Files
minstrel/internal/recsettings/service_test.go
T
bvandeusenandClaude Opus 5 799dab029a
test-go / test (push) Successful in 1m0s
test-go / integration (push) Failing after 4m55s
feat(discover): rank suggestions by taste-tag overlap — #2377 (server)
The payoff slice. Until now a candidate's only claim on a slot was "some
artist you play is adjacent to it in a similarity graph" — a fact that says
nothing about whether the music sounds like anything you like. Now the
candidate's own folksonomy tags (cached by slice 5) are compared against
the user's taste-profile tags, so the deck ranks on taste and can say WHY.

The blend is MULTIPLICATIVE — score × (1 + weight × overlap) — and that
choice carries the whole safety argument:

  - An untagged candidate has overlap 0, so its score is EXACTLY unchanged.
    Tag coverage is permanently partial (#2376); it must cost a candidate
    nothing, not sink it (rule #131).
  - Nothing can leapfrog on tags alone. An additive term with a large
    weight would let a near-zero-similarity artist outrank a strong match
    for sharing one popular tag, which reads as noise.
  - Weight 0 restores pure similarity order bit-for-bit, so the operator's
    knob has a real off position.

overlap = Σ(shared) candWeight × normalizedTasteWeight ÷ Σ(all) candWeight.
Normalizing the taste side by the user's strongest tag makes the score
comparable across users (taste weights accumulate with listening, so a
heavy listener's raw numbers dwarf a new user's while meaning the same
thing). Dividing by the candidate's own mass makes it comparable across
candidates, so a densely-tagged artist can't win on tag count alone.

Applied to the whole over-fetched pool BEFORE selectSuggestions, so the
rotation and diversity rules operate on blended scores — boosting only the
twelve already chosen by similarity would leave the re-ranking undone.

A query failure is returned, NOT degraded past. Graceful degradation is
for expected absence (no taste profile, no cached tags) and both are
handled explicitly as empty inputs; swallowing a real error would hide a
broken DB behind a subtly worse ranking that nothing reports.

Migration 0051 adds a FOURTH tuning scope rather than columns on
taste_tuning, because snooze_days lives here too and a snooze must never
be read as taste signal (#2374) — filing it under 'taste' would put it one
careless join from the leak that design forbids. Expanding
recommendation_tuning_audit's CHECK is in the same migration per rule #36,
and a test asserts the audit row lands, which is what would catch its
absence.

snooze_days moves out of a Go constant onto the tuning card (rule #25),
closing the deferral from #2374.

Tag-overlap tests use deliberately SKEWED fixtures: an evenly-matching pool
cannot exercise a re-ranking, since every candidate gets the same
multiplier and the order is unchanged whether the blend works or not.

Admin UI + client attribution follow in this batch — rule #27.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-02 20:31:12 -04:00

