1c3f2dfc04
CI / benchmark-publish (pull_request) Has been skipped
CI / helm (pull_request) Successful in 23s
CI / lint (pull_request) Successful in 3m18s
CI / build (pull_request) Successful in 3m18s
CI / quality (pull_request) Successful in 3m42s
CI / typecheck (pull_request) Successful in 3m55s
CI / security (pull_request) Successful in 4m6s
CI / unit_tests (pull_request) Failing after 6m41s
CI / docker (pull_request) Has been skipped
CI / e2e_tests (pull_request) Failing after 16m3s
CI / coverage (pull_request) Successful in 13m35s
CI / integration_tests (pull_request) Failing after 22m1s
CI / status-check (pull_request) Failing after 1s
CI / benchmark-regression (pull_request) Successful in 56m9s
Both slow_integration_tests and e2e_tests sessions require a database (via setup_workspace() in helper scripts) but were not using the pre-migrated template DB optimization already present in unit_tests, integration_tests, and coverage_report. Changes: - slow_integration_tests: add _create_template_db() call, set CLEVERAGENTS_TEMPLATE_DB env var, upgrade from robot to pabot for parallel execution, add NO_COLOR/PYTHONPATH/PATH/compileall setup, add --include slow / --exclude discovery/code_blocks/wip/E2E/tdd_fixture tag filters, and update docstring. - e2e_tests: add _create_template_db() call and set CLEVERAGENTS_TEMPLATE_DB env var. The existing setup_workspace() in helper_e2e_common.py already checks this env var and copies the template instead of running 25+ Alembic migrations. No changes to test helper files are required since setup_workspace() already implements the fast-path copy logic when CLEVERAGENTS_TEMPLATE_DB is set. ISSUES CLOSED: #2334
856 lines
28 KiB
Python
856 lines
28 KiB
Python
import json
|
|
import os
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import nox
|
|
|
|
# Global configuration
|
|
DEFAULT_PYTHON = "3.13"
|
|
SUPPORTED_PYTHONS = ["3.13"]
|
|
nox.options.reuse_existing_virtualenvs = True
|
|
nox.options.error_on_external_run = True
|
|
|
|
BEHAVE_PARALLEL_VERSION = "2.0.0"
|
|
|
|
|
|
def _default_processes() -> int:
|
|
env_override = os.environ.get("TEST_PROCESSES")
|
|
if env_override:
|
|
return int(env_override)
|
|
try:
|
|
cpus = len(os.sched_getaffinity(0)) or 1
|
|
except AttributeError:
|
|
cpus = os.cpu_count() or 1
|
|
# Keep default parallelism conservative to avoid timeout/OOM flakes
|
|
# under heavy Robot/pabot subprocess fan-out in CI and shared runners.
|
|
# Callers can still override with TEST_PROCESSES / --processes.
|
|
return min(cpus, 2)
|
|
|
|
|
|
def _behave_parallel_args(posargs: list[str]) -> list[str]:
|
|
has_custom_processes = any(
|
|
arg in {"--processes", "-j"} or arg.startswith(("--processes=", "-j"))
|
|
for arg in posargs
|
|
)
|
|
if has_custom_processes:
|
|
return []
|
|
return ["--processes", str(_default_processes())]
|
|
|
|
|
|
def _pabot_parallel_args(posargs: list[str]) -> list[str]:
|
|
has_custom_processes = any(
|
|
arg in {"--processes"} or arg.startswith("--processes=") for arg in posargs
|
|
)
|
|
if has_custom_processes:
|
|
return []
|
|
return ["--processes", str(_default_processes())]
|
|
|
|
|
|
def _split_pabot_args(posargs: list[str]) -> tuple[list[str], list[str]]:
|
|
pabot_args: list[str] = []
|
|
robot_args: list[str] = []
|
|
i = 0
|
|
while i < len(posargs):
|
|
arg = posargs[i]
|
|
if arg == "--processes" and i + 1 < len(posargs):
|
|
pabot_args.extend([arg, posargs[i + 1]])
|
|
i += 2
|
|
continue
|
|
if arg.startswith("--processes="):
|
|
pabot_args.append(arg)
|
|
i += 1
|
|
continue
|
|
robot_args.append(arg)
|
|
i += 1
|
|
return pabot_args, robot_args
|
|
|
|
|
|
def _create_template_db(session: nox.Session) -> str:
|
|
"""Build the pre-migrated SQLite template and return its path.
