FROM python:3.11-slim

# System deps for llama-cpp-python build + audio
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    cmake \
    libopenblas-dev \
    libsndfile1 \
    ffmpeg \
    git \
    curl \
    && rm -rf /var/lib/apt/lists/*

WORKDIR /app

# Copy requirements first for layer caching
COPY requirements.txt .

# Install Python deps
# llama-cpp-python: CPU-only build (set CMAKE_ARGS for GPU at build time)
ENV CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS"
RUN pip install --no-cache-dir -r requirements.txt

# Copy app
COPY app.py .

# Model cache dir (populated at first run from HF Hub)
RUN mkdir -p /app/model

# Kokoro voices cache
ENV HF_HOME=/app/hf_cache
RUN mkdir -p /app/hf_cache

EXPOSE 7860

CMD ["python", "app.py"]