Merge PR #96: recommendation batch (You-might-like fallback + taste 2b + observability)

internal/api/api.go

@@ -74,6 +74,7 @@ func Mount(r chi.Router, pool *pgxpool.Pool, logger *slog.Logger, events *playev
 			authed.Post("/auth/logout", h.handleLogout)
 			authed.Get("/me", h.handleGetMe)
 			authed.Get("/me/system-playlists-status", h.handleGetSystemPlaylistsStatus)
+			authed.Get("/me/recommendation-metrics", h.handleGetRecommendationMetrics)
 			authed.Get("/me/listenbrainz", h.handleGetListenBrainz)
 			authed.Put("/me/listenbrainz", h.handlePutListenBrainz)
 			authed.Get("/me/history", h.handleGetMyHistory)

internal/api/me_recommendation_metrics.go

@@ -0,0 +1,94 @@
+package api
+
+import (
+	"net/http"
+	"strconv"
+
+	"git.fabledsword.com/bvandeusen/minstrel/internal/apierror"
+	"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
+)
+
+const (
+	recMetricsDefaultDays = 30
+	recMetricsMaxDays     = 365
+)
+
+// 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
+	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]
+}
+
+type recommendationMetricsResp struct {
+	WindowDays int                    `json:"window_days"`
+	Sources    []recommendationMetric `json:"sources"`
+}
+
+// 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.
+func (h *handlers) handleGetRecommendationMetrics(w http.ResponseWriter, r *http.Request) {
+	caller, ok := requireUser(w, r)
+	if !ok {
+		return
+	}
+	days, ok := parseMetricsDays(w, r)
+	if !ok {
+		return
+	}
+
+	rows, err := dbq.New(h.pool).RecommendationSourceMetricsForUser(r.Context(),
+		dbq.RecommendationSourceMetricsForUserParams{UserID: caller.ID, Column2: float64(days)})
+	if err != nil {
+		h.logger.Error("api: recommendation metrics", "err", err)
+		writeErr(w, apierror.InternalMsg("lookup failed", err))
+		return
+	}
+
+	out := recommendationMetricsResp{
+		WindowDays: days,
+		Sources:    make([]recommendationMetric, 0, len(rows)),
+	}
+	for _, row := range rows {
+		source := ""
+		if row.Source != nil {
+			source = *row.Source
+		}
+		var skipRate float64
+		if row.Plays > 0 {
+			skipRate = float64(row.Skips) / float64(row.Plays)
+		}
+		out.Sources = append(out.Sources, recommendationMetric{
+			Source:        source,
+			Plays:         row.Plays,
+			Skips:         row.Skips,
+			SkipRate:      skipRate,
+			AvgCompletion: row.AvgCompletion,
+		})
+	}
+	writeJSON(w, http.StatusOK, out)
+}
+
+// parseMetricsDays reads the `days` query param (default 30, capped at 365).
+// Writes a 400 and returns ok=false on a malformed value.
+func parseMetricsDays(w http.ResponseWriter, r *http.Request) (int, bool) {
+	v := r.URL.Query().Get("days")
+	if v == "" {
+		return recMetricsDefaultDays, true
+	}
+	n, err := strconv.Atoi(v)
+	if err != nil || n < 1 {
+		writeErr(w, apierror.BadRequest("bad_request", "invalid days"))
+		return 0, false
+	}
+	if n > recMetricsMaxDays {
+		n = recMetricsMaxDays
+	}
+	return n, true
+}

internal/api/me_recommendation_metrics_test.go

@@ -0,0 +1,108 @@
+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"
+)
+
+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 (library/radio play).
+func seedSourcedPlay(
+	t *testing.T, h *handlers, userID, trackID, sessionID pgtype.UUID,
+	source *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, completion_ratio, was_skipped)
+		 VALUES ($1, $2, $3, now(), $4, $5, $6)`,
+		userID, trackID, sessionID, source, 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)
+	}
+}
+
+func TestRecommendationMetrics_AggregatesBySourceExcludingNull(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"
+	discover := "discover"
+	// 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.
+	seedSourcedPlay(t, h, user.ID, tk.ID, session, 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)
+	}
+	bySource := map[string]recommendationMetric{}
+	for _, m := range resp.Sources {
+		bySource[m.Source] = m
+	}
+	if _, present := bySource[""]; present {
+		t.Error("NULL-source (library) plays should be excluded")
+	}
+	fy, ok := bySource["for_you"]
+	if !ok {
+		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)
+	}
+	if d, ok := bySource["discover"]; !ok || d.Plays != 1 || d.Skips != 0 {
+		t.Errorf("discover metrics = %+v, want plays=1 skips=0", d)
+	}
+}