|
|
|
|
Runs ``scripts/create_template_db.py`` to produce a SQLite file with all
|
|
tables already created via ``Base.metadata.create_all()`` and the
|
|
alembic_version table stamped at HEAD. Each test scenario can then
|
|
``shutil.copy`` this file instead of running 25 Alembic migrations.
|
|
"""
|
|
template_path = str(Path("build/.template-migrated.db").resolve())
|
|
session.run(
|
|
"python",
|
|
"scripts/create_template_db.py",
|
|
template_path,
|
|
silent=True,
|
|
)
|
|
return template_path
|
|
|
|
|
|
def _install_behave_parallel(session: nox.Session) -> None:
|
|
"""Install behave-parallel with an in-process parallel runner.
|
|
|
|
Instead of spawning one subprocess per feature file (the old model),
|
|
the new CLI runs features in-process via behave's Python API. Step
|
|
definitions and environment hooks are loaded once; each feature file
|
|
is then parsed and executed without interpreter startup overhead.
|
|
|
|
Parallel execution uses ``multiprocessing.Pool`` with the ``fork``
|
|
start method so that already-imported modules are shared (copy-on-write)
|
|
across workers.
|
|
|
|
The runner script is read from ``scripts/run_behave_parallel.py`` so
|
|
that the noxfile stays concise and the script can be linted and typed
|
|
independently.
|
|
"""
|
|
tmp_dir = Path(session.create_tmp())
|
|
source_dir = tmp_dir / "behave-parallel-inprocess"
|
|
source_dir.mkdir(parents=True, exist_ok=True)
|
|
|
|
pkg_dir = source_dir / "behave_parallel"
|
|
pkg_dir.mkdir(parents=True, exist_ok=True)
|
|
(pkg_dir / "__init__.py").write_text("\n")
|
|
|
|
runner_script = Path(__file__).parent / "scripts" / "run_behave_parallel.py"
|
|
(pkg_dir / "cli.py").write_text(runner_script.read_text(encoding="utf-8"))
|
|
|
|
setup_path = source_dir / "setup.py"
|
|
setup_path.write_text(
|
|
"from setuptools import find_packages, setup\n"
|
|
"setup(\n"
|
|
' name="behave-parallel",\n'
|
|
f' version="{BEHAVE_PARALLEL_VERSION}",\n'
|
|
" packages=find_packages(),\n"
|
|
' install_requires=["behave>=1.2.6"],\n'
|
|
" entry_points={\n"
|
|
' "console_scripts": '
|
|
'["behave-parallel=behave_parallel.cli:main"],\n'
|
|
" },\n"
|
|
")\n"
|
|
)
|
|
|
|
session.install("setuptools", "wheel")
|
|
session.install(str(source_dir))
|
|
|
|
|
|
# =============================================================================
|
|
|
|
|
|
# QUICK DEVELOPMENT SESSIONS (Fast - Run daily)
|
|
# =============================================================================
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def lint(session: nox.Session):
|
|
"""Check code formatting and linting."""
|
|
session.install("ruff>=0.15,<0.16")
|
|
session.run("ruff", "check", "src/", "scripts/", "examples/", "features/", "robot/")
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def format(session: nox.Session):
|
|
"""Format code with ruff. Pass --check to verify without modifying."""
|
|
session.install("ruff>=0.15,<0.16")
|
|
session.run("ruff", "format", *session.posargs, ".")
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def typecheck(session: nox.Session):
|
|
"""Check types with pyright."""
|
|
session.install("pyright")
|
|
session.install("-e", ".")
|
|
session.run("pyright", stderr=sys.stdout)
|
|
|
|
|
|
@nox.session(python=SUPPORTED_PYTHONS, reuse_venv=True, venv_backend="uv")
|
|
def unit_tests(session: nox.Session):
|
|
"""Run BDD tests with Behave."""
