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>

internal/adapters/store/channel_caption.go

@@ -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
+	})
+}

internal/adapters/store/channel_caption_test.go

@@ -0,0 +1,67 @@
+package store_test
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestChannelCaptionMemory_SuppressesAfterThreshold(t *testing.T) {
+	ctx := context.Background()
+	s := newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUser(t, super, userA)
+
+	const threshold = 3
+	window := time.Hour
+
+	// Below threshold: not yet suppressed.
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanX", false, threshold, window))
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanX", false, threshold, window))
+	got, err := s.CaptionlessChannels(ctx, userA)
+	require.NoError(t, err)
+	require.NotContains(t, got, "chanX", "2 < threshold 3: not suppressed yet")
+
+	// Crossing the threshold suppresses the channel.
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanX", false, threshold, window))
+	got, err = s.CaptionlessChannels(ctx, userA)
+	require.NoError(t, err)
+	require.Contains(t, got, "chanX", "3 consecutive no-caption results suppress the channel")
+
+	// A successful caption fetch resets it.
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanX", true, threshold, window))
+	got, err = s.CaptionlessChannels(ctx, userA)
+	require.NoError(t, err)
+	require.NotContains(t, got, "chanX", "a captioned video clears suppression")
+}
+
+func TestChannelCaptionMemory_WindowExpiryReProbes(t *testing.T) {
+	ctx := context.Background()
+	s := newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUser(t, super, userA)
+
+	// A negative window means captionless_until lands in the past — modelling an
+	// elapsed suppression window, which must make the channel eligible again.
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanY", false, 1, -time.Hour))
+	got, err := s.CaptionlessChannels(ctx, userA)
+	require.NoError(t, err)
+	require.NotContains(t, got, "chanY", "an expired window re-enables the channel for a re-probe")
+}
+
+func TestChannelCaptionMemory_DisabledThresholdIsNoOp(t *testing.T) {
+	ctx := context.Background()
+	s := newStore(t)
+	super := rawPool(t)
+	resetDB(t, super)
+	seedUser(t, super, userA)
+
+	require.NoError(t, s.RecordChannelCaptionOutcome(ctx, userA, "chanZ", false, 0, time.Hour))
+	got, err := s.CaptionlessChannels(ctx, userA)
+	require.NoError(t, err)
+	require.Empty(t, got, "threshold 0 disables the memory — nothing recorded")
+}

internal/adapters/store/migrate_test.go

@@ -53,7 +53,9 @@ func TestMigration010LoginEventsUpDown(t *testing.T) {
 	require.True(t, loginEventsExists(t), "login_events must exist at latest migration")
 
 	m := fileMigrator(t)
-	// 011..015 sit above 010; step them down first so 010 is exercised in isolation.
+	// 011..016 sit above 010; step them down first so 010 is exercised in isolation.
+	require.NoError(t, m.Steps(-1), "down 016 drops channel_caption_state, login_events intact")
+	require.True(t, loginEventsExists(t), "016 down leaves login_events intact")
 	require.NoError(t, m.Steps(-1), "down 015 reshapes transcripts, login_events intact")
 	require.True(t, loginEventsExists(t), "015 down leaves login_events intact")
 	require.NoError(t, m.Steps(-1), "down 014 drops channel_title, login_events intact")
@@ -68,7 +70,7 @@ func TestMigration010LoginEventsUpDown(t *testing.T) {
 	require.NoError(t, m.Steps(-1), "down 010 must drop login_events")
 	require.False(t, loginEventsExists(t), "login_events must be gone after the down migration")
 
-	require.NoError(t, m.Steps(6), "up must recreate 010 then re-apply 011..015")
+	require.NoError(t, m.Steps(7), "up must recreate 010 then re-apply 011..016")
 	require.True(t, loginEventsExists(t), "login_events must be restored after the up migration")
 }
 
