NexusOS/tests/test_packaging_deps.py

"""Guard the wheel's dependency list against drift.

There are now two dependency declarations: requirements-base.txt (what the
desktop installers pip -r) and pyproject.toml (what the wheel ships). They will
drift. What actually breaks a user is narrower than "they differ", though: it
is an import that no declared distribution provides, so that is what this pins.
"""
from __future__ import annotations

import ast
import sys
import tomllib
from pathlib import Path

import pytest

ROOT = Path(__file__).resolve().parents[1]
SHIPPED_PACKAGES = ("synapse", "nexusos_cli", "modules")

# Import name -> distribution name, where PyPI disagrees with the module.
DISTRIBUTION_OF = {
    "docx": "python-docx",
    "dotenv": "python-dotenv",
    "faster_whisper": "faster-whisper",
    "imap_tools": "imap-tools",
    "sqlite_vec": "sqlite-vec",
    "yaml": "pyyaml",
    "PIL": "pillow",
}

# Provided by another declared distribution rather than named directly.
TRANSITIVE = {"starlette", "socketio", "engineio"}

# Modules that ship inside this repo.
FIRST_PARTY = {"synapse", "nexusos_cli", "modules", "management", "bin", "tests"}


def _pyproject() -> dict:
    return tomllib.loads((ROOT / "pyproject.toml").read_text(encoding="utf-8"))


def _requirement_name(spec: str) -> str:
    """'pypdf>=5,<7' -> 'pypdf'; strips extras and environment markers."""
    head = spec.split(";", 1)[0].strip()
    for sep in ("[", "=", ">", "<", "!", "~", " "):
        head = head.split(sep, 1)[0]
    return head.strip().lower().replace("_", "-")


def _declared() -> set[str]:
    project = _pyproject()["project"]
    specs = list(project.get("dependencies", []))
    for extra in project.get("optional-dependencies", {}).values():
        specs.extend(extra)
    return {_requirement_name(s) for s in specs}


def test_wheel_includes_every_shipped_package():
    wheel = _pyproject()["tool"]["hatch"]["build"]["targets"]["wheel"]
    configured = set(wheel["packages"])
    assert configured == set(SHIPPED_PACKAGES)


def _imported_modules() -> set[str]:
    """Top-level module names imported anywhere in the shipped packages."""
    found: set[str] = set()
    for package in SHIPPED_PACKAGES:
        for path in (ROOT / package).rglob("*.py"):
            tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
            for node in ast.walk(tree):
                if isinstance(node, ast.Import):
                    found.update(alias.name.split(".")[0] for alias in node.names)
                elif isinstance(node, ast.ImportFrom):
                    # level > 0 is a relative (first-party) import.
                    if node.level == 0 and node.module:
                        found.add(node.module.split(".")[0])
    return found


def _third_party() -> set[str]:
    return {
        module for module in _imported_modules()
        if module not in sys.stdlib_module_names
        and module not in FIRST_PARTY
        and module not in TRANSITIVE
        and not module.startswith("_")
    }


def test_every_third_party_import_is_a_declared_dependency():
    declared = _declared()
    missing = sorted(
        module for module in _third_party()
        if DISTRIBUTION_OF.get(module, module).lower().replace("_", "-") not in declared
    )
    assert not missing, (
        "a shipped package imports these, but pyproject.toml declares no "
        f"distribution for them: {missing}. Add them to [project] dependencies "
        "or an extra (and to DISTRIBUTION_OF here if the names differ)."
    )


def test_all_extra_is_the_union_of_the_capability_extras():
    extras = _pyproject()["project"]["optional-dependencies"]
    combined: set[str] = set()
    for name, specs in extras.items():
        if name in ("all", "dev", "standard"):
            continue
        combined.update(_requirement_name(s) for s in specs)
    everything = {_requirement_name(s) for s in extras["all"]}
    assert combined == everything, (
        "the 'all' extra drifted from the capability extras; "
        f"missing={sorted(combined - everything)} extra={sorted(everything - combined)}"
    )


@pytest.mark.parametrize("name", ["fastapi", "uvicorn", "httpx", "pydantic", "pyyaml"])
def test_core_runtime_is_a_hard_dependency_not_an_extra(name):
    """These are imported at module scope, so the base install must carry them."""
    base = {_requirement_name(s) for s in _pyproject()["project"]["dependencies"]}
    assert name in base


def test_optional_imports_are_lazy():
    """Anything only in an extra must not be imported at module scope.

    A base `pip install nexusos-ai` has none of the extras, so a top-level
    `import psutil` in synapse would make the backend unimportable.
    """
    base = {_requirement_name(s) for s in _pyproject()["project"]["dependencies"]}
    offenders: list[str] = []
    for package in SHIPPED_PACKAGES:
        for path in (ROOT / package).rglob("*.py"):
            tree = ast.parse(path.read_text(encoding="utf-8"), filename=str(path))
            for node in tree.body:          # module scope only
                names: list[str] = []
                if isinstance(node, ast.Import):
                    names = [a.name.split(".")[0] for a in node.names]
                elif isinstance(node, ast.ImportFrom) and node.level == 0 and node.module:
                    names = [node.module.split(".")[0]]
                for module in names:
                    if module in sys.stdlib_module_names or module in FIRST_PARTY:
                        continue
                    dist = DISTRIBUTION_OF.get(module, module).lower().replace("_", "-")
                    if dist not in base and module not in TRANSITIVE:
                        offenders.append(f"{path.relative_to(ROOT)}: {module}")
    assert not offenders, (
        "optional dependencies imported at module scope (wrap in try/ImportError "
        f"or import inside the function): {offenders}"
    )