feat(tenancy): harden shared cloud runtime boundaries

tests/unit_tests/api/service/test_apikey_service.py

@@ -166,6 +166,29 @@ async def test_revoked_expired_and_unknown_keys_fail_closed(api_key_context):
     assert await service.authenticate_api_key(expired_secret) is None
 
 
+async def test_revoke_winning_last_used_update_race_fails_authentication(api_key_context):
+    application, service, context, _engine = api_key_context
+    created = await service.create_api_key(context, 'Racing revoke')
+    original_execute = application.persistence_mgr.execute_async
+    injected_revoke = False
+
+    async def execute_with_revoke(statement, *args, **kwargs):
+        nonlocal injected_revoke
+        if (
+            not injected_revoke
+            and isinstance(statement, sqlalchemy.sql.dml.Update)
+            and statement.table.name == ApiKey.__tablename__
+        ):
+            injected_revoke = True
+            await original_execute(sqlalchemy.update(ApiKey).where(ApiKey.id == created['id']).values(status='revoked'))
+        return await original_execute(statement, *args, **kwargs)
+
+    application.persistence_mgr.execute_async = execute_with_revoke
+
+    assert await service.authenticate_api_key(created['key']) is None
+    assert injected_revoke is True
+
+
 async def test_cross_workspace_crud_and_secret_guessing_are_isolated(api_key_context):
     application, service, first_context, engine = api_key_context
     second_workspace_uuid = str(uuid.uuid4())

tests/unit_tests/api/service/test_maintenance_service.py

@@ -13,6 +13,7 @@ Source: src/langbot/pkg/api/http/service/maintenance.py
 
 from __future__ import annotations
 
+import contextlib
 import pytest
 from unittest.mock import AsyncMock, Mock, patch, MagicMock
 from types import SimpleNamespace
@@ -196,6 +197,51 @@ class TestMaintenanceServiceCleanupExpiredFiles:
         assert ap.logger.warning.called
         assert 'uploaded_files' in result
 
+    async def test_cloud_cleanup_carries_scope_without_holding_database_session(self):
+        class ScopeOnlyPersistenceManager:
+            mode = SimpleNamespace(value='cloud_runtime')
+
+            def __init__(self):
+                self.active_workspace = None
+
+            @contextlib.asynccontextmanager
+            async def tenant_scope(self, workspace_uuid):
+                self.active_workspace = workspace_uuid
+                try:
+                    yield
+                finally:
+                    self.active_workspace = None
+
+            def current_session(self):
+                return None
+
+        persistence_mgr = ScopeOnlyPersistenceManager()
+        application = SimpleNamespace(
+            persistence_mgr=persistence_mgr,
+            instance_config=SimpleNamespace(data={}),
+            logger=SimpleNamespace(warning=Mock()),
+        )
+        service = MaintenanceService(application)
+
+        async def cleanup_uploads(_context, _retention_days):
+            assert persistence_mgr.active_workspace == TEST_CONTEXT.workspace_uuid
+            assert persistence_mgr.current_session() is None
+            return 2
+
+        def cleanup_logs(_retention_days):
+            assert persistence_mgr.active_workspace == TEST_CONTEXT.workspace_uuid
+            assert persistence_mgr.current_session() is None
+            return 1
+
+        service._cleanup_expired_uploaded_files = cleanup_uploads
+        service._cleanup_expired_log_files = cleanup_logs
+
+        assert await service.cleanup_expired_files(TEST_CONTEXT) == {
+            'uploaded_files': 2,
+            'log_files': 1,
+        }
+        assert persistence_mgr.active_workspace is None
+
 
 class TestMaintenanceServiceGetStorageAnalysis:
     """Tests for get_storage_analysis method."""

tests/unit_tests/api/service/test_mcp_service.py

@@ -13,6 +13,7 @@ Source: src/langbot/pkg/api/http/service/mcp.py
 
 from __future__ import annotations
 
+import asyncio
 import copy
 import pytest
 from unittest.mock import AsyncMock, Mock, MagicMock
@@ -485,6 +486,54 @@ class TestMCPServiceCreateMCPServer:
         # Verify - host_mcp_server was called
         ap.tool_mgr.mcp_tool_loader.host_mcp_server.assert_called_once()
 
