Skip to content

Remove the legacy Ant OpenHands runner #36

Remove the legacy Ant OpenHands runner

Remove the legacy Ant OpenHands runner #36

Workflow file for this run

name: CI
on:
pull_request:
push:
branches:
- main
permissions:
contents: read
concurrency:
group: ci-${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
jobs:
test:
runs-on: ubuntu-latest
timeout-minutes: 20
steps:
- uses: actions/checkout@v7.0.0
- uses: actions/setup-python@v6.3.0
with:
python-version: "3.12"
- uses: astral-sh/setup-uv@v8.3.2
with:
enable-cache: true
- name: Install dependencies
run: uv sync --extra dev --locked
- name: Validate task contracts
run: uv run python scripts/validate_tasks.py
- name: Validate native BenchFlow package
run: >-
uv run bench tasks check
tasks/simulation_heuristics_ant_v1
--level publication-grade
- name: Run native BenchFlow oracle smoke
shell: bash
run: |
full_config="$(mktemp)"
cp tasks/simulation_heuristics_ant_v1/verifier/config.toml "$full_config"
trap 'cp "$full_config" tasks/simulation_heuristics_ant_v1/verifier/config.toml; rm -f "$full_config"' EXIT
cp tasks/simulation_heuristics_ant_v1/verifier/config_smoke.toml tasks/simulation_heuristics_ant_v1/verifier/config.toml
uv run bench eval run \
--tasks-dir tasks/simulation_heuristics_ant_v1 \
--agent oracle \
--sandbox docker \
--context-root . \
--jobs-dir /tmp/genesisbench-oracle \
--concurrency 1
- name: Audit packaged leaderboard
run: uv run python scripts/audit_simulation_heuristics_ant_v1_leaderboard.py
- name: Lint
run: uv run ruff check .
- name: Test
run: uv run pytest -q
- name: Build package
run: uv build