Skip to content
Merged
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
35 changes: 32 additions & 3 deletions .github/workflows/eval-tutorial.yml
Original file line number Diff line number Diff line change
Expand Up @@ -11,23 +11,33 @@ on:
- ".github/workflows/eval-tutorial.yml"
- "evals/write-an-eval-that-can-say-no/**"

permissions:
contents: read

concurrency:
group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}

jobs:
run-example:
runs-on: ubuntu-latest
strategy:
matrix:
python-version: ["3.11", "3.12"]
env:
UV_PYTHON: ${{ matrix.python-version }}
defaults:
run:
working-directory: evals/write-an-eval-that-can-say-no
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@v6
- uses: astral-sh/setup-uv@v8.1.0
with:
python-version: "3.12"
python-version: ${{ matrix.python-version }}
- name: Install locked dependencies
run: uv sync --locked
run: |
uv sync --locked
uv run python --version
- name: Regenerate frozen rows and check expected hash
run: |
uv run python freeze.py
Expand All @@ -48,3 +58,22 @@ jobs:
uv run python run_eval.py broken
result=$?
test "$result" -eq 1
- name: Altered inputs must return exit 2
run: |
cp evals/gate.toml gate.toml.bak
printf '\n' >> evals/gate.toml
set +e
uv run python run_eval.py candidate
result=$?
set -e
mv gate.toml.bak evals/gate.toml
test "$result" -eq 2
- name: Missing model must return exit 3
run: |
mv candidate.joblib candidate.joblib.bak
set +e
uv run python run_eval.py candidate
result=$?
set -e
mv candidate.joblib.bak candidate.joblib
test "$result" -eq 3
Loading