feat(metrics): bucketed surface families + manual-plays baseline (#1248, milestone 127)

The recommendation metrics table was observable but not actionable: raw
source strings (album:<uuid> one-offs) drowned the stable surfaces, and
manual plays were excluded so skip rates had no control group.

- SQL: include NULL-source rows (the baseline) and carry completion_n
  so family merges can weight avg_completion correctly.
- Handler buckets raw sources into stable families (radio:<uuid> →
  Radio, album:/artist: → direct plays, etc.) grouped by surface
  intent: go-to / discovery / direct — each band judged against its
  job, since discovery mixes are expected to skip hotter. Families
  under 20 plays are flagged low-confidence, not hidden.
- Settings card renders the baseline row and per-surface deltas in
  percentage points vs baseline (worse-than-baseline deltas in danger
  color), intent hint copy per group, low-data rows dimmed.
- Pure-unit test for the bucketing/merge; DB test updated to the new
  contract (baseline included, radio:<uuid> collapse).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6

internal/api/me_recommendation_metrics_test.go

@@ -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)
 	}
 }