Files
FabledScribe/tests/test_note_usage.py
T
bvandeusenandClaude Opus 5 390846a3d5
CI & Build / TypeScript typecheck (push) Failing after 2s
CI & Build / Python lint (push) Successful in 3s
CI & Build / Plugin hooks (push) Successful in 8s
CI & Build / integration (push) Successful in 16s
CI & Build / Python tests (push) Successful in 42s
CI & Build / Build & push image (push) Has been skipped
fix(write-path): disclose cross-language prior art instead of hiding it
Closes #2244. Retrieval matches on concept, and concepts are language-agnostic:
asking about a TypeScript union-find scores 0.72-0.73 against a PYTHON snippet,
comfortably over the 0.68 bar. That is useful — a different-language solution
gives you the shape even when the code isn't reusable — but the menu line said
nothing about it, so the reader either dismissed a good structural reference or
pasted Python into a .ts file.

Worth noting this predates the concept-query change: raw TS code already matched
the Python snippet at 0.73, because the embedder reads identifiers and structure
semantically rather than syntactically. The fail state has been shipping quietly;
#2242 only made it an intended use rather than an accident.

- knowledge._note_to_item projects `language` from the data mirror, same shape as
  the existing verification projection — a plain column read, no body parsing.
- The semantic arm carries language through on the item it builds; it is the arm
  where these arise, since a snippet recorded AT the path you're editing is
  almost never in another language.
- _prior_art_line folds it into the marker: [similar 0.72 · python]. Together
  with the score rather than after the title, because the two jointly are the
  judgement being offered.
- One explanatory line is added to the menu, and only when something on it is
  actually tagged.

Two deliberate calls:

LABEL, DON'T FILTER. A stricter threshold for foreign-language hits would
suppress exactly the shape-borrowing this exists for. They were never the
problem; their being undisclosed was.

ONLY CLAIM A MISMATCH YOU CAN ESTABLISH. _foreign_language returns "" when either
side is unknown — unrecognised extension, or a snippet with no recorded language.
A wrong "· python" is worse than no tag. Same-language hits stay unlabelled, so
the common case keeps a clean line and the preamble stays off the menu entirely.
Operator-typed language names fold through an alias table first (py/python3 →
python, tsx → typescript, c++ → cpp); unrecognised names pass through lowercased,
which still makes an unknown-but-equal pair compare equal.

Trap found while building: _note() in the tests is a MagicMock, so `note.data`
auto-created a truthy mock that would have rendered its repr into a menu line.
Both test helpers now set data = None explicitly.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaYUaouG9jjhATyuxCKrQs
2026-07-30 10:31:56 -04:00

