test: fix test assertions for llm parameter

Co-Authored-By: Joe Moura <joao@crewai.com>

tests/crew_test.py

@@ -300,6 +300,15 @@ def test_hierarchical_process():
     )
 
 
+@mock.patch("crewai.crew.CrewEvaluator")
+@mock.patch("crewai.crew.Crew.copy")
+def test_crew_test_backward_compatibility(mock_copy, mock_evaluator):
+    crew = Crew(agents=[researcher], tasks=[Task(description="test", agent=researcher)])
+    crew.test(2, openai_model_name="gpt-4")
+    mock_evaluator.assert_called_once()
+    _, kwargs = mock_evaluator.call_args
+    assert kwargs["llm"] == "gpt-4"
+
 def test_manager_llm_requirement_for_hierarchical_process():
     task = Task(
         description="Come up with a list of 5 interesting ideas to explore for an article, then write one amazing paragraph highlight for each idea that showcases how good an article about this topic could be. Return the list of ideas with their paragraph and your notes.",
@@ -1123,7 +1132,7 @@ def test_kickoff_for_each_empty_input():
     assert results == []
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr(filter_headeruvs=["authorization"])
 def test_kickoff_for_each_invalid_input():
     """Tests if kickoff_for_each raises TypeError for invalid input types."""
 
@@ -3125,4 +3134,4 @@ def test_multimodal_agent_live_image_analysis():
     # Verify we got a meaningful response
     assert isinstance(result.raw, str)
     assert len(result.raw) > 100  # Expecting a detailed analysis
-    assert "error" not in result.raw.lower()  # No error messages in response
+    assert "error" not in result.raw.lower()  # No error messages in response

tests/utilities/evaluators/test_crew_evaluator_handler.py

@@ -4,6 +4,7 @@ import pytest
 
 from crewai.agent import Agent
 from crewai.crew import Crew
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.evaluators.crew_evaluator_handler import (
@@ -23,7 +24,7 @@ class TestCrewEvaluator:
         )
         crew = Crew(agents=[agent], tasks=[task])
 
-        return CrewEvaluator(crew, openai_model_name="gpt-4o-mini")
+        return CrewEvaluator(crew, llm="gpt-4o-mini")
 
     def test_setup_for_evaluating(self, crew_planner):
         crew_planner._setup_for_evaluating()
@@ -46,6 +47,7 @@ class TestCrewEvaluator:
         )
         assert agent.verbose is False
         assert agent.llm.model == "gpt-4o-mini"
+        assert isinstance(agent.llm, LLM)
 
     def test_evaluation_task(self, crew_planner):
         evaluator_agent = Agent(
@@ -131,6 +133,17 @@ class TestCrewEvaluator:
         # Ensure the console prints the table
         console.assert_has_calls([mock.call(), mock.call().print(table())])
 
+    def test_custom_llm_support(self):
+        agent = Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1")
+        task = Task(description="Task 1", expected_output="Output 1", agent=agent)
+        crew = Crew(agents=[agent], tasks=[task])
+        
+        custom_llm = LLM(model="custom-model")
+        evaluator = CrewEvaluator(crew, llm=custom_llm)
+        
+        assert evaluator.llm.model == "custom-model"
+        assert isinstance(evaluator.llm, LLM)
+
     def test_evaluate(self, crew_planner):
         task_output = TaskOutput(
             description="Task 1", agent=str(crew_planner.crew.agents[0])