Skip to content

Core tests with LLMs #20

Core tests with LLMs

Core tests with LLMs #20

Workflow file for this run

# This workflow will install Python dependencies and run tests with a variety of Python versions
# For more information see: https://help.github.com/actions/language-and-framework-guides/using-python-with-github-actions
name: Core tests with LLMs
on:
schedule:
- cron: "0 0 * * 0" # weekly on Sunday at midnight UTC
workflow_dispatch: # allows manual triggering of the workflow
# pull_request_target:
# branches: ["main"]
# paths:
# - "autogen/**"
# - "test/**"
# - "notebook/agentchat_auto_feedback_from_code_execution.ipynb"
# - "notebook/agentchat_function_call.ipynb"
# - "notebook/agentchat_groupchat_finite_state_machine.ipynb"
# - ".github/workflows/core-llm-test.yml"
# - "pyproject.toml"
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref }}
cancel-in-progress: true
permissions:
{}
jobs:
test:
strategy:
matrix:
llm: ["openai", "openai-realtime", "gemini", "gemini-realtime", "anthropic", "deepseek", "ollama", "bedrock", "cerebras"]
python-version: ["3.10"]
os: [ubuntu-latest]
fail-fast: false
runs-on: ${{ matrix.os }}
environment: openai1
services:
redis:
image: redis@sha256:17a235ee842cd21d8bcb7f11a49fb177cbeaf5537996304a0089e94412de2ed5
ports:
- 6379:6379
options: --entrypoint redis-server
steps:
- name: Get User Permission
id: checkAccess
uses: actions-cool/check-user-permission@c21884f3dda18dafc2f8b402fe807ccc9ec1aa5e # v2.4.0
with:
require: write
username: ${{ github.triggering_actor }}
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
- name: Check User Permission
if: steps.checkAccess.outputs.require-result == 'false'
run: |
echo "${GITHUB_TRIGGERING_ACTOR} does not have permissions on this repo."
echo "Current permission level is ${STEPS_CHECKACCESS_OUTPUTS_USER_PERMISSION}"
echo "Job originally triggered by ${GITHUB_ACTOR}"
exit 1
env:
STEPS_CHECKACCESS_OUTPUTS_USER_PERMISSION: ${{ steps.checkAccess.outputs.user-permission }}
# checkout to pr branch
- name: Checkout
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
ref: ${{ github.event.pull_request.head.sha || github.ref }}
persist-credentials: false
- uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e # v6.8.0
with:
version: "latest"
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405 # v6.2.0
with:
python-version: ${{ matrix.python-version }}
- name: Install packages for ${{ matrix.llm }}
run: |
docker --version
uv pip install --system -e ".[test,redis,${{ matrix.llm }}]"
- name: Install openai if testing gemini-realtime
if: ${{ matrix.llm == 'gemini-realtime' }}
run: |
uv pip install --system -e ".[openai]"
- name: Create OAI_CONFIG_LIST from Secret
run: |
cat > OAI_CONFIG_LIST << 'EOF'
${{ secrets.OAI_CONFIG_LIST }}
EOF
shell: bash
- name: LLM tests using ${{ matrix.llm }}
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
DEEPSEEK_API_KEY: ${{ secrets.DEEPSEEK_API_KEY }}
AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
OAI_CONFIG_LIST: ${{ secrets.OAI_CONFIG_LIST }}
run: |
llm_fixed="${{ matrix.llm }}" # Use the matrix variable
llm_fixed="${llm_fixed//-/_}" # Replace hyphen with underscore
bash scripts/test-core-llm.sh -m "$llm_fixed"
- name: Show coverage report
run: bash scripts/show-coverage-report.sh
- name: Upload coverage to Codecov
if: ${{ !contains(github.ref, 'gh-readonly-queue/') }}
uses: codecov/codecov-action@75cd11691c0faa626561e295848008c8a7dddffe # v5.5.4
with:
files: ./coverage.xml
flags: core-llm, ${{ matrix.llm }}, ${{ matrix.os }}, ${{ matrix.python-version }}
fail_ci_if_error: true
token: ${{ secrets.CODECOV_TOKEN }}