Files
minstrel/web/src/routes/admin/tuning/+page.svelte
T
bvandeusenandClaude Opus 4.8 f0c08e7326
test-go / test (push) Successful in 34s
test-web / test (push) Successful in 40s
test-go / integration (push) Successful in 4m44s
feat(taste): mood taste facet — #1534
Milestone #160 Opt 2b (mood half of the era+mood option). A fourth taste
facet alongside artists + genre tags + eras: signed weights over canonical
mood buckets (melancholic / energetic / chill / …) derived from a track's
enriched folksonomy tags (#1490).

- internal/mood: shared vocabulary — Of(tags) maps folksonomy tags to
  canonical mood buckets (synonyms collapse). Imported by both the taste
  builder and the scorer so a track's mood is derived identically.
- Migration 0047: taste_profile_moods table + taste_tuning.mood_scale
  (DEFAULT 0.5).
- Build side (internal/taste): Config.MoodScale ([0,1] damper, mirrors
  EraScale); accumulate folds each play/like's mood buckets at
  base*MoodScale; persist atomic-replaces the mood rows.
- Scorer (internal/recommendation): TasteProfile gains a mood term
  (own tanh scale + additive 0.12 share, so it never weakens the existing
  signal when a track has no mood tags). Match now takes the candidate's
  mood buckets; loaded per candidate (ListTrackTagsForTracks → mood.Of) in
  the primary similarity loader only — the near-whole-library fallback
  pool passes nil (mood → 0) to avoid a full-library tag scan.
- Tuning lab: mood_scale threaded through recsettings + admin API + web
  card ("Mood weight" row) + Go/web tests.

Coverage is partial (grows with tag enrichment; richer once Last.fm is
keyed), so mood is a supplement — neutral for tracks with no mood tags.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-14 10:32:41 -04:00

439 lines
17 KiB
Svelte
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.
<script lang="ts">
import { pageTitle } from '$lib/branding';
import {
getTuning,
patchTuning,
resetTuning,
getTrends,
type TuningScope,
type TuningSnapshot,
type WeightProfile,
type TasteTuning,
type TrendsResponse,
type TrendSeries,
type TrendMarker
} from '$lib/api/tuning';
import { errMessage } from '$lib/api/errors';
import { pushToast } from '$lib/stores/toast.svelte';
// The defaults-discovery lab (#1250): DB-backed scoring-weight
// profiles + taste-build knobs with live effect. This card exists to
// FIND good values — found-good values get baked into shipped
// defaults, so end users and other operators never need it.
const weightFields: { key: keyof WeightProfile; label: string; hint: string }[] = [
{ key: 'base_weight', label: 'Base weight', hint: 'Floor score every candidate starts from.' },
{ key: 'like_boost', label: 'Like boost', hint: 'Added when the track is liked.' },
{ key: 'recency_weight', label: 'Recency weight', hint: 'Rewards tracks not played recently (030d ramp).' },
{ key: 'skip_penalty', label: 'Skip penalty', hint: 'Subtracts skips/plays ratio.' },
{ key: 'jitter_magnitude', label: 'Jitter', hint: 'Random reshuffle magnitude for near-ties.' },
{ key: 'context_weight', label: 'Context weight', hint: 'Session-vector similarity contribution.' },
{ key: 'similarity_weight', label: 'Similarity weight', hint: 'Seed-similarity contribution.' },
{ key: 'taste_weight', label: 'Taste weight', hint: 'Learned taste-profile fit, in [-1, +1].' },
{ key: 'context_time_weight', label: 'Time-of-day weight', hint: "Artist's time-of-day/weekday affinity for the current context, in [-1, +1]. 0 = ignore when you listen." }
];
const tasteFields: { key: keyof TasteTuning; label: string; hint: string }[] = [
{ key: 'half_life_days', label: 'Half-life (days)', hint: "A play's influence halves every this-many days." },
{ key: 'engagement_hard_skip', label: 'Hard-skip point', hint: 'Completion at/below which a play reads 1.' },
{ key: 'engagement_neutral', label: 'Neutral point', hint: 'Completion at which a play reads 0.' },
{ key: 'engagement_full', label: 'Full point', hint: 'Completion at/above which a play reads +1.' },
{ key: 'enriched_tag_scale', label: 'Enriched tag weight', hint: 'How much folksonomy tags (MusicBrainz/Last.fm) count vs raw file genre, in [0, 1]. 0 = genre only.' },
{ key: 'era_scale', label: 'Era weight', hint: 'How strongly a decade-play imprints on the era facet, in [0, 1]. 0 = era ignored.' },
{ key: 'mood_scale', label: 'Mood weight', hint: 'How strongly a mood-tagged play imprints on the mood facet (from folksonomy tags), in [0, 1]. 0 = mood ignored.' }
];
const profileScopes: { scope: 'radio' | 'daily_mix'; label: string; blurb: string }[] = [
{ scope: 'radio', label: 'Radio', blurb: 'Seed-directed listening — the user picked a direction.' },
{ scope: 'daily_mix', label: 'Daily mixes', blurb: 'For You, Songs like…, and the discovery mixes.' }
];
let snapshot = $state<TuningSnapshot | null>(null);
let loadFailed = $state(false);
// Editable copies, string-typed for the inputs; parsed on save.
