Milestone 127: recommendation quality — provenance, tiered mixes, For You v2, tuning lab #107

Merged
bvandeusen merged 11 commits from dev into main 2026-07-03 10:13:50 -04:00
8 changed files with 391 additions and 111 deletions
Showing only changes of commit 60533073ad - Show all commits
+169 -29
View File
@@ -2,7 +2,9 @@ package api
import (
"net/http"
"sort"
"strconv"
"strings"
"git.fabledsword.com/bvandeusen/minstrel/internal/apierror"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
@@ -11,28 +13,135 @@ import (
const (
recMetricsDefaultDays = 30
recMetricsMaxDays = 365
// recMetricsLowVolume marks a family as low-confidence rather than
// hiding it: with fewer plays than this a skip rate is anecdote, not
// signal, but silently dropping the row would misread as "surface
// unused". The web renders low-confidence rows dimmed.
recMetricsLowVolume = 20
)
// recommendationMetric is one recommendation surface's outcomes.
type recommendationMetric struct {
Source string `json:"source"` // 'for_you' | 'discover' | mixes
Plays int64 `json:"plays"` // plays launched from this surface
// Surface intents (milestone #127): each family is judged against its
// job, not one global bar — discovery mixes are EXPECTED to run higher
// skip rates than the go-to surfaces.
const (
intentGoTo = "go_to"
intentDiscovery = "discovery"
intentDirect = "direct"
)
// surfaceMetric is one bucketed surface family's outcomes.
type surfaceMetric struct {
Key string `json:"key"` // stable family key ("for_you", "radio", …)
Label string `json:"label"` // display label
Plays int64 `json:"plays"` // plays launched from this family
Skips int64 `json:"skips"` // of those, marked skipped
SkipRate float64 `json:"skip_rate"` // skips / plays, [0,1]
AvgCompletion float64 `json:"avg_completion"` // mean completion ratio, [0,1]
LowConfidence bool `json:"low_confidence"` // plays < recMetricsLowVolume
}
// surfaceGroup is one intent band of surface families.
type surfaceGroup struct {
Intent string `json:"intent"` // go_to | discovery | direct
Label string `json:"label"`
Surfaces []surfaceMetric `json:"surfaces"`
}
type recommendationMetricsResp struct {
WindowDays int `json:"window_days"`
Sources []recommendationMetric `json:"sources"`
WindowDays int `json:"window_days"`
// Baseline is the control group: plays the user picked manually
// (source IS NULL). Surfaces are judged as deltas against it; nil
// when the window holds no manual plays.
Baseline *surfaceMetric `json:"baseline"`
Groups []surfaceGroup `json:"groups"`
}
// recFamily is the bucketing target for a raw play_events.source value.
type recFamily struct {
key string
label string
intent string
}
// bucketRecSource maps a raw client-stamped source string to its stable
// family. One-off sources (album:<uuid>, radio:<uuid>) collapse into
// their family so the table stays readable at any library size.
func bucketRecSource(src string) recFamily {
switch {
case src == "for_you":
return recFamily{"for_you", "For You", intentGoTo}
case src == "songs_like_artist":
return recFamily{"songs_like_artist", "Songs like…", intentGoTo}
case src == "radio" || strings.HasPrefix(src, "radio:"):
return recFamily{"radio", "Radio", intentGoTo}
case src == "discover":
return recFamily{"discover", "Discover", intentDiscovery}
case src == "deep_cuts":
return recFamily{"deep_cuts", "Deep cuts", intentDiscovery}
case src == "rediscover":
return recFamily{"rediscover", "Rediscover", intentDiscovery}
case src == "new_for_you":
return recFamily{"new_for_you", "New for you", intentDiscovery}
case src == "on_this_day":
return recFamily{"on_this_day", "On this day", intentDiscovery}
case src == "first_listens":
return recFamily{"first_listens", "First listens", intentDiscovery}
case strings.HasPrefix(src, "album:"):
return recFamily{"direct_album", "Album plays", intentDirect}
case strings.HasPrefix(src, "artist:"):
return recFamily{"direct_artist", "Artist plays", intentDirect}
case strings.HasPrefix(src, "offline:"):
return recFamily{"offline", "Offline pools", intentDirect}
case strings.HasPrefix(src, "home:"):
return recFamily{"home", "Home sections", intentDirect}
case src == "history":
return recFamily{"history", "History", intentDirect}
default:
return recFamily{"other", "Other", intentDirect}
}
}
// familyAccum merges raw source rows into one family, carrying the
// completion sample count so the merged average stays play-weighted.
