fix(scheduler): rotate over connected users only for true fair share

The lead-user rotation rotated the full ListAllUsers set, so a connectionless
orphan identity ate a rotation slot — collapsing onto the next real user and
skewing the lead share (two real users got 2/3 vs 1/3 instead of 50/50). Filter
to connected users BEFORE rotating so the rotation is over exactly the users that
consume the caption budget. A dead identity can no longer skew fairness.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -86,7 +86,7 @@ Skills live in the canonical library `mathias/skills` and are wired into this re
 
 ## Current build state (start here for the first task)
 
-The repo is **green and shipping** — last tag `v0.14.0`. `task check` passes (fmt, vet, lint,
+The repo is **green and shipping** — last tag `v0.15.0`. `task check` passes (fmt, vet, lint,
 `go test -p 1 ./...`). Go is `1.26.1` (see `go.mod`).
 
 - Clean Architecture core is implemented: `internal/domain` (entities), `internal/ports`
@@ -95,7 +95,8 @@ The repo is **green and shipping** — last tag `v0.14.0`. `task check` passes (
   green against it.
 - Adapters present under `internal/adapters/`: `youtube` (captions-first `VideoSource`,
   timedtext/InnerTube acquisition per ADR-010), `summarizer` + `llm` (the copied AI router,
-  Primary→Fallback per ADR-004), `store` (Postgres, golang-migrate migrations 001–015),
+  now a resilient endpoint chain — local primary → local fallback → external worst-case,
+  parse-failure-aware, ADR-004 + ADR-022), `store` (Postgres, golang-migrate migrations 001–015),
   `secrets` (file-backed `SecretStore`). The brain HTTP sink (ADR-005) is the remaining
   optional sink.
 - Stage 1 is open (ADR-012): multi-user with **DB-enforced** isolation — Postgres RLS `FORCE`d

cmd/tapir/scheduler.go

@@ -36,6 +36,11 @@ func buildUserRunner(cfg config.Config, st *store.Store, secretStore ports.Secre
 	}, secretStore)
 
 	engine := usecase.NewEngine(src, buildSummarizer(cfg), st)
+	// Share the transcript cache (ADR-021) on the scheduler path too — without
+	// this every scheduled pass re-fetches transcripts it already had, burning the
+	// scarce per-IP caption budget (ADR-014) and starving other users. The web
+	// "Summarize now" path already sets this; the scheduler omitting it was a bug.
+	engine.Transcripts = st
 
 	return runner.New(src, st, engine, userID, log,
 		runner.WithBackoff(cfg.FetchBackoff),
@@ -57,6 +62,7 @@ type userLister interface {
 // isolation). Returns the stats summed across users.
 func runDiscoveryPass(
 	ctx context.Context,
+	pass int,
 	lister userLister,
 	runUser func(context.Context, string) (runner.Stats, error),
 	log *slog.Logger,
@@ -67,15 +73,17 @@ func runDiscoveryPass(
 		return runner.Stats{}
 	}
 
-	log.Info("scheduler: starting discovery pass", "users", len(users))
-	var total runner.Stats
+	// Keep only users with a video connection. A pass for a connectionless user
+	// (e.g. a stale Dex-era orphan identity) only tries to resolve a token that
+	// was never minted, logging a spurious "ref not found" every tick. Filtering
+	// here — BEFORE rotation — also keeps fairness honest: rotation is over the
+	// users that actually consume the caption budget, so a dead identity can't eat
+	// a rotation slot and skew the lead share.
+	var connected []store.UserIdentity
 	for _, u := range users {
 		if ctx.Err() != nil {
-			break // shutting down: stop enumerating
+			return runner.Stats{} // shutting down
 		}
-		// Skip users with no video connection. A discovery pass for them only
-		// attempts to resolve a token that was never minted, logging a spurious
-		// "ref not found" every tick (e.g. stale Dex-era orphan identities).
 		conns, err := lister.ConnectionsForUser(ctx, u.UserID)
 		if err != nil {
 			log.Warn("scheduler: list connections failed", "user", u.UserID, "err", err)
@@ -85,6 +93,22 @@ func runDiscoveryPass(
 			log.Debug("scheduler: skipping user with no video connections", "user", u.UserID)
 			continue
 		}
+		connected = append(connected, u)
+	}
+
+	// Rotate who goes first each pass. Caption fetches share one per-egress-IP
+	// rate budget (ADR-014); whoever runs first each pass spends the pre-throttle
+	// window, so a FIXED order permanently starves whoever is last (a new pilot
+	// user got 0 fetches for 12h while the first-listed user got all of them).
+	// Rotation over the connected set gives each real user the lead in turn.
+	connected = rotateUsers(connected, pass)
+
+	log.Info("scheduler: starting discovery pass", "users", len(connected))
+	var total runner.Stats
+	for _, u := range connected {
+		if ctx.Err() != nil {
+			break // shutting down: stop enumerating
+		}
 		stats, err := runUser(ctx, u.UserID)
 		total = sumStats(total, stats)
 		if err != nil {
@@ -116,7 +140,8 @@ func runScheduler(
 		return // disabled
 	}
 
