feat(swarm): heartbeat-driven topology resync for agent-pinned deployments

Agent heartbeats now carry an applied-topology snapshot. The master
heartbeat handler compares the reported version_hash against what
canonical_hash yields for the hydrated topology pinned to that host
and flags Topology.needs_resync on divergence (or when the agent
reports no topology at all while master expects one).

The mutator watch loop gains reconcile_agent_resyncs, which re-pushes
the current hydrated blob via AgentClient.apply_topology without
touching status, then clears the flag on success. Push failures leave
the flag set so the next tick retries.

decnet/web/db/models.py

@@ -225,6 +225,11 @@ class Topology(SQLModel, table=True):
     # the topology or any child row when an expected_version is supplied.
     # Callers pass their last-seen version; mismatch raises VersionConflict.
     version: int = Field(default=1, nullable=False)
+    # Set by the heartbeat handler when an agent's reported
+    # ``applied_version_hash`` diverges from what we expect it to be
+    # running.  Drained by the mutator watch loop, which re-pushes via
+    # AgentClient and clears the flag.  NULL for unihost topologies.
+    needs_resync: bool = Field(default=False, nullable=False)
 
 
 class LAN(SQLModel, table=True):

decnet/web/db/repository.py

@@ -268,6 +268,12 @@ class BaseRepository(ABC):
     async def delete_topology_cascade(self, topology_id: str) -> bool:
         raise NotImplementedError
 
+    async def set_topology_resync(self, topology_id: str, value: bool) -> None:
+        raise NotImplementedError
+
+    async def list_topologies_needing_resync(self) -> list[dict[str, Any]]:
+        raise NotImplementedError
+
     async def add_lan(self, data: dict[str, Any]) -> str:
         raise NotImplementedError
 

decnet/web/db/sqlmodel_repo.py

@@ -1013,6 +1013,30 @@ class SQLModelRepository(BaseRepository):
             )
             await session.commit()
 
+    async def set_topology_resync(self, topology_id: str, value: bool) -> None:
+        async with self._session() as session:
+            result = await session.execute(
+                select(Topology).where(Topology.id == topology_id)
+            )
+            topo = result.scalar_one_or_none()
+            if topo is None:
+                return
+            topo.needs_resync = bool(value)
+            session.add(topo)
+            await session.commit()
+
+    async def list_topologies_needing_resync(self) -> list[dict[str, Any]]:
+        async with self._session() as session:
+            result = await session.execute(
+                select(Topology).where(Topology.needs_resync == True)  # noqa: E712
+            )
+            return [
+                self._deserialize_json_fields(
+                    r.model_dump(mode="json"), ("config_snapshot",)
+                )
+                for r in result.scalars().all()
+            ]
+
     async def delete_topology_cascade(self, topology_id: str) -> bool:
         """Delete topology and all children.  No portable ON DELETE CASCADE."""
         async with self._session() as session: