fix: stabilize 5 CI test failures

- Vertex AI batch cost tests: replace removed gemini-1.5-flash-001 model
  with gemini-2.0-flash-001 in pricing lookups
- MCP test_executes_tool_when_allowed: add server_id and auth_type attrs
  to StubServer to match new _resolve_allowed_mcp_servers_with_ip_filter
- MCP M2M tests: infer oauth2_flow='client_credentials' in
  _execute_with_mcp_client when client_id/client_secret/token_url present
  (NewMCPServerRequest lacks oauth2_flow field)
- Team list test: update mock find_many to filter by team_id per the
  current per-team query pattern in list_team
- Azure DALL-E 3 health check: skip test due to 410 ModelDeprecated

Co-authored-by: yuneng-jiang <yuneng-jiang@users.noreply.github.com>

litellm/proxy/_experimental/mcp_server/rest_endpoints.py

@@ -905,6 +905,12 @@ if MCP_AVAILABLE:
         try:
             client_id, client_secret, scopes = _extract_credentials(request)
 
+            _oauth2_flow = (
+                "client_credentials"
+                if client_id and client_secret and request.token_url
+                else None
+            )
+
             server_model = MCPServer(
                 server_id=request.server_id or "",
                 name=request.alias or request.server_name or "",
@@ -922,6 +928,7 @@ if MCP_AVAILABLE:
                 scopes=scopes,
                 authorization_url=request.authorization_url,
                 registration_url=request.registration_url,
+                oauth2_flow=_oauth2_flow,
             )
 
             stdio_env = global_mcp_server_manager._build_stdio_env(

tests/litellm_utils_tests/test_health_check.py

@@ -83,6 +83,7 @@ async def test_openai_img_gen_health_check():
 # asyncio.run(test_openai_img_gen_health_check())
 
 
+@pytest.mark.skip(reason="Azure DALL-E 3 model deployment is deprecated (410 ModelDeprecated)")
 @pytest.mark.asyncio
 async def test_azure_img_gen_health_check():
     """

tests/test_litellm/proxy/_experimental/mcp_server/test_rest_endpoints.py

@@ -759,12 +759,14 @@ class TestCallToolRestAPI:
             return ["server-1"]
 
         class StubServer:
+            server_id = "server-1"
             alias = "server-1"
             server_name = "server-1"
             name = "stub"
             allowed_tools = None
             mcp_info = {"server_name": "stub"}
             available_on_public_internet = True
+            auth_type = None
 
         stub_server = StubServer()
 

tests/test_litellm/proxy/management_endpoints/test_team_endpoints.py

@@ -6142,8 +6142,18 @@ async def test_list_team_v1_batches_key_queries():
         new_callable=AsyncMock,
         return_value=[],
     ):
-        mock_find_many = AsyncMock(return_value=[key1, key2, key3])
-        mock_prisma_client.db.litellm_verificationtoken.find_many = mock_find_many
+        async def filtered_find_many(**kwargs):
+            where = kwargs.get("where", {})
+            tid = where.get("team_id")
+            if tid == "team-1":
+                return [key1, key2]
+            elif tid == "team-2":
+                return [key3]
+            return [key1, key2, key3]
+
+        mock_prisma_client.db.litellm_verificationtoken.find_many = AsyncMock(
+            side_effect=filtered_find_many
+        )
 
         result = await list_team(
             http_request=mock_request,

tests/test_litellm/proxy/pass_through_endpoints/test_vertex_ai_batch_passthrough.py

@@ -395,7 +395,7 @@ class TestVertexAIBatchCostCalculation:
         ]
 
         total_cost, usage = calculate_vertex_ai_batch_cost_and_usage(
-            responses, model_name="gemini-1.5-flash-001"
+            responses, model_name="gemini-2.0-flash-001"
         )
 
         assert usage.prompt_tokens == 18
@@ -430,7 +430,7 @@ class TestVertexAIBatchCostCalculation:
         ]
 
         total_cost, usage = calculate_vertex_ai_batch_cost_and_usage(
-            responses, model_name="gemini-1.5-flash-001"
+            responses, model_name="gemini-2.0-flash-001"
         )
 
         assert usage.prompt_tokens == 18
@@ -443,7 +443,7 @@ class TestVertexAIBatchCostCalculation:
         from litellm.batches.batch_utils import calculate_vertex_ai_batch_cost_and_usage
 
         total_cost, usage = calculate_vertex_ai_batch_cost_and_usage(
-            [], model_name="gemini-1.5-flash-001"
+            [], model_name="gemini-2.0-flash-001"
         )
 
         assert total_cost == 0.0
@@ -460,7 +460,7 @@ class TestVertexAIBatchCostCalculation:
         ]
 
         total_cost, usage = calculate_vertex_ai_batch_cost_and_usage(
-            responses, model_name="gemini-1.5-flash-001"
+            responses, model_name="gemini-2.0-flash-001"
         )
 
         assert usage.prompt_tokens == 0