399 lines
13 KiB
Go

package recsettings
import (
"context"
"encoding/json"
"errors"
"io"
"log/slog"
"os"
"testing"
"github.com/jackc/pgx/v5/pgxpool"
"git.fabledsword.com/bvandeusen/minstrel/internal/db"
"git.fabledsword.com/bvandeusen/minstrel/internal/dbtest"
)
func newPool(t *testing.T) *pgxpool.Pool {
t.Helper()
if testing.Short() {
t.Skip("skipping integration test in -short mode")
}
dsn := os.Getenv("MINSTREL_TEST_DATABASE_URL")
if dsn == "" {
t.Skip("MINSTREL_TEST_DATABASE_URL not set")
}
logger := slog.New(slog.NewTextHandler(io.Discard, nil))
if err := db.Migrate(dsn, logger); err != nil {
t.Fatalf("migrate: %v", err)
}
pool, err := pgxpool.New(context.Background(), dsn)
if err != nil {
t.Fatalf("pool: %v", err)
}
t.Cleanup(pool.Close)
dbtest.ResetDB(t, pool)
return pool
}
func newService(t *testing.T, pool *pgxpool.Pool) *Service {
t.Helper()
s, err := New(context.Background(), pool, slog.New(slog.NewTextHandler(io.Discard, nil)))
if err != nil {
t.Fatalf("recsettings.New: %v", err)
}
return s
}
func auditRows(t *testing.T, pool *pgxpool.Pool) []struct {
Scope, Action string
Changes []fieldChange
} {
t.Helper()
rows, err := pool.Query(context.Background(),
`SELECT scope, action, changes FROM recommendation_tuning_audit ORDER BY id`)
if err != nil {
t.Fatalf("query audit: %v", err)
}
defer rows.Close()
var out []struct {
Scope, Action string
Changes []fieldChange
}
for rows.Next() {
var scope, action string
var raw []byte
if err := rows.Scan(&scope, &action, &raw); err != nil {
t.Fatalf("scan audit: %v", err)
}
var changes []fieldChange
if err := json.Unmarshal(raw, &changes); err != nil {
t.Fatalf("unmarshal audit changes: %v", err)
}
out = append(out, struct {
Scope, Action string
Changes []fieldChange
}{scope, action, changes})
}
return out
}
func TestNew_SeedsShippedDefaults(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if got := s.Weights(ScopeRadio); got != ShippedRadioWeights() {
t.Errorf("radio weights = %+v, want shipped defaults", got)
}
if got := s.Weights(ScopeDailyMix); got != ShippedDailyMixWeights() {
t.Errorf("daily_mix weights = %+v, want shipped defaults", got)
}
if got := s.Taste(); got != ShippedTasteTuning() {
t.Errorf("taste tuning = %+v, want shipped defaults", got)
}
// Seeding must not write audit rows — nothing changed.
if rows := auditRows(t, pool); len(rows) != 0 {
t.Errorf("boot reconcile wrote %d audit rows, want 0", len(rows))
}
}
func TestUpdateProfile_PersistsAndAudits(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if err := s.UpdateProfile(context.Background(), ScopeRadio,
map[string]float64{"taste_weight": 2.5, "skip_penalty": 3.0}); err != nil {
t.Fatalf("UpdateProfile: %v", err)
}
got := s.Weights(ScopeRadio)
if got.TasteWeight != 2.5 || got.SkipPenalty != 3.0 {
t.Errorf("weights = %+v, want taste 2.5 / skip 3.0", got)
}
// The other profile is untouched.
if s.Weights(ScopeDailyMix) != ShippedDailyMixWeights() {
t.Error("daily_mix must be unaffected by a radio update")
}
// Values survive a fresh boot (persisted, not just cached), and the
// reconcile's ON CONFLICT DO NOTHING doesn't clobber tuned rows.
s2 := newService(t, pool)
if got := s2.Weights(ScopeRadio); got.TasteWeight != 2.5 {
t.Errorf("rebooted taste_weight = %v, want 2.5", got.TasteWeight)
}
rows := auditRows(t, pool)
if len(rows) != 1 {
t.Fatalf("audit rows = %d, want 1", len(rows))
}
if rows[0].Scope != ScopeRadio || rows[0].Action != "update" || len(rows[0].Changes) != 2 {
t.Errorf("audit row = %+v, want radio/update with 2 changes", rows[0])
}
// Changes are field-sorted: skip_penalty before taste_weight.
if rows[0].Changes[0].Field != "skip_penalty" || rows[0].Changes[0].New != 3.0 {
t.Errorf("changes[0] = %+v, want skip_penalty → 3.0", rows[0].Changes[0])
}
}
func TestUpdateProfile_Validation(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
cases := []struct {
name string
scope string
patch map[string]float64
want error
}{
{"unknown scope", "banana", map[string]float64{"taste_weight": 1}, ErrUnknownScope},
{"unknown field", ScopeRadio, map[string]float64{"vibes": 1}, ErrUnknownField},
{"over bound", ScopeRadio, map[string]float64{"taste_weight": 11}, ErrOutOfRange},
{"negative jitter", ScopeRadio, map[string]float64{"jitter_magnitude": -0.1}, ErrOutOfRange},
