portfolio-optimiser/tests/test_doc_constant_sync_loadbearing.py

"""Load-bearing tests for doc↔code constant sync (kø-(h)).

``docs/extending.md`` claimed ``SEMANTIC_WEIGHT_DEFAULT = 0.5`` long after the code had lowered it
to ``0.25``. The drift was found BY ACCIDENT while editing the neighbouring line; nothing in the
suite would ever have caught it. This module is the gate that would have.

**Scope is deliberately narrow (90 %).** Only SCREAMING_CASE module constants cited with their
value inside an inline code span, and only in LIVE documents. Both bounds were MEASURED, not
assumed:

* **SCREAMING_CASE discriminates exactly.** Across every numeric ``name = value`` code span in
  ``docs/`` it selects the 2 real module constants (``SEMANTIC_WEIGHT_DEFAULT``,
  ``MAX_SAVING_FRACTION``) and rejects all 10 keyword arguments and locals (``max_attempts=3``,
  ``concurrency=3``, ``realiseringsgrad=0.79``, …). SCREAMING_CASE *is* the claim "this is a module
  constant"; ordinary prose and kwargs stay editable and never trip the gate.
* **Dated documents are observations, not contract.** A spike finding or a July review records what
  was true when it was measured; rewriting it to track the code would falsify the record. LIVE
  documents describe the framework as it is NOW, which is what a reader acts on.

The gate REFUSES rather than skips, in this repo's fail-closed tradition (``write_concept_file``,
``VerdictFrontmatterError``, ``read_spend``): an unknown constant name is an error, never a silent
pass, because a typo that quietly disables a guard is exactly the masking class this repo hunts.
For the same reason document classification is fail-closed — a new document that is neither listed
LIVE nor recognisably archived goes RED asking to be classified, so coverage cannot quietly rot.

Ambiguity is narrowed to what actually makes a lookup unsafe: a name bound in several modules is
normal Python re-export (``run`` re-exports ``SEMANTIC_WEIGHT_DEFAULT`` from ``semretrieval``), so
only genuinely DIVERGENT values are refused. Measuring this rewrote the rule — a
"same name in two modules" check would have been RED on today's code.
"""

from __future__ import annotations

import importlib
import pkgutil
import re
from pathlib import Path

import pytest

import portfolio_optimiser

REPO_ROOT = Path(__file__).resolve().parents[1]
DOCS_DIR = REPO_ROOT / "docs"

# Documents that describe the framework AS IT IS NOW. Explicit rather than derived: the companion
# classification test below goes RED on any document that is neither listed here nor archived, so
# this list cannot silently fall behind.
_LIVE_DOCS = (
    "README.md",
    "docs/extending.md",
    "docs/ekspert-svar.md",
    "docs/bestille-en-kjoring.md",
    "docs/knowledge-base-recipe.md",
)

# A dated path segment marks a point-in-time record. ``docs/fase1-spikes/`` is the one archive whose
# directory name carries no date — the phase-1 spike findings are dated by their phase, not by
# filename.
_DATED = re.compile(r"\d{4}-\d{2}")
_ARCHIVE_DIRS = ("fase1-spikes",)

# A constant citation: SCREAMING_CASE bound to a numeric literal, inside an inline code span.
_CITATION = re.compile(r"`\s*([A-Z][A-Z0-9_]{2,})\s*=\s*(-?\d+(?:\.\d+)?)\s*`")


def _is_archive(rel_path: str) -> bool:
    """A document is archived when its path carries a date or sits in a known archive directory."""
    return bool(_DATED.search(rel_path)) or any(f"/{d}/" in f"/{rel_path}" for d in _ARCHIVE_DIRS)


def _module_constants() -> dict[str, set[float]]:
    """Map every public numeric SCREAMING_CASE constant in the package to the DISTINCT values it is
    bound to. A name re-exported across modules yields one value and is unambiguous; only divergent
    values make a lookup unsafe."""
    constants: dict[str, set[float]] = {}
    for info in pkgutil.iter_modules(portfolio_optimiser.__path__):
        module = importlib.import_module(f"portfolio_optimiser.{info.name}")
        for name in dir(module):
            if not name.isupper() or name.startswith("_"):
                continue
            value = getattr(module, name)
            if isinstance(value, bool) or not isinstance(value, (int, float)):
                continue
            constants.setdefault(name, set()).add(float(value))
    return constants


