feat(tags): folksonomy tag enricher — pluggable provider chain (#1490 Step 2)
test-go / test (push) Successful in 30s
test-go / integration (push) Successful in 4m46s

Milestone #160 Option 1, Step 2. New internal/tags package that enriches
the taste profile's tag facet beyond raw ID3 genre, built so adding a
source later is "implement TrackTagProvider + Register()" — no enricher,
settings, or schema change (operator directive).

Mirrors the internal/coverart pattern:
- Provider interface + package registry (Register/AllProviders/ByID);
  TrackTagProvider fetch capability + TestableProvider for the admin test.
- DB-backed SettingsService over new tag_provider_settings +
  tag_sources_meta (migration 0043) — enable/key/version, boot
  reconciliation, and a provider-hash bump that re-opens 'none' rows when
  the compiled-in provider set changes.
- Slim self-contained httpClient (rate-limit + retry + User-Agent), kept
  local so tag enrichment never depends on coverart internals.

Providers:
- MusicBrainz: keyless, default-ON, recording tags by MBID (rule #26 baseline).
- Last.fm: keyed, default-OFF, track.getTopTags by artist+track — opt-in
  once a key is supplied.

Enricher uses MERGE semantics (differs from coverart's first-success-wins
for a single image): unions tags across every enabled provider, caps to
top-K by weight, and stamps tag_source musicbrainz|lastfm|mixed|none.
Writes are transactional (atomic replace of track_tags).

