Merge branch 'main' into enable-vector-stores-files-api-tests

This commit is contained in:
Francisco Arceo 2025-07-31 20:25:41 -04:00 committed by GitHub
commit f48f089436
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 24 additions and 226 deletions

View file

@ -192,7 +192,7 @@ runs:
if: ${{ always() }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: ${{ inputs.inference-mode }}-logs-${{ github.run_id }}-${{ github.run_attempt || '' }}-${{ inputs.provider }}-${{ inputs.run-vision-tests }}-${{ inputs.stack-config }}
name: logs-${{ github.run_id }}-${{ github.run_attempt || '' }}-${{ strategy.job-index }}
path: |
*.log
retention-days: 1

View file

@ -16,6 +16,9 @@ inputs:
description: 'Whether to setup provider for vision tests'
required: false
default: 'false'
inference-mode:
description: 'Inference mode (record or replay)'
required: true
runs:
using: 'composite'
@ -27,13 +30,13 @@ runs:
client-version: ${{ inputs.client-version }}
- name: Setup ollama
if: ${{ inputs.provider == 'ollama' }}
if: ${{ inputs.provider == 'ollama' && inputs.inference-mode == 'record' }}
uses: ./.github/actions/setup-ollama
with:
run-vision-tests: ${{ inputs.run-vision-tests }}
- name: Setup vllm
if: ${{ inputs.provider == 'vllm' }}
if: ${{ inputs.provider == 'vllm' && inputs.inference-mode == 'record' }}
uses: ./.github/actions/setup-vllm
- name: Build Llama Stack

View file

@ -8,9 +8,8 @@ Llama Stack uses GitHub Actions for Continuous Integration (CI). Below is a tabl
| Installer CI | [install-script-ci.yml](install-script-ci.yml) | Test the installation script |
| Integration Auth Tests | [integration-auth-tests.yml](integration-auth-tests.yml) | Run the integration test suite with Kubernetes authentication |
| SqlStore Integration Tests | [integration-sql-store-tests.yml](integration-sql-store-tests.yml) | Run the integration test suite with SqlStore |
| Integration Tests | [integration-tests.yml](integration-tests.yml) | Run the integration test suite from tests/integration |
| Integration Tests (Replay) | [integration-tests.yml](integration-tests.yml) | Run the integration test suite from tests/integration in replay mode |
| Vector IO Integration Tests | [integration-vector-io-tests.yml](integration-vector-io-tests.yml) | Run the integration test suite with various VectorIO providers |
| Vision Inference Integration Tests | [integration-vision-tests.yml](integration-vision-tests.yml) | Run vision inference integration test suite from tests/integration/inference |
| Pre-commit | [pre-commit.yml](pre-commit.yml) | Run pre-commit checks |
| Test Llama Stack Build | [providers-build.yml](providers-build.yml) | Test llama stack build |
| Python Package Build Test | [python-build-test.yml](python-build-test.yml) | Test building the llama-stack PyPI project |

