74 lines
1.8 KiB
YAML
74 lines
1.8 KiB
YAML
name: CI Tests Full
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- "release/**"
|
|
pull_request:
|
|
branches:
|
|
- "release/**"
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
unit-tests:
|
|
runs-on: ubuntu-latest
|
|
env:
|
|
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Set up Python 3.10
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: '3.10'
|
|
cache: 'pip'
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
python -m pip install --upgrade pip
|
|
pip install -e '.[dev,ifeval,ifbench,multi_if,needle_haystack,arena_hard]'
|
|
pip install git+https://github.com/sierra-research/tau-bench
|
|
pip install bfcl-eval==2025.10.27.1
|
|
|
|
- name: Create .env file
|
|
run: |
|
|
echo "DASHSCOPE_API_KEY=${{ secrets.DASHSCOPE_API_KEY }}" > .env
|
|
|
|
- name: Run integration tests
|
|
run: |
|
|
python -m pytest tests/cli/test_all.py::TestRun::test_benchmarks -v -s -p no:warnings
|
|
|
|
|
|
perf-tests:
|
|
runs-on: ubuntu-latest
|
|
env:
|
|
FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
|
|
|
|
steps:
|
|
- name: Checkout code
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Set up Python 3.10
|
|
uses: actions/setup-python@v5
|
|
with:
|
|
python-version: '3.10'
|
|
cache: 'pip'
|
|
|
|
- name: Install dependencies
|
|
run: |
|
|
python -m pip install --upgrade pip
|
|
pip install -e '.[dev,perf]'
|
|
|
|
- name: Create .env file
|
|
run: |
|
|
echo "DASHSCOPE_API_KEY=${{ secrets.DASHSCOPE_API_KEY }}" > .env
|
|
|
|
- name: Run perf test
|
|
run: |
|
|
python -m pytest tests/perf/test_perf_basic.py::TestPerfBasic::test_multi_parallel_sweep -v -s -p no:warnings
|