bvandeusen
1d65e98ac2
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 10s
CI & Build / TypeScript typecheck (push) Successful in 33s
CI & Build / integration (push) Successful in 43s
CI & Build / Python tests (push) Successful in 1m16s
CI & Build / Build & push image (push) Successful in 28s
The step that decides whether steps 1-4 were worth building. `verify_with` is a free-text field on the highest-volume record kind in the product; described only as "how to verify this note" it 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". Rule 119 puts this in the app's own instruction surfaces, never in a Scribe rule. So: - the using-scribe skill gains the reflex, next to "state updates in place; chronicles don't" — its other half, since supersession only fires once somebody has read a note and disagreed, which is the case where it was already believed; - update_note's docstring now states the DEFAULT rather than only deferring to create_note for the test. Found by the new guard on its first run; - plugin 0.1.48. THE _INSTRUCTIONS BUDGET, decided rather than skipped. The payload is ~1980 of the client's ~2048-char cap, so everything in it competes for the last ~68 characters. The operator declined a line for this milestone: the map's own closing sentence says each tool's description carries the full contract, and the sweep is a curation act rather than a session-start reflex like enter_project or list_always_on_rules. That reasoning is now a comment beside the constant, with the accepted cost named — an agent that never opens create_note's docstring never learns the field exists — so the question is not re-litigated blind. The guard pins STRUCTURE, never wording, for the disambiguator's reason (a test that punishes rewriting is a test that gets deleted): each write surface must still draw the norm-vs-constraint distinction, say the empty case is normal, and name where NOT to reach for it — plus that the skill carries the one-question form, because the docstrings only reach a caller who already opened the tool. `_doc` moves to tests/helpers as `tool_doc`; it had been written twice.
109 lines
4.8 KiB
Python
109 lines
4.8 KiB
Python
"""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 rule 119 puts it in the tool docstrings and the skill rather
|
|
than in a Scribe 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 = [
|
|
("scribe.mcp.tools.notes", "create_note"),
|
|
("scribe.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("scribe.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."""
|
|
import pathlib
|
|
|
|
skill = pathlib.Path(__file__).resolve().parents[1] / (
|
|
"plugin/skills/using-scribe/SKILL.md"
|
|
)
|
|
text = " ".join(skill.read_text().split())
|
|
assert "could this note become false without anyone editing it" in text.lower(), (
|
|
"the using-scribe 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."
|
|
)
|