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/timescaledb/repositories/scada.py

@@ -34,13 +34,15 @@ class ScadaRepository:
         device_ids: List[str],
         start_time: datetime,
         end_time: datetime,
+        *, row_limit: int | None = None,
     ) -> List[dict]:
         async with conn.cursor() as cur:
             await cur.execute(
                 f"SELECT {ScadaRepository.RESULT_COLUMNS} FROM scada.measurements "
                 "WHERE device_id = ANY(%s) "
-                "AND time >= %s AND time <= %s ORDER BY device_id, time",
-                (device_ids, start_time, end_time),
+                "AND time >= %s AND time <= %s ORDER BY device_id, time"
+                + (" LIMIT %s" if row_limit is not None else ""),
+                (device_ids, start_time, end_time) + ((row_limit,) if row_limit is not None else ()),
             )
             return await cur.fetchall()