Dockerfile.agent

FROM mcr.microsoft.com/mirror/docker/library/python:3.11-slim

WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    gcc \
    curl \
    && rm -rf /var/lib/apt/lists/*

# Install uv
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
ENV PATH="/root/.local/bin:/root/.cargo/bin:$PATH"

# Copy project files
COPY pyproject.toml .
COPY src/ src/
COPY config/ config/
COPY .env* ./

# Install dependencies (no torch/docling — use pymupdf4llm with markitdown fallback)
RUN uv pip install --system ".[pymupdf4llm]"

# Download spaCy NER models.
# - en_core_web_sm: used by mem0 fact extraction; without it the backend logs
#   "Failed to load spaCy full model" on every request and mem0 degrades to
#   keyword-only. ~50MB unpacked.
# - es_core_news_sm: used by the Patient Vault PII anonymiser to scrub
#   PERSON/ORG/GPE entities out of Spanish clinical documents before they
#   reach the LLM (Matucha is Spanish-first; regex alone doesn't catch names
#   or hospitals). ~40MB unpacked.
RUN python -m spacy download en_core_web_sm \
 && python -m spacy download es_core_news_sm

# Set python path, prevent bytecache issues when host mounts differ
ENV PYTHONPATH=/app/src
ENV PYTHONDONTWRITEBYTECODE=1

# Default command — override with --role and --port in docker-compose
CMD ["python", "-m", "interfaces.agent_server", "--role", "echo", "--port", "8005"]