chore: merge master into feat/multi-tenants

- Resolved conflict in provider.py: merged rerank model support with tenant context
- Resolved conflict in telegram.py: kept async.to_thread optimization and added url parameter
- Resolved conflict in test_model_manager.py: kept both cloud runtime and rerank tests

tests/unit_tests/api/service/test_provider_service.py

@@ -833,6 +833,44 @@ class TestModelProviderServiceScanProviderModels:
         assert len(result['models']) == 1
         assert result['models'][0]['type'] == 'llm'
 
+    async def test_scan_provider_marks_existing_rerank_model(self):
+        """Rerank scan results use the rerank service when computing already_added."""
+        ap = SimpleNamespace()
+        ap.persistence_mgr = SimpleNamespace()
+        ap.model_mgr = SimpleNamespace()
+        ap.llm_model_service = SimpleNamespace()
+        ap.embedding_models_service = SimpleNamespace()
+        ap.rerank_models_service = SimpleNamespace()
+
+        provider = _create_mock_provider(provider_uuid='rerank-scan-uuid')
+        ap.persistence_mgr.execute_async = AsyncMock(return_value=_create_mock_result([], first_item=provider))
+        ap.persistence_mgr.serialize_model = Mock(
+            return_value={
+                'uuid': 'rerank-scan-uuid',
+                'name': 'New API',
+                'requester': 'new-api-chat-completions',
+                'base_url': 'https://new-api.example.com/v1',
+                'api_keys': ['key'],
+            }
+        )
+
+        runtime_provider = Mock()
+        runtime_provider.token_mgr.get_token.return_value = 'token'
+        runtime_provider.requester.scan_models = AsyncMock(
+            return_value={'models': [{'id': 'Qwen3-Reranker-8B', 'type': 'rerank'}]}
+        )
+        ap.model_mgr.load_provider = AsyncMock(return_value=runtime_provider)
+        ap.llm_model_service.get_llm_models_by_provider = AsyncMock(return_value=[])
+        ap.embedding_models_service.get_embedding_models_by_provider = AsyncMock(return_value=[])
+        ap.rerank_models_service.get_rerank_models_by_provider = AsyncMock(
+            return_value=[{'name': 'Qwen3-Reranker-8B'}]
+        )
+
+        result = await ModelProviderService(ap).scan_provider_models('rerank-scan-uuid', model_type='rerank')
+
+        assert result['models'][0]['type'] == 'rerank'
+        assert result['models'][0]['already_added'] is True
+
     async def test_scan_provider_not_implemented_raises_error(self):
         """Raises ValueError when scan not implemented."""
         # Setup

tests/unit_tests/api/service/test_space_service.py

@@ -756,7 +756,7 @@ class TestSpaceServiceGetModels:
                             'uuid': 'uuid-2',
                             'model_id': 'model-2',
                             'provider': 'provider-2',
-                            'category': 'chat',
+                            'category': 'rerank',
                             'status': 'active',
                         },
                     ]
@@ -778,6 +778,7 @@ class TestSpaceServiceGetModels:
 
         # Verify
         assert len(result) == 2
+        assert result[1].category == 'rerank'
 
     async def test_get_models_api_error(self):
         """Raises ValueError on API error."""

tests/unit_tests/pipeline/test_command_handler.py

@@ -158,17 +158,21 @@ class TestCommandHandlerReal:
 
     @pytest.mark.asyncio
     async def test_admin_privilege_check(self, fake_app, mock_event_ctx, mock_execute_factory):
-        """Admin users get privilege level 2."""
+        """A per-bot admin from the database is marked as admin in command events."""
         from langbot_plugin.api.entities.builtin.provider.session import LauncherTypes
 
         command = get_command_handler()
 
-        fake_app.instance_config.data = {'admins': ['person_12345']}
+        admin_result = Mock()
+        admin_result.first.return_value = Mock()
+        fake_app.persistence_mgr.execute_async = AsyncMock(return_value=admin_result)
+        fake_app.instance_config.data = {}
         fake_app.plugin_connector.emit_event = AsyncMock(return_value=mock_event_ctx)
         fake_app.cmd_mgr.execute = mock_execute_factory()
 
         handler = command.CommandHandler(fake_app)
         query = command_query('status')
+        query.bot_uuid = 'bot-1'
         query.launcher_type = LauncherTypes.PERSON
         query.launcher_id = 12345
 
@@ -176,23 +180,28 @@ class TestCommandHandlerReal:
         async for result in handler.handle(query):
             results.append(result)
 
+        fake_app.persistence_mgr.execute_async.assert_awaited_once()
         call_args = fake_app.plugin_connector.emit_event.call_args
         event = call_args[0][0]
         assert event.is_admin is True
 
     @pytest.mark.asyncio
     async def test_non_admin_privilege_check(self, fake_app, mock_event_ctx, mock_execute_factory):
-        """Non-admin users get privilege level 1."""
+        """A launcher absent from the per-bot admin table is not an admin."""
         from langbot_plugin.api.entities.builtin.provider.session import LauncherTypes
 
         command = get_command_handler()
 
