Files
codex-app-server/cloud/tests/test_arch_conformance.py
host dba6536ac2 feat: architecture conformance checks in CI and metrics feedback loop
- cloud/arch_conformance.py: contract-version (+1 only, approved
  change record), forbidden-directory (own dir only, .. and symlink
  escapes resolved), forbidden-import layer bans audited against the
  baseline (foundation/execution/driver, server sqlite3 Row adapters
  deliberately allowed), G2 frozen-stack swap guard; skill-project
  one-call check.
- cloud/metrics.py: first-pass/defect/rework rates over terminal
  tasks, unknown rates as None (never 0), #212 dual-column per-task
  cost (total None when incomplete), pure feedback rules
  (tighten/route-with-extra-audit/recalibrate, auto_apply False),
  golden-set gate: unapproved sample set is never decision-ready.
- GET /metrics-report (authenticated, member-scoped, same as
  /metrics): attempts/defects are None until an attempt ledger
  exists, so rates stay unknown rather than fabricated.
- Tests: 29 arch + 15 metrics + 3 endpoint, each check with
  positive and negative cases; repo-level scan pins zero layer
  violations on the baseline so a future violation fails CI via the
  existing host-verify discover run (no workflow change).
2026-11-03 02:49:25 +00:00

222 lines
9.0 KiB
Python

"""Tests for cloud.arch_conformance: architecture consistency checks.
Every check has a positive and a negative case; the repo-level test
pins that the current tree passes the layer bans, so a future
violation fails CI (the existing host-verify workflow runs
``discover -s cloud/tests``; a failure here is a CI failure).
Only the standard library; no real model, no network, no secrets.
"""
import os
import sys
import tempfile
import unittest
from pathlib import Path
sys.path.insert(0, os.path.dirname(os.path.dirname(
os.path.dirname(os.path.abspath(__file__)))))
from cloud.arch_conformance import ( # noqa: E402
check_contract_version, check_frozen_stack, check_layer_imports,
check_skill_project, check_task_writes, is_within,
scan_cloud_package, scan_imports)
class TestContractVersion(unittest.TestCase):
def test_equal_versions_pass(self):
self.assertTrue(check_contract_version("v1", "v1")["ok"])
def test_approved_step_bump_passes(self):
change = {"approved": True, "backward_compatible": True,
"affected_clients": ["web"]}
self.assertTrue(
check_contract_version("v1", "v2", change=change)["ok"])
def test_breaking_bump_needs_regression_task(self):
change = {"approved": True, "backward_compatible": False,
"affected_clients": ["web"]}
verdict = check_contract_version("v1", "v2", change=change)
self.assertFalse(verdict["ok"])
self.assertTrue(any("regression" in r for r in verdict["reasons"]))
def test_breaking_bump_with_regression_task_passes(self):
change = {"approved": True, "backward_compatible": False,
"affected_clients": ["web"], "regression_task": "t-1"}
self.assertTrue(
check_contract_version("v1", "v2", change=change)["ok"])
def test_unapproved_bump_fails(self):
change = {"approved": False, "backward_compatible": True,
"affected_clients": ["web"]}
self.assertFalse(
check_contract_version("v1", "v2", change=change)["ok"])
def test_bump_without_change_record_fails(self):
self.assertFalse(check_contract_version("v1", "v2")["ok"])
def test_skip_bump_fails_even_when_approved(self):
change = {"approved": True, "backward_compatible": True,
"affected_clients": ["web"]}
verdict = check_contract_version("v1", "v3", change=change)
self.assertFalse(verdict["ok"])
def test_unparseable_version_fails(self):
self.assertFalse(check_contract_version("v1", "draft")["ok"])
class TestFrozenStack(unittest.TestCase):
def test_unchanged_stack_passes(self):
frozen = {"web": "React", "ios": "SwiftUI"}
self.assertTrue(check_frozen_stack(frozen, dict(frozen))["ok"])
def test_new_client_is_addition_not_swap(self):
frozen = {"web": "React"}
current = {"web": "React", "ios": "SwiftUI"}
self.assertTrue(check_frozen_stack(frozen, current)["ok"])
def test_swap_without_approval_fails(self):
verdict = check_frozen_stack({"web": "React"}, {"web": "Vue"})
self.assertFalse(verdict["ok"])
self.assertEqual(verdict["swapped"], ["web"])
def test_removed_client_without_approval_fails(self):
self.assertFalse(
check_frozen_stack({"web": "React", "ios": "SwiftUI"},
{"web": "React"})["ok"])
def test_swap_with_approved_change_passes(self):
change = {"approved": True, "backward_compatible": True,
