feat(discovery): drop Shorts and livestreams before the caption fetch (ADR-023)

The scarce resource is the per-IP timedtext caption fetch (ADR-014); the pilot's candidate set was mostly Shorts/clips/livestreams, each burning a fetch (a "none" result is a completed fetch — it costs budget even when it yields nothing). NewVideos now enriches candidates with one cheap Data API videos.list call (contentDetails.duration + snippet.liveBroadcastContent — the quota API, a DIFFERENT limit from the timedtext 429) and drops, before returning: videos shorter than TAPIR_MIN_VIDEO_SECONDS (default 60) and any live/upcoming broadcast. Dropped videos are never persisted, so the list declutters too. Degrade-open: MinVideoSeconds=0 disables it (no quota call); a videos.list error returns candidates unfiltered so discovery never breaks on a metadata hiccup. The paste-a-URL path (VideoByID) is not filtered — an explicit request is honoured. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-10 19:34:45 +02:00
parent 1aa8a97f95
commit 9db06d8a63
7 changed files with 250 additions and 4 deletions
@@ -186,6 +186,91 @@ func TestNewVideosCapsAtMax(t *testing.T) {
 	}
 }

+// TestNewVideosFiltersShortsAndLive: with MinVideoSeconds set, discovery enriches
+// candidates via videos.list and drops sub-threshold clips (Shorts) and
+// live/upcoming broadcasts before they reach the rate-limited caption path.
+func TestNewVideosFiltersShortsAndLive(t *testing.T) {
+	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
+		switch r.URL.Path {
+		case "/playlistItems":
+			_, _ = w.Write([]byte(`{
+				"items": [
+					{"snippet": {"title": "Real Talk", "publishedAt": "2026-06-03T10:00:00Z", "resourceId": {"videoId": "long1"}}},
+					{"snippet": {"title": "A Short", "publishedAt": "2026-06-03T09:00:00Z", "resourceId": {"videoId": "short1"}}},
+					{"snippet": {"title": "Live Now", "publishedAt": "2026-06-03T08:00:00Z", "resourceId": {"videoId": "live1"}}}
+				]
+			}`))
+		case "/videos":
+			if got := r.URL.Query().Get("part"); got != "contentDetails,snippet" {
+				t.Errorf("videos.list part=%q, want contentDetails,snippet", got)
+			}
+			_, _ = w.Write([]byte(`{
+				"items": [
+					{"id": "long1", "contentDetails": {"duration": "PT12M30S"}, "snippet": {"liveBroadcastContent": "none"}},
+					{"id": "short1", "contentDetails": {"duration": "PT45S"}, "snippet": {"liveBroadcastContent": "none"}},
+					{"id": "live1", "contentDetails": {"duration": "PT0S"}, "snippet": {"liveBroadcastContent": "live"}}
+				]
+			}`))
+		default:
+			t.Errorf("unexpected path %q", r.URL.Path)
+		}
+	})
+	a.cfg.MinVideoSeconds = 60
+
+	vids, err := a.NewVideos(context.Background(), domain.Subscription{ID: "s1", UserID: "u1", ChannelID: "UC_acme"})
+	if err != nil {
+		t.Fatalf("NewVideos: %v", err)
+	}
+	if len(vids) != 1 || vids[0].ProviderVideoID != "long1" {
+		t.Fatalf("expected only long1 to survive the filter, got %+v", vids)
+	}
+}
+
+// TestNewVideosNoFilterWhenDisabled: MinVideoSeconds=0 keeps the pre-ADR-023
+// behaviour — no videos.list call, no filtering.
+func TestNewVideosNoFilterWhenDisabled(t *testing.T) {
+	a, _ := newTestAdapter(t, func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path == "/videos" {
+			t.Errorf("videos.list must not be called when MinVideoSeconds is 0")
+		}
+		_, _ = w.Write([]byte(`{"items": [
+			{"snippet": {"title": "A Short", "publishedAt": "2026-06-03T09:00:00Z", "resourceId": {"videoId": "short1"}}}
+		]}`))
+	})
+	a.cfg.MinVideoSeconds = 0
+
+	vids, err := a.NewVideos(context.Background(), domain.Subscription{ID: "s1", UserID: "u1", ChannelID: "UC_acme"})
+	if err != nil {
+		t.Fatalf("NewVideos: %v", err)
+	}
+	if len(vids) != 1 {
+		t.Fatalf("filter disabled must keep all videos, got %d", len(vids))
+	}
+}
+
+func TestParseISO8601Seconds(t *testing.T) {
+	cases := []struct {
+		in   string
+		want int
+	}{
+		{"PT45S", 45},
+		{"PT1M30S", 90},
+		{"PT3M", 180},
+		{"PT1H2M3S", 3723},
+		{"PT2H", 7200},
+		{"PT0S", 0},
+		{"", 0},
+		{"garbage", 0},
+		{"P1D", 0},  // days component not handled → unknown
+		{"PT10", 0}, // trailing digits without a unit → malformed
+	}
+	for _, c := range cases {
+		if got := parseISO8601Seconds(c.in); got != c.want {
+			t.Errorf("parseISO8601Seconds(%q) = %d, want %d", c.in, got, c.want)
+		}
+	}
+}
+
 // TestUploadsPlaylistID covers the zero-cost UC->UU derivation, including
 // non-standard ids that must fall through unchanged (handled via fallback).
 func TestUploadsPlaylistID(t *testing.T) {