let form = $state<Record<string, Record<string, string>>>({});
let saving = $state<TuningScope | null>(null);
function fillForm(snap: TuningSnapshot) {
const f: Record<string, Record<string, string>> = { radio: {}, daily_mix: {}, taste: {} };
for (const p of ['radio', 'daily_mix'] as const) {
for (const { key } of weightFields) f[p][key] = String(snap.profiles[p][key]);
}
for (const { key } of tasteFields) f.taste[key] = String(snap.taste[key]);
form = f;
}
$effect(() => {
getTuning()
.then((snap) => {
fillForm(snap);
snapshot = snap;
})
.catch(() => {
loadFailed = true;
});
});
// A knob deviates when its CURRENT SAVED value differs from shipped;
// the dot marks where this install has drifted from defaults.
function deviates(scope: 'radio' | 'daily_mix' | 'taste', key: string): boolean {
if (!snapshot) return false;
if (scope === 'taste') {
return snapshot.taste[key as keyof TasteTuning] !== snapshot.shipped.taste[key as keyof TasteTuning];
}
return (
snapshot.profiles[scope][key as keyof WeightProfile] !==
snapshot.shipped.profiles[scope][key as keyof WeightProfile]
);
}
function currentValue(scope: TuningScope, key: string): number {
if (!snapshot) return 0;
if (scope === 'taste') return snapshot.taste[key as keyof TasteTuning];
return snapshot.profiles[scope][key as keyof WeightProfile];
}
async function save(scope: TuningScope) {
if (!snapshot) return;
const values: Record<string, number> = {};
for (const [key, raw] of Object.entries(form[scope] ?? {})) {
const v = Number(raw);
if (!Number.isFinite(v)) {
pushToast(`${key} is not a number.`, 'error');
return;
}
if (v !== currentValue(scope, key)) values[key] = v;
}
if (Object.keys(values).length === 0) {
pushToast('Nothing changed.');
return;
}
saving = scope;
try {
snapshot = await patchTuning(scope, values);
fillForm(snapshot);
pushToast('Saved — takes effect on the next scoring pass.');
} catch (e: unknown) {
pushToast(`Save failed: ${errMessage(e)}`, 'error');
} finally {
saving = null;
}
}
async function reset(scope: TuningScope) {
saving = scope;
try {
snapshot = await resetTuning(scope);
fillForm(snapshot);
pushToast('Reset to shipped defaults.');
} catch (e: unknown) {
pushToast(`Reset failed: ${errMessage(e)}`, 'error');
} finally {
saving = null;
}
}
// Trends (#1251): weekly skip-rate sparklines per surface with
// knob-turn markers — the verify half of the tune→verify loop.
let trends = $state<TrendsResponse | null>(null);
let trendsFailed = $state(false);
$effect(() => {
getTrends()
.then((t) => {
trends = t;
})
.catch(() => {
trendsFailed = true;
});
});
const SPARK_W = 220;
const SPARK_H = 36;
const TREND_LOW_VOLUME = 20;
// The week axis is the sorted union of every series' buckets, so all
// sparklines and markers share one x scale.
const weekAxis = $derived.by(() => {
if (!trends) return [] as string[];
const set = new Set<string>();
for (const s of trends.series) for (const p of s.points) set.add(p.week_start);
return [...set].sort();
});
function xFor(week: string): number {
const i = weekAxis.indexOf(week);
if (i < 0 || weekAxis.length < 2) return 0;
return (i / (weekAxis.length - 1)) * SPARK_W;
}
// Polyline of the series' weekly skip rate on a fixed [0,1] y-scale
// (higher = worse, drawn upward) so rows are visually comparable.
function sparkPoints(s: TrendSeries): string {
return s.points
.map((p) => `${xFor(p.week_start).toFixed(1)},${(SPARK_H - p.skip_rate * SPARK_H).toFixed(1)}`)
.join(' ');
}
// A marker lands on the latest axis week that starts at/before it.
