Files
minstrel/internal/api/me_recommendation_metrics_test.go
bvandeusen 5faa57634b
test-go / test (push) Successful in 31s
test-web / test (push) Successful in 38s
test-go / integration (push) Successful in 4m36s
feat(metrics): provenance as standard — pick_kind for all system mixes
The #1249 mechanism (stamp WHY a track is in the snapshot at build
time, freeze it onto the play at ingestion, break it down in metrics)
generalizes from a For You one-off to the standard for every system
mix (#1270):

- Migration 0039 widens both pick_kind CHECKs (drop + re-add in the
  same change) to taste/fresh + Discover's dormant/cross_user/random
  + tier1-3 for the rule-#131 eligibility ladders.
- GetForYouPickKindForTrack becomes GetSystemPickKindForTrack
  (user, variant, track); ingestion stamps any systemPlaylistSources
  play from its own variant's live snapshot, live + offline paths.
- Discover stamps its candidate bucket on discoverTrack before the
  interleave, making the 40/30/30 allocation measurable; dedup keeps
  the taking bucket's stamp.
- Metrics replace the for_you special-case with one pick-kind
  vocabulary — any family with attributed plays gets a breakdown,
  future stamping mixes need no metrics change.
- Web: breakdown sub-rows are now toggled per surface (collapsed by
  default) so eight stamping mixes don't swamp the card.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6
2026-07-02 23:26:52 -04:00

282 lines
11 KiB
Go

package api
import (
"context"
"encoding/json"
"net/http"
"net/http/httptest"
"os"
"testing"
"time"
"github.com/go-chi/chi/v5"
"github.com/jackc/pgx/v5/pgtype"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
)
func newMetricsRouter(h *handlers) chi.Router {
r := chi.NewRouter()
r.Get("/api/me/recommendation-metrics", h.handleGetRecommendationMetrics)
return r
}
// seedSourcedPlay inserts a play_event with an explicit source + completion +
// skip flag. A nil source inserts NULL (manual library play → baseline).
// pickKind is the For You taste/fresh attribution (#1249); nil everywhere
// except attributed for_you plays.
func seedSourcedPlay(
t *testing.T, h *handlers, userID, trackID, sessionID pgtype.UUID,
source, pickKind *string, completion float64, skipped bool,
) {
t.Helper()
if _, err := h.pool.Exec(context.Background(),
`INSERT INTO play_events
(user_id, track_id, session_id, started_at, source, pick_kind, completion_ratio, was_skipped)
VALUES ($1, $2, $3, now(), $4, $5, $6, $7)`,
userID, trackID, sessionID, source, pickKind, completion, skipped); err != nil {
t.Fatalf("seed sourced play: %v", err)
}
}
func TestRecommendationMetrics_NoSession401(t *testing.T) {
h, _ := testHandlers(t)
req := httptest.NewRequest(http.MethodGet, "/api/me/recommendation-metrics", nil)
rec := httptest.NewRecorder()
newMetricsRouter(h).ServeHTTP(rec, req)
if rec.Code != http.StatusUnauthorized {
t.Errorf("status = %d, want 401", rec.Code)
}
}
// findSurface returns the named family from any group, or nil.
func findSurface(resp recommendationMetricsResp, key string) *surfaceMetric {
for _, g := range resp.Groups {
for i := range g.Surfaces {
if g.Surfaces[i].Key == key {
return &g.Surfaces[i]
}
}
}
return nil
}
func TestBucketMetricsResponse_FamiliesGroupsBaseline(t *testing.T) {
src := func(s string) *string { return &s }
rows := []dbq.RecommendationSourceMetricsForUserRow{
{Source: src("for_you"), Plays: 3, Skips: 1, CompletionN: 3, AvgCompletion: 2.0 / 3},
// Two radio sessions collapse into one "radio" family; weighted
// completion = (0.2*1 + 0.8*1) / 2 = 0.5.
{Source: src("radio:aaaa"), Plays: 1, Skips: 1, CompletionN: 1, AvgCompletion: 0.2},
{Source: src("radio:bbbb"), Plays: 1, Skips: 0, CompletionN: 1, AvgCompletion: 0.8},
{Source: src("album:cccc"), Plays: 1, Skips: 0, CompletionN: 0, AvgCompletion: 0},
{Source: src("discover"), Plays: 1, Skips: 0, CompletionN: 1, AvgCompletion: 0.8},
// NULL source = manual plays → baseline, not a group row.