@@ -91,6 +93,7 @@ func TestMigration011AutoSummarizeDefaultUpDown(t *testing.T) {
 	require.Equal(t, "true", autoSummarizeDefault(t), "011 sets the default to TRUE")
 
 	m := fileMigrator(t)
+	require.NoError(t, m.Steps(-1), "down 016 drops channel_caption_state")
 	require.NoError(t, m.Steps(-1), "down 015 reshapes transcripts")
 	require.NoError(t, m.Steps(-1), "down 014 drops channel_title")
 	require.NoError(t, m.Steps(-1), "down 013 drops channel_errors")
@@ -104,6 +107,7 @@ func TestMigration011AutoSummarizeDefaultUpDown(t *testing.T) {
 	require.NoError(t, m.Steps(1), "up 013 creates channel_errors")
 	require.NoError(t, m.Steps(1), "up 014 recreates channel_title")
 	require.NoError(t, m.Steps(1), "up 015 reshapes transcripts to shared")
+	require.NoError(t, m.Steps(1), "up 016 recreates channel_caption_state (HEAD)")
 }
 
 // channelTitleExists reports whether videos.channel_title is present.
@@ -123,6 +127,8 @@ func TestMigration014VideoChannelTitleUpDown(t *testing.T) {
 	require.True(t, channelTitleExists(t), "channel_title exists at latest migration")
 
 	m := fileMigrator(t)
+	require.NoError(t, m.Steps(-1), "down 016 drops channel_caption_state, channel_title intact")
+	require.True(t, channelTitleExists(t), "016 down leaves channel_title intact")
 	require.NoError(t, m.Steps(-1), "down 015 reshapes transcripts, channel_title intact")
 	require.True(t, channelTitleExists(t), "015 down leaves channel_title intact")
 	require.NoError(t, m.Steps(-1), "down 014 must drop channel_title")
@@ -130,7 +136,8 @@ func TestMigration014VideoChannelTitleUpDown(t *testing.T) {
 
 	require.NoError(t, m.Steps(1), "up 014 must recreate channel_title")
 	require.True(t, channelTitleExists(t), "channel_title must be restored after the up migration")
-	require.NoError(t, m.Steps(1), "up 015 restores the shared transcripts shape (HEAD)")
+	require.NoError(t, m.Steps(1), "up 015 restores the shared transcripts shape")
+	require.NoError(t, m.Steps(1), "up 016 recreates channel_caption_state (HEAD)")
 }
 
 // TestMigration012FixAutoSummarizeRLS proves 012 runs cleanly and flips any

internal/adapters/store/migrations/016_channel_caption_state.down.sql

@@ -0,0 +1 @@
+DROP TABLE channel_caption_state;

internal/adapters/store/migrations/016_channel_caption_state.up.sql

@@ -0,0 +1,30 @@
+-- Migration 016: per-(user, channel) caption-availability memory (ADR-024).
+--
+-- Some channels never publish English captions (foreign-language news, music,
+-- etc.). Each of their new videos still costs ONE rate-limited caption fetch
+-- (ADR-014) before resolving to "none" — and on a throttled egress IP that fetch
+-- may 429 and churn through the backoff machinery first. This table remembers
+-- channels that repeatedly yield no captions so discovery can stop attempting
+-- their videos, freeing the scarce fetch budget for channels that do have them.
+--
+-- consecutive_none counts no-caption outcomes in a row; a successful fetch resets
+-- it to 0. Once it crosses the threshold the channel is suppressed until
+-- captionless_until, after which one video is re-probed (auto-recovery for a
+-- channel that starts adding captions). Per-user + RLS-scoped, consistent with
+-- the rest of the user-owned schema (subscriptions are per-user; ADR-012).
+CREATE TABLE channel_caption_state (
+    user_id           UUID        NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+    channel_id        TEXT        NOT NULL,
+    consecutive_none  INT         NOT NULL DEFAULT 0,
+    captionless_until TIMESTAMPTZ,
+    updated_at        TIMESTAMPTZ NOT NULL DEFAULT now(),
+    PRIMARY KEY (user_id, channel_id)
+);
+
+CREATE INDEX idx_channel_caption_state_user_id ON channel_caption_state(user_id);
+
+ALTER TABLE channel_caption_state ENABLE ROW LEVEL SECURITY;
+ALTER TABLE channel_caption_state FORCE ROW LEVEL SECURITY;
+CREATE POLICY channel_caption_state_isolation ON channel_caption_state
+    FOR ALL
+    USING (user_id = current_setting('tapir.current_user_id', true)::uuid);