feat: add reflexion trial loop #6

	name: CI

	on:
	push:
	pull_request:

	jobs:
	test:
	name: Python ${{ matrix.python-version }} on ${{ matrix.os }}
	runs-on: ${{ matrix.os }}
	strategy:
	fail-fast: false
	matrix:
	os: [ubuntu-latest, windows-latest]
	python-version: ["3.10", "3.11", "3.12"]

	steps:
	- name: Check out repository
	uses: actions/checkout@v4

	- name: Set up Python
	uses: actions/setup-python@v5
	with:
	python-version: ${{ matrix.python-version }}

	- name: Install package
	run: \|
	python -m pip install --upgrade pip
	python -m pip install -e ".[dev]"

	- name: Compile Python sources
	run: python -m compileall dm_agent main.py

	- name: Run tests
	run: python -m pytest

	- name: Run deterministic eval smoke test
	run: python -m dm_agent.evals.cli --variant full --task direct_finish

	- name: List coding benchmark tasks
	run: python -m dm_agent.benchmarks.cli --list

	- name: Lint
	run: python -m ruff check .

	- name: Format check
	run: python -m black --check .

Navigation Menu