MigrationRunner.get_current_revision() was creating a SQLAlchemy engine
with create_engine(self.database_url) without passing
connect_args={"check_same_thread": False} for SQLite databases.  When
called from a background thread (e.g. async startup flows), SQLite raised
ProgrammingError: SQLite objects created in a thread can only be used in
that same thread.

The sibling method init_or_upgrade() already passes check_same_thread=False
for SQLite, making this an inconsistency in the same class.  Because
get_pending_migrations() and check_migrations_needed() both delegate to
get_current_revision(), the threading bug propagated to all three methods.

This fix adds connect_args={"check_same_thread": False} to the
create_engine() call in get_current_revision() when the database URL
starts with "sqlite", consistent with the existing pattern in
init_or_upgrade().

ISSUES CLOSED: #10507

@@ -0,0 +6,4 @@
+from unittest.mock import MagicMock, patch
+
+from behave import then, when
+

@@ -0,0 +66,4 @@
+        f"Expected exactly 1 create_engine call, got {len(context.engine_creation_calls)}"
+    )
+    _url, kwargs = context.engine_creation_calls[0]
+    connect_args = kwargs.get("connect_args", {})

@@ -0,0 +1,36 @@
+@tdd_issue @tdd_issue_10507

@@ -151,10 +151,22 @@ class MigrationRunner:
     def get_current_revision(self) -> str | None:
         """Get the current migration revision of the database.
 
+        For SQLite databases, the engine is created with