test(evals): add 13 more math/time tasks; smoke-tested with mock prov… #2

	name: CI

	on:
	push:
	branches: [ main ]
	pull_request:
	branches: [ main ]

	jobs:
	test:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-python@v5
	with:
	python-version: '3.12'
	- name: Install package
	run: \|
	python -m pip install --upgrade pip
	pip install -e .[repair]
	- name: Run tests
	env:
	# Force mock provider to avoid external API calls
	LLM_PROVIDER: mock
	USE_TOOL_CALLS: '0'
	run: \|
	pytest -q
	- name: Run evals (smoke)
	env:
	LLM_PROVIDER: mock
	USE_TOOL_CALLS: '0'
	run: \|
	python evals/run_evals.py --n 6

Provide feedback