feat(store): TranscriptStatus read field + status setter/loader

Surfaces videos.transcript_status (migration 007) on SummaryRow and adds
SetTranscriptStatus / GetTranscriptStatus / RateLimitedVideoIDs.

SetTranscriptStatus is the single choke point for the rate-limit lifecycle:
"rate_limited" stamps rate_limited_at = NOW(), every other status clears it,
so the runner's backoff window and the UI badge read one consistent source.
RateLimitedVideoIDs is the per-pass loader (mirrors SeenVideoIDs) the runner
uses to skip still-throttled videos without re-hitting the caption endpoint.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-03 22:52:48 +02:00
co-authored by Claude Opus 4.8
parent f50c072d65
commit 1e81965519
3 changed files with 189 additions and 1 deletions
+7 -1
View File
@@ -49,6 +49,10 @@ type SummaryRow struct {
// set by the web "Summarize" button and cleared by the next `tapir run`. Only // set by the web "Summarize" button and cleared by the next `tapir run`. Only
// populated by ListVideos/GetVideoRow (summary-only reads leave it false). // populated by ListVideos/GetVideoRow (summary-only reads leave it false).
SummarizeRequested bool SummarizeRequested bool
// TranscriptStatus mirrors videos.transcript_status (migration 007): "" (unset),
// "none", "rate_limited", or "fetched". Drives the "Retrying later" list badge.
// Only populated by ListVideos/GetVideoRow ("" on summary-only reads).
TranscriptStatus string
} }
// selectSummary is the shared projection for both reads. videos is LEFT JOINed // selectSummary is the shared projection for both reads. videos is LEFT JOINed
@@ -132,7 +136,8 @@ const selectVideo = `
COALESCE(s.fallback_used, FALSE), COALESCE(s.fallback_used, FALSE),
COALESCE(s.created_at, v.seen_at), COALESCE(s.created_at, v.seen_at),
(s.id IS NOT NULL) AS summarized, (s.id IS NOT NULL) AS summarized,
v.summarize_requested v.summarize_requested,
COALESCE(v.transcript_status, '')
FROM videos v FROM videos v
LEFT JOIN summaries s ON s.video_id = v.id AND s.user_id = v.user_id` LEFT JOIN summaries s ON s.video_id = v.id AND s.user_id = v.user_id`
@@ -245,6 +250,7 @@ func scanVideoRow(rows pgx.Row) (SummaryRow, error) {
&row.CreatedAt, &row.CreatedAt,
&row.Summarized, &row.Summarized,
&row.SummarizeRequested, &row.SummarizeRequested,
&row.TranscriptStatus,
); err != nil { ); err != nil {
return SummaryRow{}, fmt.Errorf("store: scan video: %w", err) return SummaryRow{}, fmt.Errorf("store: scan video: %w", err)
} }
@@ -0,0 +1,102 @@
package store
import (
"context"
"errors"
"fmt"
"time"
"github.com/jackc/pgx/v5"
)
// validTranscriptStatuses bounds SetTranscriptStatus input. "" clears the status
// (column NULL); the three named states mirror migration 007's documented values.
var validTranscriptStatuses = map[string]bool{
"": true,
"none": true,
"rate_limited": true,
"fetched": true,
}
// SetTranscriptStatus records the outcome of the last transcript attempt for a
// video (migration 007). When status is "rate_limited" it also stamps
// rate_limited_at = NOW() so the runner can back off; every other status clears
// that timestamp. "" unsets the status (column NULL). An unknown status is
// rejected. Scoped via withUser, so RLS confines the UPDATE to the caller's own
// video; ErrNotFound when the user has no such video.
func (s *Store) SetTranscriptStatus(ctx context.Context, userID, videoID, status string) error {
if !validTranscriptStatuses[status] {
return fmt.Errorf("store: invalid transcript status %q", status)
}
return s.withUser(ctx, userID, func(tx pgx.Tx) error {
ct, err := tx.Exec(ctx,
`UPDATE videos
SET transcript_status = NULLIF($1, ''),
rate_limited_at = CASE WHEN $1 = 'rate_limited' THEN NOW() ELSE NULL END
WHERE id = $2`,
status, videoID)
if err != nil {
return fmt.Errorf("store: set transcript status: %w", err)
}
if ct.RowsAffected() == 0 {
return ErrNotFound
}
return nil
})
}
// GetTranscriptStatus returns a video's transcript_status ("" when unset/NULL).