+    async def test_create_mcp_server_does_not_start_host_until_transaction_commits(self):
+        """The Runtime must not observe a server row that can still roll back."""
+
+        gate = asyncio.get_running_loop().create_future()
+
+        class PersistenceManagerStub:
+            def create_after_commit_gate(self):
+                return gate
+
+        ap = SimpleNamespace()
+        ap.persistence_mgr = PersistenceManagerStub()
+        ap.instance_config = SimpleNamespace(data={'system': {'limitation': {'max_extensions': -1}}})
+        observed = []
+
+        async def host_mcp_server(context, config):
+            observed.append((context, config))
+
+        ap.tool_mgr = SimpleNamespace(
+            mcp_tool_loader=SimpleNamespace(
+                host_mcp_server=host_mcp_server,
+                _hosted_mcp_tasks=[],
+            )
+        )
+        server_entity = _create_mock_mcp_server(server_uuid='new-uuid', enable=True)
+        results = [
+            _create_mock_result([]),
+            Mock(),
+            _create_mock_result(first_item=server_entity),
+        ]
+        ap.persistence_mgr.execute_async = AsyncMock(side_effect=results)
+        ap.persistence_mgr.serialize_model = Mock(
+            return_value={'uuid': 'new-uuid', 'name': 'New Server', 'enable': True}
+        )
+        service = _service(ap)
+
+        await service.create_mcp_server(_CONTEXT, {'name': 'New Server', 'enable': True})
+        await asyncio.sleep(0)
+        assert observed == []
+
+        gate.set_result(None)
+        await ap.tool_mgr.mcp_tool_loader._hosted_mcp_tasks[0]
+        assert observed == [
+            (
+                _CONTEXT,
+                {'uuid': 'new-uuid', 'name': 'New Server', 'enable': True},
+            )
+        ]
+
     async def test_create_mcp_server_disabled_no_load(self):
         """Does not load server when disabled."""
         # Setup

tests/unit_tests/api/service/test_monitoring_tenancy.py

@@ -11,7 +11,9 @@ from langbot.pkg.api.http.authz import WorkspaceRequiredError
 from langbot.pkg.api.http.context import ExecutionContext
 from langbot.pkg.api.http.service.monitoring import MonitoringService
 from langbot.pkg.entity.persistence.base import Base
+from langbot.pkg.entity.persistence.monitoring import MonitoringMessage
 from langbot.pkg.entity.persistence.workspace import Workspace
+from langbot.pkg.persistence.mgr import PersistenceManager
 
 
 pytestmark = pytest.mark.asyncio
@@ -136,6 +138,26 @@ async def test_same_session_and_resource_ids_do_not_collide(service):
     assert (await service.get_message_details(context_a, message_b))['found'] is False
 
 
+async def test_tool_call_inherits_context_from_connection_message_row(service):
+    context = _context(WORKSPACE_A)
+    message_id = await _record_message(service, context, 'tool context')
+
+    await service.record_tool_call(
+        context,
+        tool_name='search',
+        tool_source='native',
+        duration=12,
+        message_id=message_id,
+    )
+
+    tool_calls, total = await service.get_tool_calls(context)
+    assert total == 1
+    assert tool_calls[0]['bot_id'] == 'same-bot'
+    assert tool_calls[0]['pipeline_id'] == 'same-pipeline'
+    assert tool_calls[0]['session_id'] == 'same-session'
+    assert tool_calls[0]['message_id'] == message_id
+
+
 async def test_feedback_upsert_and_cancel_are_workspace_scoped(service):
     context_a = _context(WORKSPACE_A)
     context_b = _context(WORKSPACE_B)
@@ -152,3 +174,58 @@ async def test_feedback_upsert_and_cancel_are_workspace_scoped(service):
     await service.record_feedback(context_a, feedback_id='same-feedback', feedback_type=3)
     assert (await service.get_feedback_stats(context_a))['total_feedback'] == 0
     assert (await service.get_feedback_stats(context_b))['total_feedback'] == 1
+
+
+async def test_cleanup_commits_sqlite_delete_before_vacuum(tmp_path):
+    engine = create_async_engine(
+        f'sqlite+aiosqlite:///{tmp_path / "monitoring-cleanup.db"}',
+        connect_args={'timeout': 0.1},
+    )
+    application = SimpleNamespace(
+        instance_config=SimpleNamespace(data={'database': {'use': 'sqlite'}}),
+    )
+    manager = PersistenceManager(application)
+    manager.db = SimpleNamespace(get_engine=lambda: engine)
+    application.persistence_mgr = manager
+    try:
+        async with engine.begin() as connection:
+            await connection.run_sync(Base.metadata.create_all)
+            await connection.execute(
+                sqlalchemy.insert(Workspace).values(
+                    uuid=WORKSPACE_A,
+                    instance_uuid='instance',
+                    name='A',
+                    slug='a',
+                    source='cloud_projection',
+                )
+            )
+            await connection.execute(
+                sqlalchemy.insert(MonitoringMessage).values(
+                    id='expired-message',
+                    workspace_uuid=WORKSPACE_A,
+                    timestamp=datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None)
+                    - datetime.timedelta(days=30),
+                    bot_id='bot',
+                    bot_name='Bot',
+                    pipeline_id='pipeline',
+                    pipeline_name='Pipeline',
+                    message_content='expired',
+                    session_id='session',
+                    status='success',
+                    level='info',
+                )
+            )
+
+        deleted = await MonitoringService(application).cleanup_expired_records(
+            _context(WORKSPACE_A),
+            retention_days=1,
+        )
+
+        assert deleted['monitoring_messages'] == 1
+        async with engine.connect() as connection:
+            remaining = await connection.scalar(
+                sqlalchemy.select(sqlalchemy.func.count()).select_from(MonitoringMessage)
+            )
+        assert remaining == 0
+    finally:
+        await engine.dispose()