type familyAccum struct {
fam recFamily
plays int64
skips int64
completionN int64
// completionSum is avg*count re-expanded, so merging N raw rows
// reduces to a single weighted division at the end.
completionSum float64
}
func (a *familyAccum) add(row dbq.RecommendationSourceMetricsForUserRow) {
a.plays += row.Plays
a.skips += row.Skips
a.completionN += row.CompletionN
a.completionSum += row.AvgCompletion * float64(row.CompletionN)
}
func (a *familyAccum) metric() surfaceMetric {
m := surfaceMetric{
Key: a.fam.key,
Label: a.fam.label,
Plays: a.plays,
Skips: a.skips,
LowConfidence: a.plays < recMetricsLowVolume,
}
if a.plays > 0 {
m.SkipRate = float64(a.skips) / float64(a.plays)
}
if a.completionN > 0 {
m.AvgCompletion = a.completionSum / float64(a.completionN)
}
return m
}
// handleGetRecommendationMetrics implements GET /api/me/recommendation-metrics.
// Per-source play outcomes (plays / skips / skip-rate / avg-completion) for the
// caller over the last `days` (default 30, capped at 365), so the operator can
// see which recommendation surfaces are landing and tune the taste weights.
// Only plays tagged with a system-playlist source count; library/radio plays
// (no source) are excluded.
// Bucketed per-surface-family outcomes for the caller over the last `days`
// (default 30, capped at 365), grouped by surface intent and anchored by the
// manual-plays baseline so the numbers are judgeable, not just observable.
func (h *handlers) handleGetRecommendationMetrics(w http.ResponseWriter, r *http.Request) {
caller, ok := requireUser(w, r)
if !ok {
@@ -51,28 +160,59 @@ func (h *handlers) handleGetRecommendationMetrics(w http.ResponseWriter, r *http
return
}
out := recommendationMetricsResp{
WindowDays: days,
Sources: make([]recommendationMetric, 0, len(rows)),
}
writeJSON(w, http.StatusOK, bucketMetricsResponse(days, rows))
}
// bucketMetricsResponse folds the raw per-source rows into the grouped,
// baseline-anchored response shape. Split from the handler for pure-unit
// testability.
func bucketMetricsResponse(
days int, rows []dbq.RecommendationSourceMetricsForUserRow,
) recommendationMetricsResp {
baseline := &familyAccum{fam: recFamily{"manual", "Manual library plays", ""}}
families := map[string]*familyAccum{}
for _, row := range rows {
source := ""
if row.Source != nil {
source = *row.Source
if row.Source == nil || *row.Source == "" {
baseline.add(row)
continue
}
var skipRate float64
if row.Plays > 0 {
skipRate = float64(row.Skips) / float64(row.Plays)
fam := bucketRecSource(*row.Source)
acc, exists := families[fam.key]
if !exists {
acc = &familyAccum{fam: fam}
families[fam.key] = acc
}
out.Sources = append(out.Sources, recommendationMetric{
Source: source,
Plays: row.Plays,
Skips: row.Skips,
SkipRate: skipRate,
AvgCompletion: row.AvgCompletion,
})
acc.add(row)
}
writeJSON(w, http.StatusOK, out)
resp := recommendationMetricsResp{WindowDays: days, Groups: []surfaceGroup{}}
if baseline.plays > 0 {
m := baseline.metric()
resp.Baseline = &m
}
for _, g := range []struct{ intent, label string }{
{intentGoTo, "Go-to surfaces"},
{intentDiscovery, "Discovery mixes"},
{intentDirect, "Direct plays"},
} {
group := surfaceGroup{Intent: g.intent, Label: g.label}
for _, acc := range families {
if acc.fam.intent == g.intent {
group.Surfaces = append(group.Surfaces, acc.metric())
}
}
if len(group.Surfaces) == 0 {
continue
}
sort.Slice(group.Surfaces, func(i, j int) bool {
if group.Surfaces[i].Plays != group.Surfaces[j].Plays {
return group.Surfaces[i].Plays > group.Surfaces[j].Plays
}
return group.Surfaces[i].Key < group.Surfaces[j].Key
})
resp.Groups = append(resp.Groups, group)
}
return resp
}
// parseMetricsDays reads the `days` query param (default 30, capped at 365).
