feat(server): integrate MCP queries and investigation messaging

Add project-bound OAuth MCP queries and controlled analysis with scoped evidence,
limits, timeouts and a nearby-model spatial query using EPSG:4326 inputs.
Default nearby searches to 200 meters and five results.

Integrate investigation messaging/presentation, health/readiness and typed history;
remove duplicate web search and fix online simulation and compressed baseline writes.
Include project migrations 023-025; keep local credentials and demo seeding excluded.

Validation: 319 focused pytest checks; real PostGIS temporary-table regression;
read-only Jinqian bridge radius comparison; cross-language MCP discovery/calls.

app/infra/db/postgresql/scada.py

@@ -111,14 +111,16 @@ class ScadaInfoRepository:
         conn: AsyncConnection,
         node_ids: list[str],
         link_ids: list[str],
+        *, row_limit: int | None = None,
     ) -> list[dict[str, Any]]:
         if not node_ids and not link_ids:
             return []
         async with conn.cursor() as cur:
             await cur.execute(
                 _SCADA_VIEW_SELECT
-                + " WHERE node_id = ANY(%s) OR link_id = ANY(%s) ORDER BY device_id",
-                (node_ids, link_ids),
+                + " WHERE node_id = ANY(%s) OR link_id = ANY(%s) ORDER BY device_id"
+                + (" LIMIT %s" if row_limit is not None else ""),
+                (node_ids, link_ids) + ((row_limit,) if row_limit is not None else ()),
             )
             return [_device(record) for record in await cur.fetchall()]