feat: implement full-platform STT API (v2.3 consensus plan)

Batch+realtime transcription API: faster-whisper engine w/ EngineOwner
(single GPU owner, OOM downgrade chain, persisted attempted_profiles),
hardware-adaptive device manager (T0-T3 VRAM tiers), Redis/in-proc job
queue w/ leases + crash recovery, postprocess (glossary/rules/LLM w/
egress guard), privacy-first result store (UUID keys, source deleted
after transcribe), retention sweeper, API-key auth (HMAC digests,
scopes, job ownership), WebSocket realtime lane (LocalAgreement),
CLI (detect/transcribe/bench/serve/key), Docker, benchmark runner.

127 mock-based tests pass; ruff clean. Includes verification checklist
and autoplan review notes.

docker/Dockerfile.gpu

@@ -0,0 +1,26 @@
+# luke_scribe GPU 이미지 — CUDA 12 + cuDNN 9 + faster-whisper
+# 기준: NVIDIA CUDA 12 런타임, cc>=7.0 GPU (T4 이상 권장)
+FROM nvidia/cuda:12.4.1-runtime-ubuntu22.04
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    python3.11 python3-pip python3-venv ffmpeg \
+    && rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY pyproject.toml README.md ./
+COPY src/ ./src/
+
+RUN python3.11 -m venv /opt/venv \
+    && . /opt/venv/bin/activate \
+    && pip install --no-cache-dir -e ".[engine,gpu,api]" \
+    && pip install --no-cache-dir "faster-whisper>=1.0.3"
+
+ENV PATH="/opt/venv/bin:$PATH" \
+    LUKESCRIBE_DEVICE=auto \
+    LUKESCRIBE_QUEUE_BACKEND=redis \
+    LUKESCRIBE_HOST=0.0.0.0 \
+    LUKESCRIBE_PORT=8000 \
+    NVIDIA_VISIBLE_DEVICES=all
+
+EXPOSE 8000
+CMD ["python", "-m", "luke_scribe.cli", "serve"]