mathias/tapir
1
0
Fork 0
Code Issues 25 Pull Requests Actions Packages Projects Releases Wiki Activity

feat(onboard): burst picks likely-good videos, summarizes with stronger model (ADR-028)

Browse Source 
Wire the onboarding burst to its quality-aware selection and a stronger model:
- main.go onboard uses OnboardBurstVideoIDs (junk-avoiding) instead of pure
  newest-first, bounded by MinVideoSeconds / OnboardMaxVideoSeconds.
- buildBurstProcessor builds a burst-only summarizer chain led by the onboard
  model (burstChainModels: onboard -> standard ADR-022 chain, deduped, NDA lever
  intact), over the same store/cache/sink. Collapses onto the shared Processor
  when the onboard model is empty/equal-to-primary or config is incomplete.
- summarizerEndpoint + newYouTubeSource extracted so standard and burst wiring
  share one definition.
- Remove now-superseded NewestUnsummarizedVideoIDs: OnboardBurstVideoIDs(.,0,0)
  is identical pure-newest behaviour and its test covers RLS + ordering.
This commit is contained in:
mathias
2026-06-11 19:50:56 +02:00
parent 2e6fa570a3
commit 73a6d86b11
5 changed files with 178 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/adapters/store/videos.go
-38
View File
@@ -86,44 +86,6 @@ func nullDuration(seconds int) *int {
return &seconds
}
// NewestUnsummarizedVideoIDs returns up to limit of the user's videos that have
// no summary yet, newest first (published_at DESC, NULLS LAST). It caps the
// connect-time onboarding burst (Feature 1) at a fixed count: the caller marks
// these for summarization through the shared rate gate. RLS-scoped via withUser,
// so it only ever sees the requesting user's rows. limit <= 0 returns nil.
func (s *Store) NewestUnsummarizedVideoIDs(ctx context.Context, userID string, limit int) ([]string, error) {
if limit <= 0 {
return nil, nil
}
var ids []string
if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
rows, err := tx.Query(ctx,
`SELECT v.id
FROM videos v
WHERE v.user_id = $1
AND NOT EXISTS (
SELECT 1 FROM summaries su
WHERE su.user_id = v.user_id AND su.video_id = v.id)
ORDER BY v.published_at DESC NULLS LAST, v.seen_at DESC
LIMIT $2`, userID, limit)
if err != nil {
return fmt.Errorf("store: newest unsummarized: %w", err)
}
defer rows.Close()
for rows.Next() {
var id string
if err := rows.Scan(&id); err != nil {
return fmt.Errorf("store: scan newest unsummarized: %w", err)
}
ids = append(ids, id)
}
return rows.Err()
}); err != nil {
return nil, err
}
return ids, nil
}
// OnboardBurstVideoIDs returns up to limit of the user's unsummarized videos for
// the connect-time onboarding burst (ADR-028), newest-first but quality-aware: a
// video is excluded when its duration is KNOWN and outside [minSeconds, maxSeconds]
internal/adapters/store/videos_test.go
+10 -40
View File
@@ -112,38 +112,6 @@ func TestUpsertVideo_PerUserIsolation(t *testing.T) {
require.NotEqual(t, idA, idB, "same provider video for two users must be two distinct rows")
}
func TestNewestUnsummarizedVideoIDs(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
mk := func(user, pid string, day int) string {
v := ytVideo(user, pid, pid)
v.PublishedAt = time.Date(2026, 6, day, 12, 0, 0, 0, time.UTC)
id, err := s.UpsertVideo(ctx, v)
require.NoError(t, err)
return id
}
_ = mk(userA, "a1vid000001", 1)
id2 := mk(userA, "a2vid000002", 2)
id3 := mk(userA, "a3vid000003", 3)
id4 := mk(userA, "a4vid000004", 4)
mk(userB, "b1vid000009", 9) // userB's newest — must never leak via RLS
// The newest (v4) is summarized, so it's excluded from "unsummarized".
require.NoError(t, s.Deliver(ctx, summary(userA, id4, "done")))
// Cap 2, newest-first unsummarized: v3 then v2 (v4 excluded; userB excluded).
got, err := s.NewestUnsummarizedVideoIDs(ctx, userA, 2)
require.NoError(t, err)
require.Equal(t, []string{id3, id2}, got)
none, err := s.NewestUnsummarizedVideoIDs(ctx, userA, 0)
require.NoError(t, err)
require.Empty(t, none, "limit 0 returns nothing")
}
func TestOnboardBurstVideoIDs(t *testing.T) {
ctx := context.Background()
s := newStore(t)
@@ -158,14 +126,16 @@ func TestOnboardBurstVideoIDs(t *testing.T) {
return id
}
good1 := mk(userA, "good0000001", 5, 600) // 10m, newest known-good
tooLong := mk(userA, "toolong0001", 4, 20000) // > maxSeconds -> dropped
_ = tooLong
tooShort := mk(userA, "tooshort001", 3, 30) // < minSeconds -> dropped
_ = tooShort
unknown := mk(userA, "unknown0001", 2, 0) // NULL duration -> kept, ranked last
good2 := mk(userA, "good0000002", 1, 800) // known-good but oldest
mk(userB, "bvid0000009", 9, 600) // userB -> must not leak via RLS
summarized := mk(userA, "summ0000001", 6, 600) // newest known-good, but already summarized
good1 := mk(userA, "good0000001", 5, 600) // 10m, newest UNsummarized known-good
tooLong := mk(userA, "toolong0001", 4, 20000) // > maxSeconds -> dropped
tooShort := mk(userA, "tooshort001", 3, 30) // < minSeconds -> dropped
unknown := mk(userA, "unknown0001", 2, 0) // NULL duration -> kept, ranked last
good2 := mk(userA, "good0000002", 1, 800) // known-good but oldest
mk(userB, "bvid0000009", 9, 600) // userB -> must not leak via RLS
// The newest video is summarized, so it is excluded from the burst.
require.NoError(t, s.Deliver(ctx, summary(userA, summarized, "done")))
const minSec, maxSec = 60, 14400