internal/db/dbq/recommendation.sql.go

@@ -737,6 +737,17 @@ likes_overlap AS (
     ORDER BY random()
     LIMIT $8
 ),
+taste_overlap AS (
+    SELECT t.id AS track_id, 0.0::float8 AS sim_score
+    FROM taste_profile_artists tpa
+    JOIN tracks t ON t.artist_id = tpa.artist_id
+    WHERE tpa.user_id = $1
+      AND tpa.weight > 0
+      AND t.id NOT IN (SELECT id FROM excluded_ids)
+      AND t.id <> $2
+    ORDER BY tpa.weight DESC, t.id
+    LIMIT $10
+),
 random_fill AS (
     SELECT t.id AS track_id, 0.0::float8 AS sim_score
     FROM tracks t
@@ -747,6 +758,7 @@ random_fill AS (
           UNION SELECT track_id FROM similar_artists
           UNION SELECT track_id FROM tag_overlap
           UNION SELECT track_id FROM likes_overlap
+          UNION SELECT track_id FROM taste_overlap
       )
     ORDER BY random()
     LIMIT $9
@@ -763,6 +775,7 @@ FROM (
     UNION ALL SELECT track_id, sim_score FROM similar_artists
     UNION ALL SELECT track_id, sim_score FROM tag_overlap
     UNION ALL SELECT track_id, sim_score FROM likes_overlap
+    UNION ALL SELECT track_id, sim_score FROM taste_overlap
     UNION ALL SELECT track_id, sim_score FROM random_fill
 ) u
 JOIN tracks t ON t.id = u.track_id
@@ -790,6 +803,7 @@ type LoadRadioCandidatesV2Params struct {
 	Limit_3 int32
 	Limit_4 int32
 	Limit_5 int32
+	Limit_6 int32
 }
 
 type LoadRadioCandidatesV2Row struct {
@@ -801,11 +815,15 @@ type LoadRadioCandidatesV2Row struct {
 	SimilarityScore interface{}
 }
 
-// M4c: similarity-driven candidate pool. 5-way UNION:
+// M4c: similarity-driven candidate pool. 6-way UNION:
 //
 //	$1 user_id, $2 seed_track_id, $3 recently_played_hours,
 //	$4 exclude (uuid[]), $5 lb_similar K, $6 similar_artists K,
-//	$7 tag_overlap K, $8 likes_overlap K, $9 random_fill K.
+//	$7 tag_overlap K, $8 likes_overlap K, $9 random_fill K,
+//	$10 taste_overlap K (#796 phase 2b — tracks by the user's top
+//	positively-weighted taste-profile artists, so taste-relevant tracks
+//	enter the pool even when the similarity/random arms miss them; scored
+//	in Go via TasteMatch, so sim_score here is 0 pool-inclusion).
 //
 // Returns same shape as LoadRadioCandidates plus similarity_score column.
 func (q *Queries) LoadRadioCandidatesV2(ctx context.Context, arg LoadRadioCandidatesV2Params) ([]LoadRadioCandidatesV2Row, error) {
@@ -819,6 +837,7 @@ func (q *Queries) LoadRadioCandidatesV2(ctx context.Context, arg LoadRadioCandid
 		arg.Limit_3,
 		arg.Limit_4,
 		arg.Limit_5,
+		arg.Limit_6,
 	)
 	if err != nil {
 		return nil, err

internal/db/dbq/recommendation_metrics.sql.go

@@ -0,0 +1,73 @@
+// Code generated by sqlc. DO NOT EDIT.
+// versions:
+//   sqlc v1.31.1
+// source: recommendation_metrics.sql
+
+package dbq
+
+import (
+	"context"
+
+	"github.com/jackc/pgx/v5/pgtype"
+)
+
+const recommendationSourceMetricsForUser = `-- name: RecommendationSourceMetricsForUser :many
+
+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
+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
+`
+
+type RecommendationSourceMetricsForUserParams struct {
+	UserID  pgtype.UUID
+	Column2 float64
+}
+
+type RecommendationSourceMetricsForUserRow struct {
+	Source        *string
+	Plays         int64
+	Skips         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.
+// $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).
+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 {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []RecommendationSourceMetricsForUserRow
+	for rows.Next() {
+		var i RecommendationSourceMetricsForUserRow
+		if err := rows.Scan(
+			&i.Source,
+			&i.Plays,
+			&i.Skips,
+			&i.AvgCompletion,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}

internal/db/dbq/you_might_like.sql.go

@@ -91,6 +91,70 @@ func (q *Queries) InsertYouMightLikeArtist(ctx context.Context, arg InsertYouMig
 	return err
 }
 
