feat(metrics): provenance as standard — pick_kind for all system mixes
test-go / test (push) Successful in 31s
test-web / test (push) Successful in 38s
test-go / integration (push) Successful in 4m36s

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
This commit is contained in:
2026-07-02 23:26:52 -04:00
parent fb4431207d
commit 5faa57634b
14 changed files with 410 additions and 156 deletions
+35 -29
View File
@@ -31,33 +31,6 @@ func (q *Queries) GetCurrentSessionVectorForUser(ctx context.Context, userID pgt
return session_vector_at_play, err
}
const getForYouPickKindForTrack = `-- name: GetForYouPickKindForTrack :one
SELECT pt.pick_kind
FROM playlist_tracks pt
JOIN playlists p ON p.id = pt.playlist_id
WHERE p.user_id = $1
AND p.system_variant = 'for_you'
AND pt.track_id = $2
LIMIT 1
`
type GetForYouPickKindForTrackParams struct {
UserID pgtype.UUID
TrackID pgtype.UUID
}
// Looks a track up in the user's CURRENT For You snapshot and returns
// its pick_kind ('taste'/'fresh'). Used at play-ingestion time to
// freeze exploration attribution onto the play_event — the snapshot is
// rebuilt daily, so attribution can't be reconstructed at read time
// (#1249). No row = track not in today's snapshot (caller stores NULL).
func (q *Queries) GetForYouPickKindForTrack(ctx context.Context, arg GetForYouPickKindForTrackParams) (*string, error) {
row := q.db.QueryRow(ctx, getForYouPickKindForTrack, arg.UserID, arg.TrackID)
var pick_kind *string
err := row.Scan(&pick_kind)
return pick_kind, err
}
const getMostRecentPlaySessionForUser = `-- name: GetMostRecentPlaySessionForUser :one
SELECT id, user_id, started_at, ended_at, last_event_at, track_count, client_id FROM play_sessions
WHERE user_id = $1
@@ -137,6 +110,38 @@ func (q *Queries) GetPlayEventByID(ctx context.Context, id pgtype.UUID) (PlayEve
return i, err
}
const getSystemPickKindForTrack = `-- name: GetSystemPickKindForTrack :one
SELECT pt.pick_kind
FROM playlist_tracks pt
JOIN playlists p ON p.id = pt.playlist_id
WHERE p.user_id = $1
AND p.system_variant = $2
AND pt.track_id = $3
LIMIT 1
`
type GetSystemPickKindForTrackParams struct {
UserID pgtype.UUID
SystemVariant *string
TrackID pgtype.UUID
}
// Looks a track up in the user's CURRENT snapshot of the given system
// variant and returns its pick_kind. Used at play-ingestion time to
// freeze provenance onto the play_event — snapshots rebuild daily, so
// attribution can't be reconstructed at read time (#1249/#1270). No
// row = track not in today's snapshot (caller stores NULL); a row with
// NULL pick_kind = the variant doesn't stamp (yet). songs_like_artist
// is non-singleton (up to 3 mixes/user); a track in two of them takes
// whichever LIMIT 1 hits — acceptable, tier stamps there describe the
// same eligibility ladder.
func (q *Queries) GetSystemPickKindForTrack(ctx context.Context, arg GetSystemPickKindForTrackParams) (*string, error) {
row := q.db.QueryRow(ctx, getSystemPickKindForTrack, arg.UserID, arg.SystemVariant, arg.TrackID)
var pick_kind *string
err := row.Scan(&pick_kind)
return pick_kind, err
}
const insertPlayEvent = `-- name: InsertPlayEvent :one
INSERT INTO play_events (
user_id, track_id, session_id, started_at, client_id, source, pick_kind
@@ -154,8 +159,9 @@ type InsertPlayEventParams struct {
PickKind *string
}
// pick_kind is non-NULL only for source='for_you' plays whose track was
// found in the user's live For You snapshot at ingestion time (#1249).
// pick_kind is non-NULL only for system-playlist plays whose track was
// found (with a stamped kind) in the user's live snapshot for that
// variant at ingestion time (#1249, generalized in #1270).
func (q *Queries) InsertPlayEvent(ctx context.Context, arg InsertPlayEventParams) (PlayEvent, error) {
row := q.db.QueryRow(ctx, insertPlayEvent,
arg.UserID,
@@ -0,0 +1,19 @@
-- Rows stamped with the widened vocabulary must be cleared before the
-- narrow CHECK can be re-added; NULL reads as "unattributed", which is
-- the honest downgrade.
