Files
minstrel/internal/api/me_recommendation_metrics.go
T
bvandeusen 60533073ad
test-go / test (push) Successful in 31s
test-web / test (push) Successful in 37s
test-go / integration (push) Successful in 4m30s
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
2026-07-02 18:00:40 -04:00

235 lines
7.6 KiB
Go

package api
import (
"net/http"
"sort"
"strconv"
"strings"
"git.fabledsword.com/bvandeusen/minstrel/internal/apierror"
"git.fabledsword.com/bvandeusen/minstrel/internal/db/dbq"
)
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
)
// 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"`
// 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.
// 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 {
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
}
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 {
if row.Source == nil || *row.Source == "" {
baseline.add(row)
continue
}
fam := bucketRecSource(*row.Source)
acc, exists := families[fam.key]
if !exists {
acc = &familyAccum{fam: fam}
families[fam.key] = acc
}
acc.add(row)
}
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).
// 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
}