+const listYouMightLikeAlbumFallbackForUser = `-- name: ListYouMightLikeAlbumFallbackForUser :many
+WITH liked_album_ids AS (
+    SELECT likb.album_id AS album_id
+      FROM general_likes_albums likb
+     WHERE likb.user_id = $1
+    UNION
+    SELECT trk.album_id AS album_id
+      FROM general_likes likt
+      JOIN tracks trk ON trk.id = likt.track_id
+     WHERE likt.user_id = $1
+)
+SELECT albums.id, albums.title, albums.sort_title, albums.artist_id, albums.release_date, albums.mbid, albums.cover_art_path, albums.created_at, albums.updated_at, albums.cover_art_source, albums.cover_art_sources_version, artists.name AS artist_name
+FROM liked_album_ids lai
+JOIN albums ON albums.id = lai.album_id
+JOIN artists ON artists.id = albums.artist_id
+ORDER BY md5(albums.id::text || current_date::text)
+LIMIT $2
+`
+
+type ListYouMightLikeAlbumFallbackForUserParams struct {
+	UserID pgtype.UUID
+	Limit  int32
+}
+
+type ListYouMightLikeAlbumFallbackForUserRow struct {
+	Album      Album
+	ArtistName string
+}
+
+// Broad "albums you've shown affinity for" pool: explicitly liked albums PLUS
+// the albums of liked tracks. Same projection as ListYouMightLikeAlbumsForUser.
+func (q *Queries) ListYouMightLikeAlbumFallbackForUser(ctx context.Context, arg ListYouMightLikeAlbumFallbackForUserParams) ([]ListYouMightLikeAlbumFallbackForUserRow, error) {
+	rows, err := q.db.Query(ctx, listYouMightLikeAlbumFallbackForUser, arg.UserID, arg.Limit)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []ListYouMightLikeAlbumFallbackForUserRow
+	for rows.Next() {
+		var i ListYouMightLikeAlbumFallbackForUserRow
+		if err := rows.Scan(
+			&i.Album.ID,
+			&i.Album.Title,
+			&i.Album.SortTitle,
+			&i.Album.ArtistID,
+			&i.Album.ReleaseDate,
+			&i.Album.Mbid,
+			&i.Album.CoverArtPath,
+			&i.Album.CreatedAt,
+			&i.Album.UpdatedAt,
+			&i.Album.CoverArtSource,
+			&i.Album.CoverArtSourcesVersion,
+			&i.ArtistName,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
 const listYouMightLikeAlbumsForUser = `-- name: ListYouMightLikeAlbumsForUser :many
 SELECT albums.id, albums.title, albums.sort_title, albums.artist_id, albums.release_date, albums.mbid, albums.cover_art_path, albums.created_at, albums.updated_at, albums.cover_art_source, albums.cover_art_sources_version, artists.name AS artist_name
 FROM you_might_like_albums yml
@@ -149,6 +213,90 @@ func (q *Queries) ListYouMightLikeAlbumsForUser(ctx context.Context, arg ListYou
 	return items, nil
 }
 