// Returns ErrNotFound when the user has no such video. Scoped via withUser.
func (s *Store) GetTranscriptStatus(ctx context.Context, userID, videoID string) (string, error) {
var status string
if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
err := tx.QueryRow(ctx,
`SELECT COALESCE(transcript_status, '') FROM videos WHERE id = $1`, videoID).Scan(&status)
if errors.Is(err, pgx.ErrNoRows) {
return ErrNotFound
}
return err
}); err != nil {
if errors.Is(err, ErrNotFound) {
return "", ErrNotFound
}
return "", fmt.Errorf("store: get transcript status: %w", err)
}
return status, nil
}
// RateLimitedVideoIDs returns the user's videos currently in the "rate_limited"
// state, mapped to when the 429 was stamped (rate_limited_at). The run loop loads
// it once per pass (mirroring SeenVideoIDs) to skip re-fetching a video still
// inside the backoff window, saving caption requests. Scoped by user_id.
func (s *Store) RateLimitedVideoIDs(ctx context.Context, userID string) (map[string]time.Time, error) {
out := make(map[string]time.Time)
if err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
rows, err := tx.Query(ctx,
`SELECT id, rate_limited_at FROM videos
WHERE user_id = $1 AND transcript_status = 'rate_limited' AND rate_limited_at IS NOT NULL`,
userID)
if err != nil {
return fmt.Errorf("store: rate limited video ids: %w", err)
}
defer rows.Close()
for rows.Next() {
var (
id string
at time.Time
)
if err := rows.Scan(&id, &at); err != nil {
return fmt.Errorf("store: scan rate limited id: %w", err)
}
out[id] = at
}
if err := rows.Err(); err != nil {
return fmt.Errorf("store: iterate rate limited ids: %w", err)
}
return nil
}); err != nil {
return nil, err
}
return out, nil
}
@@ -0,0 +1,80 @@
package store_test
import (
"context"
"testing"
"github.com/stretchr/testify/require"
"gitea.d-ma.be/mathias/tapir/internal/adapters/store"
)
func TestSetTranscriptStatus_RoundTrip(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
id, err := s.UpsertVideo(ctx, ytVideo(userA, "rt12345", "round trip"))
require.NoError(t, err)
// Unset by default.
got, err := s.GetTranscriptStatus(ctx, userA, id)
require.NoError(t, err)
require.Equal(t, "", got)
for _, status := range []string{"none", "fetched", "rate_limited", ""} {
require.NoError(t, s.SetTranscriptStatus(ctx, userA, id, status))
got, err := s.GetTranscriptStatus(ctx, userA, id)
require.NoError(t, err)
require.Equal(t, status, got)
}
}
func TestSetTranscriptStatus_RejectsInvalid(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
id, err := s.UpsertVideo(ctx, ytVideo(userA, "bad12345", "bad status"))
require.NoError(t, err)
require.Error(t, s.SetTranscriptStatus(ctx, userA, id, "bogus"))
// The rejected write left the status untouched.
got, err := s.GetTranscriptStatus(ctx, userA, id)
require.NoError(t, err)
require.Equal(t, "", got)
}
func TestSetTranscriptStatus_NotFound(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
require.ErrorIs(t, s.SetTranscriptStatus(ctx, userA, videoX, "fetched"), store.ErrNotFound)
_, err := s.GetTranscriptStatus(ctx, userA, videoX)
require.ErrorIs(t, err, store.ErrNotFound)
}
func TestRateLimitedVideoIDs_StampsAndClears(t *testing.T) {
ctx := context.Background()
s := newStore(t)
resetDB(t, rawPool(t))
id, err := s.UpsertVideo(ctx, ytVideo(userA, "rl12345", "rate limited"))
require.NoError(t, err)
// Marking rate_limited stamps rate_limited_at, so the video appears.
require.NoError(t, s.SetTranscriptStatus(ctx, userA, id, "rate_limited"))
rl, err := s.RateLimitedVideoIDs(ctx, userA)
require.NoError(t, err)
require.Contains(t, rl, id)
require.False(t, rl[id].IsZero(), "rate_limited_at must be stamped")
// Moving off rate_limited clears the timestamp, so it drops out.
require.NoError(t, s.SetTranscriptStatus(ctx, userA, id, "fetched"))
rl, err = s.RateLimitedVideoIDs(ctx, userA)
require.NoError(t, err)
require.NotContains(t, rl, id)
}