-        fake_app.instance_config.data = {'admins': ['person_12345']}
+        admin_result = Mock()
+        admin_result.first.return_value = None
+        fake_app.persistence_mgr.execute_async = AsyncMock(return_value=admin_result)
+        fake_app.instance_config.data = {}
         fake_app.plugin_connector.emit_event = AsyncMock(return_value=mock_event_ctx)
         fake_app.cmd_mgr.execute = mock_execute_factory()
 
         handler = command.CommandHandler(fake_app)
         query = command_query('status')
+        query.bot_uuid = 'bot-1'
         query.launcher_type = LauncherTypes.PERSON
         query.launcher_id = 67890
 
@@ -200,6 +209,7 @@ class TestCommandHandlerReal:
         async for result in handler.handle(query):
             results.append(result)
 
+        fake_app.persistence_mgr.execute_async.assert_awaited_once()
         call_args = fake_app.plugin_connector.emit_event.call_args
         event = call_args[0][0]
         assert event.is_admin is False

tests/unit_tests/provider/test_litellmchat.py

@@ -1147,6 +1147,46 @@ class TestInvokeRerank:
         assert results[0]['relevance_score'] == 1.0
         assert results[1]['relevance_score'] == 0.0
 
+    @pytest.mark.asyncio
+    @pytest.mark.parametrize(
+        ('model_extra_args', 'expected_url'),
+        [
+            ({'rerank_path': 'reranks'}, 'https://gateway.example.com/v1/reranks'),
+            ({'rerank_url': 'https://rerank.example.com/api/rerank'}, 'https://rerank.example.com/api/rerank'),
+        ],
+    )
+    async def test_invoke_rerank_openai_compatible_endpoint_override(self, model_extra_args, expected_url):
+        """Endpoint configuration controls routing and is not sent in the Cohere body."""
+        requester = litellmchat.LiteLLMRequester(
+            ap=Mock(),
+            config={
+                'base_url': 'https://gateway.example.com/v1/',
+                'custom_llm_provider': 'openai',
+            },
+        )
+        model = MockRuntimeRerankModel('Qwen3-Reranker-8B', 'test-api-key')
+        model.model_entity.extra_args = model_extra_args
+
+        mock_resp = Mock()
+        mock_resp.raise_for_status = Mock()
+        mock_resp.json = Mock(return_value={'results': [{'index': 0, 'relevance_score': 0.8}]})
+        mock_client = AsyncMock()
+        mock_client.post = AsyncMock(return_value=mock_resp)
+        mock_client.__aenter__ = AsyncMock(return_value=mock_client)
+        mock_client.__aexit__ = AsyncMock(return_value=False)
+
+        with patch('httpx.AsyncClient', return_value=mock_client):
+            await requester.invoke_rerank(model=model, query='query', documents=['document'])
+
+        assert mock_client.post.call_args.args[0] == expected_url
+        payload = mock_client.post.call_args.kwargs['json']
+        assert payload == {
+            'model': 'Qwen3-Reranker-8B',
+            'query': 'query',
+            'documents': ['document'],
+            'top_n': 1,
+        }
+
 
 class TestConvertMessages:
     """Test _convert_messages method"""

tests/unit_tests/provider/test_model_manager.py

@@ -86,6 +86,48 @@ async def test_model_manager_skips_legacy_space_sync_in_cloud_runtime(mock_app_f
     app.workspace_service.get_local_execution_binding.assert_not_awaited()
 
 
+@pytest.mark.asyncio
+async def test_sync_new_models_from_space_creates_rerank_models(mock_app_for_modelmgr):
+    """Space rerank entries are discovered and persisted under the shared provider."""
+    app = mock_app_for_modelmgr
+    provider = persistence_model.ModelProvider(
+        uuid='space-provider',
+        name='LangBot Space',
+        requester='space-chat-completions',
+        base_url='https://api.langbot.cloud/v1',
+        api_keys=['space-key'],
+    )
+    app.persistence_mgr.execute_async = AsyncMock(return_value=_make_mock_result([provider], first_item=provider))
+    app.space_service.get_models = AsyncMock(
+        return_value=[
+            SimpleNamespace(
+                uuid='rerank-model-uuid',
+                model_id='Qwen3-Reranker-8B',
+                category='rerank',
+                featured_order=10,
+            )
+        ]
+    )
+    app.llm_model_service.get_llm_models = AsyncMock(return_value=[])
+    app.embedding_models_service.get_embedding_models = AsyncMock(return_value=[])
+    app.rerank_models_service = AsyncMock()
+    app.rerank_models_service.get_rerank_models = AsyncMock(return_value=[])
+
+    model_mgr = ModelManager(app)
+    await model_mgr.sync_new_models_from_space()
+
+    app.rerank_models_service.create_rerank_model.assert_awaited_once_with(
+        {
+            'uuid': 'rerank-model-uuid',
+            'name': 'Qwen3-Reranker-8B',
+            'provider_uuid': 'space-provider',
+            'extra_args': {},
+            'prefered_ranking': 10,
+        },
+        preserve_uuid=True,
+    )
+
+
 # ============================================================================
 # Model Loading Tests
 # ============================================================================
@@ -1067,4 +1109,4 @@ def test_provider_not_found_error_str():
     error = provider_errors.ProviderNotFoundError('test-provider')
 
     assert str(error) == 'Provider test-provider not found'
-    assert error.provider_name == 'test-provider'
+    assert error.provider_name == 'test-provider'