|
|
session.install("-e", ".[tests]")
|
|
_install_behave_parallel(session)
|
|
|
|
# Build a pre-migrated template DB so each scenario can copy it
|
|
# instead of running 25 Alembic migrations from scratch.
|
|
template_path = _create_template_db(session)
|
|
session.env["CLEVERAGENTS_TEMPLATE_DB"] = template_path
|
|
|
|
behave_cmd = session.bin + "/behave-parallel"
|
|
parallel_args = _behave_parallel_args(session.posargs)
|
|
|
|
# If a specific feature file is passed, run only that file
|
|
if session.posargs and session.posargs[0].endswith(".feature"):
|
|
args = [
|
|
behave_cmd,
|
|
"-q",
|
|
*parallel_args,
|
|
*session.posargs,
|
|
]
|
|
else:
|
|
args = [
|
|
behave_cmd,
|
|
"-q",
|
|
*parallel_args,
|
|
"features/",
|
|
*session.posargs,
|
|
]
|
|
|
|
session.env["PYTHONPATH"] = str(Path("src").resolve())
|
|
# Prevent Rich from injecting ANSI escape codes into machine-readable
|
|
# CLI output (JSON/YAML) which causes json.loads() failures on CI.
|
|
session.env["NO_COLOR"] = "1"
|
|
session.run(*args)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def docs(session: nox.Session):
|
|
"""Build documentation with MkDocs."""
|
|
session.install("-e", ".[docs]")
|
|
# Suppress DeprecationWarning from the third-party `rx` package which calls
|
|
# datetime.datetime.utcfromtimestamp() (deprecated since Python 3.12).
|
|
session.env["PYTHONWARNINGS"] = "ignore::DeprecationWarning:rx"
|
|
session.run("mkdocs", "build")
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def serve_docs(session: nox.Session):
|
|
"""Serve docs locally for development."""
|
|
session.install("-e", ".[docs]")
|
|
# Suppress DeprecationWarning from the third-party `rx` package which calls
|
|
# datetime.datetime.utcfromtimestamp() (deprecated since Python 3.12).
|
|
session.env["PYTHONWARNINGS"] = "ignore::DeprecationWarning:rx"
|
|
session.run("mkdocs", "serve", "--dev-addr", "0.0.0.0:8000")
|
|
|
|
|
|
@nox.session(python=SUPPORTED_PYTHONS, reuse_venv=True, venv_backend="uv")
|
|
def build(session: nox.Session):
|
|
"""Build the wheel distribution."""
|
|
session.install("build", "pip")
|
|
session.run("python", "-m", "build", "--wheel")
|
|
|
|
|
|
@nox.session(python=SUPPORTED_PYTHONS, reuse_venv=True, venv_backend="uv")
|
|
def integration_tests(session: nox.Session):
|
|
"""Run Robot Framework integration tests (parallel via pabot).
|
|
|
|
Defaults to conservative parallelism (<=2 processes) to avoid
|
|
resource pressure in CI. Override via PABOT_PROCESSES or by passing
|
|
--processes/--processes=N in session arguments.
|
|
"""
|
|
session.install("-e", ".[tests]")
|
|
session.env["CLEVERAGENTS_AUTO_APPLY_MIGRATIONS"] = "true"
|
|
session.env["NO_COLOR"] = "1"
|
|
# Override PYTHONPATH so the editable install (src/) for this project
|
|
# is used instead of any inherited PYTHONPATH from the outer environment.
|
|
session.env["PYTHONPATH"] = "src"
|
|
|
|
# Propagate venv bin to PATH so Run Process in robot files finds
|
|
# the venv's python/robot rather than the system copies.
|
|
venv_bin = os.path.join(session.virtualenv.location, "bin")
|
|
session.env["PATH"] = venv_bin + os.pathsep + os.environ.get("PATH", "")
|
|
|
|
# Ensure output directory exists (CI starts with a clean checkout)
|
|
os.makedirs("build/reports/robot", exist_ok=True)
|
|
|
|
# Pass the venv Python path explicitly so Run Process calls use it
|
|
# instead of relying on PATH (which may not propagate to subprocesses).
|
|
venv_python = os.path.join(venv_bin, "python")
|
|
|
|
# Pre-compile bytecode so that parallel pabot workers (and the
|
|
# Python sub-processes they spawn via ``Run Python Script``) can
|
|
# read cached .pyc files instead of each cold-compiling every
|
|
# module from source simultaneously — avoids a thundering-herd
|
|
# race on CI runners with high core counts.
|
|
session.run("python", "-m", "compileall", "-q", "src/")
|
|
|
|
# Build a pre-migrated template DB so helper scripts that call
|
|
# setup_workspace() can copy it instead of running 25+ Alembic
|
|
# migrations per test — critical for parallel pabot execution.
|
|
template_path = _create_template_db(session)
|
|
session.env["CLEVERAGENTS_TEMPLATE_DB"] = template_path
|
|
|
|
pabot_args, robot_args = _split_pabot_args(session.posargs)
|
|
parallel_args = _pabot_parallel_args(pabot_args)
