Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 29 additions & 26 deletions .github/workflows/ci.yml
Original file line number Diff line number Diff line change
Expand Up @@ -14,11 +14,11 @@ jobs:
matrix:
python-version: ["3.11", "3.12", "3.13", "3.14"]
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: ${{ matrix.python-version }}
- uses: actions/setup-node@v4
- uses: actions/setup-node@v7
with:
node-version: "22"
- run: python -m pip install -e ".[dev]"
Expand Down Expand Up @@ -57,26 +57,26 @@ jobs:
- language: javascript
image: node:22-slim
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: "3.12"
- run: python -m pip install .
- run: docker pull ${{ matrix.image }}
- run: evalarc audit --task ${{ matrix.task }} --language ${{ matrix.language }} --image ${{ matrix.image }} --seeds 17 --output runs/docker-audit
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@v7
if: always()
with:
name: grader-audit-${{ matrix.task }}-${{ matrix.language }}
path: runs/docker-audit/
site:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: "3.12"
- uses: actions/setup-node@v4
- uses: actions/setup-node@v7
with:
node-version: "22"
cache: npm
Expand All @@ -97,24 +97,24 @@ jobs:
run: |
python -m pip install --quiet .
node scripts/check_reports_browser.cjs
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@v7
with:
name: evidence-site
path: dist/site/
include-hidden-files: true
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@v7
with:
name: evidence-casebook
path: dist/casebook/
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@v7
with:
name: independent-swe-dataset
path: dist/independent-swe-dataset/
action:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: "3.11"
- name: A higher headline score with regressed checks fails the action
Expand Down Expand Up @@ -245,8 +245,8 @@ jobs:
strands-recipe:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: "3.12"
cache: pip
Expand All @@ -273,15 +273,18 @@ jobs:
env:
GH_TOKEN: ${{ github.token }}
run: test "$(gh api repos/$GITHUB_REPOSITORY/git/ref/heads/main --jq .object.sha)" = "$GITHUB_SHA"
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v8
with:
name: evidence-site
path: site
- uses: actions/configure-pages@v5
- uses: actions/upload-pages-artifact@v3
- uses: actions/configure-pages@v6
- uses: actions/upload-pages-artifact@v5
with:
path: site
- uses: actions/deploy-pages@v4
# v4+ drops dotfiles by default; the published behavior-audit evidence lists
# node_modules/.pnpm/lock.yaml in its manifest, so keep hidden files.
include-hidden-files: true
- uses: actions/deploy-pages@v5
id: deployment
huggingface:
if: github.event_name != 'pull_request' && github.ref == 'refs/heads/main' && github.repository == 'noteflowai/evalarc'
Expand All @@ -291,19 +294,19 @@ jobs:
group: huggingface
cancel-in-progress: false
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
- uses: actions/checkout@v7
- uses: actions/setup-python@v7
with:
python-version: "3.12"
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v8
with:
name: evidence-site
path: dist/site
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v8
with:
name: evidence-casebook
path: dist/casebook
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v8
with:
name: independent-swe-dataset
path: dist/independent-swe-dataset
Expand All @@ -318,7 +321,7 @@ jobs:
python scripts/publish_space.py --bundle dist/site
python scripts/publish_dataset.py --bundle dist/casebook
python scripts/swe_dataset.py --publish --output dist/independent-swe-dataset
- uses: actions/setup-node@v4
- uses: actions/setup-node@v7
with:
node-version: "22"
cache: npm
Expand Down
8 changes: 4 additions & 4 deletions .github/workflows/publish-pypi.yml
Original file line number Diff line number Diff line change
Expand Up @@ -24,11 +24,11 @@ jobs:
check:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v7
with:
ref: refs/tags/${{ inputs.tag }}
persist-credentials: false
- uses: actions/setup-python@v5
- uses: actions/setup-python@v7
with:
python-version: "3.12"
- name: Download the release distributions and check their digests
Expand All @@ -55,7 +55,7 @@ jobs:
cd "$RUNNER_TEMP"
PYTHONPATH="" "$RUNNER_TEMP/installed/bin/python" \
"$GITHUB_WORKSPACE/scripts/check_installed.py" --source "$GITHUB_WORKSPACE"
- uses: actions/upload-artifact@v4
- uses: actions/upload-artifact@v7
with:
name: python-distributions
path: dist/
Expand All @@ -69,7 +69,7 @@ jobs:
permissions:
id-token: write
steps:
- uses: actions/download-artifact@v4
- uses: actions/download-artifact@v8
with:
name: python-distributions
path: dist/
Expand Down
Loading