}
for _, c := range cases {
if err := s.UpdateProfile(context.Background(), c.scope, c.patch); !errors.Is(err, c.want) {
t.Errorf("%s: err = %v, want %v", c.name, err, c.want)
}
}
if s.Weights(ScopeRadio) != ShippedRadioWeights() {
t.Error("rejected patches must not partially apply")
}
if rows := auditRows(t, pool); len(rows) != 0 {
t.Errorf("rejected patches wrote %d audit rows, want 0", len(rows))
}
}
func TestUpdateTaste_CurveOrderingEnforced(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
// Moving neutral above full must reject on the PATCHED result.
err := s.UpdateTaste(context.Background(), map[string]float64{"engagement_neutral": 0.95})
if !errors.Is(err, ErrOutOfRange) {
t.Fatalf("err = %v, want ErrOutOfRange (curve ordering)", err)
}
// A coherent multi-point move is fine.
if err := s.UpdateTaste(context.Background(), map[string]float64{
"engagement_neutral": 0.40, "engagement_full": 0.95, "half_life_days": 30,
}); err != nil {
t.Fatalf("UpdateTaste: %v", err)
}
cfg := s.TasteConfig()
if cfg.HalfLifeDays != 30 || cfg.Engagement.NeutralCompletion != 0.40 {
t.Errorf("taste config = %+v, want tuned values", cfg)
}
// WindowDays scales with the half-life at the shipped ratio.
if cfg.WindowDays != 30*3.6 {
t.Errorf("WindowDays = %v, want %v", cfg.WindowDays, 30*3.6)
}
}
func TestUpdateTaste_EnrichedTagScale(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
// In-range update persists into cache + the assembled taste config.
if err := s.UpdateTaste(context.Background(),
map[string]float64{"enriched_tag_scale": 0.8}); err != nil {
t.Fatalf("UpdateTaste: %v", err)
}
if got := s.Taste().EnrichedTagScale; got != 0.8 {
t.Errorf("Taste().EnrichedTagScale = %v, want 0.8", got)
}
if got := s.TasteConfig().EnrichedTagScale; got != 0.8 {
t.Errorf("TasteConfig().EnrichedTagScale = %v, want 0.8", got)
}
// Out of [0,1] rejects.
if err := s.UpdateTaste(context.Background(),
map[string]float64{"enriched_tag_scale": 1.5}); !errors.Is(err, ErrOutOfRange) {
t.Errorf("err = %v, want ErrOutOfRange for 1.5", err)
}
}
func TestUpdateTaste_EraScale(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
// In-range update persists into cache + the assembled taste config.
if err := s.UpdateTaste(context.Background(),
map[string]float64{"era_scale": 0.8}); err != nil {
t.Fatalf("UpdateTaste: %v", err)
}
if got := s.Taste().EraScale; got != 0.8 {
t.Errorf("Taste().EraScale = %v, want 0.8", got)
}
if got := s.TasteConfig().EraScale; got != 0.8 {
t.Errorf("TasteConfig().EraScale = %v, want 0.8", got)
}
// Out of [0,1] rejects.
if err := s.UpdateTaste(context.Background(),
map[string]float64{"era_scale": 1.5}); !errors.Is(err, ErrOutOfRange) {
t.Errorf("err = %v, want ErrOutOfRange for 1.5", err)
}
}
func TestUpdateTaste_MoodScale(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if err := s.UpdateTaste(context.Background(),
map[string]float64{"mood_scale": 0.8}); err != nil {
t.Fatalf("UpdateTaste: %v", err)
}
if got := s.Taste().MoodScale; got != 0.8 {
t.Errorf("Taste().MoodScale = %v, want 0.8", got)
}
if got := s.TasteConfig().MoodScale; got != 0.8 {
t.Errorf("TasteConfig().MoodScale = %v, want 0.8", got)
}
if err := s.UpdateTaste(context.Background(),
map[string]float64{"mood_scale": 1.5}); !errors.Is(err, ErrOutOfRange) {
t.Errorf("err = %v, want ErrOutOfRange for 1.5", err)
}
}
func TestReset_RestoresShippedAndAudits(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
// Reset with nothing changed is a no-op (no audit row).
if err := s.Reset(context.Background(), ScopeDailyMix); err != nil {
t.Fatalf("no-op reset: %v", err)
}
if rows := auditRows(t, pool); len(rows) != 0 {
t.Fatalf("no-op reset wrote audit rows")
}
if err := s.UpdateProfile(context.Background(), ScopeDailyMix,
map[string]float64{"similarity_weight": 4}); err != nil {
t.Fatalf("UpdateProfile: %v", err)
}
if err := s.Reset(context.Background(), ScopeDailyMix); err != nil {
t.Fatalf("Reset: %v", err)
}
if s.Weights(ScopeDailyMix) != ShippedDailyMixWeights() {
t.Error("reset must restore shipped defaults")
}
rows := auditRows(t, pool)
if len(rows) != 2 || rows[1].Action != "reset" {
t.Fatalf("audit rows = %+v, want update then reset", rows)
}
}