+84 -16
View File
@@ -11,6 +11,8 @@ import (
"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 {
@@ -20,7 +22,7 @@ func newMetricsRouter(h *handlers) chi.Router {
}
// seedSourcedPlay inserts a play_event with an explicit source + completion +
// skip flag. A nil source inserts NULL (library/radio play).
// skip flag. A nil source inserts NULL (manual library play → baseline).
func seedSourcedPlay(
t *testing.T, h *handlers, userID, trackID, sessionID pgtype.UUID,
source *string, completion float64, skipped bool,
@@ -45,7 +47,77 @@ func TestRecommendationMetrics_NoSession401(t *testing.T) {
}
}
func TestRecommendationMetrics_AggregatesBySourceExcludingNull(t *testing.T) {
// 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")
}
// 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 TestRecommendationMetrics_BucketsWithBaseline(t *testing.T) {
if os.Getenv("MINSTREL_TEST_DATABASE_URL") == "" {
t.Skip("MINSTREL_TEST_DATABASE_URL not set")
}
@@ -57,14 +129,14 @@ func TestRecommendationMetrics_AggregatesBySourceExcludingNull(t *testing.T) {
session := seedPlaySession(t, pool, user.ID, time.Now())
forYou := "for_you"
discover := "discover"
radioA := "radio:11111111-1111-1111-1111-111111111111"
// for_you: 3 plays, 1 skipped; completions 1.0, 0.95, 0.05 → mean 0.6667.
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, 1.0, false)
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, 0.95, false)
seedSourcedPlay(t, h, user.ID, tk.ID, session, &forYou, 0.05, true)
// discover: 1 play.
seedSourcedPlay(t, h, user.ID, tk.ID, session, &discover, 0.8, false)
// library play (NULL source) — must be excluded.
// A radio session play collapses into the "radio" family.
seedSourcedPlay(t, h, user.ID, tk.ID, session, &radioA, 0.8, false)
// Manual play (NULL source) — the baseline row.
seedSourcedPlay(t, h, user.ID, tk.ID, session, nil, 1.0, false)
req := httptest.NewRequest(http.MethodGet, "/api/me/recommendation-metrics", nil)
@@ -82,15 +154,11 @@ func TestRecommendationMetrics_AggregatesBySourceExcludingNull(t *testing.T) {
if resp.WindowDays != recMetricsDefaultDays {
t.Errorf("window_days = %d, want %d", resp.WindowDays, recMetricsDefaultDays)
}
bySource := map[string]recommendationMetric{}
for _, m := range resp.Sources {
bySource[m.Source] = m
if resp.Baseline == nil || resp.Baseline.Plays != 1 {
t.Fatalf("baseline = %+v, want plays=1", resp.Baseline)
}
if _, present := bySource[""]; present {
t.Error("NULL-source (library) plays should be excluded")
}
fy, ok := bySource["for_you"]
if !ok {
fy := findSurface(resp, "for_you")
if fy == nil {
t.Fatal("for_you metrics missing")
}
if fy.Plays != 3 || fy.Skips != 1 {
@@ -102,7 +170,7 @@ func TestRecommendationMetrics_AggregatesBySourceExcludingNull(t *testing.T) {
if fy.AvgCompletion < 0.66 || fy.AvgCompletion > 0.67 {
t.Errorf("for_you avg_completion = %.4f, want ~0.6667", fy.AvgCompletion)
}
if d, ok := bySource["discover"]; !ok || d.Plays != 1 || d.Skips != 0 {
t.Errorf("discover metrics = %+v, want plays=1 skips=0", d)
if radio := findSurface(resp, "radio"); radio == nil || radio.Plays != 1 {
t.Errorf("radio family = %+v, want plays=1 (collapsed from radio:<uuid>)", radio)
}
}
+11 -7
View File
@@ -17,12 +17,10 @@ SELECT
pe.source,
count(*)::bigint AS plays,
count(*) FILTER (WHERE pe.was_skipped)::bigint AS skips,
COALESCE(
avg(pe.completion_ratio) FILTER (WHERE pe.completion_ratio IS NOT NULL),
0)::float8 AS avg_completion
count(pe.completion_ratio)::bigint AS completion_n,
COALESCE(avg(pe.completion_ratio), 0)::float8 AS avg_completion
FROM play_events pe
WHERE pe.user_id = $1
AND pe.source IS NOT NULL
AND pe.started_at > now() - ($2::float8 * INTERVAL '1 day')
GROUP BY pe.source
ORDER BY plays DESC
@@ -37,16 +35,21 @@ type RecommendationSourceMetricsForUserRow struct {
Source *string
Plays int64
Skips int64
CompletionN int64
AvgCompletion float64
}
// Recommendation observability (#796 phase 4). Per-source play outcomes so the
// operator can see whether each recommendation surface is landing and tune the
// taste weights. Source is stamped on play_events when a play is launched from
// a system-playlist surface ('for_you' | 'discover' | the discovery mixes);
// NULL for library / radio / user-playlist plays, which are excluded here.
