feat(youtube): process-wide caption-fetch rate gate (ADR-014 item 2)

ADR-014 item 2 — a single per-egress-IP rate gate shared by every caption
fetch — was specced but only per-video backoff (rate_limited_at) shipped.
Build the real gate now: it is load-bearing once ADR-018 puts auto-summarize
on an in-process schedule across multiple users (all fetches leave one pod's
egress IP, concurrently with live "Summarize" clicks — without a shared gate
that self-inflicts 429s every cycle).

globalFetchGate (golang.org/x/time/rate, default 2s/req burst 1) is consulted
in httpDo before every live outbound fetch — player, watch-page, timedtext —
so the scheduler runners and the web click-path serialise through one limiter
regardless of how many users/goroutines are upstream. The test seam
(a.transport != nil) skips the gate so fakes are not throttled.

TAPIR_FETCH_RATE (Go duration, default 2s, 0 = unlimited) wires SetFetchRate in
cmdRun; the existing per-video backoff stays as the complementary 429 handler.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-05 23:36:17 +02:00
co-authored by Claude Opus 4.8
parent 88294d38bc
commit f5021a8436
8 changed files with 176 additions and 1 deletions
+84
View File
@@ -0,0 +1,84 @@
package youtube
import (
"context"
"sync"
"sync/atomic"
"testing"
"time"
"github.com/stretchr/testify/require"
"golang.org/x/time/rate"
)
// waitOn drives a test-scoped limiter the same way WaitFetchGate drives the
// global one, so these tests exercise the gate's behaviour without mutating the
// process-wide gate (which would pollute sibling tests / the click-path).
func waitOn(t *testing.T, lim *rate.Limiter) func(context.Context) error {
t.Helper()
return func(ctx context.Context) error { return lim.Wait(ctx) }
}
func TestFetchGateSerialisesConcurrentCallers(t *testing.T) {
const (
n = 5
interval = 10 * time.Millisecond
)
lim := rate.NewLimiter(rate.Every(interval), 1)
wait := waitOn(t, lim)
var (
inFlight, maxInFlight atomic.Int32
wg sync.WaitGroup
)
start := time.Now()
for i := 0; i < n; i++ {
wg.Add(1)
go func() {
defer wg.Done()
require.NoError(t, wait(context.Background()))
cur := inFlight.Add(1)
for {
old := maxInFlight.Load()
if cur <= old || maxInFlight.CompareAndSwap(old, cur) {
break
}
}
// Hold the "critical section" briefly so overlap would be observable.
time.Sleep(interval / 4)
inFlight.Add(-1)
}()
}
wg.Wait()
elapsed := time.Since(start)
require.Equal(t, int32(1), maxInFlight.Load(),
"the gate must admit at most one caller per interval — no overlap")
require.GreaterOrEqual(t, elapsed, time.Duration(n-1)*interval,
"N gated callers take at least (N-1)*interval wall time")
}
func TestFetchGateRespectsContextCancellation(t *testing.T) {
// A slow gate (1 token/hour, burst already spent) blocks; a cancelled ctx must
// unblock Wait with an error rather than hang.
lim := rate.NewLimiter(rate.Every(time.Hour), 1)
require.True(t, lim.Allow(), "spend the single burst token")
ctx, cancel := context.WithCancel(context.Background())
cancel()
require.Error(t, waitOn(t, lim)(ctx), "cancelled ctx must fail Wait, not block")
}
func TestSetFetchRateZeroIsUnlimited(t *testing.T) {
// Snapshot and restore the global so this test does not pollute the process.
prev := globalFetchGate
t.Cleanup(func() { globalFetchGate = prev })
SetFetchRate(0)
require.Equal(t, rate.Inf, globalFetchGate.Limit(), "0 interval = unlimited gate")
// An unlimited gate never blocks, even back-to-back.
for i := 0; i < 100; i++ {
require.NoError(t, WaitFetchGate(context.Background()))
}
}