Fatalf("load %q: %v", orderSeed, err)
}
ids := make([]string, 0, len(cs))
for _, c := range cs {
ids = append(ids, fmt.Sprintf("%x", c.Track.ID.Bytes))
}
sort.Strings(ids)
seen[strings.Join(ids, ",")] = true
}
if len(seen) < 2 {
t.Errorf("six different seeds produced %d distinct set(s); the ordering is not "+
"varying with the seed at all", len(seen))
}
}