+const listYouMightLikeArtistFallbackForUser = `-- name: ListYouMightLikeArtistFallbackForUser :many
+WITH liked_artist_ids AS (
+    SELECT lika.artist_id AS artist_id
+      FROM general_likes_artists lika
+     WHERE lika.user_id = $1
+    UNION
+    SELECT alb.artist_id AS artist_id
+      FROM general_likes_albums likb
+      JOIN albums alb ON alb.id = likb.album_id
+     WHERE likb.user_id = $1
+    UNION
+    SELECT trk.artist_id AS artist_id
+      FROM general_likes likt
+      JOIN tracks trk ON trk.id = likt.track_id
+     WHERE likt.user_id = $1
+)
+SELECT artists.id, artists.name, artists.sort_name, artists.mbid, artists.created_at, artists.updated_at, artists.artist_thumb_path, artists.artist_fanart_path, artists.artist_art_source, artists.artist_art_sources_version,
+       cov.id AS cover_album_id,
+       cnt.album_count::bigint AS album_count
+FROM liked_artist_ids lai
+JOIN artists ON artists.id = lai.artist_id
+LEFT JOIN LATERAL (
+    SELECT id FROM albums
+    WHERE artist_id = artists.id AND cover_art_path IS NOT NULL
+    ORDER BY created_at DESC LIMIT 1
+) cov ON true
+LEFT JOIN LATERAL (
+    SELECT count(*) AS album_count
+    FROM albums WHERE artist_id = artists.id
+) cnt ON true
+ORDER BY md5(artists.id::text || current_date::text)
+LIMIT $2
+`
+
+type ListYouMightLikeArtistFallbackForUserParams struct {
+	UserID pgtype.UUID
+	Limit  int32
+}
+
+type ListYouMightLikeArtistFallbackForUserRow struct {
+	Artist       Artist
+	CoverAlbumID pgtype.UUID
+	AlbumCount   int64
+}
+
+// Broad "artists you've shown affinity for" pool to fill a thin
+// You-might-like artists row: explicitly liked artists PLUS the artists of
+// liked albums and liked tracks. Most users like albums/tracks far more than
+// they like artists explicitly, so the union is much deeper than
+// general_likes_artists alone. Daily-stable order; same projection as
+// ListYouMightLikeArtistsForUser so the Go layer reuses it directly.
+func (q *Queries) ListYouMightLikeArtistFallbackForUser(ctx context.Context, arg ListYouMightLikeArtistFallbackForUserParams) ([]ListYouMightLikeArtistFallbackForUserRow, error) {
+	rows, err := q.db.Query(ctx, listYouMightLikeArtistFallbackForUser, arg.UserID, arg.Limit)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	var items []ListYouMightLikeArtistFallbackForUserRow
+	for rows.Next() {
+		var i ListYouMightLikeArtistFallbackForUserRow
+		if err := rows.Scan(
+			&i.Artist.ID,
+			&i.Artist.Name,
+			&i.Artist.SortName,
+			&i.Artist.Mbid,
+			&i.Artist.CreatedAt,
+			&i.Artist.UpdatedAt,
+			&i.Artist.ArtistThumbPath,
+			&i.Artist.ArtistFanartPath,
+			&i.Artist.ArtistArtSource,
+			&i.Artist.ArtistArtSourcesVersion,
+			&i.CoverAlbumID,
+			&i.AlbumCount,
+		); err != nil {
+			return nil, err
+		}
+		items = append(items, i)
+	}
+	if err := rows.Err(); err != nil {
+		return nil, err
+	}
+	return items, nil
+}
+
 const listYouMightLikeArtistsForUser = `-- name: ListYouMightLikeArtistsForUser :many
 SELECT artists.id, artists.name, artists.sort_name, artists.mbid, artists.created_at, artists.updated_at, artists.artist_thumb_path, artists.artist_fanart_path, artists.artist_art_source, artists.artist_art_sources_version,
        cov.id AS cover_album_id,

internal/db/queries/recommendation.sql

@@ -33,10 +33,14 @@ WHERE t.id <> $2
   );
 
 -- name: LoadRadioCandidatesV2 :many
--- M4c: similarity-driven candidate pool. 5-way UNION:
+-- M4c: similarity-driven candidate pool. 6-way UNION:
 --   $1 user_id, $2 seed_track_id, $3 recently_played_hours,
 --   $4 exclude (uuid[]), $5 lb_similar K, $6 similar_artists K,
---   $7 tag_overlap K, $8 likes_overlap K, $9 random_fill K.
+--   $7 tag_overlap K, $8 likes_overlap K, $9 random_fill K,
+--   $10 taste_overlap K (#796 phase 2b — tracks by the user's top
+--   positively-weighted taste-profile artists, so taste-relevant tracks
+--   enter the pool even when the similarity/random arms miss them; scored
+--   in Go via TasteMatch, so sim_score here is 0 pool-inclusion).
 -- Returns same shape as LoadRadioCandidates plus similarity_score column.
 
