Files
minstrel/internal/api/me_recommendation_metrics.go
bvandeusen 5faa57634b
test-go / test (push) Successful in 31s
test-web / test (push) Successful in 38s
test-go / integration (push) Successful in 4m36s
feat(metrics): provenance as standard — pick_kind for all system mixes
The #1249 mechanism (stamp WHY a track is in the snapshot at build
time, freeze it onto the play at ingestion, break it down in metrics)
generalizes from a For You one-off to the standard for every system
mix (#1270):

- Migration 0039 widens both pick_kind CHECKs (drop + re-add in the
  same change) to taste/fresh + Discover's dormant/cross_user/random
  + tier1-3 for the rule-#131 eligibility ladders.
- GetForYouPickKindForTrack becomes GetSystemPickKindForTrack
  (user, variant, track); ingestion stamps any systemPlaylistSources
  play from its own variant's live snapshot, live + offline paths.
- Discover stamps its candidate bucket on discoverTrack before the
  interleave, making the 40/30/30 allocation measurable; dedup keeps
  the taking bucket's stamp.
- Metrics replace the for_you special-case with one pick-kind
  vocabulary — any family with attributed plays gets a breakdown,
  future stamping mixes need no metrics change.
- Web: breakdown sub-rows are now toggled per surface (collapsed by
  default) so eight stamping mixes don't swamp the card.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6
2026-07-02 23:26:52 -04:00

324 lines
11 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
// Breakdown splits the family into the pick-kind populations its
// builder stamped (#1249, generalized #1270): For You's taste/fresh,
// Discover's buckets, tier1-3 for tiered mixes — plus earlier plays
// that predate attribution. Present only when the family has at
// least one attributed play; the parent row remains the sum of its
// breakdown.
Breakdown []surfaceMetric `json:"breakdown,omitempty"`
}
// 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))
}
// pickKindLabels is the display vocabulary for play_events.pick_kind
// values (mirrors the CHECK in migration 0039). Every system mix that
// stamps provenance gets its breakdown from this one map — adding a
// stamping mix needs no metrics change.
var pickKindLabels = map[string]string{
"taste": "Taste picks",
"fresh": "Fresh picks",
"dormant": "Dormant artists",
"cross_user": "Liked by others",
"random": "Random unheard",
"tier1": "Tier 1 (exact)",
"tier2": "Tier 2 (relaxed)",
"tier3": "Tier 3 (stretched)",
}
// pickKindOrder fixes breakdown row order; unattributed ("", i.e. NULL
// pick_kind — plays recorded before the mix stamped provenance, or
// whose track had rotated out of the snapshot at ingestion) renders
// last, kept visible so the parent row's sums stay transparent instead
// of silently shrinking. The DB CHECK gates pick_kind to exactly this
// vocabulary, so iterating the list is exhaustive.
var pickKindOrder = []string{
"taste", "fresh", "dormant", "cross_user", "random",
"tier1", "tier2", "tier3", "",
}
// pickKindFamily derives the sub-family for one (family, pick_kind)
// population, e.g. ("for_you", "taste") → for_you_taste "Taste picks".
func pickKindFamily(parent recFamily, kind string) recFamily {
if kind == "" {
return recFamily{parent.key + "_unattributed", "Earlier plays", parent.intent}
}
label, ok := pickKindLabels[kind]
if !ok {
label = kind
}
return recFamily{parent.key + "_" + kind, label, parent.intent}
}
// pickKindBreakdown folds a family's per-pick-kind accums into its
// Breakdown rows. Attached only when at least one attributed play
// exists — an all-unattributed breakdown would just repeat the parent
// row, and families that never stamp (radio, direct plays) stay flat.
func pickKindBreakdown(picks map[string]*familyAccum) []surfaceMetric {
attributed := int64(0)
for kind, acc := range picks {
if kind != "" {
attributed += acc.plays
}
}
if attributed == 0 {
return nil
}
out := make([]surfaceMetric, 0, len(picks))
for _, kind := range pickKindOrder {
if acc, ok := picks[kind]; ok && acc.plays > 0 {
out = append(out, acc.metric())
}
}
return out
}
// 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{}
picks := map[string]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)
// Accumulate the pick-kind population unconditionally; families
// that never stamp end up all-unattributed and get no breakdown.
kind := ""
if row.PickKind != nil {
kind = *row.PickKind
}
byKind, ok := picks[fam.key]
if !ok {
byKind = map[string]*familyAccum{}
picks[fam.key] = byKind
}
pick, ok := byKind[kind]
if !ok {
pick = &familyAccum{fam: pickKindFamily(fam, kind)}
byKind[kind] = pick
}
pick.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 {
m := acc.metric()
m.Breakdown = pickKindBreakdown(picks[acc.fam.key])
group.Surfaces = append(group.Surfaces, m)
}
}
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
}