mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
a8aa815b6a
This PR refactors the integration test system to use global "setups"
which provides better separation of concerns:
**suites = what to test, setups = how to configure.**
NOTE: if you naming suggestions, please provide feedback
Changes:
- New `tests/integration/setups.py` with global, reusable configurations
(ollama, vllm, gpt, claude)
- Modified `scripts/integration-tests.sh` options to match with the
underlying pytest options
- Updated documentation to reflect the new global setup system
The main benefit is that setups can be reused across multiple suites
(e.g., use "gpt" with any suite) even though sometimes they could
specifically tailored for a suite (vision <> ollama-vision). It is now
easier to add new configurations without modifying existing suites.
Usage examples:
- `pytest tests/integration --suite=responses --setup=gpt`
- `pytest tests/integration --suite=vision` # auto-selects
"ollama-vision" setup
- `pytest tests/integration --suite=base --setup=vllm`
77 lines
3 KiB
YAML
77 lines
3 KiB
YAML
name: Integration Tests (Replay)
|
|
|
|
run-name: Run the integration test suites from tests/integration in replay mode
|
|
|
|
on:
|
|
push:
|
|
branches: [ main ]
|
|
pull_request:
|
|
branches: [ main ]
|
|
types: [opened, synchronize, reopened]
|
|
paths:
|
|
- 'llama_stack/**'
|
|
- '!llama_stack/ui/**'
|
|
- 'tests/**'
|
|
- 'uv.lock'
|
|
- 'pyproject.toml'
|
|
- '.github/workflows/integration-tests.yml' # This workflow
|
|
- '.github/actions/setup-ollama/action.yml'
|
|
- '.github/actions/setup-test-environment/action.yml'
|
|
- '.github/actions/run-and-record-tests/action.yml'
|
|
schedule:
|
|
# If changing the cron schedule, update the provider in the test-matrix job
|
|
- cron: '0 0 * * *' # (test latest client) Daily at 12 AM UTC
|
|
- cron: '1 0 * * 0' # (test vllm) Weekly on Sunday at 1 AM UTC
|
|
workflow_dispatch:
|
|
inputs:
|
|
test-all-client-versions:
|
|
description: 'Test against both the latest and published versions'
|
|
type: boolean
|
|
default: false
|
|
test-setup:
|
|
description: 'Test against a specific setup'
|
|
type: string
|
|
default: 'ollama'
|
|
|
|
concurrency:
|
|
# Skip concurrency for pushes to main - each commit should be tested independently
|
|
group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
|
|
run-replay-mode-tests:
|
|
runs-on: ubuntu-latest
|
|
name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client-type, matrix.setup, matrix.python-version, matrix.client-version, matrix.suite) }}
|
|
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
client-type: [library, server]
|
|
# Use vllm on weekly schedule, otherwise use test-setup input (defaults to ollama)
|
|
setup: ${{ (github.event.schedule == '1 0 * * 0') && fromJSON('["vllm"]') || fromJSON(format('["{0}"]', github.event.inputs.test-setup || 'ollama')) }}
|
|
# Use Python 3.13 only on nightly schedule (daily latest client test), otherwise use 3.12
|
|
python-version: ${{ github.event.schedule == '0 0 * * *' && fromJSON('["3.12", "3.13"]') || fromJSON('["3.12"]') }}
|
|
client-version: ${{ (github.event.schedule == '0 0 * * *' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
|
|
suite: [base, vision]
|
|
|
|
steps:
|
|
- name: Checkout repository
|
|
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
|
|
|
|
- name: Setup test environment
|
|
uses: ./.github/actions/setup-test-environment
|
|
with:
|
|
python-version: ${{ matrix.python-version }}
|
|
client-version: ${{ matrix.client-version }}
|
|
setup: ${{ matrix.setup }}
|
|
suite: ${{ matrix.suite }}
|
|
inference-mode: 'replay'
|
|
|
|
- name: Run tests
|
|
uses: ./.github/actions/run-and-record-tests
|
|
with:
|
|
stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
|
|
setup: ${{ matrix.setup }}
|
|
inference-mode: 'replay'
|
|
suite: ${{ matrix.suite }}
|