 WITH
@@ -109,6 +113,17 @@ likes_overlap AS (
     ORDER BY random()
     LIMIT $8
 ),
+taste_overlap AS (
+    SELECT t.id AS track_id, 0.0::float8 AS sim_score
+    FROM taste_profile_artists tpa
+    JOIN tracks t ON t.artist_id = tpa.artist_id
+    WHERE tpa.user_id = $1
+      AND tpa.weight > 0
+      AND t.id NOT IN (SELECT id FROM excluded_ids)
+      AND t.id <> $2
+    ORDER BY tpa.weight DESC, t.id
+    LIMIT $10
+),
 random_fill AS (
     SELECT t.id AS track_id, 0.0::float8 AS sim_score
     FROM tracks t
@@ -119,6 +134,7 @@ random_fill AS (
           UNION SELECT track_id FROM similar_artists
           UNION SELECT track_id FROM tag_overlap
           UNION SELECT track_id FROM likes_overlap
+          UNION SELECT track_id FROM taste_overlap
       )
     ORDER BY random()
     LIMIT $9
@@ -135,6 +151,7 @@ FROM (
     UNION ALL SELECT track_id, sim_score FROM similar_artists
     UNION ALL SELECT track_id, sim_score FROM tag_overlap
     UNION ALL SELECT track_id, sim_score FROM likes_overlap
+    UNION ALL SELECT track_id, sim_score FROM taste_overlap
     UNION ALL SELECT track_id, sim_score FROM random_fill
 ) u
 JOIN tracks t ON t.id = u.track_id

internal/db/queries/recommendation_metrics.sql

@@ -0,0 +1,22 @@
+-- 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.
+
+-- 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).
+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
+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;

internal/db/queries/you_might_like.sql

@@ -64,3 +64,62 @@ LEFT JOIN LATERAL (
 WHERE yml.user_id = $1
 ORDER BY yml.rank
 LIMIT $2;
+
+-- name: ListYouMightLikeArtistFallbackForUser :many
+-- Broad "artists you've shown affinity for" pool to fill a thin
+-- You-might-like artists row: explicitly liked artists PLUS the artists of
+-- liked albums and liked tracks. Most users like albums/tracks far more than
+-- they like artists explicitly, so the union is much deeper than
+-- general_likes_artists alone. Daily-stable order; same projection as
+-- ListYouMightLikeArtistsForUser so the Go layer reuses it directly.
+WITH liked_artist_ids AS (
+    SELECT lika.artist_id AS artist_id
+      FROM general_likes_artists lika
+     WHERE lika.user_id = $1
+    UNION
+    SELECT alb.artist_id AS artist_id
+      FROM general_likes_albums likb
+      JOIN albums alb ON alb.id = likb.album_id
+     WHERE likb.user_id = $1
+    UNION
+    SELECT trk.artist_id AS artist_id
+      FROM general_likes likt
+      JOIN tracks trk ON trk.id = likt.track_id
+     WHERE likt.user_id = $1
+)
+SELECT sqlc.embed(artists),
+       cov.id AS cover_album_id,
+       cnt.album_count::bigint AS album_count
+FROM liked_artist_ids lai
+JOIN artists ON artists.id = lai.artist_id
+LEFT JOIN LATERAL (
+    SELECT id FROM albums
+    WHERE artist_id = artists.id AND cover_art_path IS NOT NULL
+    ORDER BY created_at DESC LIMIT 1
+) cov ON true
+LEFT JOIN LATERAL (
+    SELECT count(*) AS album_count
+    FROM albums WHERE artist_id = artists.id
+) cnt ON true
+ORDER BY md5(artists.id::text || current_date::text)
+LIMIT $2;
+
+-- name: ListYouMightLikeAlbumFallbackForUser :many
+-- Broad "albums you've shown affinity for" pool: explicitly liked albums PLUS
+-- the albums of liked tracks. Same projection as ListYouMightLikeAlbumsForUser.
+WITH liked_album_ids AS (
+    SELECT likb.album_id AS album_id
+      FROM general_likes_albums likb
+     WHERE likb.user_id = $1
+    UNION
+    SELECT trk.album_id AS album_id
+      FROM general_likes likt
+      JOIN tracks trk ON trk.id = likt.track_id
+     WHERE likt.user_id = $1
+)
+SELECT sqlc.embed(albums), artists.name AS artist_name
+FROM liked_album_ids lai
+JOIN albums ON albums.id = lai.album_id
+JOIN artists ON artists.id = albums.artist_id
+ORDER BY md5(albums.id::text || current_date::text)
+LIMIT $2;

internal/playlists/system.go

@@ -329,6 +329,10 @@ func systemForYouSourceLimits() recommendation.CandidateSourceLimits {
 		TagOverlap:    60,
 		LikesOverlap:  40,
 		RandomFill:    150,
+		// For-You / You-might-like are the taste-driven surfaces, so pull a
+		// deep slice of the user's top taste-profile artists into the pool
+		// (#796 phase 2b). Empty for cold-start users (no profile yet).
+		TasteOverlap: 80,
 	}
 }
 

