fix: normalize faster-whisper segments to dicts + in-proc auto-worker

Colab run 3 (A100) surfaced three GPU/API-path bugs mocks couldn't catch:

1. faster-whisper yields namedtuple Segments, but batch/bench consume
   them as dicts (.get) -> AttributeError 'Segment' has no attribute
   'get' on every real transcription. Engine now normalizes segments
   to dicts (_to_dict_segments) at the boundary.

2. API TranscribeOptions carries engine-irrelevant keys (formats,
   timestamps, glossary_id, post_correction, diarize); worker's
   TranscriptionOptions(**job.options) crashed with TypeError. Worker
   now filters job.options to TranscriptionOptions.__slots__.

3. in-proc server never consumed its own queue (jobs stayed queued
   forever). Added opt-in Settings.auto_worker (default off): lifespan
   starts a daemon Worker thread for inproc backend, stopped on
   shutdown. Notebook enables it via LUKESCRIBE_AUTO_WORKER=true so the
   API upload -> completed flow works end to end.

Notebook: bench manifest now uses clips schema (audio_path/duration_sec/
entities); cell 22 reads error_message/error_code; upload poll window
raised to 4min (first-run model download).

+ 5 tests (namedtuple/dict segments, API-style options, auto_worker
on/off); 136 tests pass, ruff clean.

tests/integration/test_api.py

@@ -44,6 +44,34 @@ class TestHealth:
         assert body["model_ready"] is False  # 모델 캐시 없음 → 프로비저닝 보류
 
 
+class TestAutoWorker:
+    def test_auto_worker_off_by_default(self, client: TestClient):
+        """기본(False)에서는 워커 스레드를 띄우지 않는다 (테스트/프로덕션 안전)."""
+        assert client.app.state.inproc_worker is None
+
+    def test_auto_worker_started_when_enabled(self, tmp_path):
+        """auto_worker=true + inproc → lifespan이 워커 스레드를 시작하고 종료 시 정지."""
+        from luke_scribe.api.app import create_app
+        from luke_scribe.config import Settings
+
+        settings = Settings(
+            _env_file=None,
+            results_dir=str(tmp_path / "results"),
+            api_key_file=str(tmp_path / "api_keys.json"),
+            queue_backend="inproc",
+            model_cache_dir=None,
+            tunnel="none",
+            auto_worker=True,
+        )
+        app = create_app(settings)
+        with TestClient(app) as c:
+            w = c.app.state.inproc_worker
+            assert w is not None
+            assert not w._stop.is_set()
+        # lifespan 종료 → 워커 정지 요청
+        assert w._stop.is_set()
+
+
 class TestAuth:
     def test_missing_key_rejected(self, client: TestClient):
         r = client.get("/v1/jobs")

tests/integration/test_worker.py

@@ -30,6 +30,42 @@ def _job(**kw) -> Job:
 
 
 class TestWorkerLifecycle:
+    def test_api_style_options_filtered(self, settings, tmp_path):
+        """API TranscribeOptions(엔진 무관 키 포함) → 워커가 엔진 필드만 골라 처리.
+
+        Colab 실전에서 잡이 계속 실패한 원인: job.options에 formats/timestamps/
+        diarize 등이 포함돼 TranscriptionOptions(**job.options)가 TypeError를 냄.
+        """
+        broker = InProcBroker(settings)
+        store = ResultStore(str(tmp_path / "results"))
+        worker = Worker(
+            settings=settings,
+            broker=broker,
+            store=store,
+            owner=FakeEngineOwner(),
+            ingestor=FakeIngestor(),
+        )
+        job = _job(
+            options={
+                "language": "ko",
+                "device": "auto",
+                "timestamps": True,
+                "formats": ["json", "srt"],
+                "word_timestamps": False,
+                "vad": True,
+                "hotwords": [],
+                "glossary_id": None,
+                "post_correction": None,
+                "diarize": False,
+            }
+        )
+        broker.enqueue(job)
+        worker.drain()
+        assert broker.get(job.id).status == JobStatus.COMPLETED
+        result = store.read_result(job.id)
+        assert result is not None
+        assert result.status == "completed"
+
     def test_complete_flow(self, settings, tmp_path):
         """enqueue → worker 처리 → completed + 결과 저장 + 콜백."""
         broker = InProcBroker(settings)