|
|
|
|
# TDD expected-fail listener — inverts results for @tdd_expected_fail
|
|
# tagged tests and validates TDD tag combinations.
|
|
# See CONTRIBUTING.md > TDD Issue Test Tags.
|
|
# Resolved relative to this file (not CWD) so ``nox`` invocations from
|
|
# a non-root directory still find the listener module.
|
|
tdd_listener = str(
|
|
Path(__file__).parent / "robot" / "tdd_expected_fail_listener.py"
|
|
)
|
|
|
|
session.run(
|
|
"pabot",
|
|
*parallel_args,
|
|
*pabot_args,
|
|
"--outputdir",
|
|
"build/reports/robot",
|
|
"--loglevel",
|
|
"INFO",
|
|
"--report",
|
|
"report.html",
|
|
"--log",
|
|
"log.html",
|
|
"--xunit",
|
|
"xunit.xml",
|
|
"--variable",
|
|
f"PYTHON:{venv_python}",
|
|
"--listener",
|
|
tdd_listener,
|
|
"--exclude",
|
|
"slow",
|
|
"--exclude",
|
|
"discovery",
|
|
"--exclude",
|
|
"code_blocks",
|
|
"--exclude",
|
|
"wip",
|
|
"--exclude",
|
|
"E2E",
|
|
"--exclude",
|
|
"tdd_fixture",
|
|
*robot_args,
|
|
"robot/",
|
|
)
|
|
|
|
|
|
@nox.session(python=SUPPORTED_PYTHONS, reuse_venv=True, venv_backend="uv")
|
|
def slow_integration_tests(session: nox.Session):
|
|
"""Run Robot Framework slow integration tests (parallel via pabot).
|
|
|
|
Runs all tests tagged ``slow`` that are excluded from the standard
|
|
``integration_tests`` session. Defaults to conservative parallelism
|
|
(<=2 processes) to avoid resource pressure in CI. Override via
|
|
TEST_PROCESSES or by passing --processes/--processes=N in session
|
|
arguments.
|
|
"""
|
|
session.install("-e", ".[tests]")
|
|
session.env["CLEVERAGENTS_AUTO_APPLY_MIGRATIONS"] = "true"
|
|
session.env["NO_COLOR"] = "1"
|
|
# Override PYTHONPATH so the editable install (src/) for this project
|
|
# is used instead of any inherited PYTHONPATH from the outer environment.
|
|
session.env["PYTHONPATH"] = "src"
|
|
|
|
# Propagate venv bin to PATH so Run Process in robot files finds
|
|
# the venv's python/robot rather than the system copies.
|
|
venv_bin = os.path.join(session.virtualenv.location, "bin")
|
|
session.env["PATH"] = venv_bin + os.pathsep + os.environ.get("PATH", "")
|
|
|
|
# Ensure output directory exists (CI starts with a clean checkout)
|
|
os.makedirs("build/reports/robot", exist_ok=True)
|
|
|
|
# Pass the venv Python path explicitly so Run Process calls use it
|
|
# instead of relying on PATH (which may not propagate to subprocesses).
|
|
venv_python = os.path.join(venv_bin, "python")
|
|
|
|
# Pre-compile bytecode so that parallel pabot workers (and the
|
|
# Python sub-processes they spawn via ``Run Python Script``) can
|
|
# read cached .pyc files instead of each cold-compiling every
|
|
# module from source simultaneously — avoids a thundering-herd
|
|
# race on CI runners with high core counts.
|
|
session.run("python", "-m", "compileall", "-q", "src/")
|
|
|
|
# Build a pre-migrated template DB so helper scripts that call
|
|
# setup_workspace() can copy it instead of running 25+ Alembic
|
|
# migrations per test — critical for parallel pabot execution.
|
|
template_path = _create_template_db(session)
|
|
session.env["CLEVERAGENTS_TEMPLATE_DB"] = template_path
|
|
|
|
pabot_args, robot_args = _split_pabot_args(session.posargs)
|
|
parallel_args = _pabot_parallel_args(pabot_args)