function markerX(m: TrendMarker): number {
const day = m.changed_at.slice(0, 10);
let idx = -1;
for (let i = 0; i < weekAxis.length; i++) {
if (weekAxis[i] <= day) idx = i;
}
if (idx < 0 || weekAxis.length < 2) return 0;
return (idx / (weekAxis.length - 1)) * SPARK_W;
}
function windowTasteHitRate(s: TrendSeries): number {
let plays = 0;
let hits = 0;
for (const p of s.points) {
plays += p.plays;
hits += p.taste_hit_rate * p.plays;
}
return plays > 0 ? hits / plays : 0;
}
function latest(s: TrendSeries): { skip: number; completion: number } {
const last = s.points[s.points.length - 1];
return last ? { skip: last.skip_rate, completion: last.avg_completion } : { skip: 0, completion: 0 };
}
function pct(v: number): string {
return `${(v * 100).toFixed(0)}%`;
}
function markerSummary(m: TrendMarker): string {
const when = m.changed_at.slice(0, 10);
if (m.action === 'reset') return `${when}${m.scope} reset to defaults`;
const fields = (m.changes ?? []).map((c) => `${c.field} ${c.old}${c.new}`).join(', ');
return `${when}${m.scope}: ${fields}`;
}
</script>
<svelte:head>
<title>{pageTitle('Tuning')}</title>
</svelte:head>
<div class="space-y-6 p-4">
<div>
<h1 class="text-xl font-semibold">Recommendation tuning</h1>
<p class="mt-1 max-w-3xl text-sm text-text-secondary">
The defaults-discovery lab. Changes apply live — radio on the next request, daily mixes on
the next rebuild — and every change is recorded so the metrics page can tie outcome shifts
to knob turns. Found-good values get baked into shipped defaults; a dot marks knobs that
currently deviate from them.
</p>
</div>
{#if loadFailed}
<p class="text-sm text-text-secondary">Couldn't load tuning settings.</p>
{:else if !snapshot}
<p class="text-sm text-text-secondary">Loading…</p>
{:else}
<section class="grid gap-4 lg:grid-cols-2">
{#each profileScopes as p (p.scope)}
<div class="space-y-3 rounded border border-border bg-surface p-4">
<div>
<h2 class="text-lg font-semibold">{p.label}</h2>
<p class="text-xs text-text-secondary">{p.blurb}</p>
</div>
<div class="space-y-2">
{#each weightFields as f (f.key)}
<div class="grid grid-cols-[1fr_7rem] items-center gap-2">
<label class="text-sm" for="{p.scope}-{f.key}" title={f.hint}>
{f.label}
{#if deviates(p.scope, f.key)}
<span
class="ml-1 inline-block h-1.5 w-1.5 rounded-full bg-accent align-middle"
title="Deviates from the shipped default ({snapshot.shipped.profiles[p.scope][f.key]})"
></span>
{/if}
</label>
<input
id="{p.scope}-{f.key}"
type="number"
step="0.1"
bind:value={form[p.scope][f.key]}
class="w-full rounded border border-border bg-background px-2 py-1 text-right text-sm tabular-nums outline-none focus:border-accent"
/>
</div>
{/each}
</div>
<div class="flex gap-2">
<button
type="button"
disabled={saving !== null}
onclick={() => save(p.scope)}
class="rounded bg-accent px-3 py-1.5 text-sm text-white disabled:opacity-50"
>
Save {p.label.toLowerCase()}
</button>
<button
type="button"
disabled={saving !== null}
onclick={() => reset(p.scope)}
class="rounded border border-border px-3 py-1.5 text-sm text-text-secondary hover:text-text-primary disabled:opacity-50"
>
Reset to defaults
</button>
</div>
</div>
{/each}
</section>
<section class="space-y-3 rounded border border-border bg-surface p-4 lg:max-w-xl">
<div>
<h2 class="text-lg font-semibold">Taste profile build</h2>
<p class="text-xs text-text-secondary">
How plays become the learned taste profile: the influence half-life and the
completion→engagement curve (must stay ordered: hard-skip &lt; neutral &lt; full).
