refactor: solidify startup UX and engine-aware preprocessing

- Slim core deps: move ML stack to optional extras (paddle/tables/figures/scientific/full)
- Lazy settings proxy with config search paths (env var, cwd, user dir)
- New commands: init, demo, setup [basic|full], first-run guard on run/watch
- Engine-aware preprocessing: Paddle gets original image (fixes dark mode 0.83->0.95)
- Results table shows Skipped count; lazy run-dir creation
- kg_ocr marked experimental with extra, Docker defaults with OCR_PIPELINE_CONFIG
- 25/25 tests, ruff clean

Dockerfile

@@ -2,25 +2,24 @@ FROM python:3.11-slim
 
 RUN apt-get update && apt-get install -y --no-install-recommends \
     tesseract-ocr \
-    libtesseract-dev \
-    poppler-utils \
     libgl1 \
     libglib2.0-0 \
-    libsm6 \
-    libxext6 \
-    libxrender-dev \
-    libgomp1 \
     && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 
 COPY pyproject.toml uv.lock ./
-RUN pip install --no-cache-dir uv && uv sync --frozen --no-dev
+RUN pip install --no-cache-dir uv && uv sync --frozen --no-dev --no-install-project
 
 COPY src ./src
-COPY config.yaml ./
+# Optional ML stack: docker build --build-arg EXTRAS="--extra full" .
+ARG EXTRAS=""
+RUN uv sync --frozen --no-dev ${EXTRAS}
 
-ENV PYTHONPATH=/app/src
-ENV OMP_NUM_THREADS=4
+COPY docker/config.docker.yaml ./config.docker.yaml
 
-ENTRYPOINT ["ocr-pipeline"]
+ENV PATH="/app/.venv/bin:$PATH" \
+    OCR_PIPELINE_CONFIG=/app/config.docker.yaml \
+    OMP_NUM_THREADS=4
+
+ENTRYPOINT ["ocr-pipeline"]