189 lines
7.2 KiB
Python

"""Tests for the usage signal (#2085) — was a surfaced record ever pulled?
Covers the payload shaping and the two contracts that make this safe to leave in
the hot path: telemetry never raises, and telemetry never blocks. Plus the thing
the feature exists for — that the write-path PLACE arm is now recorded, since
before this it surfaced snippets while leaving no trace anywhere.
"""
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from scribe.services import note_usage
from scribe.services.note_usage import (
empty_usage,
record_pulled,
record_surfaced,
usage_for_notes,
)
def _note(nid, title, user_id=1):
n = MagicMock()
n.id, n.title, n.user_id = nid, title, user_id
n.note_type = "snippet"
# See the same note in test_write_path_trigger: an auto-created mock on
# `.data` is truthy and would leak into a rendered menu line (#2244).
n.data = None
return n
# --- recording ------------------------------------------------------------
async def test_record_surfaced_writes_one_row_per_note():
with patch.object(note_usage, "_schedule") as sched:
record_surfaced(user_id=7, note_ids=[11, 12], source="auto_inject")
rows = sched.call_args[0][0]
assert [r["note_id"] for r in rows] == [11, 12]
assert {r["event"] for r in rows} == {"surfaced"}
assert {r["source"] for r in rows} == {"auto_inject"}
assert {r["user_id"] for r in rows} == {7}
async def test_record_pulled_writes_a_single_row():
with patch.object(note_usage, "_schedule") as sched:
record_pulled(user_id=7, note_id=11, source="mcp_get_snippet")
rows = sched.call_args[0][0]
assert rows == [
{"user_id": 7, "note_id": 11, "event": "pulled", "source": "mcp_get_snippet"}
]
async def test_empty_menu_schedules_nothing():
"""No notes surfaced is not an event — it must not cost a write."""
with patch.object(note_usage, "_insert_events") as ins:
record_surfaced(user_id=1, note_ids=[], source="auto_inject")
ins.assert_not_called()
async def test_recording_never_raises_on_bad_input():
"""Telemetry sits in the hot path of every retrieval. A malformed id must
cost a data point, never the operator's request."""
with patch.object(note_usage, "_schedule"):
record_surfaced(user_id=1, note_ids=["not-an-int"], source="auto_inject")
record_pulled(user_id=1, note_id=None, source="mcp_get_note")
async def test_recording_without_an_event_loop_is_skipped_not_raised():
"""Called from a sync context outside the app (a script, a test helper),
there is no loop to schedule on. Skip rather than blow up."""
with patch.object(
note_usage.asyncio, "get_running_loop", side_effect=RuntimeError
):
record_pulled(user_id=1, note_id=5, source="mcp_get_note")
# --- readout --------------------------------------------------------------
async def test_usage_for_notes_zero_fills_every_requested_id():
"""The caller renders this shape unconditionally, so a note with no events
must come back as zeroes, not as a missing key."""
session = MagicMock()
session.execute = AsyncMock(return_value=MagicMock(all=MagicMock(return_value=[])))
ctx = MagicMock()
ctx.__aenter__ = AsyncMock(return_value=session)
ctx.__aexit__ = AsyncMock(return_value=False)
with patch.object(note_usage, "async_session", return_value=ctx):
out = await usage_for_notes([3, 4])
assert out == {3: empty_usage(), 4: empty_usage()}
async def test_usage_for_notes_splits_counts_by_event():
from datetime import datetime, timezone
ts = datetime(2026, 7, 28, tzinfo=timezone.utc)
rows = [(3, "surfaced", 9, ts), (3, "pulled", 2, ts)]
session = MagicMock()
session.execute = AsyncMock(
return_value=MagicMock(all=MagicMock(return_value=rows))
)
ctx = MagicMock()
ctx.__aenter__ = AsyncMock(return_value=session)
ctx.__aexit__ = AsyncMock(return_value=False)
with patch.object(note_usage, "async_session", return_value=ctx):
out = await usage_for_notes([3])
assert out[3]["surfaced_count"] == 9
assert out[3]["pull_count"] == 2
assert out[3]["last_pulled_at"] == ts.isoformat()
async def test_usage_readout_failure_degrades_to_zeroes():
"""A telemetry readout must not be able to break the list it decorates."""
with patch.object(note_usage, "async_session", side_effect=RuntimeError("boom")):
out = await usage_for_notes([3])
assert out == {3: empty_usage()}
async def test_no_ids_short_circuits_without_a_query():
with patch.object(note_usage, "async_session") as sess:
assert await usage_for_notes([]) == {}
sess.assert_not_called()
# --- the gap this closes --------------------------------------------------
@pytest.mark.parametrize(
"marker, expected_source",
[("here", "write_path_place"), ("nearby", "write_path_place")],
)
async def test_write_path_place_arm_is_recorded(marker, expected_source):
"""The place arm carries no score, so it has no home in retrieval_logs — it
surfaced snippets while leaving no trace anywhere. That was the blocker
#2082 recorded against this task; this is the assertion that it's closed."""
from scribe.services import plugin_context
here = [{"id": 42, "title": "helper", "user_id": 1, "note_type": "snippet"}]
with (
patch.object(
plugin_context,
"get_writepath_config",
AsyncMock(return_value={"enabled": True, "threshold": 0.55, "top_k": 3}),
),
patch.object(
plugin_context.snippets_svc,
"list_snippets",
AsyncMock(side_effect=[(here, 1), ([], 0)]),
),
patch.object(
plugin_context, "semantic_search_notes", AsyncMock(return_value=[])
),
patch.object(plugin_context, "owner_names_for", AsyncMock(return_value={})),
patch.object(plugin_context, "record_retrieval"),
patch.object(plugin_context, "record_surfaced") as surfaced,
):
out = await plugin_context.build_write_path_hint(
1, "src/a.py", code="def f(): pass"
)
assert out["note_ids"] == [42]
sources = {c.kwargs["source"] for c in surfaced.call_args_list}
assert expected_source in sources
async def test_auto_inject_records_what_survived_the_margin_gate():
"""Not what the ranker returned — retrieval_logs already holds that. These
two numbers must not silently mean different things per surface."""
from scribe.services import plugin_context
hits = [(0.90, _note(1, "kept")), (0.40, _note(2, "cut by the margin gate"))]
with (
patch.object(
plugin_context,
"get_autoinject_config",
AsyncMock(return_value={"enabled": True, "threshold": 0.3, "top_k": 5}),
),
patch.object(
plugin_context, "semantic_search_notes", AsyncMock(return_value=hits)
),
patch.object(plugin_context, "owner_names_for", AsyncMock(return_value={})),
patch.object(plugin_context, "record_retrieval"),
patch.object(plugin_context, "record_surfaced") as surfaced,
):
await plugin_context.build_autoinject_hint(1, "a query")
assert surfaced.call_args.kwargs["note_ids"] == [1]
assert surfaced.call_args.kwargs["source"] == "auto_inject"