fix(supersession): one query for both directions, not two per note read
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 10s
CI & Build / integration (push) Successful in 12s
CI & Build / TypeScript typecheck (push) Successful in 35s
CI & Build / Python tests (push) Successful in 47s
CI & Build / Build & push image (push) Successful in 25s

CI failed on 8d9e96c — eight tests in test_mcp_tool_notes.py, all
"Connect call failed (127.0.0.1, 5432)".

The proximate cause is that `_attach_supersession` runs on every note
read/write and those are unit tests of the tool layer with no database. But the
test failure exposed a worse decision underneath it.

I had written the two directions as two service calls, so every `get_note`
made TWO extra round trips plus TWO ACL checks — on the hottest path in the
product — to save a two-line partition in Python. That is the wrong trade
whether or not a test noticed.

`get_relations` replaces both: one OR query, one ACL check, partitioned by
which column holds the note's id. Its test asserts `execute.await_count == 1`,
so the collapse can't quietly come apart later.

The tests then get an autouse stub rather than the code getting a swallow. The
tool genuinely has a new dependency; hiding that behind a try/except to keep
unit tests green would be arranging for the code to lie about what it does.
This file already records the same hazard for note 2109, so the stub sits next
to that precedent.

Added the test that matters, which the first pass missed: a superseded record
still surfaces, so an agent WILL read stale material — and it must arrive with
a plain-language warning, not just a numeric field to notice. Also pinned that
both keys are ABSENT rather than present-and-empty when there are no relations.