{Source: nil, Plays: 25, Skips: 5, CompletionN: 20, AvgCompletion: 0.9},
}
resp := bucketMetricsResponse(recMetricsDefaultDays, rows)
if resp.Baseline == nil {
t.Fatal("baseline missing")
}
if resp.Baseline.Plays != 25 || resp.Baseline.SkipRate != 0.2 {
t.Errorf("baseline = %+v, want plays=25 skip_rate=0.2", resp.Baseline)
}
if resp.Baseline.LowConfidence {
t.Error("baseline with 25 plays should not be low-confidence")
}
radio := findSurface(resp, "radio")
if radio == nil {
t.Fatal("radio family missing")
}
if radio.Plays != 2 || radio.Skips != 1 {
t.Errorf("radio plays/skips = %d/%d, want 2/1", radio.Plays, radio.Skips)
}
if radio.AvgCompletion < 0.49 || radio.AvgCompletion > 0.51 {
t.Errorf("radio avg_completion = %.3f, want 0.5 (play-weighted merge)", radio.AvgCompletion)
}
if !radio.LowConfidence {
t.Error("radio with 2 plays should be low-confidence")
}
if s := findSurface(resp, "direct_album"); s == nil || s.Plays != 1 {
t.Errorf("direct_album = %+v, want plays=1", s)
}
if s := findSurface(resp, ""); s != nil {
t.Error("NULL source must not appear as a surface family")
}
// No attributed (taste/fresh) plays in this fixture → no breakdown;
// an all-unattributed breakdown would just repeat the parent row.
if fy := findSurface(resp, "for_you"); fy == nil || fy.Breakdown != nil {
t.Errorf("for_you breakdown = %+v, want nil without attributed plays", fy)
}
// Group ordering is intent-banded: go_to before discovery before direct.
wantOrder := []string{intentGoTo, intentDiscovery, intentDirect}
if len(resp.Groups) != len(wantOrder) {
t.Fatalf("groups = %d, want %d", len(resp.Groups), len(wantOrder))
}
for i, g := range resp.Groups {
if g.Intent != wantOrder[i] {
t.Errorf("group[%d].intent = %s, want %s", i, g.Intent, wantOrder[i])
}
}
}
func TestBucketMetricsResponse_ForYouBreakdown(t *testing.T) {
src := func(s string) *string { return &s }
kind := func(s string) *string { return &s }
rows := []dbq.RecommendationSourceMetricsForUserRow{
{Source: src("for_you"), PickKind: kind("taste"), Plays: 30, Skips: 3,
CompletionN: 30, AvgCompletion: 0.9},
{Source: src("for_you"), PickKind: kind("fresh"), Plays: 10, Skips: 4,
CompletionN: 10, AvgCompletion: 0.5},
// NULL pick_kind = plays that predate attribution.
{Source: src("for_you"), Plays: 5, Skips: 1, CompletionN: 5, AvgCompletion: 0.7},
}
resp := bucketMetricsResponse(recMetricsDefaultDays, rows)
fy := findSurface(resp, "for_you")
if fy == nil {
t.Fatal("for_you family missing")
}
// The parent row stays the sum of its breakdown.
if fy.Plays != 45 || fy.Skips != 8 {
t.Errorf("for_you plays/skips = %d/%d, want 45/8", fy.Plays, fy.Skips)
}
if len(fy.Breakdown) != 3 {
t.Fatalf("breakdown rows = %d, want 3 (taste, fresh, earlier)", len(fy.Breakdown))
}
wantKeys := []string{"for_you_taste", "for_you_fresh", "for_you_unattributed"}
for i, k := range wantKeys {
if fy.Breakdown[i].Key != k {
t.Errorf("breakdown[%d].key = %s, want %s", i, fy.Breakdown[i].Key, k)
}
}
taste, fresh := fy.Breakdown[0], fy.Breakdown[1]
if taste.Plays != 30 || taste.SkipRate != 0.1 || taste.LowConfidence {
t.Errorf("taste = %+v, want plays=30 skip_rate=0.1 confident", taste)
}
if fresh.Plays != 10 || fresh.SkipRate != 0.4 || !fresh.LowConfidence {
t.Errorf("fresh = %+v, want plays=10 skip_rate=0.4 low-confidence", fresh)
}
// Breakdown rows never appear as their own surface families.
if s := findSurface(resp, "for_you_taste"); s != nil {
t.Error("for_you_taste must not be a top-level surface")
}
}
func TestBucketMetricsResponse_DiscoverBucketBreakdown(t *testing.T) {
// Provenance is standard (#1270): Discover's bucket stamps surface as
// a breakdown exactly like For You's taste/fresh — this is what makes
// the 40/30/30 allocation judgeable instead of a guess.
src := func(s string) *string { return &s }
kind := func(s string) *string { return &s }
rows := []dbq.RecommendationSourceMetricsForUserRow{
{Source: src("discover"), PickKind: kind("dormant"), Plays: 8, Skips: 2,
CompletionN: 8, AvgCompletion: 0.8},
{Source: src("discover"), PickKind: kind("cross_user"), Plays: 6, Skips: 3,
CompletionN: 6, AvgCompletion: 0.6},
{Source: src("discover"), PickKind: kind("random"), Plays: 4, Skips: 3,
CompletionN: 4, AvgCompletion: 0.4},
// NULL pick_kind = plays that predate bucket stamping.