// a recommendation surface; NULL means the user picked the track manually —
// those rows are INCLUDED here as the baseline control group the surfaces are
// judged against (milestone #127: delta-vs-baseline is what makes the numbers
// actionable). Raw source strings are bucketed into stable surface families in
// the Go handler; completion_n is carried so family merges can weight
// avg_completion correctly.
// $1 user_id, $2 window_days. plays/skips are counts; avg_completion is the
// mean completion ratio over plays that recorded one (0 when none did).
// mean completion ratio over the completion_n plays that recorded one.
func (q *Queries) RecommendationSourceMetricsForUser(ctx context.Context, arg RecommendationSourceMetricsForUserParams) ([]RecommendationSourceMetricsForUserRow, error) {
rows, err := q.db.Query(ctx, recommendationSourceMetricsForUser, arg.UserID, arg.Column2)
if err != nil {
@@ -60,6 +63,7 @@ func (q *Queries) RecommendationSourceMetricsForUser(ctx context.Context, arg Re
&i.Source,
&i.Plays,
&i.Skips,
&i.CompletionN,
&i.AvgCompletion,
); err != nil {
return nil, err
@@ -1,22 +1,24 @@
-- Recommendation observability (#796 phase 4). Per-source play outcomes so the
-- operator can see whether each recommendation surface is landing and tune the
-- taste weights. Source is stamped on play_events when a play is launched from
-- a system-playlist surface ('for_you' | 'discover' | the discovery mixes);
-- NULL for library / radio / user-playlist plays, which are excluded here.
-- a recommendation surface; NULL means the user picked the track manually —
-- those rows are INCLUDED here as the baseline control group the surfaces are
-- judged against (milestone #127: delta-vs-baseline is what makes the numbers
-- actionable). Raw source strings are bucketed into stable surface families in
-- the Go handler; completion_n is carried so family merges can weight
-- avg_completion correctly.
-- name: RecommendationSourceMetricsForUser :many
-- $1 user_id, $2 window_days. plays/skips are counts; avg_completion is the
-- mean completion ratio over plays that recorded one (0 when none did).
-- mean completion ratio over the completion_n plays that recorded one.
SELECT
pe.source,
count(*)::bigint AS plays,
count(*) FILTER (WHERE pe.was_skipped)::bigint AS skips,
COALESCE(
avg(pe.completion_ratio) FILTER (WHERE pe.completion_ratio IS NOT NULL),
0)::float8 AS avg_completion
count(pe.completion_ratio)::bigint AS completion_n,
COALESCE(avg(pe.completion_ratio), 0)::float8 AS avg_completion
FROM play_events pe
WHERE pe.user_id = $1
AND pe.source IS NOT NULL
AND pe.started_at > now() - ($2::float8 * INTERVAL '1 day')
GROUP BY pe.source
ORDER BY plays DESC;
+17 -20
View File
@@ -1,18 +1,31 @@
import { createQuery } from '@tanstack/svelte-query';
import { api } from './client';
// Mirrors internal/api/me_recommendation_metrics.go.
export type RecommendationMetric = {
source: string;
// Mirrors internal/api/me_recommendation_metrics.go: raw play sources are
// bucketed server-side into stable surface families, grouped by intent, and
// anchored by the manual-plays baseline (milestone #127).
