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/analysis.py

@@ -221,6 +221,7 @@ class AnalysisRepository:
         *,
         limit: int = 100,
         offset: int = 0,
+        lookahead: bool = False,
     ) -> list[dict]:
         if not 1 <= limit <= 500 or offset < 0:
             raise ValueError("analysis result page is out of range")
@@ -235,7 +236,7 @@ class AnalysisRepository:
             query += " AND result_type = %s"
             params = (run_id, result_type)
         query += " ORDER BY created_at, result_id LIMIT %s OFFSET %s"
-        params += (limit, offset)
+        params += (limit + int(lookahead), offset)
 
         async with conn.cursor() as cur:
             await cur.execute(query, params)