Unit-tested without a DB: registry mechanics, provider JSON parsing +
weight normalization via httptest, and the pure merge/top-K/source-label
helpers. Wiring (startup + on-scan), integration tests, and the taste
union (Step 3) + Settings UI (Step 4) come next.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-07-13 21:43:58 -04:00
parent d6ee5a304d
commit fbfd5550ff
15 changed files with 1795 additions and 0 deletions
+15
View File
@@ -532,6 +532,21 @@ type SystemPlaylistRun struct {
LastError *string
}
type TagProviderSetting struct {
ProviderID string
Enabled bool
ApiKey *string
DisplayOrder int32
CreatedAt pgtype.Timestamptz
UpdatedAt pgtype.Timestamptz
}
type TagSourcesMetum struct {
ID bool
CurrentVersion int32
LastRegisteredProvidersHash string
}
type TasteProfileArtist struct {
UserID pgtype.UUID
ArtistID pgtype.UUID
+157
View File
@@ -0,0 +1,157 @@
// Code generated by sqlc. DO NOT EDIT.
// versions:
// sqlc v1.31.1
// source: tag_settings.sql
package dbq
import (
"context"
)
const bumpTagSourcesVersion = `-- name: BumpTagSourcesVersion :one
UPDATE tag_sources_meta
SET current_version = current_version + 1
WHERE id = true
RETURNING current_version
`
// Increment + return the new version. Called only when the enabled set
// changes (not on key edits).
func (q *Queries) BumpTagSourcesVersion(ctx context.Context) (int32, error) {
row := q.db.QueryRow(ctx, bumpTagSourcesVersion)
var current_version int32
err := row.Scan(&current_version)
return current_version, err
}
const bumpTagVersionAndSetProvidersHash = `-- name: BumpTagVersionAndSetProvidersHash :one
UPDATE tag_sources_meta
SET current_version = current_version + 1,
last_registered_providers_hash = $1
WHERE id = true
RETURNING current_version
`
// Atomically increment the version and store the new registered-provider
// hash. Called at boot when the compiled-in provider set changed, so
// 'none' rows become eligible for a retry through the new chain.
func (q *Queries) BumpTagVersionAndSetProvidersHash(ctx context.Context, lastRegisteredProvidersHash string) (int32, error) {
row := q.db.QueryRow(ctx, bumpTagVersionAndSetProvidersHash, lastRegisteredProvidersHash)
var current_version int32
err := row.Scan(&current_version)
return current_version, err
}
const getCurrentTagSourcesVersion = `-- name: GetCurrentTagSourcesVersion :one
SELECT current_version FROM tag_sources_meta WHERE id = true
`
func (q *Queries) GetCurrentTagSourcesVersion(ctx context.Context) (int32, error) {
row := q.db.QueryRow(ctx, getCurrentTagSourcesVersion)
var current_version int32
err := row.Scan(&current_version)
return current_version, err
}
const getTagProvidersHash = `-- name: GetTagProvidersHash :one
SELECT last_registered_providers_hash
FROM tag_sources_meta
WHERE id = true
`
func (q *Queries) GetTagProvidersHash(ctx context.Context) (string, error) {
row := q.db.QueryRow(ctx, getTagProvidersHash)
var last_registered_providers_hash string
err := row.Scan(&last_registered_providers_hash)
return last_registered_providers_hash, err
}
const listTagProviderSettings = `-- name: ListTagProviderSettings :many
SELECT provider_id, enabled, api_key, display_order, created_at, updated_at
FROM tag_provider_settings
ORDER BY display_order, provider_id
`
// Tag-enrichment provider settings queries (milestone #160, #1490 Step 2).
// The tags.SettingsService consumes these — parallel to the cover-art
// SettingsService (coverart_settings.sql). Keeping the two independent
// means a new tag source is added without touching the art settings.
// All rows, for boot reconciliation and the admin GET handler.
func (q *Queries) ListTagProviderSettings(ctx context.Context) ([]TagProviderSetting, error) {
rows, err := q.db.Query(ctx, listTagProviderSettings)
if err != nil {
return nil, err
}
defer rows.Close()
var items []TagProviderSetting
for rows.Next() {
var i TagProviderSetting
if err := rows.Scan(
&i.ProviderID,
&i.Enabled,
&i.ApiKey,
&i.DisplayOrder,
&i.CreatedAt,
&i.UpdatedAt,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
const updateTagProviderSettings = `-- name: UpdateTagProviderSettings :exec
UPDATE tag_provider_settings
SET enabled = COALESCE($2, enabled),
api_key = CASE WHEN $3::boolean THEN $4 ELSE api_key END,
updated_at = now()
WHERE provider_id = $1
`
type UpdateTagProviderSettingsParams struct {
ProviderID string
Enabled bool
Column3 bool
ApiKey *string
}
// Admin PATCH. $2 sets enabled. Pass FALSE for the $3 apiKeyChanged flag
// to leave api_key untouched; TRUE with empty string clears it, TRUE with
// a value sets it.
func (q *Queries) UpdateTagProviderSettings(ctx context.Context, arg UpdateTagProviderSettingsParams) error {
_, err := q.db.Exec(ctx, updateTagProviderSettings,
arg.ProviderID,
arg.Enabled,
arg.Column3,
arg.ApiKey,
)
return err
}
const upsertTagProviderSettings = `-- name: UpsertTagProviderSettings :exec