internal/playlists/you_might_like.go

@@ -89,9 +89,15 @@ func buildYouMightLike(
 	}
 
 	zeroVec := recommendation.SessionVector{Seed: true}
+	// You-might-like surfaces in-library artists the user does NOT actively
+	// engage with, so it deliberately skips the taste_overlap arm — that arm
+	// pulls top-taste (mostly already-played) artists, which would crowd the
+	// pool with entities the read-time dedup then strips. For-You/radio keep it.
+	ymlLimits := systemForYouSourceLimits()
+	ymlLimits.TasteOverlap = 0
 	cands, err := recommendation.LoadCandidatesFromSimilarity(
 		ctx, q, userID, seed, 1, zeroVec,
-		[]pgtype.UUID{seed}, systemForYouSourceLimits(),
+		[]pgtype.UUID{seed}, ymlLimits,
 	)
 	if err != nil {
 		logger.Warn("you-might-like: candidate load failed; skipping",

internal/recommendation/candidates.go

@@ -72,6 +72,10 @@ type CandidateSourceLimits struct {
 	TagOverlap    int
 	LikesOverlap  int
 	RandomFill    int
+	// TasteOverlap (#796 phase 2b): tracks by the user's top positively-
+	// weighted taste-profile artists. 0 disables the arm (e.g. cold-start
+	// users have an empty profile, so it contributes nothing anyway).
+	TasteOverlap int
 }
 
 // DefaultCandidateSourceLimits returns the v1 hardcoded constants per spec.
@@ -82,6 +86,7 @@ func DefaultCandidateSourceLimits() CandidateSourceLimits {
 		TagOverlap:    20,
 		LikesOverlap:  20,
 		RandomFill:    30,
+		TasteOverlap:  20,
 	}
 }
 
@@ -113,6 +118,7 @@ func LoadCandidatesFromSimilarity(
 		Limit_3: int32(limits.TagOverlap),
 		Limit_4: int32(limits.LikesOverlap),
 		Limit_5: int32(limits.RandomFill),
+		Limit_6: int32(limits.TasteOverlap),
 	})
 	if err != nil {
 		return nil, err

internal/recommendation/candidates_v2_test.go

@@ -262,6 +262,61 @@ func TestLoadCandidatesFromSimilarity_DedupTakesMaxScore(t *testing.T) {
 	}
 }
 
+// TestLoadCandidatesFromSimilarity_TasteOverlapArm (#796 phase 2b): a track by
+// a positively-weighted taste-profile artist enters the pool via taste_overlap
+// even with every other arm disabled; a negatively-weighted artist's track does
+// not (the WHERE weight > 0 filter).
+func TestLoadCandidatesFromSimilarity_TasteOverlapArm(t *testing.T) {
+	f := newFixture(t, 2) // seed + 1 other, both by the fixture artist
+	seed := f.tracks[0]
+	target := f.tracks[1]
+	ctx := context.Background()
+
+	// Fixture artist gets a positive taste weight.
+	if _, err := f.pool.Exec(ctx,
+		`INSERT INTO taste_profile_artists (user_id, artist_id, weight) VALUES ($1, $2, 5.0)`,
+		f.user, seed.ArtistID); err != nil {
+		t.Fatalf("insert taste (positive): %v", err)
+	}
+
+	// A second artist with a NEGATIVE weight — its track must be excluded.
+	negArtist, _ := f.q.UpsertArtist(ctx, dbq.UpsertArtistParams{Name: "NegArtist", SortName: "NegArtist"})
+	negAlbum, _ := f.q.UpsertAlbum(ctx, dbq.UpsertAlbumParams{Title: "NegAlbum", SortTitle: "NegAlbum", ArtistID: negArtist.ID})
+	negTrack, _ := f.q.UpsertTrack(ctx, dbq.UpsertTrackParams{
+		Title: "NegTrack", AlbumID: negAlbum.ID, ArtistID: negArtist.ID,
+		FilePath: "/tmp/neg.flac", DurationMs: 180_000,
+	})
+	if _, err := f.pool.Exec(ctx,
+		`INSERT INTO taste_profile_artists (user_id, artist_id, weight) VALUES ($1, $2, -3.0)`,
+		f.user, negArtist.ID); err != nil {
+		t.Fatalf("insert taste (negative): %v", err)
+	}
+
+	// Only the taste_overlap arm is enabled.
+	limits := CandidateSourceLimits{TasteOverlap: 10}
+	got, err := LoadCandidatesFromSimilarity(
+		ctx, f.q, f.user, seed.ID, 1, SessionVector{Seed: true}, nil, limits,
+	)
+	if err != nil {
+		t.Fatalf("load: %v", err)
+	}
+	var sawTarget, sawNeg bool
+	for _, c := range got {
+		switch c.Track.ID {
+		case target.ID:
+			sawTarget = true
+		case negTrack.ID:
+			sawNeg = true
+		}
+	}
+	if !sawTarget {
+		t.Error("positive-taste-artist track missing (taste_overlap arm didn't contribute)")
+	}
+	if sawNeg {
+		t.Error("negative-taste-artist track present (weight > 0 filter failed)")
+	}
+}
+
 func TestLoadCandidatesFromSimilarity_EmptyLibrary_NoError(t *testing.T) {
 	f := newFixture(t, 1) // just the seed
 	seed := f.tracks[0]

