Files
FabledScribe/tests/test_snippet_duplicates.py
T
bvandeusenandClaude Fable 5 272b7dbddf
CI & Build / Python lint (push) Successful in 4s
CI & Build / Plugin hooks (push) Successful in 10s
CI & Build / integration (push) Successful in 19s
CI & Build / TypeScript typecheck (push) Successful in 33s
CI & Build / Python tests (push) Successful in 53s
CI & Build / Build & push image (push) Successful in 42s
feat(dedup): per-kind duplicate-report floors — notes/tasks default 0.93
At chunk grain (#280) a note-pair's similarity is its closest chunk pair,
so the shared 0.82 floor saturated the note/task reports with related
families (38 note / 155 task groups against the 200-pair cap, measured
2026-08-09). Split kb_duplicate_threshold into per-kind settings keys
with per-kind defaults: snippet 0.82 (single-chunk, scale unchanged),
note/task 0.93 (points the report at genuinely-alike records). Settings
UI grows the two new knobs; report entrypoints inherit the change via
get_duplicate_threshold(user_id, kind).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01UaYUaouG9jjhATyuxCKrQs
2026-08-09 10:33:11 -04:00

128 lines
5.1 KiB
Python

"""Tests for the near-duplicate finder (#2088).
The SQL half needs a database and lives in the integration lane; what's covered
here is the grouping rule — which is where the interesting decisions are — plus
the fail-open contract and the threshold resolution.
"""
from unittest.mock import AsyncMock, patch
import pytest
from scribe.services import dedup as dedup_svc
from scribe.services.dedup import (
DUPLICATE_DEFAULT_THRESHOLDS,
get_duplicate_threshold,
group_pairs,
)
# --- grouping -------------------------------------------------------------
def test_a_simple_pair_becomes_one_set():
assert group_pairs([(1, 2, 0.9)]) == [[1, 2]]
def test_grouping_is_transitive():
"""A~B and B~C puts all three in one set even though A and C never cleared
the bar together. That mirrors merge, which folds every source into one
survivor — three overlapping pairs would just be the same chore, unsorted."""
assert group_pairs([(1, 2, 0.9), (2, 3, 0.9)]) == [[1, 2, 3]]
def test_disjoint_clusters_stay_separate():
groups = group_pairs([(1, 2, 0.9), (3, 4, 0.9)])
assert groups == [[1, 2], [3, 4]]
def test_largest_cluster_comes_first():
"""The most tangled thing is the most worth fixing."""
groups = group_pairs([(5, 6, 0.9), (1, 2, 0.9), (2, 3, 0.9), (3, 4, 0.9)])
assert groups[0] == [1, 2, 3, 4]
def test_output_is_stable_across_input_order():
"""A report that reshuffles between runs is one nobody can work through."""
a = group_pairs([(1, 2, 0.9), (2, 3, 0.9), (7, 8, 0.9)])
b = group_pairs([(7, 8, 0.9), (2, 3, 0.9), (1, 2, 0.9)])
assert a == b
def test_no_pairs_means_no_groups():
assert group_pairs([]) == []
def test_a_node_never_forms_a_group_with_itself():
"""The SQL uses `note_id <` so this shouldn't arrive, but a singleton set
would render as a "duplicate" of nothing and offer an impossible merge."""
assert group_pairs([(1, 1, 1.0)]) == []
# --- threshold ------------------------------------------------------------
@pytest.mark.parametrize("kind", ["snippet", "note", "task"])
async def test_threshold_falls_back_to_the_per_kind_default_when_unset(kind):
default = DUPLICATE_DEFAULT_THRESHOLDS[kind]
with patch("scribe.services.settings.get_setting",
AsyncMock(return_value=str(default))):
assert await get_duplicate_threshold(1, kind) == default
async def test_each_kind_reads_its_own_settings_key():
"""Tuning the note floor must not move the snippet report — the whole
point of splitting the setting is that the kinds calibrate independently."""
get = AsyncMock(return_value="0.5")
with patch("scribe.services.settings.get_setting", get):
await get_duplicate_threshold(1, "note")
key, default = get.await_args.args[1], get.await_args.args[2]
assert key == "kb_duplicate_threshold_note"
assert default == str(DUPLICATE_DEFAULT_THRESHOLDS["note"])
async def test_a_garbage_setting_falls_back_rather_than_raising():
with patch("scribe.services.settings.get_setting",
AsyncMock(return_value="not-a-number")):
assert (await get_duplicate_threshold(1, "snippet")
== DUPLICATE_DEFAULT_THRESHOLDS["snippet"])
@pytest.mark.parametrize("stored, expected", [("2.5", 1.0), ("-3", 0.0)])
async def test_threshold_is_clamped_to_the_valid_range(stored, expected):
with patch("scribe.services.settings.get_setting", AsyncMock(return_value=stored)):
assert await get_duplicate_threshold(1, "snippet") == expected
def test_the_snippet_report_threshold_is_looser_than_the_write_gate():
"""The gate BLOCKS a create and must be unforgiving of noise; the snippet
report only suggests a merge the operator reviews, so it has to reach
further or it would never surface the pairs the gate already let through.
Snippet-only on purpose: note/task floors sit ABOVE the gate because chunk
grain (#280) lifts related families over it — see the module comment."""
assert DUPLICATE_DEFAULT_THRESHOLDS["snippet"] < dedup_svc._SEMANTIC_THRESHOLD
def test_the_note_and_task_floors_are_stricter_than_the_snippet_floor():
"""At chunk grain, 0.82 is a related-families view; the report's default
must point at genuinely-alike records (measured 2026-08-09, note #2551)."""
assert DUPLICATE_DEFAULT_THRESHOLDS["note"] == 0.93
assert DUPLICATE_DEFAULT_THRESHOLDS["task"] == 0.93
# --- fail-open ------------------------------------------------------------
async def test_a_failed_scan_returns_an_empty_report_not_an_error():
"""A suggestion feature must not be able to break the page it decorates."""
with (
patch.object(dedup_svc, "get_duplicate_threshold", AsyncMock(return_value=0.8)),
patch.object(dedup_svc, "async_session", side_effect=RuntimeError("boom")),
):
out = await dedup_svc.find_duplicate_snippets(1)
# The empty report still carries its per-kind `suggestion` (#2547) — a
# failed scan must be indistinguishable in SHAPE from a clean one, or every
# consumer needs a second code path for the degraded case.
assert out["groups"] == [] and out["pairs"] == []
assert out["threshold"] == 0.8
assert "merge" in out["suggestion"]