-	runDiscoveryPass(ctx, lister, runUser, log)
+	pass := 0
+	runDiscoveryPass(ctx, pass, lister, runUser, log)
 
 	ticker := time.NewTicker(interval)
 	defer ticker.Stop()
@@ -125,11 +150,32 @@ func runScheduler(
 		case <-ctx.Done():
 			return
 		case <-ticker.C:
-			runDiscoveryPass(ctx, lister, runUser, log)
+			pass++
+			runDiscoveryPass(ctx, pass, lister, runUser, log)
 		}
 	}
 }
 
+// rotateUsers left-rotates users by pass positions so a different user leads each
+// pass. With n users, user i leads on every pass where pass ≡ i (mod n). A pass
+// offset that is negative or exceeds n is normalised. Order within the rotation
+// is otherwise preserved, so the set of users run is unchanged — only who is
+// first (and thus wins the scarce caption-fetch budget) rotates.
+func rotateUsers(users []store.UserIdentity, pass int) []store.UserIdentity {
+	n := len(users)
+	if n <= 1 {
+		return users
+	}
+	off := ((pass % n) + n) % n
+	if off == 0 {
+		return users
+	}
+	out := make([]store.UserIdentity, 0, n)
+	out = append(out, users[off:]...)
+	out = append(out, users[:off]...)
+	return out
+}
+
 // sumStats adds two passes' stats field-wise, so runDiscoveryPass can report a
 // per-tick aggregate across all users.
 func sumStats(a, b runner.Stats) runner.Stats {

cmd/tapir/scheduler_test.go

@@ -45,6 +45,7 @@ func (f fakeLister) ConnectionsForUser(_ context.Context, userID string) ([]stor
 type countingRunUser struct {
 	mu      sync.Mutex
 	calls   map[string]int
+	order   []string // userIDs in the order they were run, across all passes
 	failFor map[string]bool
 }
 
@@ -60,12 +61,19 @@ func (c *countingRunUser) run(_ context.Context, userID string) (runner.Stats, e
 	c.mu.Lock()
 	defer c.mu.Unlock()
 	c.calls[userID]++
+	c.order = append(c.order, userID)
 	if c.failFor[userID] {
 		return runner.Stats{Errors: 1}, errors.New("boom")
 	}
 	return runner.Stats{Summarized: 1}, nil
 }
 
+func (c *countingRunUser) runOrder() []string {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+	return append([]string(nil), c.order...)
+}
+
 func (c *countingRunUser) count(userID string) int {
 	c.mu.Lock()
 	defer c.mu.Unlock()
@@ -94,7 +102,7 @@ func TestDiscoveryPassRunsEveryUserOnce(t *testing.T) {
 	lister := fakeLister{users: usersN("a", "b", "c")}
 	rc := newCountingRunUser()
 
-	stats := runDiscoveryPass(context.Background(), lister, rc.run, quietLog())
+	stats := runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
 
 	require.Equal(t, 1, rc.count("a"))
 	require.Equal(t, 1, rc.count("b"))
@@ -102,13 +110,46 @@ func TestDiscoveryPassRunsEveryUserOnce(t *testing.T) {
 	require.Equal(t, 3, stats.Summarized, "stats are summed across users")
 }
 