|
|
|
|
# TDD expected-fail listener — inverts results for @tdd_expected_fail
|
|
# tagged tests and validates TDD tag combinations.
|
|
# See CONTRIBUTING.md > TDD Issue Test Tags.
|
|
# Resolved relative to this file (not CWD) so ``nox`` invocations from
|
|
# a non-root directory still find the listener module.
|
|
tdd_listener = str(
|
|
Path(__file__).parent / "robot" / "tdd_expected_fail_listener.py"
|
|
)
|
|
|
|
session.run(
|
|
"pabot",
|
|
*parallel_args,
|
|
*pabot_args,
|
|
"--outputdir",
|
|
"build/reports/robot",
|
|
"--loglevel",
|
|
"INFO",
|
|
"--report",
|
|
"report.html",
|
|
"--log",
|
|
"log.html",
|
|
"--xunit",
|
|
"xunit.xml",
|
|
"--variable",
|
|
f"PYTHON:{venv_python}",
|
|
"--listener",
|
|
tdd_listener,
|
|
"--include",
|
|
"slow",
|
|
"--exclude",
|
|
"discovery",
|
|
"--exclude",
|
|
"code_blocks",
|
|
"--exclude",
|
|
"wip",
|
|
"--exclude",
|
|
"E2E",
|
|
"--exclude",
|
|
"tdd_fixture",
|
|
*robot_args,
|
|
"robot/",
|
|
)
|
|
|
|
|
|
@nox.session(python=SUPPORTED_PYTHONS, reuse_venv=True, venv_backend="uv")
|
|
def e2e_tests(session: nox.Session):
|
|
"""Run end-to-end Robot Framework tests with real LLM API keys.
|
|
|
|
E2E tests use zero mocking — they exercise the real CleverAgents CLI
|
|
against real LLM API keys (Anthropic/OpenAI). Tests are tagged with
|
|
``E2E`` and live in the ``robot/e2e/`` directory.
|
|
|
|
This session is NOT included in the default ``nox`` run because it
|
|
requires real API keys. Run explicitly via ``nox -s e2e_tests``.
|
|
|
|
Tests that require LLM API keys will skip gracefully when the keys
|
|
are not present in the environment.
|
|
"""
|
|
session.install("-e", ".[tests]")
|
|
session.env["CLEVERAGENTS_AUTO_APPLY_MIGRATIONS"] = "true"
|
|
session.env["NO_COLOR"] = "1"
|
|
session.env["PYTHONPATH"] = "src"
|
|
|
|
# Propagate venv bin to PATH so Run Process in robot files finds
|
|
# the venv's python/robot rather than the system copies.
|
|
venv_bin = os.path.join(session.virtualenv.location, "bin")
|
|
session.env["PATH"] = venv_bin + os.pathsep + os.environ.get("PATH", "")
|
|
venv_python = os.path.join(venv_bin, "python")
|
|
|
|
# Ensure output directory exists
|
|
os.makedirs("build/reports/robot-e2e", exist_ok=True)
|
|
|
|
# Pre-compile bytecode to avoid cold-compilation overhead.
|
|
session.run("python", "-m", "compileall", "-q", "src/")
|
|
|
|
# Build a pre-migrated template DB so helper scripts that call
|
|
# setup_workspace() can copy it instead of running 25+ Alembic
|
|
# migrations per test — reduces per-test setup from ~1-3 s to ~1 ms.
|
|
template_path = _create_template_db(session)
|
|
session.env["CLEVERAGENTS_TEMPLATE_DB"] = template_path
|
|
|
|
# Propagate LLM API keys from the environment into the session
|
|
# so that real E2E tests can authenticate with providers.
|
|
for key in (
|
|
"ANTHROPIC_API_KEY",
|
|
"OPENAI_API_KEY",
|
|
"GOOGLE_API_KEY",
|
|
"GEMINI_API_KEY",
|
|
):
|
|
value = os.environ.get(key)
|
|
if value:
|
|
session.env[key] = value
|
|
|
|
session.run(
|
|
"robot",
|
|
"--outputdir",
|
|
"build/reports/robot-e2e",
|
|
"--loglevel",
|
|
"INFO",
|
|
"--report",
|
|
"report.html",
|
|
"--log",
|
|
"log.html",
|
|
"--xunit",
|
|
"xunit.xml",
|
|
"--variable",
|
|
f"PYTHON:{venv_python}",
|
|
"--include",
|
|
"E2E",
|
|
"--listener",
|
|
str(Path(__file__).parent / "robot" / "tdd_expected_fail_listener.py"),
|
|
*session.posargs,
|
|
"robot/e2e/",
|
|
)
|
|
|
|
|
|
COVERAGE_THRESHOLD = 97
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def coverage_report(session: nox.Session):
|
|
"""Generate coverage report from Behave tests.
|
|
|
|
Runs all behave features in a single process under slipcover.
