feat(discovery): per-channel caption-availability memory (ADR-024)
After transcript caching (ADR-021) and the Shorts filter (ADR-023), the remaining caption waste is the first fetch on every new video of a channel that never has English captions — each costs one rate-limited fetch to resolve to "none", and on a throttled IP churns the backoff machinery first. Remember, per (user, channel), a streak of consecutive no-caption outcomes (channel_caption_state, migration 016, RLS-scoped). Once it reaches TAPIR_CHANNEL_CAPTIONLESS_THRESHOLD (default 5) the channel is suppressed — videos discovered/listed but not caption-fetched — for TAPIR_CHANNEL_CAPTIONLESS_WINDOW (default 14d), then one is re-probed (auto-recovery). A successful fetch resets the streak; a 429 does not count; an explicit manual request bypasses suppression. threshold=0 disables. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -0,0 +1,83 @@
|
||||
package store
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/jackc/pgx/v5"
|
||||
)
|
||||
|
||||
// CaptionlessChannels returns the set of channel ids currently suppressed for the
|
||||
// user — channels whose recent videos all yielded no captions, within their
|
||||
// suppression window (ADR-024). The runner skips caption fetches for these
|
||||
// channels' videos. A channel whose window has expired is not returned, so its
|
||||
// next video is re-probed (auto-recovery).
|
||||
func (s *Store) CaptionlessChannels(ctx context.Context, userID string) (map[string]bool, error) {
|
||||
out := map[string]bool{}
|
||||
err := s.withUser(ctx, userID, func(tx pgx.Tx) error {
|
||||
rows, err := tx.Query(ctx, `
|
||||
SELECT channel_id FROM channel_caption_state
|
||||
WHERE user_id = $1 AND captionless_until IS NOT NULL AND captionless_until > now()`,
|
||||
userID)
|
||||
if err != nil {
|
||||
return fmt.Errorf("store: caption-less channels: %w", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
for rows.Next() {
|
||||
var ch string
|
||||
if err := rows.Scan(&ch); err != nil {
|
||||
return fmt.Errorf("store: scan caption-less channel: %w", err)
|
||||
}
|
||||
out[ch] = true
|
||||
}
|
||||
return rows.Err()
|
||||
})
|
||||
return out, err
|
||||
}
|
||||
|
||||
// RecordChannelCaptionOutcome updates a channel's caption-availability memory
|
||||
// after a fetch attempt (ADR-024). hadCaptions resets the channel (consecutive
|
||||
// count to 0, suppression cleared). Otherwise the consecutive no-caption count is
|
||||
// incremented; once it reaches threshold the channel is suppressed for window.
|
||||
// threshold <= 0 is a no-op (feature disabled). An empty channelID is ignored
|
||||
// (some sources may not carry one).
|
||||
func (s *Store) RecordChannelCaptionOutcome(ctx context.Context, userID, channelID string, hadCaptions bool, threshold int, window time.Duration) error {
|
||||
if channelID == "" || threshold <= 0 {
|
||||
return nil
|
||||
}
|
||||
return s.withUser(ctx, userID, func(tx pgx.Tx) error {
|
||||
if hadCaptions {
|
||||
_, err := tx.Exec(ctx, `
|
||||
INSERT INTO channel_caption_state (user_id, channel_id, consecutive_none, captionless_until, updated_at)
|
||||
VALUES ($1, $2, 0, NULL, now())
|
||||
ON CONFLICT (user_id, channel_id)
|
||||
DO UPDATE SET consecutive_none = 0, captionless_until = NULL, updated_at = now()`,
|
||||
userID, channelID)
|
||||
if err != nil {
|
||||
return fmt.Errorf("store: reset channel caption state: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
// No captions: increment the streak; suppress once it reaches threshold.
|
||||
// captionless_until is set from the NEW count inside the same statement so
|
||||
// the decision is atomic with the increment.
|
||||
until := time.Now().Add(window)
|
||||
_, err := tx.Exec(ctx, `
|
||||
INSERT INTO channel_caption_state (user_id, channel_id, consecutive_none, captionless_until, updated_at)
|
||||
VALUES ($1, $2, 1, CASE WHEN 1 >= $3 THEN $4::timestamptz ELSE NULL END, now())
|
||||
ON CONFLICT (user_id, channel_id)
|
||||
DO UPDATE SET
|
||||
consecutive_none = channel_caption_state.consecutive_none + 1,
|
||||
captionless_until = CASE
|
||||
WHEN channel_caption_state.consecutive_none + 1 >= $3 THEN $4::timestamptz
|
||||
ELSE channel_caption_state.captionless_until
|
||||
END,
|
||||
updated_at = now()`,
|
||||
userID, channelID, threshold, until)
|
||||
if err != nil {
|
||||
return fmt.Errorf("store: record channel no-caption: %w", err)
|
||||
}
|
||||
return nil
|
||||
})
|
||||
}
|
||||
Reference in New Issue
Block a user