feat(youtube): map caption 429 to SourceRateLimited

The baseUrl fetch mapped every non-200 to SourceNone, recording a 429 as a
permanent "no captions". 429 is the IP being rate-limited, not an absent
transcript. Return SourceRateLimited (still a graceful degrade, no error) so
the runner can retry after a backoff window. Other non-200s (403/404/5xx)
stay SourceNone.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-03 22:45:29 +02:00
co-authored by Claude Opus 4.8
parent c63b2de66d
commit 4678d473b8
2 changed files with 37 additions and 0 deletions
+6
View File
@@ -60,6 +60,12 @@ func (a *Adapter) FetchTranscript(ctx context.Context, v domain.Video) (domain.T
if err != nil { if err != nil {
return domain.Transcript{}, fmt.Errorf("download caption track for %q: %w", v.ProviderVideoID, err) return domain.Transcript{}, fmt.Errorf("download caption track for %q: %w", v.ProviderVideoID, err)
} }
if status == http.StatusTooManyRequests {
// 429 means the IP is rate-limited; record for retry, not a permanent
// absence. Degrade gracefully (no error, no text) like SourceNone, but
// flag it distinctly so the runner backs off and retries (ADR-007/010).
return domain.Transcript{VideoID: v.ID, UserID: v.UserID, Source: domain.SourceRateLimited}, nil
}
if status != http.StatusOK { if status != http.StatusOK {
// Owner-only 403, region/age gate, or transient unavailability: not an error. // Owner-only 403, region/age gate, or transient unavailability: not an error.
return noTranscript(v), nil return noTranscript(v), nil
+31
View File
@@ -388,6 +388,37 @@ func TestFetchTranscriptBaseURLForbiddenDegrades(t *testing.T) {
} }
} }
// A 429 on the baseUrl fetch is the IP being rate-limited, NOT a permanent
// absence of captions: it returns SourceRateLimited (no error, no text) so the
// runner can record it and retry after a backoff window rather than recording a
// false "no transcript".
func TestFetchTranscriptRateLimitedReturnsSourceRateLimited(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
switch r.URL.Path {
case "/youtubei/v1/player":
base := "http://" + r.Host
_, _ = w.Write([]byte(`{"captions":{"playerCaptionsTracklistRenderer":{"captionTracks":[` +
`{"baseUrl":"` + base + `/api/timedtext?lang=en","languageCode":"en"}]}}}`))
case "/api/timedtext":
w.WriteHeader(http.StatusTooManyRequests)
}
})
tr, err := a.FetchTranscript(context.Background(), domain.Video{ID: "v1", UserID: "u1", ProviderVideoID: "vid1"})
if err != nil {
t.Fatalf("429 on baseUrl must degrade, not error: %v", err)
}
if tr.Source != domain.SourceRateLimited {
t.Fatalf("expected SourceRateLimited on 429, got %q", tr.Source)
}
if tr.HasText() {
t.Error("expected HasText() false for SourceRateLimited")
}
if tr.Content != "" {
t.Errorf("expected empty content on 429, got %q", tr.Content)
}
}
// An empty baseUrl on the selected track degrades to SourceNone, never an error. // An empty baseUrl on the selected track degrades to SourceNone, never an error.
func TestFetchTranscriptEmptyBaseURLDegrades(t *testing.T) { func TestFetchTranscriptEmptyBaseURLDegrades(t *testing.T) {
a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) { a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {