feat(clustering): roll session digraph SimHashes into identity centroid

The identity clusterer folds an identity's per-session
motor.digraph_simhash observations into one 8-byte bitwise-majority
centroid (denoises per-session jitter) and writes it to
AttackerIdentity.kd_digraph_simhash via update_identity_fingerprints —
the orphaned column is now populated. list_identities_for_clustering
projects it so the campaign clusterer can read it.

Extends the repo abstract + DummyRepo stub/coverage.
This commit is contained in:
2026-06-16 17:05:34 -04:00
parent 66c73ce59d
commit 869d1eabb7
7 changed files with 150 additions and 10 deletions

View File

@@ -0,0 +1,47 @@
# SPDX-License-Identifier: AGPL-3.0-or-later
"""``_digraph_centroid`` — bitwise-majority rollup of session SimHashes."""
from __future__ import annotations
from decnet.clustering.impl.connected_components import _digraph_centroid
from decnet.util.simhash import from_bytes8, to_bytes8
_ALL_ONES = (1 << 64) - 1
class _FakeRepo:
"""Returns canned digraph observations for one identity."""
def __init__(self, hash_ints: list[int]) -> None:
self._values = [to_bytes8(h).hex() for h in hash_ints]
async def observations_for_identity_primitive(self, identity_uuid, primitive):
assert primitive == "motor.digraph_simhash"
return [{"value": v} for v in self._values]
async def test_no_observations_returns_none() -> None:
assert await _digraph_centroid(_FakeRepo([]), "id") is None
async def test_single_session_centroid_is_that_hash() -> None:
out = await _digraph_centroid(_FakeRepo([0xDEADBEEFCAFEF00D]), "id")
assert from_bytes8(out) == 0xDEADBEEFCAFEF00D
async def test_majority_wins_per_bit() -> None:
# 2 of 3 sessions all-ones → every bit majority-set → all ones.
out = await _digraph_centroid(_FakeRepo([_ALL_ONES, _ALL_ONES, 0]), "id")
assert from_bytes8(out) == _ALL_ONES
async def test_tie_is_not_set() -> None:
# 1-1 tie per bit: majority requires strictly more than half → 0.
out = await _digraph_centroid(_FakeRepo([_ALL_ONES, 0]), "id")
assert from_bytes8(out) == 0
async def test_garbage_values_skipped() -> None:
repo = _FakeRepo([])
repo._values = ["not-hex-zz", "deadbeef", to_bytes8(_ALL_ONES).hex()] # only the last is valid
out = await _digraph_centroid(repo, "id")
assert from_bytes8(out) == _ALL_ONES