tests/unit/test_engine_faster_whisper.py

@@ -16,16 +16,17 @@ from luke_scribe.engine.faster_whisper_engine import FasterWhisperEngine
 
 
 class FakeWhisperModel:
-    """faster_whisper.WhisperModel 대체 — 생성 인자만 기록한다."""
+    """faster_whisper.WhisperModel 대체 — 생성 인자/세그먼트를 기록한다."""
 
     calls: list[dict] = []
+    segments: list = []  # transcribe()가 yield할 세그먼트 (기본: namedtuple)
 
     def __init__(self, *args, **kwargs) -> None:
         self.kwargs = kwargs
         self.__class__.calls.append(kwargs)
 
     def transcribe(self, audio_path, **kwargs):
-        return iter([]), {}
+        return iter(list(self.__class__.segments)), {}
 
 
 def _install_fake(monkeypatch) -> None:
@@ -33,6 +34,7 @@ def _install_fake(monkeypatch) -> None:
     mod.WhisperModel = FakeWhisperModel
     monkeypatch.setitem(sys.modules, "faster_whisper", mod)
     FakeWhisperModel.calls.clear()
+    FakeWhisperModel.segments = []
 
 
 def _opts(**kw) -> TranscriptionOptions:
@@ -78,3 +80,60 @@ def test_split_device_helper():
     assert FasterWhisperEngine._split_device("cuda") == ("cuda", 0)
     # 파싱 불가 인덱스는 그대로 전달 (모델 로드 시 명시적 오류로 fail-explicit)
     assert FasterWhisperEngine._split_device("cuda:xx") == ("cuda:xx", 0)
+
+
+def test_namedtuple_segments_normalized_to_dicts(monkeypatch):
+    """faster-whisper Segment(namedtuple) → dict 정규화 (GPU 실전 버그)."""
+    from collections import namedtuple
+
+    _install_fake(monkeypatch)
+    Seg = namedtuple(
+        "Segment",
+        [
+            "id",
+            "seek",
+            "start",
+            "end",
+            "text",
+            "tokens",
+            "temperature",
+            "avg_logprob",
+            "compression_ratio",
+            "no_speech_prob",
+        ],
+    )
+    FakeWhisperModel.segments = [
+        Seg(
+            id=0,
+            seek=0,
+            start=0.0,
+            end=2.5,
+            text="오늘 vLLM을 배포합니다.",
+            tokens=[1, 2],
+            temperature=0.0,
+            avg_logprob=-0.2,
+            compression_ratio=1.0,
+            no_speech_prob=0.01,
+        )
+    ]
+    outcome = FasterWhisperEngine().transcribe(
+        "/tmp/x.wav", _opts(device="cpu", compute_type="int8")
+    )
+    segs = list(outcome.segments)
+    assert len(segs) == 1
+    seg = segs[0]
+    # dict 계약: .get() 사용 가능 (파이프라인이 이걸로 접근)
+    assert seg.get("text") == "오늘 vLLM을 배포합니다."
+    assert seg.get("end") == 2.5
+    assert seg.get("avg_logprob") == -0.2
+
+
+def test_dict_segments_passthrough(monkeypatch):
+    """이미 dict인 세그먼트는 그대로 (mock 계약과 호환)."""
+    _install_fake(monkeypatch)
+    FakeWhisperModel.segments = [{"index": 0, "start": 0.0, "end": 1.0, "text": "x"}]
+    outcome = FasterWhisperEngine().transcribe(
+        "/tmp/x.wav", _opts(device="cpu", compute_type="int8")
+    )
+    segs = list(outcome.segments)
+    assert segs == [{"index": 0, "start": 0.0, "end": 1.0, "text": "x"}]