lean-bench/.gitea/workflows/ci.yml

name: ci

# Runs on the ubuntu24.04-x64-lean4.35 runner. That runner executes jobs directly on
# the host (no job container): Lean 4.35 lives in /root/.elan, Python 3.12 is the
# system Python, and there is no Node, so actions/checkout cannot run -- each job
# clones the commit with git instead.
#
#   python  lint + unit tests (LLM scripted, Lean faked), every push
#   lean    the real pipeline against real Lean + Mathlib (host-cached project)
#   image   only after both pass: build the Docker image, smoke-test it, keep it

on:
  push:
    branches: [main]
  workflow_dispatch:

env:
  PIP_DISABLE_PIP_VERSION_CHECK: "1"

jobs:
  python:
    if: gitea.ref == 'refs/heads/main'
    runs-on: ubuntu24.04-x64-lean4.35
    timeout-minutes: 20
    steps:
      - name: Check out
        run: |
          set -eu
          git init -q . && git remote add origin "${{ github.server_url }}/${{ github.repository }}.git"
          git -c http.extraHeader="Authorization: token ${{ github.token }}" fetch -q --depth 1 origin "${{ github.sha }}"
          git checkout -q FETCH_HEAD && git log --oneline -1

      - name: Set up Python
        run: |
          set -eu
          python3 -m venv .venv 2>/dev/null || { apt-get update -qq && apt-get install -y -qq python3-venv && python3 -m venv .venv; }
          .venv/bin/python --version
          .venv/bin/python -m pip install --quiet --upgrade pip
          .venv/bin/python -m pip install --quiet -e ".[dev]"

      - name: Lint
        run: .venv/bin/python -m ruff check .

      - name: Test
        run: .venv/bin/python -m pytest -q

      - name: CLI entry point
        run: |
          .venv/bin/lean-bench --help > /dev/null
          .venv/bin/lean-bench doctor --skip-llm --env /dev/null

  lean:
    if: gitea.ref == 'refs/heads/main'
    needs: python
    runs-on: ubuntu24.04-x64-lean4.35
    timeout-minutes: 150
    steps:
      - name: Check out
        run: |
          set -eu
          git init -q . && git remote add origin "${{ github.server_url }}/${{ github.repository }}.git"
          git -c http.extraHeader="Authorization: token ${{ github.token }}" fetch -q --depth 1 origin "${{ github.sha }}"
          git checkout -q FETCH_HEAD

      - name: Host environment
        run: |
          echo "host=$(hostname) cpus=$(nproc)"; free -h; df -h /
          elan --version; lean --version; lake --version

      - name: Lean + Mathlib (cached on the host)
        run: |
          set -eu
          dir="$(.gitea/scripts/prepare-mathlib.sh lean)"
          echo "LEANBENCH_LEAN_PROJECT=$dir" >> "$GITHUB_ENV"
          cd "$dir" && time lake env lean LeanBench.lean && echo "Mathlib OK in $dir"

      - name: End-to-end smoke (real Lean, scripted LLM)
        run: |
          set -eu
          python3 -m venv .venv 2>/dev/null || { apt-get update -qq && apt-get install -y -qq python3-venv && python3 -m venv .venv; }
          .venv/bin/python -m pip install --quiet .
          .venv/bin/python docker/smoke.py

  image:
    needs: [python, lean]
    if: ${{ gitea.ref == 'refs/heads/main' && (github.event_name != 'pull_request') }}
    runs-on: ubuntu24.04-x64-lean4.35
    timeout-minutes: 180
    steps:
      - name: Check out
        run: |
          set -eu
          git init -q . && git remote add origin "${{ github.server_url }}/${{ github.repository }}.git"
          git -c http.extraHeader="Authorization: token ${{ github.token }}" fetch -q --depth 1 origin "${{ github.sha }}"
          git checkout -q FETCH_HEAD

      - name: Ensure Docker on the runner host
        run: |
          set -eu
          if ! command -v docker >/dev/null; then
            echo "Docker not installed; installing docker.io + docker-buildx from Ubuntu"
            apt-get update -qq
            DEBIAN_FRONTEND=noninteractive apt-get install -y -qq docker.io docker-buildx
            systemctl enable --now docker
          fi
          docker version --format 'client {{.Client.Version}} / server {{.Server.Version}}'
          docker info --format 'storage={{.Driver}} root={{.DockerRootDir}}'

      - name: Preflight (disk, memory)
        run: |
          set -eu
          free_gb=$(df -BG --output=avail "$(docker info --format '{{.DockerRootDir}}' | xargs dirname)" | tail -1 | tr -dc 0-9)
          mem_gb=$(awk '/MemTotal/ {print int($2/1048576)}' /proc/meminfo)
          echo "free disk ${free_gb} GB, memory ${mem_gb} GB"
          [ "$free_gb" -ge 30 ] || { echo "need >= 30 GB free for a ~16 GB image"; exit 1; }
          [ "$mem_gb" -ge 7 ] || { echo "need >= 8 GB RAM to elaborate Mathlib"; exit 1; }

      - name: Build
        run: |
          set -eu
          short="$(git rev-parse --short HEAD)"
          echo "SHORT=$short" >> "$GITHUB_ENV"
          DOCKER_BUILDKIT=1 docker build --progress=plain -f docker/Dockerfile \
            -t "lean-bench:sha-$short" -t "lean-bench:lean4.35" .

      - name: Smoke-test the image (real Lean inside)
        run: docker run --rm -i --entrypoint python3 "lean-bench:sha-$SHORT" - < docker/smoke.py

      - name: Keep the image
        run: |
          set -eu
          if [ "${{ github.ref }}" = "refs/heads/main" ]; then
            docker tag "lean-bench:sha-$SHORT" lean-bench:latest
            docker tag "lean-bench:sha-$SHORT" lean-bench:main
          fi
          docker images lean-bench --format 'table {{.Repository}}:{{.Tag}}\t{{.ID}}\t{{.Size}}\t{{.CreatedSince}}'
          {
            echo "### lean-bench image kept on $(hostname)"
            echo
            docker images lean-bench --format '- `{{.Repository}}:{{.Tag}}` {{.ID}} ({{.Size}})'
          } >> "${GITHUB_STEP_SUMMARY:-/dev/null}"