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/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"}]