mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
628e38b3d5
# What does this PR do? This prevents interference from already running servers, and allows multiple concurrent integration test runs. Unleash the AIs! ## Test Plan start a LS server at port 8321 Then observe test uses port 8322: ❯ uv run --no-sync ./scripts/integration-tests.sh --stack-config server:ci-tests --inference-mode replay --setup ollama --suite base --pattern '(telemetry or safety)' === Llama Stack Integration Test Runner === Stack Config: server:ci-tests Setup: ollama Inference Mode: replay Test Suite: base Test Subdirs: Test Pattern: (telemetry or safety) Checking llama packages llama-stack 0.4.0.dev0 /Users/erichuang/projects/new_test_server llama-stack-client 0.3.0 ollama 0.6.0 === Applying Setup Environment Variables === Setting SQLITE_STORE_DIR: /var/folders/cz/vyh7y1d11xg881lsxsshnc5c0000gn/T/tmp.bKLsaVAxyU Setting stack config type: server Setting up environment variables: export OLLAMA_URL='http://0.0.0.0:11434' export SAFETY_MODEL='ollama/llama-guard3:1b' Will use port: 8322 === Starting Llama Stack Server === Waiting for Llama Stack Server to start on port 8322... ✅ Llama Stack Server started successfully
93 lines
3.8 KiB
YAML
93 lines
3.8 KiB
YAML
name: Integration Tests (Replay)
|
|
|
|
run-name: Run the integration test suites from tests/integration in replay mode
|
|
|
|
on:
|
|
push:
|
|
branches:
|
|
- main
|
|
- 'release-[0-9]+.[0-9]+.x'
|
|
pull_request:
|
|
branches:
|
|
- main
|
|
- 'release-[0-9]+.[0-9]+.x'
|
|
types: [opened, synchronize, reopened]
|
|
paths:
|
|
- 'src/llama_stack/**'
|
|
- '!src/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'
|
|
- 'scripts/integration-tests.sh'
|
|
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.config.setup, matrix.python-version, matrix.client-version, matrix.config.suite) }}
|
|
|
|
strategy:
|
|
fail-fast: false
|
|
matrix:
|
|
client-type: [library, docker, server]
|
|
# 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"]') }}
|
|
# Define (setup, suite) pairs - they are always matched and cannot be independent
|
|
# Weekly schedule (Sun 1 AM): vllm+base
|
|
# Input test-setup=ollama-vision: ollama-vision+vision
|
|
# Default (including test-setup=ollama): ollama+base, ollama-vision+vision, gpt+responses
|
|
config: >-
|
|
${{
|
|
github.event.schedule == '1 0 * * 0'
|
|
&& fromJSON('[{"setup": "vllm", "suite": "base"}]')
|
|
|| github.event.inputs.test-setup == 'ollama-vision'
|
|
&& fromJSON('[{"setup": "ollama-vision", "suite": "vision"}]')
|
|
|| fromJSON('[{"setup": "ollama", "suite": "base"}, {"setup": "ollama-vision", "suite": "vision"}, {"setup": "gpt", "suite": "responses"}]')
|
|
}}
|
|
|
|
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.config.setup }}
|
|
suite: ${{ matrix.config.suite }}
|
|
inference-mode: 'replay'
|
|
|
|
- name: Run tests
|
|
uses: ./.github/actions/run-and-record-tests
|
|
env:
|
|
OPENAI_API_KEY: dummy
|
|
with:
|
|
stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || matrix.client-type == 'server' && 'server:ci-tests' || 'docker:ci-tests' }}
|
|
setup: ${{ matrix.config.setup }}
|
|
inference-mode: 'replay'
|
|
suite: ${{ matrix.config.suite }}
|