|
|
The in-process behave-parallel runner avoids subprocess overhead,
|
|
so a single slipcover invocation collects coverage for the entire
|
|
suite -- no per-worker files or merge step required.
|
|
|
|
Coverage threshold is enforced at >=97%.
|
|
|
|
On success, emits: COVERAGE OK: <pct>% (threshold: 97%)
|
|
On failure, emits: COVERAGE FAILED: <pct>% < 97% threshold
|
|
Both are single-line, CI-parseable summary strings.
|
|
"""
|
|
session.install("-e", ".[tests]")
|
|
_install_behave_parallel(session)
|
|
|
|
os.makedirs("build", exist_ok=True)
|
|
|
|
# Build a pre-migrated template DB so each scenario can copy it
|
|
# instead of running 25 Alembic migrations from scratch.
|
|
template_path = _create_template_db(session)
|
|
session.env["CLEVERAGENTS_TEMPLATE_DB"] = template_path
|
|
|
|
session.env["PYTHONPATH"] = str(Path("src").resolve())
|
|
session.env["NO_COLOR"] = "1"
|
|
source_paths = "src"
|
|
omit_patterns = ",".join(
|
|
[
|
|
"*/tests/*",
|
|
"*/test_*",
|
|
"features/*",
|
|
"*/features/*",
|
|
"*/__pycache__/*",
|
|
"*/site-packages/*",
|
|
"*/dependency_injector/*",
|
|
"*/venv/*",
|
|
"*/.venv/*",
|
|
"*/.nox/*",
|
|
"src/cleveragents/discovery/*",
|
|
]
|
|
)
|
|
|
|
# Force sequential mode so slipcover wraps the entire process.
|
|
session.env["BEHAVE_PARALLEL_COVERAGE"] = "1"
|
|
|
|
# Clean up any existing slipcover data
|
|
for path in Path("build").glob(".slipcover.*.json"):
|
|
path.unlink()
|
|
|
|
# Build behave-parallel args (sequential for coverage).
|
|
behave_cmd = session.bin + "/behave-parallel"
|
|
if session.posargs and session.posargs[0].endswith(".feature"):
|
|
behave_args = [
|
|
behave_cmd,
|
|
"-q",
|
|
"--tags=-discovery",
|
|
"--no-capture",
|
|
*session.posargs,
|
|
]
|
|
else:
|
|
behave_args = [
|
|
behave_cmd,
|
|
"-q",
|
|
"--tags=-discovery",
|
|
"--no-capture",
|
|
"features/",
|
|
*session.posargs,
|
|
]
|
|
|
|
# Wrap the entire behave-parallel run under slipcover.
|
|
# A single process produces a single JSON output file directly.
|
|
# Allow exit code 1 (test failures) — coverage data is still produced.
|
|
session.run(
|
|
"python",
|
|
"-m",
|
|
"slipcover",
|
|
"--json",
|
|
"--out",
|
|
"build/coverage.json",
|
|
"--source",
|
|
source_paths,
|
|
"--omit",
|
|
omit_patterns,
|
|
"--",
|
|
*behave_args,
|
|
success_codes=[0, 1],
|
|
)
|
|
|
|
# Generate XML report for CI
|
|
session.run(
|
|
"python",
|
|
"-m",
|
|
"slipcover",
|
|
"--merge",
|
|
"build/coverage.json",
|
|
"--xml",
|
|
"--out",
|
|
"build/coverage.xml",
|
|
)