INSERT INTO tag_provider_settings (provider_id, enabled, display_order)
VALUES ($1, $2, $3)
ON CONFLICT (provider_id) DO UPDATE
SET display_order = EXCLUDED.display_order,
updated_at = now()
`
type UpsertTagProviderSettingsParams struct {
ProviderID string
Enabled bool
DisplayOrder int32
}
// INSERT a default row for a newly-registered provider, or refresh an
// existing row's display_order on boot. Does NOT overwrite enabled /
// api_key on conflict — the operator's settings persist across restarts.
func (q *Queries) UpsertTagProviderSettings(ctx context.Context, arg UpsertTagProviderSettingsParams) error {
_, err := q.db.Exec(ctx, upsertTagProviderSettings, arg.ProviderID, arg.Enabled, arg.DisplayOrder)
return err
}
@@ -0,0 +1,3 @@
-- Reverse 0043_tag_provider_settings.up.sql.
DROP TABLE IF EXISTS tag_sources_meta;
DROP TABLE IF EXISTS tag_provider_settings;
@@ -0,0 +1,37 @@
-- Tag-enrichment provider settings (milestone #160, #1490 Step 2).
--
-- Mirrors the cover-art provider-settings substrate (migration 0018) so
-- adding a new tag source later is "register a provider + it auto-upserts
-- a row here" — never a schema change. The tag enricher reads the enabled
-- set + api keys from tag_provider_settings and stamps the current version
-- from tag_sources_meta onto tracks.tag_sources_version (added in 0042).
--
-- current_version starts at 1 while tracks.tag_sources_version defaults to
-- 0 (migration 0042), so every existing track is "stale" relative to
-- current and gets enriched on the first pass after this migrates.
CREATE TABLE tag_provider_settings (
provider_id text PRIMARY KEY,
enabled boolean NOT NULL DEFAULT true,
api_key text,
display_order int NOT NULL DEFAULT 0,
created_at timestamptz NOT NULL DEFAULT now(),
updated_at timestamptz NOT NULL DEFAULT now()
);
CREATE TABLE tag_sources_meta (
id boolean PRIMARY KEY DEFAULT true,
current_version int NOT NULL DEFAULT 1,
last_registered_providers_hash text NOT NULL DEFAULT '',
CONSTRAINT tag_sources_meta_singleton CHECK (id = true)
);
INSERT INTO tag_sources_meta (id, current_version) VALUES (true, 1);
-- Seed the v1 providers. MusicBrainz is the keyless always-on default;
-- Last.fm ships disabled and is opt-in once the operator supplies a key
-- (Step 4 Settings UI), per the no-coercive-settings rule (#26). The
-- SettingsService also upserts these at boot, so the seed is belt-and-
-- suspenders / documents the intended defaults.
INSERT INTO tag_provider_settings (provider_id, enabled, display_order) VALUES
('musicbrainz', true, 0),
('lastfm', false, 1);
+56
View File
@@ -0,0 +1,56 @@
-- Tag-enrichment provider settings queries (milestone #160, #1490 Step 2).
-- The tags.SettingsService consumes these — parallel to the cover-art
-- SettingsService (coverart_settings.sql). Keeping the two independent
-- means a new tag source is added without touching the art settings.
-- name: ListTagProviderSettings :many
-- All rows, for boot reconciliation and the admin GET handler.
SELECT provider_id, enabled, api_key, display_order, created_at, updated_at
FROM tag_provider_settings
ORDER BY display_order, provider_id;
-- name: UpsertTagProviderSettings :exec
-- INSERT a default row for a newly-registered provider, or refresh an
-- existing row's display_order on boot. Does NOT overwrite enabled /
-- api_key on conflict — the operator's settings persist across restarts.
INSERT INTO tag_provider_settings (provider_id, enabled, display_order)
VALUES ($1, $2, $3)
ON CONFLICT (provider_id) DO UPDATE
SET display_order = EXCLUDED.display_order,
updated_at = now();
-- name: UpdateTagProviderSettings :exec
-- Admin PATCH. $2 sets enabled. Pass FALSE for the $3 apiKeyChanged flag
-- to leave api_key untouched; TRUE with empty string clears it, TRUE with
-- a value sets it.
UPDATE tag_provider_settings
SET enabled = COALESCE($2, enabled),
api_key = CASE WHEN $3::boolean THEN $4 ELSE api_key END,
updated_at = now()
WHERE provider_id = $1;
-- name: GetCurrentTagSourcesVersion :one
SELECT current_version FROM tag_sources_meta WHERE id = true;
-- name: BumpTagSourcesVersion :one
-- Increment + return the new version. Called only when the enabled set
-- changes (not on key edits).
UPDATE tag_sources_meta
SET current_version = current_version + 1
WHERE id = true
RETURNING current_version;
-- name: GetTagProvidersHash :one
SELECT last_registered_providers_hash
FROM tag_sources_meta
WHERE id = true;
-- name: BumpTagVersionAndSetProvidersHash :one
-- Atomically increment the version and store the new registered-provider
-- hash. Called at boot when the compiled-in provider set changed, so
-- 'none' rows become eligible for a retry through the new chain.
UPDATE tag_sources_meta
SET current_version = current_version + 1,
last_registered_providers_hash = $1
WHERE id = true
RETURNING current_version;