export type SurfaceMetric = {
key: string;
label: string;
plays: number;
skips: number;
skip_rate: number;
avg_completion: number;
low_confidence: boolean;
};
export type SurfaceIntent = 'go_to' | 'discovery' | 'direct';
export type SurfaceGroup = {
intent: SurfaceIntent;
label: string;
surfaces: SurfaceMetric[];
};
export type RecommendationMetrics = {
window_days: number;
sources: RecommendationMetric[];
baseline: SurfaceMetric | null;
groups: SurfaceGroup[];
};
export function getRecommendationMetrics(): Promise<RecommendationMetrics> {
@@ -28,19 +41,3 @@ export function createRecommendationMetricsQuery() {
staleTime: 60_000
});
}
// Friendly labels for the system-playlist source keys (play_events.source).
const SOURCE_LABELS: Record<string, string> = {
for_you: 'For You',
discover: 'Discover',
deep_cuts: 'Deep cuts',
rediscover: 'Rediscover',
new_for_you: 'New for you',
on_this_day: 'On this day',
first_listens: 'First listens',
songs_like_artist: 'Songs like…'
};
export function sourceLabel(source: string): string {
return SOURCE_LABELS[source] ?? source;
}
+97 -26
View File
@@ -10,8 +10,9 @@
} from '$lib/api/listenbrainz';
import {
createRecommendationMetricsQuery,
sourceLabel,
type RecommendationMetrics
type RecommendationMetrics,
type SurfaceIntent,
type SurfaceMetric
} from '$lib/api/metrics';
import { theme, setTheme, type ThemePreference } from '$lib/stores/theme.svelte';
import { player, setCrossfade } from '$lib/player/store.svelte';
@@ -30,6 +31,34 @@
const status = createLBStatusQuery() as CreateQueryResult<LBStatus>;
const metrics = createRecommendationMetricsQuery() as CreateQueryResult<RecommendationMetrics>;
// Per-intent expectation copy: each surface band is judged against its
// job — discovery mixes are supposed to run hotter skip rates.
const intentHints: Record<SurfaceIntent, string> = {
go_to: 'Everyday surfaces — these should beat your own picking.',
discovery: 'Exploration surfaces — higher skip rates here are expected and healthy.',
direct: 'Music you chose yourself — naturally close to the baseline.'
};
function pct(v: number): string {
return `${(v * 100).toFixed(0)}%`;
}
// Delta in percentage points vs the baseline, signed ("+12" / "5").
function deltaPts(value: number, baseline: number): string {
const pts = Math.round((value - baseline) * 100);
return pts > 0 ? `+${pts}` : `${pts}`;
}
// A surface's skip delta is "worse" when it skips more than the
// baseline; completion delta is "worse" when it completes less.
function skipDeltaClass(m: SurfaceMetric, baseline: SurfaceMetric): string {
return m.skip_rate > baseline.skip_rate ? 'text-danger' : 'text-text-secondary';
}
function completionDeltaClass(m: SurfaceMetric, baseline: SurfaceMetric): string {
return m.avg_completion < baseline.avg_completion ? 'text-danger' : 'text-text-secondary';
}
const tokenMutation = createTokenMutation(queryClient);
const enabledMutation = createEnabledMutation(queryClient);
@@ -278,37 +307,79 @@
<h2 class="text-lg font-semibold">Recommendation metrics</h2>
<p class="text-sm text-text-secondary">
How plays launched from each recommendation surface land, over the last
{$metrics.data?.window_days ?? 30} days. Lower skip rate and higher average
completion mean the surface is hitting.
{$metrics.data?.window_days ?? 30} days — compared against the baseline of
music you picked yourself. Deltas are percentage points vs that baseline.