UPDATE play_events SET pick_kind = NULL
WHERE pick_kind NOT IN ('taste', 'fresh');
UPDATE playlist_tracks SET pick_kind = NULL
WHERE pick_kind NOT IN ('taste', 'fresh');
ALTER TABLE play_events
DROP CONSTRAINT play_events_pick_kind_check;
ALTER TABLE play_events
ADD CONSTRAINT play_events_pick_kind_check
CHECK (pick_kind IN ('taste', 'fresh'));
ALTER TABLE playlist_tracks
DROP CONSTRAINT playlist_tracks_pick_kind_check;
ALTER TABLE playlist_tracks
ADD CONSTRAINT playlist_tracks_pick_kind_check
CHECK (pick_kind IN ('taste', 'fresh'));
@@ -0,0 +1,41 @@
-- Provenance as standard (milestone #127, Scribe #1270).
--
-- #1249 introduced pick_kind as a For You one-off ('taste'/'fresh').
-- The mechanism — stamp WHY a track is in the snapshot at build time,
-- freeze it onto the play at ingestion, break it down in metrics — is
-- now the standard for every system mix, so the CHECK vocabulary
-- widens to cover:
--
-- taste / fresh For You head vs freshness-injection tail
-- dormant / cross_user / random
-- Discover's three candidate buckets — makes
-- the 40/30/30 allocation measurable instead
-- of a guess
-- tier1 / tier2 / tier3 the tiered-eligibility ladder (project rule
-- #131): tier 1 pins the mix's exact desire,
-- each higher tier steps back a little. Tier
-- provenance is how we measure what the
-- step-back trades away.
--
-- Postgres CHECK whitelists can't be altered in place: DROP + re-ADD
-- with the expanded list, in the same migration.
ALTER TABLE playlist_tracks
DROP CONSTRAINT playlist_tracks_pick_kind_check;
ALTER TABLE playlist_tracks
ADD CONSTRAINT playlist_tracks_pick_kind_check
CHECK (pick_kind IN (
'taste', 'fresh',
'dormant', 'cross_user', 'random',
'tier1', 'tier2', 'tier3'
));
ALTER TABLE play_events
DROP CONSTRAINT play_events_pick_kind_check;
ALTER TABLE play_events
ADD CONSTRAINT play_events_pick_kind_check
CHECK (pick_kind IN (
'taste', 'fresh',
'dormant', 'cross_user', 'random',
'tier1', 'tier2', 'tier3'
));
+15 -10
View File
@@ -24,25 +24,30 @@ ORDER BY started_at DESC
LIMIT 1;
-- name: InsertPlayEvent :one
-- pick_kind is non-NULL only for source='for_you' plays whose track was
-- found in the user's live For You snapshot at ingestion time (#1249).
-- pick_kind is non-NULL only for system-playlist plays whose track was
-- found (with a stamped kind) in the user's live snapshot for that
-- variant at ingestion time (#1249, generalized in #1270).
INSERT INTO play_events (
user_id, track_id, session_id, started_at, client_id, source, pick_kind
) VALUES ($1, $2, $3, $4, $5, $6, sqlc.narg(pick_kind)::text)
RETURNING *;
-- name: GetForYouPickKindForTrack :one
-- Looks a track up in the user's CURRENT For You snapshot and returns
-- its pick_kind ('taste'/'fresh'). Used at play-ingestion time to
-- freeze exploration attribution onto the play_event — the snapshot is
-- rebuilt daily, so attribution can't be reconstructed at read time
-- (#1249). No row = track not in today's snapshot (caller stores NULL).
-- name: GetSystemPickKindForTrack :one
-- Looks a track up in the user's CURRENT snapshot of the given system
-- variant and returns its pick_kind. Used at play-ingestion time to
-- freeze provenance onto the play_event — snapshots rebuild daily, so
-- attribution can't be reconstructed at read time (#1249/#1270). No
-- row = track not in today's snapshot (caller stores NULL); a row with
-- NULL pick_kind = the variant doesn't stamp (yet). songs_like_artist
-- is non-singleton (up to 3 mixes/user); a track in two of them takes
-- whichever LIMIT 1 hits — acceptable, tier stamps there describe the
-- same eligibility ladder.
SELECT pt.pick_kind
FROM playlist_tracks pt
JOIN playlists p ON p.id = pt.playlist_id
WHERE p.user_id = $1
AND p.system_variant = 'for_you'
AND pt.track_id = $2
AND p.system_variant = $2
AND pt.track_id = $3
LIMIT 1;
-- name: UpdatePlayEventEnded :one