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.

tests/unit/test_peripheral_work_order_activity.py

@@ -1,5 +1,7 @@
 from uuid import uuid4
 
+import pytest
+
 from samples.peripheral.auth import Identity
 from samples.peripheral.config import SampleSettings
 from samples.peripheral.schemas import CreateWorkOrder, UpdateWorkOrder, WorkOrder
@@ -41,6 +43,25 @@ def test_create_and_update_record_flat_order_activity(monkeypatch):
     assert "progress_note" not in updated
 
 
+@pytest.mark.parametrize(("work_order_type", "detail"), [
+    ("general", "预约工单已创建。"),
+    ("water_quality_complaint", "投诉工单已创建。"),
+    ("burst_report", "爆管上报工单已创建。"),
+])
+def test_created_activity_distinguishes_work_order_type(monkeypatch, work_order_type, detail):
+    store = PostgresStore(SampleSettings())
+    actor = Identity(str(uuid4()), str(uuid4()), True)
+    monkeypatch.setattr(store, "_mutate", lambda who, key, command, operation: operation(None, "normal"))
+    monkeypatch.setattr(store, "_save_work_order", lambda _conn, _who, document: document)
+
+    created = store.create_work_order(actor, CreateWorkOrder(
+        request_id=uuid4(), title="测试工单", summary="验证创建活动语义",
+        work_order_type=work_order_type,
+    ))
+
+    assert created["activity"][0]["detail"] == detail
+
+
 def test_legacy_order_reads_flat_without_claiming_unrecorded_progress():
     legacy = {"work_order_id": str(uuid4()), "subtasks": [{"stages": [{"status": "done"}]}]}
     projected = PostgresStore._active_managed_document(legacy)