llama-stack-mirror/.github/workflows/integration-tests.yml
Ashwin Bharambe 81e44b06ff fix: harden storage semantics (#4118)
Fixes issues in the storage system by guaranteeing immediate durability
for responses and ensuring background writers stay alive. Three related
fixes:

* Responses to the OpenAI-compatible API now write directly to
Postgres/SQLite inside the request instead of detouring through an async
queue that might never drain; this restores the expected
read-after-write behavior and removes the "response not found" races
reported by users.

* The access-control shim was stamping owner_principal/access_attributes
as SQL NULL, which Postgres interprets as non-public rows; fixing it to
use the empty-string/JSON-null pattern means conversations and responses
stored without an authenticated user stay queryable (matching SQLite).

* The inference-store queue remains for batching, but its worker tasks
now start lazily on the live event loop so server startup doesn't cancel
them—writes keep flowing even when the stack is launched via llama stack
run.

Closes #4115

Added a matrix entry to test our "base" suite against Postgres as the
store.
2025-11-12 12:40:23 -08:00

110 lines
4.3 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:
- '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'
- 'scripts/integration-tests.sh'
- 'scripts/generate_ci_matrix.py'
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:
generate-matrix:
runs-on: ubuntu-latest
outputs:
matrix: ${{ steps.set-matrix.outputs.matrix }}
steps:
- name: Checkout repository
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
- name: Generate test matrix
id: set-matrix
run: |
# Generate matrix from CI_MATRIX in tests/integration/suites.py
# Supports schedule-based and manual input overrides
MATRIX=$(PYTHONPATH=. python3 scripts/generate_ci_matrix.py \
--schedule "${{ github.event.schedule }}" \
--test-setup "${{ github.event.inputs.test-setup }}")
echo "matrix=$MATRIX" >> $GITHUB_OUTPUT
echo "Generated matrix: $MATRIX"
run-replay-mode-tests:
needs: generate-matrix
runs-on: ubuntu-latest
name: ${{ format('Integration Tests ({0}, {1}, {2}, client={3}, {4})', matrix.client, matrix.config.setup, matrix.python-version, matrix.client-version, matrix.config.suite) }}
strategy:
fail-fast: false
matrix:
client: [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"]') }}
# Test configurations: Generated from CI_MATRIX in tests/integration/suites.py
# See scripts/generate_ci_matrix.py for generation logic
config: ${{ fromJSON(needs.generate-matrix.outputs.matrix).include }}
steps:
- name: Checkout repository
uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
- name: Setup test environment
if: ${{ matrix.config.allowed_clients == null || contains(matrix.config.allowed_clients, matrix.client) }}
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
if: ${{ matrix.config.allowed_clients == null || contains(matrix.config.allowed_clients, matrix.client) }}
uses: ./.github/actions/run-and-record-tests
env:
OPENAI_API_KEY: dummy
with:
stack-config: >-
${{ matrix.config.stack_config
|| (matrix.client == 'library' && 'ci-tests')
|| (matrix.client == 'server' && 'server:ci-tests')
|| 'docker:ci-tests' }}
setup: ${{ matrix.config.setup }}
inference-mode: 'replay'
suite: ${{ matrix.config.suite }}