+// Caption fetches share one per-IP budget; a fixed user order starves whoever is
+// last. Each pass must rotate which user leads so the lead slot is shared.
+func TestDiscoveryPassRotatesLeadUser(t *testing.T) {
+	lister := fakeLister{users: usersN("a", "b", "c")}
+	rc := newCountingRunUser()
+
+	runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
+	runDiscoveryPass(context.Background(), 1, lister, rc.run, quietLog())
+	runDiscoveryPass(context.Background(), 2, lister, rc.run, quietLog())
+
+	require.Equal(t, []string{"a", "b", "c", "b", "c", "a", "c", "a", "b"}, rc.runOrder(),
+		"each pass left-rotates the user order so every user leads in turn")
+	// Fairness: over a full rotation cycle every user ran the same number of times.
+	require.Equal(t, 3, rc.count("a"))
+	require.Equal(t, 3, rc.count("b"))
+	require.Equal(t, 3, rc.count("c"))
+}
+
+// A connectionless orphan must not consume a rotation slot: rotation is over the
+// connected users only, so two real users alternate the lead 50/50 even with a
+// dead identity listed between them.
+func TestDiscoveryPassRotationIgnoresConnectionlessUsers(t *testing.T) {
+	lister := fakeLister{users: usersN("a", "orphan", "c"), noConn: map[string]bool{"orphan": true}}
+	rc := newCountingRunUser()
+
+	runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
+	runDiscoveryPass(context.Background(), 1, lister, rc.run, quietLog())
+
+	require.Equal(t, []string{"a", "c", "c", "a"}, rc.runOrder(),
+		"only connected users rotate; the orphan never runs and never holds a slot")
+	require.Equal(t, 0, rc.count("orphan"))
+}
+
 func TestDiscoveryPassSkipsUsersWithoutConnections(t *testing.T) {
 	// b never connected a video source (e.g. a stale Dex-era orphan identity).
 	// It must be skipped silently — not run and logged as a token error every pass.
 	lister := fakeLister{users: usersN("a", "b", "c"), noConn: map[string]bool{"b": true}}
 	rc := newCountingRunUser()
 
-	stats := runDiscoveryPass(context.Background(), lister, rc.run, quietLog())
+	stats := runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
 
 	require.Equal(t, 1, rc.count("a"))
 	require.Equal(t, 0, rc.count("b"), "a user with no connection must be skipped, not run")
@@ -121,7 +162,7 @@ func TestDiscoveryPassOneUserFailureDoesNotStopOthers(t *testing.T) {
 	lister := fakeLister{users: usersN("a", "b", "c")}
 	rc := newCountingRunUser("b") // user b's pass errors
 
-	stats := runDiscoveryPass(context.Background(), lister, rc.run, quietLog())
+	stats := runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
 
 	require.Equal(t, 1, rc.count("a"))
 	require.Equal(t, 1, rc.count("b"))
@@ -134,7 +175,7 @@ func TestDiscoveryPassListerErrorIsContained(t *testing.T) {
 	lister := fakeLister{err: errors.New("db down")}
 	rc := newCountingRunUser()
 
-	stats := runDiscoveryPass(context.Background(), lister, rc.run, quietLog())
+	stats := runDiscoveryPass(context.Background(), 0, lister, rc.run, quietLog())
 
 	require.Equal(t, 0, rc.total(), "no users enumerated → no passes")
 	require.Equal(t, runner.Stats{}, stats)

internal/web/handlers.go

@@ -233,11 +233,20 @@ func (a *App) handleList(w http.ResponseWriter, r *http.Request) {
 	}
 	hasConnected := len(conns) > 0
 
-	if isHTMX(r) {
-		a.render(w, r, summaryList(buckets, hasConnected))
+	// Summarization mode drives the backlog copy: an auto user is told summaries
+	// land gradually; a manual user is told to click Summarize (the first pilot
+	// user sat in manual mode reading "land automatically" and waited forever).
+	autoSummarize, err := a.Store.GetAutoSummarize(r.Context(), userID)
+	if err != nil {
+		a.serverError(w, r, "summarize mode", err)
 		return
 	}
-	a.render(w, r, ListPage(buckets, f, stats, takeFlash(w, r), hasConnected, channels))
+
+	if isHTMX(r) {
+		a.render(w, r, summaryList(buckets, hasConnected, autoSummarize))
+		return
+	}
+	a.render(w, r, ListPage(buckets, f, stats, takeFlash(w, r), hasConnected, channels, autoSummarize))
 }
 
 // handleDetail renders one summary in full (highlights, takeaways, action group).

