FROM python:3.11-slim

# Install Ollama
RUN apt-get update && apt-get install -y curl && \
    curl -fsSL https://ollama.com/install.sh | sh && \
    apt-get clean

WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

ENV OLLAMA_MAX_LOADED_MODELS=2
ENV COMPUTE_STRATEGY=round_robin
ENV PORT=8000

EXPOSE 8000 11434

# Pull both models then start orchestrator
CMD bash -c "\
  ollama serve & sleep 5 && \
  ollama pull ${REASONER_MODEL:-gemma4:e4b-instruct-q4_K_M} && \
  ollama pull ${CODER_MODEL:-qwen3.5:4b-instruct-q4_K_M} && \
  python orchestrator.py"