|
|
|
|
# Generate terminal report and check threshold.
|
|
# slipcover exits with code 2 if below threshold; nox intercepts the exit.
|
|
report_path = "build/coverage-report.txt"
|
|
session.run(
|
|
"python",
|
|
"-m",
|
|
"slipcover",
|
|
"--merge",
|
|
"build/coverage.json",
|
|
"--out",
|
|
report_path,
|
|
"--source",
|
|
source_paths,
|
|
"--omit",
|
|
omit_patterns,
|
|
f"--fail-under={COVERAGE_THRESHOLD}",
|
|
success_codes=[0, 2],
|
|
silent=False,
|
|
)
|
|
|
|
try:
|
|
with open(report_path) as report_file:
|
|
print(report_file.read(), end="")
|
|
except FileNotFoundError:
|
|
session.log(f"Slipcover report not found at {report_path}")
|
|
|
|
# Parse the total percentage from the slipcover JSON report for the summary
|
|
total_pct: float = 0.0
|
|
try:
|
|
with open("build/coverage.json") as f:
|
|
payload = json.load(f)
|
|
|
|
summary = payload.get("summary") or payload.get("totals") or {}
|
|
percent_value = None
|
|
for key in (
|
|
"percent_covered",
|
|
"percent_covered_display",
|
|
"line_coverage_percent",
|
|
):
|
|
percent_value = summary.get(key)
|
|
if percent_value is not None:
|
|
break
|
|
|
|
if percent_value is None:
|
|
covered = (
|
|
summary.get("lines_covered")
|
|
or summary.get("covered_lines")
|
|
or summary.get("covered")
|
|
)
|
|
total = (
|
|
summary.get("lines")
|
|
or summary.get("total_lines")
|
|
or summary.get("num_lines")
|
|
or summary.get("total")
|
|
)
|
|
if covered is not None and total:
|
|
percent_value = (float(covered) / float(total)) * 100.0
|
|
|
|
if isinstance(percent_value, str):
|
|
percent_value = percent_value.strip().rstrip("%")
|
|
|
|
if percent_value is not None:
|
|
total_pct = float(percent_value)
|
|
except (FileNotFoundError, KeyError, TypeError, ValueError, json.JSONDecodeError):
|
|
total_pct = 0.0
|
|
|
|
rounded_pct = round(total_pct, 1)
|
|
|
|
if rounded_pct >= COVERAGE_THRESHOLD:
|
|
session.log(f"COVERAGE OK: {rounded_pct}% (threshold: {COVERAGE_THRESHOLD}%)")
|
|
else:
|
|
session.error(
|
|
f"COVERAGE FAILED: {rounded_pct}% < {COVERAGE_THRESHOLD}% threshold"
|
|
)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def pre_commit(session: nox.Session):
|
|
"""Run all pre-commit hooks on all files."""
|
|
session.install("-e", ".[dev]")
|
|
session.run("pre-commit", "run", "--all-files", *session.posargs)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def security_scan(session: nox.Session):
|
|
"""Run security checks matching Forgejo CI: bandit + semgrep + vulture.
|
|
|
|
Steps:
|
|
1. Bandit medium-severity report (non-blocking JSON export to build/)
|
|
2. Bandit high-severity gate (blocks on findings)
|
|
3. Semgrep custom rules from .semgrep.yml (blocks on ERROR-level findings)
|
|
4. Vulture dead-code detection (blocks on confidence >=80%)
|
|
|
|
Severity gates:
|
|
- Bandit HIGH: hard fail (blocks merge)
|
|
- Bandit MEDIUM: report-only (review, do not block)
|
|
- Semgrep ERROR: hard fail (eval/exec/os.system detection)
|
|
- Semgrep WARNING: report-only (pickle.loads)
|
|
- Vulture >=80% confidence: hard fail
|
|
"""
|
|
session.install("-e", ".[dev]")
|
|
# Python 3.13 no longer bundles pkg_resources. Semgrep transitively imports
|
|
# it via opentelemetry instrumentation, so pin setuptools to a version that
|
|
# still provides pkg_resources.
|
|
session.install("setuptools<81")
|
|
|
|
# Ensure output directory exists (CI starts with a clean checkout)
|
|
os.makedirs("build", exist_ok=True)
|
|
|
|
# Step 1: Bandit - medium-severity report (non-blocking, mirrors CI JSON export)
|
|
session.run(
|
|
"bandit",
|
|
"-c",
|
|
"pyproject.toml",
|
|
"-r",
|
|
"src/cleveragents",
|
|
"--severity-level",
|
|
"medium",
|
|
"--format",
|
|
"json",
|
|
"--output",
|
|
"build/bandit-report.json",
|
|
success_codes=[0, 1],
|
|
)
|
|
|
|
# Step 2: Bandit - high-severity gate (blocks on findings)
|
|
session.run(
|
|
"bandit",
|
|
"-c",
|
|
"pyproject.toml",
|
|
"-r",
|
|
"src/cleveragents",
|
|
"--severity-level",
|
|
"high",
|
|
)
|
|
|
|
# Step 3: Semgrep custom rules (blocks on ERROR-severity matches)
|
|
semgrep_config = Path(".semgrep.yml")
|
|
if semgrep_config.exists():
|
|
session.run(
|
|
"semgrep",
|
|
"--config=.semgrep.yml",
|
|
"--error",
|
|
"--quiet",
|
|
"src/",
|
|
success_codes=[0, 1],
|
|
)
|
|
else:
|
|
session.warn("No .semgrep.yml found, skipping semgrep scan")
|
|
|
|
# Step 4: Vulture dead-code detection
|
|
session.run(
|
|
"vulture",
|
|
"src/cleveragents",
|
|
"vulture_whitelist.py",
|
|
"--min-confidence",
|
|
"80",
|
|
"--exclude",
|
|
"src/cleveragents/discovery",
|
|
)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def dead_code(session: nox.Session):
|
|
"""Run vulture to detect dead code."""