View file

@ -1,13 +1,13 @@
name: Integration Tests
name: Integration Tests (Replay)
run-name: Run the integration test suite from tests/integration
run-name: Run the integration test suite from tests/integration in replay mode
on:
push:
branches: [ main ]
pull_request_target:
pull_request:
branches: [ main ]
types: [opened, synchronize, labeled]
types: [opened, synchronize, reopened]
paths:
- 'llama_stack/**'
- 'tests/**'
@ -31,35 +31,17 @@ on:
description: 'Test against a specific provider'
type: string
default: 'ollama'
force-inference-mode:
description: 'Force inference mode (record or replay)'
type: string
default: ''
concurrency:
# Skip concurrency for pushes to main - each commit should be tested independently
# For other events, create concurrency groups:
# ${{ github.workflow }}-${{ github.ref }}-rerecord (for labeled events with re-record-tests label)
# ${{ github.workflow }}-${{ github.ref }}-replay (for all non-labeled events)
# ${{ github.workflow }}-${{ github.ref }}-no-run (for labeled events without re-record-tests label)
# The "no-run" group ensures that irrelevant label events don't interfere with the real workflows.
group: >-
${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-${{
github.event.action == 'labeled' && (
contains(github.event.pull_request.labels.*.name, 're-record-tests') && 'rerecord' || 'no-run'
) || 'replay'
}}
group: ${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}
cancel-in-progress: true
jobs:
discover-tests:
if: |
github.event.action != 'labeled' ||
contains(github.event.pull_request.labels.*.name, 're-record-tests')
runs-on: ubuntu-latest
outputs:
test-types: ${{ steps.generate-test-types.outputs.test-types }}
rerecord-tests: ${{ steps.check-rerecord-tests.outputs.rerecord-tests }}
steps:
- name: Checkout repository
@ -69,61 +51,13 @@ jobs:
id: generate-test-types
run: |
# Get test directories dynamically, excluding non-test directories
# NOTE: we are excluding post_training since the tests take too long
TEST_TYPES=$(find tests/integration -maxdepth 1 -mindepth 1 -type d -printf "%f\n" |
grep -Ev "^(__pycache__|fixtures|test_cases|recordings)$" |
grep -Ev "^(__pycache__|fixtures|test_cases|recordings|post_training)$" |
sort | jq -R -s -c 'split("\n")[:-1]')
echo "test-types=$TEST_TYPES" >> $GITHUB_OUTPUT
- name: Check if re-record-tests label exists
id: check-rerecord-tests
run: |
if [[ "${{ inputs.force-inference-mode }}" == "record" ]]; then
echo "rerecord-tests=true" >> $GITHUB_OUTPUT
elif [[ "${{ inputs.force-inference-mode }}" == "replay" ]]; then
echo "rerecord-tests=false" >> $GITHUB_OUTPUT
else
if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
echo "rerecord-tests=true" >> $GITHUB_OUTPUT
else
echo "rerecord-tests=false" >> $GITHUB_OUTPUT
fi
fi
record-tests:
# Sequential job for recording to avoid SQLite conflicts
if: ${{ needs.discover-tests.outputs.rerecord-tests == 'true' }}
needs: discover-tests
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ github.event.pull_request.head.ref }}
fetch-depth: 0
- name: Setup test environment
uses: ./.github/actions/setup-test-environment
with:
python-version: "3.12" # Use single Python version for recording
client-version: "latest"
provider: ${{ inputs.test-provider || 'ollama' }}
- name: Run and record tests
uses: ./.github/actions/run-and-record-tests
with:
test-types: ${{ needs.discover-tests.outputs.test-types }}
stack-config: 'server:ci-tests' # recording must be done with server since more tests are run
provider: ${{ inputs.test-provider || 'ollama' }}
inference-mode: 'record'
run-replay-mode-tests:
# Skip this job if we're in recording mode (handled by record-tests job)
if: ${{ needs.discover-tests.outputs.rerecord-tests != 'true' }}
needs: discover-tests
runs-on: ubuntu-latest
@ -133,8 +67,10 @@ jobs:
client-type: [library, server]
# Use vllm on weekly schedule, otherwise use test-provider input (defaults to ollama)
provider: ${{ (github.event.schedule == '1 0 * * 0') && fromJSON('["vllm"]') || fromJSON(format('["{0}"]', github.event.inputs.test-provider || 'ollama')) }}
python-version: ["3.12", "3.13"]
client-version: ${{ (github.event.schedule == '0 0 * * 0' || github.event.inputs.test-all-client-versions == 'true') && fromJSON('["published", "latest"]') || fromJSON('["latest"]') }}
# 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"]') }}
run-vision-tests: ['true', 'false']
steps:
- name: Checkout repository
@ -146,11 +82,14 @@ jobs:
python-version: ${{ matrix.python-version }}
client-version: ${{ matrix.client-version }}
provider: ${{ matrix.provider }}
run-vision-tests: ${{ matrix.run-vision-tests }}
inference-mode: 'replay'
- name: Run and record tests
- name: Run tests
uses: ./.github/actions/run-and-record-tests
with:
test-types: ${{ needs.discover-tests.outputs.test-types }}
stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
provider: ${{ matrix.provider }}
inference-mode: 'replay'
run-vision-tests: ${{ matrix.run-vision-tests }}

