llama-stack-mirror/.github/actions/run-and-record-tests/action.yml
Ashwin Bharambe a8aa815b6a
feat(tests): migrate to global "setups" system for test configuration (#3390)
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`
2025-09-09 15:50:56 -07:00

94 lines
3 KiB
YAML

name: 'Run and Record Tests'
description: 'Run integration tests and handle recording/artifact upload'
inputs:
stack-config:
description: 'Stack configuration to use'
required: true
setup:
description: 'Setup to use for tests (e.g., ollama, gpt, vllm)'
required: false
default: ''
inference-mode:
description: 'Inference mode (record or replay)'
required: true
suite:
description: 'Test suite to use: base, responses, vision, etc.'
required: false
default: ''
subdirs:
description: 'Comma-separated list of test subdirectories to run; overrides suite'
required: false
default: ''
pattern:
description: 'Regex pattern to pass to pytest -k'
required: false
default: ''
runs:
using: 'composite'
steps:
- name: Check Storage and Memory Available Before Tests
if: ${{ always() }}
shell: bash
run: |
free -h
df -h
- name: Run Integration Tests
shell: bash
run: |
SCRIPT_ARGS="--stack-config ${{ inputs.stack-config }} --inference-mode ${{ inputs.inference-mode }}"
# Add optional arguments only if they are provided
if [ -n '${{ inputs.setup }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --setup ${{ inputs.setup }}"
fi
if [ -n '${{ inputs.suite }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --suite ${{ inputs.suite }}"
fi
if [ -n '${{ inputs.subdirs }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --subdirs ${{ inputs.subdirs }}"
fi
if [ -n '${{ inputs.pattern }}' ]; then
SCRIPT_ARGS="$SCRIPT_ARGS --pattern ${{ inputs.pattern }}"
fi
uv run --no-sync ./scripts/integration-tests.sh $SCRIPT_ARGS | tee pytest-${{ inputs.inference-mode }}.log
- name: Commit and push recordings
if: ${{ inputs.inference-mode == 'record' }}
shell: bash
run: |
echo "Checking for recording changes"
git status --porcelain tests/integration/recordings/
if [[ -n $(git status --porcelain tests/integration/recordings/) ]]; then
echo "New recordings detected, committing and pushing"
git add tests/integration/recordings/
git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
git fetch origin ${{ github.ref_name }}
git rebase origin/${{ github.ref_name }}
echo "Rebased successfully"
git push origin HEAD:${{ github.ref_name }}
echo "Pushed successfully"
else
echo "No recording changes"
fi
- name: Write inference logs to file
if: ${{ always() }}
shell: bash
run: |
sudo docker logs ollama > ollama-${{ inputs.inference-mode }}.log || true
- name: Upload logs
if: ${{ always() }}
uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
with:
name: logs-${{ github.run_id }}-${{ github.run_attempt || '' }}-${{ strategy.job-index }}
path: |
*.log
retention-days: 1