</p>
</div>
<div class="space-y-2">
{#each tasteFields as f (f.key)}
<div class="grid grid-cols-[1fr_7rem] items-center gap-2">
<label class="text-sm" for="taste-{f.key}" title={f.hint}>
{f.label}
{#if deviates('taste', f.key)}
<span
class="ml-1 inline-block h-1.5 w-1.5 rounded-full bg-accent align-middle"
title="Deviates from the shipped default ({snapshot.shipped.taste[f.key]})"
></span>
{/if}
</label>
<input
id="taste-{f.key}"
type="number"
step={f.key === 'half_life_days' ? '1' : '0.05'}
bind:value={form.taste[f.key]}
class="w-full rounded border border-border bg-background px-2 py-1 text-right text-sm tabular-nums outline-none focus:border-accent"
/>
</div>
{/each}
</div>
<div class="flex gap-2">
<button
type="button"
disabled={saving !== null}
onclick={() => save('taste')}
class="rounded bg-accent px-3 py-1.5 text-sm text-white disabled:opacity-50"
>
Save taste
</button>
<button
type="button"
disabled={saving !== null}
onclick={() => reset('taste')}
class="rounded border border-border px-3 py-1.5 text-sm text-text-secondary hover:text-text-primary disabled:opacity-50"
>
Reset to defaults
</button>
</div>
</section>
{/if}
<!-- Weekly trends (#1251): the verify half. Sparklines share one
week axis; dashed ticks mark knob turns so cause→effect reads
off the chart. -->
<section class="space-y-3 rounded border border-border bg-surface p-4">
<div>
<h2 class="text-lg font-semibold">Weekly trends</h2>
<p class="text-xs text-text-secondary">
Skip rate per surface over the last {trends?.weeks ?? 12} weeks (lower is better; all
users aggregated, rates only). Dashed ticks mark tuning changes. Taste hit is the share
of plays whose artist fits the current taste profile.
</p>
</div>
{#if trendsFailed}
<p class="text-sm text-text-secondary">Couldn't load trends.</p>
{:else if !trends}
<p class="text-sm text-text-secondary">Loading…</p>
{:else if trends.series.length === 0}
<p class="text-sm text-text-secondary">
No plays recorded yet — trends appear once listening accumulates.
</p>
{:else}
<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 font-medium">Skip rate by week</th>
<th class="py-1 text-right font-medium">Plays</th>
<th class="py-1 text-right font-medium">Latest skip</th>
<th class="py-1 text-right font-medium">Latest completion</th>
<th class="py-1 text-right font-medium">Taste hit</th>
</tr>
</thead>
<tbody>
{#each trends.series as s (s.key)}
<tr
class="border-t border-border"
class:opacity-60={s.plays < TREND_LOW_VOLUME}
title={s.plays < TREND_LOW_VOLUME
? 'Fewer than 20 plays in the window — treat as anecdote, not signal.'
: undefined}
>
<td class="py-1.5 pr-2">{s.label}</td>
<td class="py-1.5">
<svg
width={SPARK_W}
height={SPARK_H}
viewBox="0 0 {SPARK_W} {SPARK_H}"
role="img"
aria-label="{s.label} weekly skip rate"
data-testid="sparkline-{s.key}"
>
<line x1="0" y1={SPARK_H - 0.5} x2={SPARK_W} y2={SPARK_H - 0.5}
stroke="currentColor" opacity="0.15" />
{#each trends.markers as m, i (i)}
<line
x1={markerX(m)} y1="0" x2={markerX(m)} y2={SPARK_H}
stroke="currentColor" opacity="0.35" stroke-dasharray="2,2"
>
<title>{markerSummary(m)}</title>
</line>
{/each}
{#if s.points.length > 1}
<polyline
class="text-accent"
points={sparkPoints(s)}
fill="none"
stroke="currentColor"
stroke-width="1.5"
/>
{:else if s.points.length === 1}
<circle
class="text-accent"
cx={xFor(s.points[0].week_start)}
cy={SPARK_H - s.points[0].skip_rate * SPARK_H}
r="2" fill="currentColor"
/>
{/if}
</svg>
</td>
<td class="py-1.5 text-right tabular-nums">{s.plays}</td>
<td class="py-1.5 text-right tabular-nums">{pct(latest(s).skip)}</td>
<td class="py-1.5 text-right tabular-nums">{pct(latest(s).completion)}</td>
<td class="py-1.5 text-right tabular-nums">{pct(windowTasteHitRate(s))}</td>
</tr>
{/each}
</tbody>
</table>
{#if trends.markers.length > 0}
<div class="space-y-1">
<h3 class="text-sm font-medium">Tuning changes in this window</h3>
<ul class="space-y-0.5 text-xs text-text-secondary">
{#each trends.markers as m, i (i)}
<li>{markerSummary(m)}</li>
{/each}
</ul>
</div>
{/if}
{/if}
</section>
</div>