plonecli/tox.ini at master · plone/plonecli · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
[tox]
envlist =
    {py311,py312,py313,py314},
    lint,

skip_missing_interpreters = True

labels =
    # billing: headless Claude Code runs — invoke explicitly via `tox -m evals`
    evals = evals-sonnet, evals-haiku, evals-opus

[testenv]
usedevelop = True
extras =
    test

basepython:
    py311: python3.11
    py312: python3.12
    py313: python3.13
    py314: python3.14

commands =
    pytest --cov=plonecli tests {posargs}

setenv =
    PYTHONPATH = {toxinidir}

passenv =
    VERBOSE
    PLONECLI_TEMPLATES_REPO_URL
    PLONECLI_TEMPLATES_BRANCH
    PLONECLI_TEMPLATES_DIR

deps =
    pytest
    pytest-cov

[testenv:evals-{sonnet,haiku,opus}]
description = behavioral skill evals via headless Claude Code (bills model usage)
usedevelop = True
extras =
    test
setenv =
    PYTHONPATH = {toxinidir}
    RUN_SKILL_EVALS = 1
    sonnet: SKILL_EVAL_MODEL = sonnet
    haiku: SKILL_EVAL_MODEL = haiku
    opus: SKILL_EVAL_MODEL = opus
passenv =
    HOME
    CLAUDE_CONFIG_DIR
    ANTHROPIC_API_KEY
commands =
    pytest -m evals -v tests/test_skill_evals.py {posargs}

[testenv:evals-baseline]
description = skill vs no-skill A/B via the CLI runner (bills model usage)
usedevelop = True
extras =
    test
setenv =
    PYTHONPATH = {toxinidir}
passenv =
    HOME
    CLAUDE_CONFIG_DIR
    ANTHROPIC_API_KEY
commands =
    python evals/skill/run_evals.py --mode both {posargs}

[testenv:lint]
basepython = python3.13
skip_install = true
deps =
    ruff
commands =
    ruff check {toxinidir}/plonecli {toxinidir}/tests {toxinidir}/evals
    ruff format --check {toxinidir}/plonecli {toxinidir}/tests {toxinidir}/evals