fix a bug

sentence_api/tests/test_api.py

@@ -936,7 +936,7 @@ def test_admin_batch_applies_merge_and_split_once(tmp_path, monkeypatch):
     assert all(not (item.zh_text or "").strip() for item in document.sentences)
 
 
-def test_admin_batch_can_persist_provisional_split_without_processing(tmp_path):
+def test_admin_batch_can_persist_provisional_split_without_processing(tmp_path, monkeypatch):
     settings = replace(Settings.from_env(), data_dir=tmp_path / "data")
     settings.ensure_directories()
     repository = VideoRepository(settings.database_path)
@@ -962,21 +962,43 @@ def test_admin_batch_can_persist_provisional_split_without_processing(tmp_path):
         None,
     )
     repository.save_sentence_translations(VIDEO_HASH, {1: "未变化。"})
+    (settings.videos_dir / f"{VIDEO_HASH}.mp4").write_bytes(b"video")
+    from sentence_api.transcription import Transcript, TranscriptionSegment, WordTimestamp
+
     calls = []
 
-    class MustNotTranscribe:
+    class DeferredTranscriber:
         available = True
+        allowed = False
 
         def transcribe(self, audio_path, language=None):
+            assert self.allowed, "provisional save must not transcribe"
             calls.append(audio_path)
-            raise AssertionError("provisional save must not transcribe")
+            return Transcript(
+                text="First part second part",
+                segments=[
+                    TranscriptionSegment(
+                        start_seconds=0.0,
+                        end_seconds=1.0,
+                        text="First part second part",
+                        words=[
+                            WordTimestamp(0.0, 0.2, "First"),
+                            WordTimestamp(0.2, 1.0, "part second part"),
+                        ],
+                    )
+                ],
+            )
 
+    monkeypatch.setattr(
+        "sentence_api.processing.extract_audio_segment",
+        lambda media_path, output_path, *, start_ms, duration_ms: output_path.write_bytes(b"audio"),
+    )
     client = TestClient(
         create_app(
             BoundaryStore(tmp_path / "boundaries.json"),
             settings=settings,
             repository=repository,
-            transcriber=MustNotTranscribe(),
+            transcriber=DeferredTranscriber(),
         )
     )
     response = client.put(
@@ -1001,6 +1023,25 @@ def test_admin_batch_can_persist_provisional_split_without_processing(tmp_path):
     assert [item.text for item in document.sentences] == ["First part", "second part", "Unchanged."]
     assert [item.zh_text for item in document.sentences] == [None, None, "未变化。"]
 
+    client.app.state.transcriber.allowed = True
+    processed = client.put(
+        f"/api/v1/admin/videos/{VIDEO_HASH}/sentences/batch",
+        json={
+            "process_timings": True,
+            "sentences": [
+                {"start_ms": 0, "end_ms": 2500, "text": "First part", "language": "en", "zh_text": None, "reference_speech_duration_ms": 2300, "source_start_ms": 0, "source_end_ms": 5000},
+                {"start_ms": 2500, "end_ms": 5000, "text": "second part", "language": "en", "zh_text": None, "reference_speech_duration_ms": 2300, "source_start_ms": 0, "source_end_ms": 5000},
+                {"start_ms": 5000, "end_ms": 12000, "text": "Unchanged.", "language": "en", "zh_text": "未变化。", "reference_speech_duration_ms": 6400},
+            ],
+        },
+    )
+
+    assert processed.status_code == 200, processed.text
+    processed_payload = processed.json()
+    assert [item["start_ms"] for item in processed_payload] == [0, 1000, 5000]
+    assert [item["end_ms"] for item in processed_payload] == [1000, 5000, 12000]
+    assert len(calls) == 1
+
 
 def test_admin_sentence_merge_does_not_start_subtitle_translation(tmp_path, monkeypatch):
     client = make_client(tmp_path)