{Source: src("discover"), Plays: 2, Skips: 0, CompletionN: 2, AvgCompletion: 0.9},
}
resp := bucketMetricsResponse(recMetricsDefaultDays, rows)
d := findSurface(resp, "discover")
if d == nil {
t.Fatal("discover family missing")
}
if d.Plays != 20 || d.Skips != 8 {
t.Errorf("discover plays/skips = %d/%d, want 20/8", d.Plays, d.Skips)
}
wantKeys := []string{
"discover_dormant", "discover_cross_user", "discover_random",
"discover_unattributed",
}
if len(d.Breakdown) != len(wantKeys) {
t.Fatalf("breakdown rows = %d, want %d", len(d.Breakdown), len(wantKeys))
}
for i, k := range wantKeys {
if d.Breakdown[i].Key != k {
t.Errorf("breakdown[%d].key = %s, want %s", i, d.Breakdown[i].Key, k)
}
}
if b := d.Breakdown[0]; b.Label != "Dormant artists" || b.Plays != 8 {
t.Errorf("dormant row = %+v, want label=Dormant artists plays=8", b)
}
}
func TestRecommendationMetrics_BucketsWithBaseline(t *testing.T) {
if os.Getenv("MINSTREL_TEST_DATABASE_URL") == "" {
t.Skip("MINSTREL_TEST_DATABASE_URL not set")
}
h, pool := testHandlers(t)
user := seedUser(t, pool, "metrics", "pw", false)
artist := seedArtist(t, pool, "MetricArtist")
album := seedAlbum(t, pool, artist.ID, "MetricAlbum", 2020)
tk := seedTrack(t, pool, album.ID, artist.ID, "MetricTrack", 1, 200000)
session := seedPlaySession(t, pool, user.ID, time.Now())
forYou := "for_you"
radioA := "radio:11111111-1111-1111-1111-111111111111"
taste, fresh := "taste", "fresh"
// for_you: 3 plays, 1 skipped; completions 1.0, 0.95, 0.05 → mean 0.6667.
// Two attributed as taste picks, the skipped one as a fresh pick (#1249).
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, &taste, 1.0, false)
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, &taste, 0.95, false)
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, &fresh, 0.05, true)
// A radio session play collapses into the "radio" family.
seedSourcedPlay(t, h, user.ID, tk.ID, session, &radioA, nil, 0.8, false)
// Manual play (NULL source) — the baseline row.
seedSourcedPlay(t, h, user.ID, tk.ID, session, nil, nil, 1.0, false)
req := httptest.NewRequest(http.MethodGet, "/api/me/recommendation-metrics", nil)
req = withUser(req, user)
rec := httptest.NewRecorder()
newMetricsRouter(h).ServeHTTP(rec, req)
if rec.Code != http.StatusOK {
t.Fatalf("status = %d, want 200", rec.Code)
}
var resp recommendationMetricsResp
if err := json.Unmarshal(rec.Body.Bytes(), &resp); err != nil {
t.Fatalf("decode: %v", err)
}
if resp.WindowDays != recMetricsDefaultDays {
t.Errorf("window_days = %d, want %d", resp.WindowDays, recMetricsDefaultDays)
}
if resp.Baseline == nil || resp.Baseline.Plays != 1 {
t.Fatalf("baseline = %+v, want plays=1", resp.Baseline)
}
fy := findSurface(resp, "for_you")
if fy == nil {
t.Fatal("for_you metrics missing")
}
if fy.Plays != 3 || fy.Skips != 1 {
t.Errorf("for_you plays/skips = %d/%d, want 3/1", fy.Plays, fy.Skips)
}
if fy.SkipRate < 0.32 || fy.SkipRate > 0.34 {
t.Errorf("for_you skip_rate = %.3f, want ~0.333", fy.SkipRate)
}
if fy.AvgCompletion < 0.66 || fy.AvgCompletion > 0.67 {
t.Errorf("for_you avg_completion = %.4f, want ~0.6667", fy.AvgCompletion)
}
// Pick-kind attribution surfaces as the For You breakdown (#1249).
if len(fy.Breakdown) != 2 {
t.Fatalf("for_you breakdown rows = %d, want 2 (taste, fresh)", len(fy.Breakdown))
}
if b := fy.Breakdown[0]; b.Key != "for_you_taste" || b.Plays != 2 || b.Skips != 0 {
t.Errorf("breakdown[0] = %+v, want for_you_taste plays=2 skips=0", b)
}
if b := fy.Breakdown[1]; b.Key != "for_you_fresh" || b.Plays != 1 || b.Skips != 1 {
t.Errorf("breakdown[1] = %+v, want for_you_fresh plays=1 skips=1", b)
}
if radio := findSurface(resp, "radio"); radio == nil || radio.Plays != 1 {
t.Errorf("radio family = %+v, want plays=1 (collapsed from radio:<uuid>)", radio)
}
}