Refs #278
This commit is contained in:
2026-08-07 22:45:56 -04:00
parent 8d9e96cc6d
commit 984407f931
5 changed files with 106 additions and 35 deletions
+5 -6
View File
@@ -69,12 +69,11 @@ async def _attach_supersession(uid: int, note_id: int, data: dict) -> None:
permanently-empty lists. A field that always says nothing trains readers to
skip fields, which is the lesson `consolidated_at` cost us (#2483).
"""
supersedes = await supersession_svc.get_supersedes(uid, note_id)
superseded_by = await supersession_svc.get_superseded_by(uid, note_id)
if supersedes:
data["supersedes"] = supersedes
if superseded_by:
data["superseded_by"] = superseded_by
rel = await supersession_svc.get_relations(uid, note_id)
if rel["supersedes"]:
data["supersedes"] = rel["supersedes"]
if rel["superseded_by"]:
data["superseded_by"] = rel["superseded_by"]
data["superseded_note"] = (
"A later note claims to bring this up to date — see superseded_by. "
"Read this as what was true when written, and check the newer one "
+5 -6
View File
@@ -36,12 +36,11 @@ async def _attach_supersession(uid: int, note_id: int, data: dict) -> None:
Omitted when empty: a field that always says nothing trains readers to skip
fields, which is what `consolidated_at` cost (#2483).
"""
supersedes = await supersession_svc.get_supersedes(uid, note_id)
superseded_by = await supersession_svc.get_superseded_by(uid, note_id)
if supersedes:
data["supersedes"] = supersedes
if superseded_by:
data["superseded_by"] = superseded_by
rel = await supersession_svc.get_relations(uid, note_id)
if rel["supersedes"]:
data["supersedes"] = rel["supersedes"]
if rel["superseded_by"]:
data["superseded_by"] = rel["superseded_by"]
from scribe.services.note_versions import list_versions, get_version
logger = logging.getLogger(__name__)
+28 -21
View File
@@ -129,33 +129,40 @@ async def set_supersedes(
return wanted
async def get_supersedes(user_id: int, note_id: int) -> list[int]:
"""Ids this note claims to supersede. Empty if the caller can't read it."""
if not await access.can_read_note(user_id, note_id):
return []
async with async_session() as session:
return [int(i) for i in (await session.execute(
select(NoteSupersession.superseded_id)
.where(NoteSupersession.superseder_id == note_id)
.order_by(NoteSupersession.superseded_id)
)).scalars().all()]
async def get_relations(user_id: int, note_id: int) -> dict[str, list[int]]:
"""Both directions for one note: what it supersedes, and what supersedes it.
ONE query and ONE ACL check, because this runs on every note read. Asking
the two questions separately doubled the round trips on the hottest path in
the product to save a two-line partition — the wrong trade, and one I made
on the first attempt.
async def get_superseded_by(user_id: int, note_id: int) -> list[int]:
"""Ids claiming to supersede this note.
Returns {"supersedes": [...], "superseded_by": [...]}, both sorted. Empty
lists when the caller cannot read the note.
The direction that matters to a READER, and the one the note itself cannot
know. An agent handed a stale record with no marker acts on it confidently;
that is worse than never surfacing it at all.
`superseded_by` is the direction that matters to a READER and the one the
note itself cannot know. An agent handed a stale record with no marker acts
on it confidently, which is worse than never surfacing it at all.
"""
empty: dict[str, list[int]] = {"supersedes": [], "superseded_by": []}
if not await access.can_read_note(user_id, note_id):
return []
return empty
async with async_session() as session:
return [int(i) for i in (await session.execute(
select(NoteSupersession.superseder_id)
.where(NoteSupersession.superseded_id == note_id)
.order_by(NoteSupersession.superseder_id)
)).scalars().all()]
rows = (await session.execute(
select(
NoteSupersession.superseder_id, NoteSupersession.superseded_id
).where(
(NoteSupersession.superseder_id == note_id)
| (NoteSupersession.superseded_id == note_id)
)
)).all()
supersedes = sorted(
int(old) for new, old in rows if int(new) == note_id
)
superseded_by = sorted(
int(new) for new, old in rows if int(old) == note_id
)
return {"supersedes": supersedes, "superseded_by": superseded_by}
async def superseded_ids(note_ids: list[int]) -> set[int]:
+39
View File
@@ -17,6 +17,21 @@ def _bind_user():
_user_id_ctx.reset(token)
@pytest.fixture(autouse=True)
def _no_supersession():
"""Every note read/write now asks for its supersession relations (#278).
These are unit tests of the TOOL layer and this job has no database — the
same hazard the `_fake_note` comment below records for note 2109. Stubbed
to "no relations", which is the state of essentially every note; the
relation's own behaviour is covered in test_services_supersession.py, and
the attachment is covered explicitly below.
"""
with patch("scribe.mcp.tools.notes.supersession_svc.get_relations",
AsyncMock(return_value={"supersedes": [], "superseded_by": []})):
yield
def _fake_note(*, user_id: int = 7, **overrides) -> MagicMock:
note = MagicMock()
base = {"id": 1, "title": "t", "body": "b", "tags": [], "is_task": False}
@@ -123,6 +138,30 @@ async def test_get_note_returns_dict():
assert out["title"] == "found"
# Own record: no provenance noise.
assert "shared" not in out
# No supersession relations: both keys ABSENT, not present-and-empty. A
# field that always says nothing trains readers to skip fields (#2483).
assert "supersedes" not in out
assert "superseded_by" not in out
@pytest.mark.asyncio
async def test_get_note_warns_in_words_when_a_later_note_overtook_it():
"""The label is the point, not the ids.
A superseded record still surfaces — supersession demotes, it never hides —
so an agent WILL read stale material. Handing it over with only a numeric
field to notice would be worse than not surfacing it, because the reader
acts on it confidently either way.
"""
fake = _fake_note(id=5, title="June's answer")
with patch("scribe.mcp.tools.notes.notes_svc.get_note_for_user",
AsyncMock(return_value=(fake, "owner"))), \
patch("scribe.mcp.tools.notes.supersession_svc.get_relations",
AsyncMock(return_value={"supersedes": [], "superseded_by": [9]})):
out = await get_note(note_id=5)
assert out["superseded_by"] == [9]
assert "superseded_note" in out
assert "before acting" in out["superseded_note"]
@pytest.mark.asyncio
+29 -2
View File
@@ -144,5 +144,32 @@ async def test_superseded_ids_is_empty_for_an_empty_candidate_set():
async def test_reads_are_empty_when_the_caller_cannot_read_the_note():
with patch("scribe.services.supersession.access.can_read_note",
AsyncMock(return_value=False)):
assert await supersession.get_supersedes(7, 1) == []
assert await supersession.get_superseded_by(7, 1) == []
assert await supersession.get_relations(7, 1) == {
"supersedes": [], "superseded_by": []
}
@pytest.mark.asyncio
async def test_get_relations_partitions_both_directions_from_one_query():
"""ONE round trip for both directions, because this runs on every note read.
Note 5 supersedes 2 and 3, and is itself superseded by 9. All four rows come
back from a single OR query and are partitioned by which column holds 5.
"""
session = AsyncMock()
session.__aenter__ = AsyncMock(return_value=session)
session.__aexit__ = AsyncMock(return_value=False)
result = MagicMock()
result.all.return_value = [(5, 3), (5, 2), (9, 5)] # (superseder, superseded)
session.execute = AsyncMock(return_value=result)
with patch("scribe.services.supersession.access.can_read_note",
AsyncMock(return_value=True)), \
patch("scribe.services.supersession.async_session", return_value=session):
rel = await supersession.get_relations(7, 5)
assert rel == {"supersedes": [2, 3], "superseded_by": [9]}
assert session.execute.await_count == 1, (
"both directions must come from one query — asking separately doubles "
"the round trips on the hottest path in the product"
)