View file

@ -1,141 +0,0 @@
name: Vision Inference Integration Tests
run-name: Run vision inference integration test suite from tests/integration/inference
on:
push:
branches: [ main ]
pull_request_target:
branches: [ main ]
types: [opened, synchronize, labeled]
paths:
- 'llama_stack/**'
- 'tests/**'
- 'uv.lock'
- 'pyproject.toml'
- '.github/workflows/integration-vision-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'
workflow_dispatch:
inputs:
test-all-client-versions:
description: 'Test against both the latest and published versions'
type: boolean
default: false
force-inference-mode:
description: 'Force inference mode (record or replay)'
type: string
default: ''
concurrency:
# Skip concurrency for pushes to main - each commit should be tested independently
# For other events, create concurrency groups:
# ${{ github.workflow }}-${{ github.ref }}-rerecord (for labeled events with re-record-tests label)
# ${{ github.workflow }}-${{ github.ref }}-replay (for all non-labeled events)
# ${{ github.workflow }}-${{ github.ref }}-no-run (for labeled events without re-record-tests label)
# The "no-run" group ensures that irrelevant label events don't interfere with the real workflows.
group: >-
${{ github.workflow }}-${{ github.ref == 'refs/heads/main' && github.run_id || github.ref }}-${{
github.event.action == 'labeled' && (
contains(github.event.pull_request.labels.*.name, 're-record-tests') && 'rerecord' || 'no-run'
) || 'replay'
}}
cancel-in-progress: true
jobs:
discover-tests:
if: |
github.event.action != 'labeled' ||
contains(github.event.pull_request.labels.*.name, 're-record-tests')
runs-on: ubuntu-latest
outputs:
rerecord-tests: ${{ steps.check-rerecord-tests.outputs.rerecord-tests }}
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Check if re-record-tests label exists
id: check-rerecord-tests
run: |
if [[ "${{ inputs.force-inference-mode }}" == "record" ]]; then
echo "rerecord-tests=true" >> $GITHUB_OUTPUT
elif [[ "${{ inputs.force-inference-mode }}" == "replay" ]]; then
echo "rerecord-tests=false" >> $GITHUB_OUTPUT
else
if [[ "${{ contains(github.event.pull_request.labels.*.name, 're-record-tests') }}" == "true" ]]; then
echo "rerecord-tests=true" >> $GITHUB_OUTPUT
else
echo "rerecord-tests=false" >> $GITHUB_OUTPUT
fi
fi
record-tests:
# Sequential job for recording to avoid SQLite conflicts
if: ${{ needs.discover-tests.outputs.rerecord-tests == 'true' }}
needs: discover-tests
runs-on: ubuntu-latest
permissions:
contents: write
pull-requests: write
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
with:
ref: ${{ github.event.pull_request.head.ref }}
fetch-depth: 0
- name: Setup test environment
uses: ./.github/actions/setup-test-environment
with:
python-version: "3.12" # Use single Python version for recording
client-version: "latest"
provider: 'ollama'
run-vision-tests: 'true'
- name: Run and record tests
uses: ./.github/actions/run-and-record-tests
with:
test-types: '["vision"]'
stack-config: 'server:ci-tests' # re-recording must be done in server mode
provider: 'ollama'
inference-mode: 'record'
run-vision-tests: 'true'
run-replay-mode-tests:
# Skip this job if we're in recording mode (handled by record-tests job)
if: ${{ needs.discover-tests.outputs.rerecord-tests != 'true' }}
needs: discover-tests
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
client-type: [library]
provider: [ollama]
python-version: ["3.12"]
client-version: ["latest"]
steps:
- name: Checkout repository
uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
- name: Setup test environment
uses: ./.github/actions/setup-test-environment
with:
python-version: ${{ matrix.python-version }}
client-version: ${{ matrix.client-version }}
provider: ${{ matrix.provider }}
run-vision-tests: 'true'
- name: Run and record tests
uses: ./.github/actions/run-and-record-tests
with:
test-types: '["vision"]'
stack-config: ${{ matrix.client-type == 'library' && 'ci-tests' || 'server:ci-tests' }}
provider: ${{ matrix.provider }}
inference-mode: 'replay'
run-vision-tests: 'true'

View file

@ -12,15 +12,13 @@ on:
- 'tests/integration/**'
- 'uv.lock'
- 'pyproject.toml'
- 'requirements.txt'
- 'tests/external/*'
- '.github/workflows/test-external-provider-module.yml' # This workflow
# This workflow is disabled. See https://github.com/meta-llama/llama-stack/pull/2975#issuecomment-3138702984 for details
if: false
jobs:
test-external-providers-from-module:
# This workflow is disabled. See https://github.com/meta-llama/llama-stack/pull/2975#issuecomment-3138702984 for details
if: false
runs-on: ubuntu-latest
strategy:
matrix: