# lean-bench: Lean 4 + Mathlib + the ingestion pipeline, in one image.
#
# Build from the repository root:
#   docker build -f docker/Dockerfile -t lean-bench:latest .
#
# The Mathlib revision and the Lean toolchain are resolved against each other at
# build time (see docker/resolve-mathlib.sh); override with --build-arg MATHLIB_REV=v4.33.0.
FROM ubuntu:24.04

LABEL org.opencontainers.image.title="lean-bench" \
      org.opencontainers.image.description="Detect formalizable mathematics in books and turn it into verified, indexed Lean 4" \
      org.opencontainers.image.source="https://gitea.entroia.com/Zayden-Jung/lean-bench"

ENV DEBIAN_FRONTEND=noninteractive \
    ELAN_HOME=/opt/elan \
    PATH=/opt/elan/bin:$PATH \
    PYTHONUNBUFFERED=1

RUN apt-get update && apt-get install -y --no-install-recommends \
        build-essential ca-certificates curl git jq sqlite3 \
        libgmp-dev python3 python3-pip \
    && rm -rf /var/lib/apt/lists/*

# -- elan (the Lean toolchain manager) --------------------------------------
RUN curl -fsSL https://raw.githubusercontent.com/leanprover/elan/master/elan-init.sh -o /tmp/elan-init.sh \
    && sh /tmp/elan-init.sh -y --no-modify-path --default-toolchain none \
    && rm /tmp/elan-init.sh \
    && elan --version

WORKDIR /opt/lean-bench

# -- Lean project: toolchain, Mathlib, and its prebuilt cache ---------------
# Its own layer, because it is the expensive one and it changes rarely.
ARG MATHLIB_REV=auto
COPY lean/ lean/
COPY docker/resolve-mathlib.sh docker/resolve-mathlib.sh
RUN chmod +x docker/resolve-mathlib.sh && docker/resolve-mathlib.sh lean "$MATHLIB_REV"
RUN elan toolchain install "$(cat lean/lean-toolchain)" \
    && elan default "$(cat lean/lean-toolchain)"
RUN cd lean \
    && lake update \
    && (lake exe cache get || echo "no Mathlib cache available; building from source") \
    && lake build \
    && lake env lean --version

# -- the pipeline -----------------------------------------------------------
COPY pyproject.toml README.md ./
COPY leanbench/ leanbench/
RUN pip install --break-system-packages --no-cache-dir . \
    && lean-bench --help > /dev/null

COPY docker/entrypoint.sh /usr/local/bin/leanbench-entrypoint
RUN chmod +x /usr/local/bin/leanbench-entrypoint

ENV LEANBENCH_LEAN_PROJECT=/opt/lean-bench/lean \
    LEANBENCH_LEAN_COMMAND='["lake","env","lean"]' \
    LEANBENCH_DATABASE=/data/leanbench.sqlite \
    LEANBENCH_LLM_MODEL=qwen-max \
    LEANBENCH_LLM_BASE_URL=https://dashscope.aliyuncs.com/compatible-mode/v1 \
    LEANBENCH_LLM_API_KEY_ENV=DASHSCOPE_API_KEY

# /books is where you put the source you are submitting; /data holds the database.
VOLUME ["/data", "/books"]
WORKDIR /work

# Prove the environment works while the image is still being built.
RUN mkdir -p /work && cd /opt/lean-bench/lean \
    && printf 'import Mathlib\ntheorem image_smoke (n : Nat) : n + 0 = n := by simp\n' > /tmp/Smoke.lean \
    && lake env lean /tmp/Smoke.lean && rm /tmp/Smoke.lean

ENTRYPOINT ["leanbench-entrypoint"]
CMD ["doctor"]