func TestUpdate_NoOpWritesNoAudit(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
shipped := ShippedRadioWeights()
if err := s.UpdateProfile(context.Background(), ScopeRadio,
map[string]float64{"taste_weight": shipped.TasteWeight}); err != nil {
t.Fatalf("UpdateProfile: %v", err)
}
if rows := auditRows(t, pool); len(rows) != 0 {
t.Errorf("no-op update wrote %d audit rows, want 0", len(rows))
}
}
// --- Discover scope (#2377, milestone #268 slice 6) ---
func TestNew_SeedsDiscoverDefaults(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
got := s.Discover()
want := ShippedDiscoverTuning()
if got != want {
t.Errorf("Discover() = %+v, want shipped %+v", got, want)
}
}
func TestUpdateDiscover_PersistsAndAudits(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if err := s.UpdateDiscover(context.Background(), map[string]float64{
"tag_overlap_weight": 2.5,
"snooze_days": 30,
}); err != nil {
t.Fatalf("UpdateDiscover: %v", err)
}
if got := s.Discover().TagOverlapWeight; got != 2.5 {
t.Errorf("TagOverlapWeight = %v, want 2.5", got)
}
if got := s.Discover().SnoozeDays; got != 30 {
t.Errorf("SnoozeDays = %v, want 30", got)
}
// The audit row must land under the new scope. This is the assertion that
// would have caught a missing rule-#36 CHECK migration: without expanding
// recommendation_tuning_audit's whitelist, this INSERT fails at runtime.
rows := auditRows(t, pool)
if len(rows) != 1 {
t.Fatalf("audit rows = %d, want 1", len(rows))
}
if rows[0].Scope != ScopeDiscover {
t.Errorf("audit scope = %q, want %q", rows[0].Scope, ScopeDiscover)
}
if len(rows[0].Changes) != 2 {
t.Errorf("audit changes = %+v, want both fields", rows[0].Changes)
}
// Reload from the DB to prove it persisted rather than only caching.
s2 := newService(t, pool)
if got := s2.Discover().TagOverlapWeight; got != 2.5 {
t.Errorf("after reload TagOverlapWeight = %v, want 2.5 (not re-seeded to shipped)", got)
}
}
func TestUpdateDiscover_Validation(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
cases := []struct {
name string
patch map[string]float64
}{
{"unknown field", map[string]float64{"nope": 1}},
{"negative weight", map[string]float64{"tag_overlap_weight": -1}},
{"weight past the typo bound", map[string]float64{"tag_overlap_weight": 100}},
// A sub-day snooze isn't a snooze, it's a flicker.
{"snooze under a day", map[string]float64{"snooze_days": 0.5}},
// Past a year it's a permanent dismissal wearing a snooze's clothes —
// the shape rule #101 rules out.
{"snooze past a year", map[string]float64{"snooze_days": 400}},
}
for _, c := range cases {
if err := s.UpdateDiscover(context.Background(), c.patch); err == nil {
t.Errorf("%s: expected rejection, got nil", c.name)
}
}
if got := s.Discover(); got != ShippedDiscoverTuning() {
t.Errorf("a rejected patch mutated state: %+v", got)
}
if rows := auditRows(t, pool); len(rows) != 0 {
t.Errorf("rejected patches wrote %d audit rows, want 0", len(rows))
}
}
// Weight 0 must be accepted — it's the operator's off switch for the whole
// tag term, so a "must be positive" bound would remove their ability to
// disable the feature.
func TestUpdateDiscover_ZeroWeightIsAllowed(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if err := s.UpdateDiscover(context.Background(),
map[string]float64{"tag_overlap_weight": 0}); err != nil {
t.Fatalf("UpdateDiscover(0): %v", err)
}
if got := s.Discover().TagOverlapWeight; got != 0 {
t.Errorf("TagOverlapWeight = %v, want 0", got)
}
}
func TestResetDiscover_RestoresShippedDefaults(t *testing.T) {
pool := newPool(t)
s := newService(t, pool)
if err := s.UpdateDiscover(context.Background(),
map[string]float64{"tag_overlap_weight": 4}); err != nil {
t.Fatalf("UpdateDiscover: %v", err)
}
if err := s.Reset(context.Background(), ScopeDiscover); err != nil {
t.Fatalf("Reset: %v", err)
}
if got := s.Discover(); got != ShippedDiscoverTuning() {
t.Errorf("after reset = %+v, want shipped %+v", got, ShippedDiscoverTuning())
}
// Already-at-defaults is a no-op: update + reset = 2 rows, not 3.
if err := s.Reset(context.Background(), ScopeDiscover); err != nil {
t.Fatalf("second Reset: %v", err)
}
if rows := auditRows(t, pool); len(rows) != 2 {
t.Errorf("audit rows = %d, want 2 (the no-op reset must not audit)", len(rows))
}
}