def _check_citations(text: str, label: str) -> list[str]:
    """Return one message per citation that does NOT match the code. Unknown and ambiguous names are
    failures, never skips — the whole point is that a citation cannot quietly stop being checked."""
    constants = _module_constants()
    problems: list[str] = []
    for lineno, line in enumerate(text.splitlines(), 1):
        for name, literal in _CITATION.findall(line):
            where = f"{label}:{lineno}"
            values = constants.get(name)
            if values is None:
                problems.append(
                    f"{where}: cites `{name} = {literal}` but no public numeric constant named "
                    f"{name} exists in portfolio_optimiser"
                )
            elif len(values) > 1:
                problems.append(
                    f"{where}: cites `{name}` but it is bound to divergent values "
                    f"{sorted(values)} — the citation cannot be checked safely"
                )
            elif float(literal) != next(iter(values)):
                problems.append(
                    f"{where}: says `{name} = {literal}` but the code says {next(iter(values))}"
                )
    return problems


def _live_doc_paths() -> list[Path]:
    return [REPO_ROOT / rel for rel in _LIVE_DOCS]


@pytest.mark.parametrize("rel_path", _LIVE_DOCS)
def test_live_docs_cite_constants_that_match_the_code(rel_path: str) -> None:
    """THE GATE. Every constant a live document cites with its value must equal what the code
    actually holds. Goes RED on precisely the drift that shipped undetected: ``extending.md``
    saying 0.5 while ``semretrieval.SEMANTIC_WEIGHT_DEFAULT`` is 0.25."""
    path = REPO_ROOT / rel_path
    assert path.is_file(), f"{rel_path} is listed LIVE but does not exist"
    problems = _check_citations(path.read_text(encoding="utf-8"), rel_path)
    assert not problems, "documentation cites constants the code contradicts:\n" + "\n".join(
        problems
    )


def test_a_drifted_citation_is_caught() -> None:
    """The gate must FAIL on drift, not merely pass on a clean tree. Uses the real constant so the
    check is anchored to live code rather than to a fixture's idea of it."""
    real = _module_constants()["SEMANTIC_WEIGHT_DEFAULT"]
    assert len(real) == 1, "test premise: the constant must be unambiguous"
    wrong = next(iter(real)) + 1.0
    problems = _check_citations(f"blends `SEMANTIC_WEIGHT_DEFAULT = {wrong}` today", "synthetic.md")
    assert len(problems) == 1, problems
    assert "but the code says" in problems[0]


def test_an_unknown_constant_name_is_refused_not_skipped() -> None:
    """Fail-closed: a name that resolves to nothing is an error. If unknown names were skipped, a
    typo in a doc — or a constant deleted from the code — would silently retire the check."""
    problems = _check_citations("see `NO_SUCH_CONSTANT_HERE = 7` for details", "synthetic.md")
    assert len(problems) == 1, problems
    assert "no public numeric constant" in problems[0]


def test_prose_and_keyword_arguments_do_not_trip_the_gate() -> None:
    """The measured bound: ordinary prose, kwargs and lowercase locals stay freely editable. A gate
    that made routine documentation edits brittle would be switched off, catching nothing."""
    text = (
        "run with `max_attempts=3` and `concurrency=1`, giving `realiseringsgrad=0.79` "
        "against a p50 of `p50 = 95443.98966314227`"
    )
    assert _check_citations(text, "synthetic.md") == []


def test_every_document_is_classified_live_or_archive() -> None:
    """Fail-closed coverage: a new document must be deliberately classified. Without this, adding a
    live guide would leave it silently unguarded — a hole indistinguishable from a passing gate."""
    live = set(_LIVE_DOCS)
    unclassified = [
        rel
        for path in [REPO_ROOT / "README.md", *sorted(DOCS_DIR.rglob("*.md"))]
        if (rel := path.relative_to(REPO_ROOT).as_posix()) not in live and not _is_archive(rel)
    ]
    assert not unclassified, (
        "these documents are neither listed in _LIVE_DOCS nor recognisable as archive — classify "
        "them (a live guide belongs in _LIVE_DOCS; a point-in-time record needs a dated path):\n"
        + "\n".join(unclassified)
    )


def test_the_gate_actually_reaches_a_real_citation() -> None:
    """Coverage, not vocabulary: a gate that scans only documents containing no citations would be
    green forever. At least one live document must genuinely exercise the comparison."""
    cited = [
        (rel, name)
        for path, rel in ((p, p.relative_to(REPO_ROOT).as_posix()) for p in _live_doc_paths())
        for name, _ in _CITATION.findall(path.read_text(encoding="utf-8"))
    ]
    assert cited, "no live document cites any constant — the gate would pass vacuously"