</p>
{#if $metrics.isPending}
<p class="text-sm text-text-secondary">Loading…</p>
{:else if $metrics.isError}
<p class="text-sm text-text-secondary">Couldn't load metrics.</p>
{:else if $metrics.data && $metrics.data.sources.length > 0}
<table class="w-full text-sm">
<thead>
<tr class="text-left text-text-secondary">
<th class="py-1 font-medium">Surface</th>
<th class="py-1 text-right font-medium">Plays</th>
<th class="py-1 text-right font-medium">Skip rate</th>
<th class="py-1 text-right font-medium">Avg completion</th>
</tr>
</thead>
<tbody>
{#each $metrics.data.sources as m (m.source)}
<tr class="border-t border-border">
<td class="py-1">{sourceLabel(m.source)}</td>
<td class="py-1 text-right tabular-nums">{m.plays}</td>
<td class="py-1 text-right tabular-nums">{(m.skip_rate * 100).toFixed(0)}%</td>
<td class="py-1 text-right tabular-nums">{(m.avg_completion * 100).toFixed(0)}%</td>
</tr>
{/each}
</tbody>
</table>
{:else if $metrics.data && ($metrics.data.groups.length > 0 || $metrics.data.baseline)}
{@const baseline = $metrics.data.baseline}
{#if baseline}
<p class="rounded bg-background px-3 py-2 text-sm">
<span class="font-medium">Baseline — manual plays:</span>
<span class="text-text-secondary">
{baseline.plays} plays · {pct(baseline.skip_rate)} skip ·
{pct(baseline.avg_completion)} completion
</span>
</p>
{:else}
<p class="text-sm text-text-secondary">
No manual plays in this window yet, so deltas are hidden — raw rates only.
</p>
{/if}
{#each $metrics.data.groups as group (group.intent)}
<div class="space-y-1">
<h3 class="text-sm font-medium">{group.label}</h3>
<p class="text-xs text-text-secondary">{intentHints[group.intent]}</p>
<table class="w-full text-sm">
<thead>
<tr class="text-left text-text-secondary">
<th class="py-1 font-medium">Surface</th>
<th class="py-1 text-right font-medium">Plays</th>
<th class="py-1 text-right font-medium">Skip rate</th>
<th class="py-1 text-right font-medium">Avg completion</th>
</tr>
</thead>
<tbody>
{#each group.surfaces as m (m.key)}
<tr
class="border-t border-border"
class:opacity-60={m.low_confidence}
title={m.low_confidence
? 'Fewer than 20 plays — treat these rates as anecdote, not signal.'
: undefined}
>
<td class="py-1">
{m.label}{#if m.low_confidence}<span class="ml-1 text-xs text-text-secondary">· low data</span>{/if}
</td>
<td class="py-1 text-right tabular-nums">{m.plays}</td>
<td class="py-1 text-right tabular-nums">
{pct(m.skip_rate)}
{#if baseline}
<span class="ml-1 text-xs {skipDeltaClass(m, baseline)}">
{deltaPts(m.skip_rate, baseline.skip_rate)}
</span>
{/if}
</td>
<td class="py-1 text-right tabular-nums">
{pct(m.avg_completion)}
{#if baseline}
<span class="ml-1 text-xs {completionDeltaClass(m, baseline)}">
{deltaPts(m.avg_completion, baseline.avg_completion)}
</span>
{/if}
</td>
</tr>
{/each}
</tbody>
</table>
</div>
{/each}
{:else}
<p class="text-sm text-text-secondary">
No recommendation plays yet. Play something from For You, Discover, or a mix.
No plays recorded yet. Play something from For You, Discover, or a mix.
</p>
{/if}
</section>
+2 -3
View File
@@ -28,11 +28,10 @@ vi.mock('$lib/api/listenbrainz', () => {
vi.mock('$lib/api/metrics', () => ({
createRecommendationMetricsQuery: () => ({
subscribe: (run: (v: unknown) => void) => {
run({ isPending: false, isError: false, data: { window_days: 30, sources: [] } });
run({ isPending: false, isError: false, data: { window_days: 30, baseline: null, groups: [] } });
return () => {};
}
}),
sourceLabel: (s: string) => s
})
}));
beforeEach(() => {
+2 -3
View File
@@ -23,11 +23,10 @@ vi.mock('$lib/api/me', () => ({
vi.mock('$lib/api/metrics', () => ({
createRecommendationMetricsQuery: () => ({
subscribe: (run: (v: unknown) => void) => {
run({ isPending: false, isError: false, data: { window_days: 30, sources: [] } });
run({ isPending: false, isError: false, data: { window_days: 30, baseline: null, groups: [] } });
return () => {};
}
}),
sourceLabel: (s: string) => s
})
}));
import SettingsPage from './+page.svelte';