internal/recommendation/home.go

@@ -199,11 +199,12 @@ func HomeData(ctx context.Context, pool *pgxpool.Pool, userID pgtype.UUID) (*Hom
 const youMightLikeFallbackFetch = 100
 
 // topUpYouMightLikeArtists fills a thin You-might-like artist row from the
-// user's liked artists (daily-stable sample), excluding what's already shown
-// on Home (the section itself, Rediscover, Most/Last Played) so the fallback
-// neither duplicates a tile nor suggests an actively-played artist. The liked
-// pool dwarfs the similarity roll-up, so the same exclusions still fill it.
-// Best-effort: a query error leaves the section as-is.
+// artists the user has shown affinity for — explicit artist-likes PLUS the
+// artists of liked albums and liked tracks (most users like albums/tracks far
+// more than artists, so the broad pool is what actually fills the row).
+// Excludes what's already shown on Home (the section itself, Rediscover,
+// Most/Last Played) so the fallback neither duplicates a tile nor suggests an
+// actively-played artist. Best-effort: a query error leaves the section as-is.
 func topUpYouMightLikeArtists(
 	ctx context.Context, q *dbq.Queries, userID pgtype.UUID, out *HomePayload,
 ) []dbq.ListYouMightLikeArtistsForUserRow {
@@ -218,7 +219,7 @@ func topUpYouMightLikeArtists(
 	for _, r := range result {
 		excluded[r.Artist.ID] = struct{}{}
 	}
-	fb, err := q.ListRediscoverArtistsFallbackForUser(ctx, dbq.ListRediscoverArtistsFallbackForUserParams{
+	fb, err := q.ListYouMightLikeArtistFallbackForUser(ctx, dbq.ListYouMightLikeArtistFallbackForUserParams{
 		UserID: userID, Limit: youMightLikeFallbackFetch,
 	})
 	if err != nil {
@@ -249,7 +250,7 @@ func topUpYouMightLikeAlbums(
 	for _, r := range result {
 		excluded[r.Album.ID] = struct{}{}
 	}
-	fb, err := q.ListRediscoverAlbumsFallbackForUser(ctx, dbq.ListRediscoverAlbumsFallbackForUserParams{
+	fb, err := q.ListYouMightLikeAlbumFallbackForUser(ctx, dbq.ListYouMightLikeAlbumFallbackForUserParams{
 		UserID: userID, Limit: youMightLikeFallbackFetch,
 	})
 	if err != nil {

internal/recommendation/home_integration_test.go

@@ -48,6 +48,40 @@ func TestHomeData_YouMightLike_FallbackFillsFromLikedArtists(t *testing.T) {
 	}
 }
 
