FabledGrimoire/tests/test_verification_guidance_survives.py

"""The write surfaces say WHEN a note earns a check — not just that it can.

WHY THIS EXISTS

`verify_with` is a free-text field on the highest-volume record kind in the
product. A field described only as "how to verify this note" gets filled in on
every note within a week, and at that point the sweep returns the whole corpus
and means nothing. The signal is not "has a check" — it is "has a check AND
almost nothing else does".

So the guidance is not decoration on this feature, it IS the feature's
precondition, and product guidance lives in the tool docstrings and the skill
rather than in a Grimoire rule. That makes it exactly the kind of prose a later
docstring tidy-up deletes without noticing what it was for.

WHAT THIS PINS, AND WHAT IT DOES NOT

Structure, never wording, for `test_create_tools_disambiguate`'s reason: a test
that punishes rewriting is a test that gets deleted. Each write surface must
still (a) draw the norm-vs-constraint distinction in some form, (b) say the
empty case is normal, and (c) name where NOT to reach for it.

It cannot tell whether the guidance is any good — only that the paragraph
explaining when to leave the field alone has not quietly become a parameter
list.
"""
import re

import pytest
from tests.helpers import tool_doc as _doc

# The surfaces that OFFER the field. The read surfaces (the sweep, the stamp)
# explain what a RESULT means, which is a different job — they are deliberately
# not held to this.
_WRITE_SURFACES = [
    ("grimoire.mcp.tools.notes", "create_note"),
    ("grimoire.mcp.tools.notes", "update_note"),
]


@pytest.mark.parametrize("module,name", _WRITE_SURFACES)
def test_the_norm_versus_constraint_distinction_is_stated(module, name):
    """The whole discipline in one line: a decision cannot go stale, a claim
    about someone else's software can. Without it, "how would you check this"
    reads as a chore to complete rather than a question with a usual answer of
    "you wouldn't"."""
    doc = _doc(module, name).lower()
    assert "norm" in doc and "constraint" in doc, (
        f"{name} no longer draws the norm-vs-constraint distinction. Without "
        f"it the field is just a box, and a box gets filled in."
    )


@pytest.mark.parametrize("module,name", _WRITE_SURFACES)
def test_the_empty_case_is_stated_as_normal(module, name):
    """Said POSITIVELY, or an empty field reads as an unfinished record. This
    is the single sentence standing between the sweep and irrelevance."""
    doc = _doc(module, name).lower()
    assert re.search(r"leave (it|both|them|this|these)? ?empty|empty for", doc), (
        f"{name} no longer says that leaving the check empty is the normal "
        f"case. Most notes are decisions; the field's default must read as a "
        f"deliberate state, not a gap."
    )


@pytest.mark.parametrize("module,name", _WRITE_SURFACES)
def test_the_wrong_places_to_reach_for_it_are_named(module, name):
    """A task's decay is its status; a snippet has verify_snippet. The service
    refuses both — this is what should mean nobody ever hits that error."""
    doc = _doc(module, name).lower()
    assert "task" in doc and "snippet" in doc, (
        f"{name} no longer names the records that must NOT carry a check. The "
        f"gate still refuses them, but a refusal the caller could have "
        f"foreseen is a worse door than one that explained itself."
    )


def test_expires_when_is_described_as_a_state_not_a_date():
    """The one field whose obvious reading is wrong. A date invents a staleness
    schedule nobody can justify; a constraint expires when the ground moves,
    which is a condition and not a time."""
    doc = _doc("grimoire.mcp.tools.notes", "create_note")
    assert "STATE" in doc, (
        "create_note no longer says expires_when is a STATE. Left to itself, "
        '"expires" reads as a date, and every check would get an arbitrary one.'
    )


def test_the_skill_carries_the_test_a_writer_can_actually_apply():
    """The docstrings are read by whatever is holding the tool; the skill is
    read while deciding what to write. The one-question form has to be in the
    second place too, or the guidance only reaches callers who already opened
    the tool."""
    from tests.helpers import skill_text

    # Reference files included: the full statement sits in writing-records.md
    # and SKILL.md keeps the pointer.
    text = " ".join(skill_text("using-grimoire").split())
    assert "could this note become false without anyone editing it" in text.lower(), (
        "the using-grimoire skill no longer carries the one-question test. That "
        "question is what makes the distinction applicable rather than merely "
        "true."
    )
    assert "notes_due_for_verification" in text, (
        "the skill names the fields but not the surface that reads them — "
        "guidance for writing a check with no route to acting on one."
    )