af4db1f79d
A handful of soak / bench / replay / proof / eval-matrix tests dominate the suite wall-clock (~50 tests ≈ the entire 73-min serial runtime; the other ~10k are near-instant). Classify them so developers can run a fast lane locally. Mechanism — central registry in conftest.py beside QUARANTINE (cost is empirical test-infra metadata, not test semantics, so it lives in one auditable place, not as decorators across ~24 files). Marker-only: it stamps `slow`, it NEVER skips, so `-m slow` SELECTS the slow tests. - SLOW_FILES (10): whole-file, where a module/session fixture carries the cost (marking one test would just shift the fixture cost to the next requester). - SLOW_TESTS (26 nodeids): mixed files, so the file's fast predicate/unit tests stay in the fast lane. - pytest_collection_modifyitems stamps `slow`; marker registered in pyproject. 912 of 10,596 tests classified (801 = test_cognition_eval_register_matrix eval-matrix; called out in docs — honest accounting). Lanes (Makefile + docs/testing-lanes.md): fast: pytest -m "not quarantine and not slow" slow: pytest -m "slow and not quarantine" full: pytest -m "not quarantine" (unchanged — what CI runs) CI is unaffected: smoke.yml and full-pytest.yml run `-m "not quarantine"`, which still includes the slow tests. No CI behavior change; no test logic touched (the change cannot alter pass/fail in the full lane — it only adds a marker). Timings (10-core, numpy): full 73min serial / 25min -n auto; fast ~26min serial / 9.5min -n auto (7.7x combined). The 975s test_inner_loop_phase2 outlier was probed (expected proof-scale work, not a bug; finding in docs). Deferred to follow-up PRs: -n auto by default (needs xdist hermeticity — fresh-env-dict subprocess + report.json/proposals writers race under parallel workers) and a warm-runtime fixture for the remaining 1-15s ChatRuntime tail.
66 lines
1.9 KiB
TOML
66 lines
1.9 KiB
TOML
[project]
|
|
name = "core-versor"
|
|
version = "0.1.0"
|
|
description = "Versor Engine: cognitive field system on Cl(4,1) Conformal Geometric Algebra"
|
|
requires-python = ">=3.11"
|
|
|
|
dependencies = [
|
|
"hypothesis>=6.152.7",
|
|
"numpy>=1.26",
|
|
"pytest>=9.0.3",
|
|
"pytest-asyncio>=1.3.0",
|
|
"pytest-xdist>=3.6",
|
|
"psutil>=7.0",
|
|
"pyrage==1.2.3",
|
|
"pyyaml>=6.0",
|
|
"ruff>=0.15.12",
|
|
"datasets>=4.8.5",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
dev = [
|
|
"pytest>=8.0",
|
|
"pytest-asyncio>=0.23",
|
|
"hypothesis>=6.100",
|
|
]
|
|
# ADR-0181 PR-6 — audio teacher / shadow lanes. Strictly optional: the
|
|
# deterministic compiler is the substrate; these models only label or align and
|
|
# are admitted as typed hints (sensorium.audio.teachers). Never runtime-required.
|
|
audio-whisper = ["openai-whisper>=20231117"]
|
|
audio-nemo = ["nemo_toolkit[asr]>=1.23"]
|
|
audio-clap = ["laion-clap>=1.1.6"]
|
|
audio-encodec = ["encodec>=0.1.1"]
|
|
|
|
[project.scripts]
|
|
core = "core.cli:main"
|
|
|
|
[tool.setuptools.packages.find]
|
|
where = ["."]
|
|
include = [
|
|
"algebra*",
|
|
"alignment*",
|
|
"chat*",
|
|
"core*",
|
|
"field*",
|
|
"formation*",
|
|
"generate*",
|
|
"ingest*",
|
|
"language_packs*",
|
|
"morphology*",
|
|
"persona*",
|
|
"recognition*",
|
|
"sensorium*",
|
|
"session*",
|
|
"vault*",
|
|
"vocab*",
|
|
"workbench*",
|
|
]
|
|
|
|
[tool.pytest.ini_options]
|
|
asyncio_mode = "auto"
|
|
testpaths = ["tests"]
|
|
markers = [
|
|
"quarantine: pre-existing failure tracked in conftest.py QUARANTINE registry; excluded from full-pytest CI gate. See docs/test-debt-quarantine.md.",
|
|
"uses_default_engine_state: test intentionally exercises the process default engine-state directory; opt out of per-test default isolation. See docs/issues/default-engine-state-test-hygiene.md.",
|
|
"slow: soak / bench / replay / proof / eval-matrix test that dominates suite wall-clock; classified in conftest.py SLOW_FILES/SLOW_TESTS (not in-file decorators). Fast lane: -m 'not quarantine and not slow'. See docs/testing-lanes.md.",
|
|
]
|