internal/web/handlers_test.go

@@ -477,3 +477,36 @@ func postAction(t *testing.T, app *web.App, videoID, action string, htmx bool) *
 	}
 	return do(t, app, req)
 }
+
+// TestListManualModeBannerCopy: a manual-mode user with un-summarized videos
+// sees the manual prompt (click Summarize), NOT the "summaries land
+// automatically" copy that misled the first pilot user into waiting forever.
+func TestListManualModeBannerCopy(t *testing.T) {
+	ctx := context.Background()
+	app := newApp(t)
+	p := rawPool(t)
+	resetDB(t, p)
+	seedVideo(t, p, videoX, "X Title", "https://x", time.Time{}) // pending, un-summarized
+	require.NoError(t, app.Store.SetAutoSummarize(ctx, userID, false))
+
+	html := body(t, do(t, app, httptest.NewRequest(http.MethodGet, "/", nil)))
+	require.Contains(t, html, "Manual mode")
+	require.Contains(t, html, "are not summarized automatically")
+	require.NotContains(t, html, "land gradually",
+		"manual-mode user must not be told summaries arrive automatically")
+}
+
+// TestListAutoModeBannerCopy: an auto-mode user with a backlog sees the
+// gradual-delivery copy, not the manual prompt.
+func TestListAutoModeBannerCopy(t *testing.T) {
+	ctx := context.Background()
+	app := newApp(t)
+	p := rawPool(t)
+	resetDB(t, p)
+	seedVideo(t, p, videoX, "X Title", "https://x", time.Time{})
+	require.NoError(t, app.Store.SetAutoSummarize(ctx, userID, true))
+
+	html := body(t, do(t, app, httptest.NewRequest(http.MethodGet, "/", nil)))
+	require.Contains(t, html, "land gradually")
+	require.NotContains(t, html, "are not summarized automatically")
+}

internal/web/paste_test.go

@@ -65,7 +65,7 @@ func TestParseYouTubeVideoID(t *testing.T) {
 func TestListPageShowsPasteFormOnlyWhenConnected(t *testing.T) {
 	render := func(connected bool) string {
 		var buf bytes.Buffer
-		if err := ListPage(listBuckets{}, Filter{}, PipelineStats{}, "", connected, nil).Render(context.Background(), &buf); err != nil {
+		if err := ListPage(listBuckets{}, Filter{}, PipelineStats{}, "", connected, nil, true).Render(context.Background(), &buf); err != nil {
 			t.Fatalf("render: %v", err)
 		}
 		return buf.String()

internal/web/views.templ

@@ -104,7 +104,7 @@ templ flashBanner(code string) {
 // #summary-list region; a non-HTMX request renders the whole page. flash carries
 // a one-shot notification (e.g. "connected", "registered") surfaced on arrival
 // after a POST→redirect.
-templ ListPage(b listBuckets, f Filter, stats PipelineStats, flash string, hasConnected bool, channels []string) {
+templ ListPage(b listBuckets, f Filter, stats PipelineStats, flash string, hasConnected bool, channels []string, autoSummarize bool) {
 	@Layout("Tapir — Summaries") {
 		@flashBanner(flash)
 		if hasConnected {
@@ -116,14 +116,23 @@ templ ListPage(b listBuckets, f Filter, stats PipelineStats, flash string, hasCo
 		if stats.RateLimited > 0 || stats.Pending > 0 || stats.NoText > 0 {
 			@pipelineBar(stats)
 		}
-		if stats.RateLimited+stats.Pending > 0 {
+		if (stats.RateLimited+stats.Pending) > 0 && autoSummarize {
 			<p class="pipeline-note muted">
 				Tapir fetches captions slowly on purpose, to respect YouTube's limits —
 				new summaries land gradually. Check back tomorrow.
 			</p>
 		}
+		if (stats.RateLimited+stats.Pending) > 0 && !autoSummarize {
+			<p class="pipeline-note muted">
+				You are in Manual mode: new videos appear here but are not summarized
+				automatically. Use the Summarize button on the ones you want.
+			</p>
+			<p class="pipeline-note muted">
+				<a href="/account">Switch to Automatic</a> to have new videos summarized for you.
+			</p>
+		}
 		<div id="summary-list">
-			@summaryList(b, hasConnected)
+			@summaryList(b, hasConnected, autoSummarize)
 		</div>
 	}
 }
@@ -203,12 +212,16 @@ templ filterForm(f Filter, channels []string) {
 // and a single disclosure holding the older un-summarized back-catalogue. Cards
 // reflow to a single column on mobile; an empty list shows a friendly first-run
 // state instead of a blank table.
-templ summaryList(b listBuckets, hasConnected bool) {
+templ summaryList(b listBuckets, hasConnected bool, autoSummarize bool) {
 	if b.empty() {
 		if hasConnected {
 			<div class="empty empty-connected">
 				<strong>Your account is connected</strong>
+				if autoSummarize {
 					<span>Tapir is finding your subscriptions and fetching captions — summaries appear here gradually. Check back later.</span>
+				} else {
+					<span>Tapir is finding your subscriptions. You are in Manual mode, so videos appear here with a Summarize button — pick the ones you want, or switch to Automatic in your account.</span>
+				}
 			</div>
 		} else {
 			<div class="empty">