FROM python:3.12-slim

# Set up user for HuggingFace Spaces
RUN useradd -m -u 1000 user
USER user
ENV HOME=/home/user \
    PATH=/home/user/.local/bin:$PATH

WORKDIR $HOME/app

# Install dependencies
COPY --chown=user requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Copy application files
COPY --chown=user . .

# Download data from HF Dataset on build (all task suites + fixture data)
RUN python -c "from huggingface_hub import hf_hub_download; \
    import os; os.makedirs('data', exist_ok=True); \
    r='ibm-research/BPO-Bench'; d='dataset'; \
    hf_hub_download(r, 'candidate_data.parquet', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks_type_mismatch.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks_http_errors.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks_schema_violations.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks_edge_cases.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'tasks_undocumented.json', local_dir='data', repo_type=d); \
    hf_hub_download(r, 'large_response_fixture.json', local_dir='data', repo_type=d)"

# Expose port for Gradio
EXPOSE 7860

# Start the application
CMD ["python", "app.py"]