feat(correlation/attribution): wire bus handler, persist state (Phase 4)

attribution_worker.handle_observation_event now executes the full
end-to-end path:

* ensure stub identity (Phase 1)
* observations_for_identity_primitive() — new repo helper joining
  observations through attackers.identity_id, so v1's clusterer
  gets cross-attacker rollup for free
* aggregate_observations() with ValueKind dispatched off the BEHAVE
  PRIMITIVE_REGISTRY; unknown primitives default to categorical
* upsert_attribution_state() — last_change_ts locked when state is
  unchanged so the dashboard can render "stable since X"
* publish attribution.profile.state_changed only on transition;
  idempotent re-runs over the same observation set fire nothing
  (loop-prevention invariant matching ttp.tagged)

Tests:
* 5 end-to-end attribution scenarios over in-memory SQLite + FakeBus.
* test_base_repo's DummyRepo + coverage body now stub every abstract
  surface BaseRepository declares — the 6 added by this branch plus
  the 12 left un-stubbed by earlier work (BEHAVE Phase 1, TTP
  rollups, iter helpers). The coverage test could not previously
  even instantiate.
* test_aggregate_categorical's dispatcher rejection updated for the
  Phase 3 + 4 contract — ValueError on unknown kinds, not
  NotImplementedError.
This commit is contained in:
2026-05-09 02:16:12 -04:00
parent c39802a4bb
commit dd265d7520
6 changed files with 536 additions and 17 deletions

View File

@@ -341,6 +341,20 @@ class BaseRepository(ABC):
ordered by ``ts`` ASC. Empty list when none."""
raise NotImplementedError
@abstractmethod
async def observations_for_identity_primitive(
self, identity_uuid: str, primitive: str,
) -> list[dict[str, Any]]:
"""Every observation of ``primitive`` across all attackers
rolling up to ``identity_uuid``, ordered by ``ts`` ASC.
Empty list when the identity has no observations of this
primitive. v0 with 1:1 stub identities returns the same set
as ``observations_time_series(attacker_uuid, primitive)``;
v1's clusterer makes the union meaningful.
"""
raise NotImplementedError
@abstractmethod
async def has_observations_for_evidence(self, evidence_ref: str) -> bool:
"""True iff any observation row carries this ``evidence_ref``.

View File

@@ -25,7 +25,7 @@ from typing import Any, Optional
from sqlalchemy import desc, func, select
from sqlmodel import col
from decnet.web.db.models import ObservationRow
from decnet.web.db.models import Attacker, ObservationRow
from decnet.web.db.sqlmodel_repo._helpers import _MixinBase
@@ -164,6 +164,34 @@ class ObservationsMixin(_MixinBase):
return None
return row.model_dump(mode="json")
async def observations_for_identity_primitive(
self, identity_uuid: str, primitive: str,
) -> list[dict[str, Any]]:
"""Union of every observation of *primitive* across the
attackers rolling up to *identity_uuid*, ordered ``ts`` ASC.
v0 with 1:1 stub identities returns the same set as
``observations_time_series(attacker_uuid, primitive)``.
v1's clusterer makes the union load-bearing — multiple
attackers point at the same identity_id and this query is
what gives the merger a cross-attacker view.
"""
async with self._session() as session:
stmt = (
select(ObservationRow)
.join(Attacker, ObservationRow.attacker_uuid == Attacker.uuid)
.where(
Attacker.identity_id == identity_uuid,
ObservationRow.primitive == primitive,
)
.order_by(ObservationRow.ts)
)
rows = (await session.execute(stmt)).scalars().all()
return [
{"ts": row.ts, "value": row.value, "confidence": row.confidence}
for row in rows
]
async def has_observations_for_evidence(
self, evidence_ref: str,
) -> bool: