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>

cmd/tapir/main.go

@@ -136,7 +136,8 @@ func cmdRun(ctx context.Context, log *slog.Logger) error {
 
 	r := runner.New(engine.Source, st, engine, cfg.UserID, log,
 		runner.WithBackoff(cfg.FetchBackoff),
-		runner.WithAutoWindow(cfg.AutoSummarizeWindow))
+		runner.WithAutoWindow(cfg.AutoSummarizeWindow),
+		runner.WithCaptionMemory(cfg.ChannelCaptionlessThreshold, cfg.ChannelCaptionlessWindow))
 
 	log.Info("starting run", "user", cfg.UserID, "model", cfg.SummarizerModel,
 		"gateway", cfg.GatewayURL, "poll_interval", cfg.PollInterval, "fetch_backoff", cfg.FetchBackoff,

cmd/tapir/scheduler.go

@@ -45,7 +45,8 @@ func buildUserRunner(cfg config.Config, st *store.Store, secretStore ports.Secre
 
 	return runner.New(src, st, engine, userID, log,
 		runner.WithBackoff(cfg.FetchBackoff),
-		runner.WithAutoWindow(cfg.AutoSummarizeWindow)), nil
+		runner.WithAutoWindow(cfg.AutoSummarizeWindow),
+		runner.WithCaptionMemory(cfg.ChannelCaptionlessThreshold, cfg.ChannelCaptionlessWindow)), nil
 }
 
 // userLister enumerates every registered user and reports a user's video
@@ -121,6 +122,7 @@ func runDiscoveryPass(
 		"skipped_seen", total.SkippedSeen, "skipped_no_text", total.SkippedNoText,
 		"skipped_manual", total.SkippedManual, "skipped_too_old", total.SkippedTooOld,
 		"skipped_rate_limited", total.SkippedRateLimited,
+		"skipped_no_caption_channel", total.SkippedNoCaptionChannel,
 		"channel_unavailable", total.ChannelUnavailable, "errors", total.Errors)
 	return total
 }
@@ -181,14 +183,15 @@ func rotateUsers(users []store.UserIdentity, pass int) []store.UserIdentity {
 // per-tick aggregate across all users.
 func sumStats(a, b runner.Stats) runner.Stats {
 	return runner.Stats{
-		Candidates:         a.Candidates + b.Candidates,
-		Summarized:         a.Summarized + b.Summarized,
-		SkippedSeen:        a.SkippedSeen + b.SkippedSeen,
-		SkippedNoText:      a.SkippedNoText + b.SkippedNoText,
-		SkippedManual:      a.SkippedManual + b.SkippedManual,
-		SkippedTooOld:      a.SkippedTooOld + b.SkippedTooOld,
-		SkippedRateLimited: a.SkippedRateLimited + b.SkippedRateLimited,
-		ChannelUnavailable: a.ChannelUnavailable + b.ChannelUnavailable,
-		Errors:             a.Errors + b.Errors,
+		Candidates:              a.Candidates + b.Candidates,
+		Summarized:              a.Summarized + b.Summarized,
+		SkippedSeen:             a.SkippedSeen + b.SkippedSeen,
+		SkippedNoText:           a.SkippedNoText + b.SkippedNoText,
+		SkippedManual:           a.SkippedManual + b.SkippedManual,
+		SkippedTooOld:           a.SkippedTooOld + b.SkippedTooOld,
+		SkippedRateLimited:      a.SkippedRateLimited + b.SkippedRateLimited,
+		SkippedNoCaptionChannel: a.SkippedNoCaptionChannel + b.SkippedNoCaptionChannel,
+		ChannelUnavailable:      a.ChannelUnavailable + b.ChannelUnavailable,
+		Errors:                  a.Errors + b.Errors,
 	}
 }