+// TestHomeData_YouMightLike_FallbackFromLikedTrackArtists: the broad fallback
+// must surface the artists of LIKED TRACKS even with no explicit artist-likes
+// (most users like tracks/albums, rarely artists). 12 liked tracks by distinct
+// artists, no artist-likes, no plays → the artist row fills from them.
+func TestHomeData_YouMightLike_FallbackFromLikedTrackArtists(t *testing.T) {
+	pool := newPool(t)
+	user := seedUser(t, pool, "home-yml-trackartists")
+	fromLiked := make(map[pgtype.UUID]bool, 12)
+	for i := 0; i < 12; i++ {
+		a := seedArtist(t, pool, fmt.Sprintf("TrkArtist%02d", i), "")
+		al := seedAlbumForArtist(t, pool, a.ID, fmt.Sprintf("Alb%02d", i))
+		tr := seedTrackOnAlbum(t, pool, al.ID, a.ID, fmt.Sprintf("Trk%02d", i))
+		if _, err := pool.Exec(context.Background(),
+			`INSERT INTO general_likes (user_id, track_id) VALUES ($1, $2)`, user.ID, tr.ID); err != nil {
+			t.Fatalf("like track: %v", err)
+		}
+		fromLiked[a.ID] = true
+	}
+
+	got, err := HomeData(context.Background(), pool, user.ID)
+	if err != nil {
+		t.Fatalf("HomeData: %v", err)
+	}
+	if len(got.YouMightLikeArtists) != HomeYouMightLikeLimit {
+		t.Fatalf("you-might-like artists = %d, want %d (from liked-track artists)",
+			len(got.YouMightLikeArtists), HomeYouMightLikeLimit)
+	}
+	for _, r := range got.YouMightLikeArtists {
+		if !fromLiked[r.Artist.ID] {
+			t.Errorf("artist %s not from the liked-track pool", r.Artist.Name)
+		}
+	}
+}
+
 func TestHomeData_NewUser_AllSectionsEmpty(t *testing.T) {
 	pool := newPool(t)
 	user := seedUser(t, pool, "home-newuser")

web/src/lib/api/metrics.ts

@@ -0,0 +1,46 @@
+import { createQuery } from '@tanstack/svelte-query';
+import { api } from './client';
+
+// Mirrors internal/api/me_recommendation_metrics.go.
+export type RecommendationMetric = {
+  source: string;
+  plays: number;
+  skips: number;
+  skip_rate: number;
+  avg_completion: number;
+};
+
+export type RecommendationMetrics = {
+  window_days: number;
+  sources: RecommendationMetric[];
+};
+
+export function getRecommendationMetrics(): Promise<RecommendationMetrics> {
+  return api.get<RecommendationMetrics>('/api/me/recommendation-metrics');
+}
+
+export const REC_METRICS_QUERY_KEY = ['settings', 'recommendation-metrics'] as const;
+
+export function createRecommendationMetricsQuery() {
+  return createQuery({
+    queryKey: REC_METRICS_QUERY_KEY,
+    queryFn: getRecommendationMetrics,
+    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;
+}

web/src/routes/settings/+page.svelte

@@ -8,6 +8,11 @@
     createEnabledMutation,
     type LBStatus
   } from '$lib/api/listenbrainz';
+  import {
+    createRecommendationMetricsQuery,
+    sourceLabel,
+    type RecommendationMetrics
+  } from '$lib/api/metrics';
   import { theme, setTheme, type ThemePreference } from '$lib/stores/theme.svelte';
   import { player, setCrossfade } from '$lib/player/store.svelte';
   import {
@@ -24,6 +29,7 @@
   const queryClient = useQueryClient();
 
   const status = createLBStatusQuery() as CreateQueryResult<LBStatus>;
+  const metrics = createRecommendationMetricsQuery() as CreateQueryResult<RecommendationMetrics>;
   const tokenMutation = createTokenMutation(queryClient);
   const enabledMutation = createEnabledMutation(queryClient);
 
@@ -267,6 +273,46 @@
     {/if}
   </section>
 
+  <!-- Recommendation metrics card -->
+  <section class="space-y-3 rounded border border-border bg-surface p-4">
+    <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.
+    </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}
+      <p class="text-sm text-text-secondary">
+        No recommendation plays yet. Play something from For You, Discover, or a mix.
+      </p>
+    {/if}
+  </section>
+
   <!-- Profile card -->
   <section class="space-y-3 rounded border border-border bg-surface p-4">
     <h2 class="text-lg font-semibold">Profile</h2>

web/src/routes/settings/Appearance.test.ts

@@ -25,6 +25,16 @@ 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: [] } });
+      return () => {};
+    }
+  }),
+  sourceLabel: (s: string) => s
+}));
+
 beforeEach(() => {
   globalThis.localStorage.clear();
   document.documentElement.removeAttribute('data-theme');

web/src/routes/settings/settings.test.ts

@@ -20,6 +20,16 @@ vi.mock('$lib/api/me', () => ({
   regenerateAPIToken: vi.fn()
 }));
 
+vi.mock('$lib/api/metrics', () => ({
+  createRecommendationMetricsQuery: () => ({
+    subscribe: (run: (v: unknown) => void) => {
+      run({ isPending: false, isError: false, data: { window_days: 30, sources: [] } });
+      return () => {};
+    }
+  }),
+  sourceLabel: (s: string) => s
+}));
+
 import SettingsPage from './+page.svelte';
 import {
   createLBStatusQuery,