docs(notes): the surfaces say WHEN a note earns a check, and a guard keeps them saying it (#3168, milestone 317 step 5)
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.
This commit is contained in:
2026-08-29 00:10:43 -04:00
parent 1ec44071d2
commit 1d65e98ac2
7 changed files with 176 additions and 20 deletions
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "scribe",
"description": "Scribe system-of-record for Claude Code: MCP tools over your notes/tasks/projects/rules, a session-start push channel that surfaces your always-on rules + active-project context, process-skills (writing-plans, systematic-debugging, verification, brainstorming, reusing-code), and your saved Scribe Processes auto-surfaced as skills (/scribe:sync). Replaces superpowers + file-memory with one app-backed plugin.",
"version": "0.1.47",
"version": "0.1.48",
"author": {
"name": "Bryan Van Deusen"
},
+24
View File
@@ -106,6 +106,30 @@ Two constraints on *how* that's achieved:
re-measurement, a reversed decision), pass the old id in `supersedes` so the
stale record is demoted and labelled rather than left competing.
9. **A few notes assert a FACT, and those can carry their own check.**
Supersession only fires once somebody has read a note and disagreed — which
is the case where it was already believed. A note asserting something about
*someone else's* software — what a service does on a duplicate upload, how a
forge numbers its CI runs, what an updater compares — can instead carry
`verify_with` (how to check it) and `expires_when` (the STATE that ends it:
"when the forge numbers runs per workflow", never "in six months").
`notes_due_for_verification` lists them least-recently-confirmed first, with
never-checked at the top; `mark_note_verified` records what you found, and
`still_true=False` deliberately writes nothing — a note whose check failed
is wrong rather than in a state worth recording, so it keeps its place.
**The test is one question: could this note become false without anyone
editing it?** If no, leave both fields empty. That is the normal case, and
an empty `verify_with` is the positive marker for "this is a decision, there
is nothing to go and check" — not an unfinished record. The sweep is only
worth reading while almost nothing is on it, so a check added out of
tidiness costs the whole surface, not just that note.
Not for tasks — a task's decay is its status, and a done issue records what
happened rather than asserting something that can go false. Not for snippets
either: `verify_snippet` compares the recorded location and code against the
repo, which is richer and already wired to drift detection.
## Stay inside the active project's scope
Once a project is in scope — you called `enter_project`, or the working repo is
+15
View File
@@ -30,6 +30,21 @@ from quart import Quart
# duplicate gate, the untagged-record systems_hint) act in-band in tool
# responses, at the moment they apply.
# Grow one of those, not this block.
# BUDGET: ~1980 of the client's ~2048-char cap (#2562). Everything below is
# competing for the last ~68 characters, so an addition here is a trade, never
# an append.
#
# Milestone 317 (a note's own verify_with / expires_when, and the sweep over
# them) was DECLINED a line, deliberately, by the operator — not overlooked.
# The reasoning, so it is not re-litigated blind: this is a map, and its own
# closing line says each tool's description carries the full contract. The
# sweep is a curation act, not a session-start reflex like enter_project or
# list_always_on_rules. Spending the last of the budget on it would leave the
# map unable to grow for something more central later.
#
# The accepted cost: an agent that never opens create_note's docstring never
# learns the field exists. Guidance lives in the create_note / update_note
# docstrings and the using-scribe skill instead.
_INSTRUCTIONS = """
Scribe is the operator's self-hosted second brain and system of record — and
yours: recall from it before acting, record as you go. Keep no parallel copy
+6 -4
View File
@@ -224,10 +224,12 @@ async def update_note(
supersedes: Replace the ids of earlier notes this one replaces
(set-semantics). None = leave unchanged; [] = clear all. See
create_note for when to reach for it.
verify_with: How to check this note is still true. See create_note for
the norm-vs-constraint test that decides whether it should carry
one at all; the short form is "could this become false without
anyone editing it?".
verify_with: How to check this note is still true. Almost every note
should leave this empty — that is the normal, finished state, not
a gap: an empty check is the marker for "this is a decision, there
is nothing to go and check". See create_note for the full
norm-vs-constraint test; the short form is "could this become
false without anyone editing it?".
expires_when: The STATE that ends it, not a date.
clear: Names of fields to UNSET — "verify_with", "expires_when".
Needed because "" means "leave this alone" here, so there is no
+21
View File
@@ -38,6 +38,27 @@ async def drive_update_note(note, **kwargs):
return await update_note(user_id=7, note_id=note.id, **kwargs)
def tool_doc(module: str, name: str) -> str:
"""An MCP tool's docstring, whitespace-flattened.
Flattened because these are hard-wrapped at ~76 characters, so any phrase
worth asserting on is liable to straddle a line break — a property of the
formatter, not of the guidance. The disambiguator guard (#3123) learned
that on its own first run, matching raw text and reporting a phrase absent
that was plainly there.
Used by every test that pins the docstring CONTRACT rather than its
wording. The tool docstring is the agent-facing contract (rule 119), so
these guards exist to catch it being tidied down to a parameter list.
"""
import importlib
import re as _re
fn = getattr(importlib.import_module(module), name)
assert fn.__doc__, f"{name} has no docstring at all"
return _re.sub(r"\s+", " ", fn.__doc__)
def compiled_sql(element) -> str:
"""A SQLAlchemy clause or statement rendered as literal SQL text.
+1 -15
View File
@@ -29,6 +29,7 @@ parameters, with the "is this even the right tool" paragraph quietly gone.
import re
import pytest
from tests.helpers import tool_doc as _doc
# The create surfaces and where they live. `start_planning` is here because
# it is a create in everything but name — it is how a plan comes into being.
@@ -50,21 +51,6 @@ _ALTERNATIVES = [
]
def _doc(module: str, name: str) -> str:
"""The docstring with its whitespace flattened.
Flattened because a docstring is hard-wrapped: "design system" spans a
line break in at least one of these, and matching the raw text would
report it absent. The first draft of this check did exactly that, and
caught it on itself.
"""
import importlib
fn = getattr(importlib.import_module(module), name)
assert fn.__doc__, f"{name} has no docstring at all"
return re.sub(r"\s+", " ", fn.__doc__)
@pytest.mark.parametrize(("module", "name"), _SURFACES)
def test_a_create_surface_names_at_least_two_alternatives(module, name):
"""Reaching for the wrong tool must still put the right one in view."""
@@ -0,0 +1,108 @@
"""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."
)