Add dedicated test workflow with parallel pytest execution

[Copilot]

No CI workflow existed to run tests on PRs/pushes, leaving pytest-xdist (already a dev dependency) unused and PRs unvalidated automatically.

Changes

• .github/workflows/test.yml (new): Runs on push to main, pull_request, and workflow_dispatch. Uses Python 3.13, pip cache keyed on pyproject.toml, installs via pip install -e ".[dev]", and executes pytest tests/ -n auto for parallel distribution across available CPU cores. Scoped to permissions: contents: read.

• pyproject.toml: Adds [tool.pytest.ini_options] — sets testpaths, discovery patterns, and addopts = "-v --strict-markers" so verbosity and strict markers apply globally without repeating flags per invocation.

[tool.pytest.ini_options]
testpaths = ["tests"]
python_files = "test_*.py"
python_functions = "test_*"
addopts = "-v --strict-markers"

Original prompt

---

This section details on the original issue you should resolve

<issue_title>[Code Quality] Create dedicated test workflow with parallel pytest execution</issue_title>
<issue_description>### Description

The project has pytest-xdist configured in pyproject.toml dev dependencies but no dedicated test workflow to run tests in CI. Currently, tests can only be run manually or through custom actions. This creates a gap where PRs aren't automatically validated with test execution.

Problem

• No .github/workflows/test.yml workflow exists
• pytest-xdist is installed but not utilized for parallel test execution
• PRs lack automated test validation
• Test execution time could be reduced by 40-60% with parallelization

Suggested Changes

1. Create .github/workflows/test.yml:

   • Trigger on: pull_request, push to main, workflow_dispatch
   • Use Python 3.13 (matching sync.yml)
   • Enable pip caching (matching sync.yml pattern)
   • Install dev dependencies: pip install -e ".[dev]"
   • Run tests with parallel execution: pytest tests/ -n auto -v

2. Optional: Add pytest configuration in pyproject.toml:

   [tool.pytest.ini_options]
   testpaths = ["tests"]
   python_files = "test_*.py"
   python_functions = "test_*"
   addopts = "-v --strict-markers"

Files Affected

• .github/workflows/test.yml (new file)
• pyproject.toml (optional pytest config)

Success Criteria

• ✅ test.yml workflow runs on PRs and pushes to main
• ✅ Tests execute in parallel using pytest-xdist (-n auto)
• ✅ All 19+ test files pass successfully
• ✅ Pip dependencies are cached for faster CI runs
• ✅ Test execution time reduced by 40%+ compared to sequential

Priority

High - Improves CI/CD reliability and developer experience with faster feedback

Estimated Effort

1-2 hours

Source

Extracted from Daily Perf Improver discussion abhimehro/ctrld-sync#219 and Daily QA Report abhimehro/ctrld-sync#337

Performance Research Findings (Discussion #219):

Target: Speed up test execution by 40%+

Opportunities:

• CI dependency caching (pip cache in GitHub Actions)
• Parallel pytest execution (pytest -n auto)
• Faster test isolation (pytest-xdist)

QA Report Findings (Discussion #337):

Test execution: Tests run via custom action but no dedicated test.yml workflow for PR validation

🔍 Task mining by Discussion Task Miner - Code Quality Improvement Agent

To install this workflow, run gh aw add github/gh-aw/.github/workflows/discussion-task-miner.md@94662b1dee8ce96c876ba9f33b3ab8be32de82a4. View source at https://github.com/github/gh-aw/tree/94662b1dee8ce96c876ba9f33b3ab8be32de82a4/.github/workflows/discussion-task-miner.md.

• expires on Feb 20, 2026, 8:57 PM UTC

Comments on the Issue (you are @copilot in this section)

Custom agent used: Development Partner
The Development Partner Protocol

• Fixes [Code Quality] Create dedicated test workflow with parallel pytest execution #385

---

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

[trunk-io]

Merging to main in this repository is managed by Trunk.

• To merge this pull request, check the box to the left or comment /trunk merge below.

[github-actions]

👋 Development Partner is reviewing this PR. Will provide feedback shortly.

[Copilot]

Pull request overview

This PR creates a dedicated test workflow to automatically run pytest tests on PRs and pushes to main, addressing a gap where the repository had pytest-xdist configured but no CI workflow to leverage it.

Changes:

• Adds .github/workflows/test.yml to run tests automatically on push/PR with parallel execution via pytest-xdist
• Adds pytest configuration to pyproject.toml to centralize test discovery patterns and default options

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
.github/workflows/test.yml	New CI workflow that runs pytest with parallel execution (-n auto) on push to main, pull requests, and manual dispatch
pyproject.toml	Adds [tool.pytest.ini_options] section with test discovery patterns and default options (-v --strict-markers)

[Copilot]

The workflow uses pip for dependency installation, but the repository has a uv.lock file and the performance.yml workflow uses uv (astral-sh/setup-uv@v4 + uv sync --all-extras). For consistency with the existing performance workflow and to ensure deterministic builds using the lockfile, this workflow should also use uv. Replace the setup-python caching and pip install steps with uv installation and sync, similar to performance.yml lines 19-30.

Suggested change

	# PERFORMANCE: Cache pip dependencies to speed up CI runs
	# Cache key is based on pyproject.toml hash since dev deps are defined there
	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: '3.13'
	cache: 'pip'
	cache-dependency-path: 'pyproject.toml'
	# Install the package with dev dependencies (pytest, pytest-mock, pytest-xdist)
	- name: Install dependencies
	run: pip install -e ".[dev]"
	# PERFORMANCE: -n auto enables parallel execution via pytest-xdist,
	# distributing tests across available CPU cores for 40%+ faster runs
	- name: Run tests
	run: pytest tests/ -n auto
	# Set up Python and uv; uv will manage dependencies via the lockfile
	- name: Set up Python with uv
	uses: astral-sh/setup-uv@v4
	with:
	python-version: '3.13'
	# Install the package and dependencies using uv and the uv.lock file
	# Using --all-extras keeps behavior consistent with installing extras via pip
	- name: Install dependencies
	run: uv sync --all-extras
	# PERFORMANCE: -n auto enables parallel execution via pytest-xdist,
	# distributing tests across available CPU cores for 40%+ faster runs
	- name: Run tests
	run: uv run pytest tests/ -n auto

[Copilot]

For consistency and to ensure all pytest invocations benefit from parallel execution (not just CI runs), consider adding "-n auto" to the addopts configuration. This ensures developers running pytest locally and other workflows also get parallel execution by default. Suggested: addopts = "-n auto -v --strict-markers". This aligns with the performance optimization goal mentioned in the PR description and follows the pattern where configuration is centralized in pyproject.toml.

Suggested change

	addopts = "-v --strict-markers"
	addopts = "-n auto -v --strict-markers"

[abhimehro]

Closing: duplicate of test workflow (#395 is superset with uv caching). Use #395 instead.