"affected_clients": ["web"]}
self.assertTrue(
check_frozen_stack({"web": "React"}, {"web": "Vue"},
change=change)["ok"])
class TestDirectoryGuard(unittest.TestCase):
def test_inside_passes_and_outside_fails(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "work")
os.makedirs(own)
self.assertTrue(is_within(own, os.path.join(own, "a.txt")))
self.assertTrue(is_within(own, own))
self.assertFalse(is_within(own, os.path.join(tmp, "other")))
def test_dotdot_escape_fails(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "work")
os.makedirs(own)
escape = os.path.join(own, "..", "secret.txt")
self.assertFalse(is_within(own, escape))
self.assertEqual(check_task_writes(own, [escape]), [escape])
def test_symlink_escape_fails(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "work")
outside = os.path.join(tmp, "outside")
os.makedirs(own)
os.makedirs(outside)
link = os.path.join(own, "link")
try:
os.symlink(outside, link)
except OSError:
self.skipTest("symlinks unavailable")
self.assertFalse(is_within(own, link))
def test_mixed_writes_report_only_violations(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "work")
os.makedirs(own)
good = os.path.join(own, "ok.txt")
bad = os.path.join(tmp, "bad.txt")
self.assertEqual(check_task_writes(own, [good, bad]), [bad])
class TestLayerImports(unittest.TestCase):
def test_foundation_importing_server_fails(self):
verdict = check_layer_imports(
{"db": "from cloud.server import foo\n"})
self.assertEqual(len(verdict), 1)
self.assertEqual(verdict[0]["rule"],
"foundation_must_not_import_orchestration")
def test_foundation_importing_store_passes(self):
# db importing nothing, models importing nothing: the baseline
# shape. A foundation module importing another foundation
# module is not an upward import.
self.assertEqual(check_layer_imports(
{"models": "import os\n", "queue": "from cloud.models import x\n"}),
[])
def test_sandbox_importing_db_fails(self):
verdict = check_layer_imports(
{"sandbox": "from cloud.db import connect\n"})
self.assertEqual(len(verdict), 1)
def test_sandbox_stdlib_only_passes(self):
self.assertEqual(check_layer_imports(
{"sandbox": "import os\nimport subprocess\n"}), [])
def test_service_opening_sqlite_directly_fails(self):
verdict = check_layer_imports(
{"server": "import sqlite3\nconn = sqlite3.connect('x.db')\n"})
self.assertTrue(any(v["rule"] == "service_must_not_open_driver_"
"connection_directly" for v in verdict))
def test_service_sqlite_row_adapter_passes(self):
# Deliberate narrow ban: Row/exception adapters on a
# cloud.db connection are adaptation, not a bypass.
self.assertEqual(check_layer_imports(
{"server": "import sqlite3\nconn.row_factory = sqlite3.Row\n"
"try:\n pass\nexcept sqlite3.IntegrityError:\n"
" pass\n"}), [])
def test_service_importing_psycopg_fails(self):
verdict = check_layer_imports(
{"worker": "import psycopg\n"})
self.assertTrue(any(v["rule"] == "service_must_not_open_driver_"
"connection_directly" for v in verdict))
def test_driver_adjacent_modules_exempt(self):
self.assertEqual(check_layer_imports(
{"backup": "import sqlite3\nsqlite3.connect('x.db')\n",
"migrations": "import sqlite3\nsqlite3.connect('y.db')\n"}), [])
def test_scan_imports_sees_from_cloud_form(self):
scanned = scan_imports("from cloud.worker import Worker\n")
self.assertIn("worker", scanned["cloud"])
class TestRepoLevelScan(unittest.TestCase):
def test_current_tree_has_zero_layer_violations(self):
repo_root = Path(__file__).resolve().parents[2]
violations = scan_cloud_package(repo_root)
self.assertEqual(violations, [])
class TestSkillProjectFixture(unittest.TestCase):
def test_frozen_project_passes_all_checks(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "apps", "web")
os.makedirs(own)
verdict = check_skill_project(
tmp, "v1", "v1", {"web": "React"}, {"web": "React"},
own, [os.path.join(own, "App.tsx")])
self.assertTrue(verdict["ok"])
def test_drifting_project_fails_each_changed_check(self):
with tempfile.TemporaryDirectory() as tmp:
own = os.path.join(tmp, "apps", "web")
os.makedirs(own)
verdict = check_skill_project(
tmp, "v1", "v2", {"web": "React"}, {"web": "Vue"},
own, [os.path.join(tmp, "apps", "ios", "leak.txt")])
self.assertFalse(verdict["ok"])
self.assertFalse(verdict["contract"]["ok"])
self.assertFalse(verdict["stack"]["ok"])
self.assertFalse(verdict["directory"]["ok"])
if __name__ == "__main__":
unittest.main()