Files
logic-skeleton-bench/.gitea/workflows/short-eval.yml
T

45 lines
1.7 KiB
YAML

name: Dynamic world reasoning evaluation
on:
workflow_dispatch:
jobs:
short-eval:
runs-on: minecraft-and-affine-server
timeout-minutes: 45
env:
RENDERER_API_KEY: ${{ secrets.RENDERER_API_KEY }}
RENDERER_BASE_URL: ${{ vars.RENDERER_BASE_URL }}
RENDERER_API_STYLE: ${{ vars.RENDERER_API_STYLE }}
RENDERER_MODEL: ${{ vars.RENDERER_MODEL }}
SOLVER_API_KEY: ${{ secrets.SOLVER_API_KEY }}
SOLVER_BASE_URL: ${{ vars.SOLVER_BASE_URL }}
SOLVER_API_STYLE: ${{ vars.SOLVER_API_STYLE }}
SOLVER_MODEL: ${{ vars.SOLVER_MODEL }}
SOLVER_ENABLE_THINKING: "false"
steps:
- name: Check out repository
uses: actions/checkout@v4
- name: Run unit tests
run: python3 -m unittest discover -s tests -v
- name: Run five large-world live cases
run: python3 -m logicbench run tasks/short-smoke.json
- name: Show dynamic worlds, rendered histories, results, and summary
if: always()
run: |
test -f artifacts/short-smoke/skeletons.jsonl && cat artifacts/short-smoke/skeletons.jsonl || true
test -f artifacts/short-smoke/rendered.jsonl && cat artifacts/short-smoke/rendered.jsonl || true
test -f artifacts/short-smoke/solver-outputs.jsonl && cat artifacts/short-smoke/solver-outputs.jsonl || true
test -f artifacts/short-smoke/results.jsonl && cat artifacts/short-smoke/results.jsonl || true
test -f artifacts/short-smoke/summary.json && cat artifacts/short-smoke/summary.json || true
- name: Preserve evaluation artifacts
if: always()
uses: actions/upload-artifact@v3
with:
name: dynamic-world-evaluation
path: artifacts/short-smoke/