|
|
session.install("-e", ".[dev]")
|
|
session.run(
|
|
"vulture",
|
|
"src/cleveragents",
|
|
"vulture_whitelist.py",
|
|
"--min-confidence",
|
|
"80",
|
|
"--exclude",
|
|
"src/cleveragents/discovery",
|
|
)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def complexity(session: nox.Session):
|
|
"""Check code complexity using radon."""
|
|
session.install("-e", ".[dev]")
|
|
session.run(
|
|
"radon",
|
|
"cc",
|
|
"src/cleveragents",
|
|
"--min",
|
|
"C",
|
|
"--show-complexity",
|
|
"--total-average",
|
|
)
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def adr_compliance(session: nox.Session):
|
|
"""Check code compliance with Architecture Decision Records."""
|
|
session.install("-e", ".[dev]")
|
|
session.run("python", "scripts/check-adr-compliance.py")
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def benchmark(session: nox.Session):
|
|
"""Run Airspeed Velocity benchmarks and publish results."""
|
|
session.install("-e", ".[tests]")
|
|
config_path = "asv.conf.json"
|
|
session.run(
|
|
"asv",
|
|
"machine",
|
|
"--machine=forgejo-runner",
|
|
"--os=Linux_6.x",
|
|
"--arch=x86_64",
|
|
"--num_cpu=32",
|
|
"--ram=32GB",
|
|
"--cpu=AMD",
|
|
f"--config={config_path}",
|
|
)
|
|
session.run(
|
|
"asv",
|
|
"run",
|
|
"--machine=forgejo-runner",
|
|
"--append-samples",
|
|
"--launch-method=spawn",
|
|
"--show-stderr",
|
|
"--verbose",
|
|
f"--config={config_path}",
|
|
success_codes=[0, 2],
|
|
)
|
|
session.run("asv", "publish", f"--config={config_path}")
|
|
|
|
|
|
@nox.session(python=DEFAULT_PYTHON, reuse_venv=True, venv_backend="uv")
|
|
def benchmark_regression(session: nox.Session):
|
|
"""Run Airspeed Velocity benchmarks regression test."""
|
|
session.install("-e", ".[tests]")
|
|
config_path = "asv.conf.json"
|
|
asv_base_sha = os.environ.get("ASV_BASE_SHA", "master")
|
|
session.run(
|
|
"asv",
|
|
"machine",
|
|
"--machine=forgejo-runner",
|
|
"--os=Linux_6.x",
|
|
"--arch=x86_64",
|
|
"--num_cpu=32",
|
|
"--ram=32GB",
|
|
"--cpu=AMD",
|
|
f"--config={config_path}",
|
|
)
|
|
session.run(
|
|
"asv",
|
|
"continuous",
|
|
"--machine=forgejo-runner",
|
|
"--append-samples",
|
|
"--show-stderr",
|
|
"--verbose",
|
|
"--factor=1.50",
|
|
f"--config={config_path}",
|
|
asv_base_sha,
|
|
"HEAD",
|
|
success_codes=[0, 2],
|
|
)
|
|
session.run("asv", "publish", f"--config={config_path}")
|
|
|
|
|
|
# Sessions to run by default when running `nox` without arguments
|
|
nox.options.sessions = [
|
|
"lint", # ~5-10 seconds
|
|
"format", # ~5-10 seconds (auto-fixes issues)
|
|
"typecheck", # ~10-20 seconds
|
|
"security_scan", # bandit + vulture (mirrors Forgejo CI security job)
|
|
"dead_code", # vulture dead-code detection
|
|
"unit_tests", # ~30-60 seconds (without ML deps)
|
|
"integration_tests",
|
|
"docs", # ~10-30 seconds
|
|
"build", # ~5-10 seconds
|
|
"benchmark", # ASV benchmarks for performance tracking
|
|
"coverage_report", # ~30-60 seconds (without ML deps)
|
|
]
|