feat(tuning): weekly trend view — per-surface series + knob-turn markers
test-go / test (push) Successful in 33s
test-web / test (push) Failing after 38s
test-go / integration (push) Successful in 4m44s

The verify half of the tune→verify loop (#1251), on the same admin
Tuning page as the knobs:

- RecommendationWeeklyTrends: weekly per-source outcomes aggregated
  across all users (the knobs are global, so judging a turn needs
  global outcomes — rows carry rates only, no track/user identity),
  with a taste-hit count per bucket: plays whose track's artist has a
  positive weight in the player's current taste profile. That's the
  "cheap recompute" reading — retroactive over the whole window, at
  the cost of profile drift.
- GET /api/admin/recommendation-trends?weeks=N (default 12, cap 52):
  per-family weekly series (skip rate, sample-weighted completion,
  taste-hit rate) plus the tuning-audit markers inside the window.
- Web: sparkline table under the tuning cards — skip rate per week on
  a shared axis with dashed ticks at knob turns, latest-week columns,
  window taste-hit rate, low-volume rows dimmed as anecdote, and a
  plain-text list of the window's tuning changes.

Also fixes the revive unused-parameter lint on the tuning GET handler
that failed CI run 1903 on the previous commit.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TsF3cNoKrqCYsU78cXC8U6
This commit is contained in:
2026-07-03 09:29:33 -04:00
parent 0d0a8f46b1
commit 9ad4343c76
9 changed files with 773 additions and 15 deletions
+80 -10
View File
@@ -12,7 +12,6 @@ import (
)
const recommendationSourceMetricsForUser = `-- name: RecommendationSourceMetricsForUser :many
SELECT
pe.source,
pe.pick_kind,
@@ -41,15 +40,6 @@ type RecommendationSourceMetricsForUserRow struct {
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 recommendation surface; NULL means the user picked the track manually —
// those rows are INCLUDED here as the baseline control group the surfaces are
// judged against (milestone #127: delta-vs-baseline is what makes the numbers
// actionable). Raw source strings are bucketed into stable surface families in
// the Go handler; completion_n is carried so family merges can weight
// avg_completion correctly.
// $1 user_id, $2 window_days. plays/skips are counts; avg_completion is the
// mean completion ratio over the completion_n plays that recorded one.
// pick_kind splits For You plays into taste/fresh/unattributed (#1249);
@@ -80,3 +70,83 @@ func (q *Queries) RecommendationSourceMetricsForUser(ctx context.Context, arg Re
}
return items, nil
}
const recommendationWeeklyTrends = `-- name: RecommendationWeeklyTrends :many
SELECT
date_trunc('week', pe.started_at)::date AS week_start,
pe.source,
count(*)::bigint AS plays,
count(*) FILTER (WHERE pe.was_skipped)::bigint AS skips,
count(pe.completion_ratio)::bigint AS completion_n,
COALESCE(avg(pe.completion_ratio), 0)::float8 AS avg_completion,
count(*) FILTER (WHERE tpa.artist_id IS NOT NULL)::bigint AS taste_hits
FROM play_events pe
JOIN tracks t ON t.id = pe.track_id
LEFT JOIN taste_profile_artists tpa
ON tpa.user_id = pe.user_id
AND tpa.artist_id = t.artist_id
AND tpa.weight > 0
WHERE pe.started_at > now() - ($1::int * INTERVAL '1 week')
GROUP BY 1, 2
ORDER BY 1, 2
`
type RecommendationWeeklyTrendsRow struct {
WeekStart pgtype.Date
Source *string
Plays int64
Skips int64
CompletionN int64
AvgCompletion float64
TasteHits int64
}
// 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 recommendation surface; NULL means the user picked the track manually —
// those rows are INCLUDED here as the baseline control group the surfaces are
// judged against (milestone #127: delta-vs-baseline is what makes the numbers
// actionable). Raw source strings are bucketed into stable surface families in
// the Go handler; completion_n is carried so family merges can weight
// avg_completion correctly.
// Weekly per-source outcome series for the tuning lab's trend view
// (#1251). Aggregated across ALL users: the tuning knobs are global,
// so judging a knob turn needs global outcomes — rows carry rates
// only, no track or user identity. NULL-source (manual) rows are
// included as the baseline family.
//
// taste_hits counts plays whose track's artist has a positive weight
// in that user's CURRENT taste profile — the "cheap recompute" option:
// retroactive over the whole window, at the cost of drift (the profile
// is today's, the play may be weeks old). Good enough to read whether
// a surface is feeding taste-fitting tracks.
// $1 window in weeks.
func (q *Queries) RecommendationWeeklyTrends(ctx context.Context, weeks int32) ([]RecommendationWeeklyTrendsRow, error) {
rows, err := q.db.Query(ctx, recommendationWeeklyTrends, weeks)
if err != nil {
return nil, err
}
defer rows.Close()
var items []RecommendationWeeklyTrendsRow
for rows.Next() {
var i RecommendationWeeklyTrendsRow
if err := rows.Scan(
&i.WeekStart,
&i.Source,
&i.Plays,
&i.Skips,
&i.CompletionN,
&i.AvgCompletion,
&i.TasteHits,
); err != nil {
return nil, err
}
items = append(items, i)
}
if err := rows.Err(); err != nil {
return nil, err
}
return items, nil
}
@@ -8,6 +8,37 @@
-- the Go handler; completion_n is carried so family merges can weight
-- avg_completion correctly.
-- name: RecommendationWeeklyTrends :many
-- Weekly per-source outcome series for the tuning lab's trend view
-- (#1251). Aggregated across ALL users: the tuning knobs are global,
-- so judging a knob turn needs global outcomes — rows carry rates
-- only, no track or user identity. NULL-source (manual) rows are
-- included as the baseline family.
--
-- taste_hits counts plays whose track's artist has a positive weight
-- in that user's CURRENT taste profile — the "cheap recompute" option:
-- retroactive over the whole window, at the cost of drift (the profile
-- is today's, the play may be weeks old). Good enough to read whether
-- a surface is feeding taste-fitting tracks.
-- $1 window in weeks.
SELECT
date_trunc('week', pe.started_at)::date AS week_start,
pe.source,
count(*)::bigint AS plays,
count(*) FILTER (WHERE pe.was_skipped)::bigint AS skips,
count(pe.completion_ratio)::bigint AS completion_n,
COALESCE(avg(pe.completion_ratio), 0)::float8 AS avg_completion,
count(*) FILTER (WHERE tpa.artist_id IS NOT NULL)::bigint AS taste_hits
FROM play_events pe
JOIN tracks t ON t.id = pe.track_id
LEFT JOIN taste_profile_artists tpa
ON tpa.user_id = pe.user_id
AND tpa.artist_id = t.artist_id
AND tpa.weight > 0
WHERE pe.started_at > now() - (sqlc.arg(weeks)::int * INTERVAL '1 week')
GROUP BY 1, 2
ORDER BY 1, 2;
-- name: RecommendationSourceMetricsForUser :many
-- $1 user_id, $2 window_days. plays/skips are counts; avg_completion is the
-- mean completion ratio over the completion_n plays that recorded one.