refactor: improve type safety and test patterns

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

src/crewai/crew.py

@@ -4,6 +4,7 @@ import uuid
 import warnings
 from concurrent.futures import Future
 from hashlib import md5
+from crewai.llm import LLM
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 from pydantic import (
@@ -1075,19 +1076,36 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        openai_model_name: Optional[str] = None,
+        llm: Union[str, LLM],
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
-        """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
+        """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures.
+        
+        Args:
+            n_iterations: Number of test iterations to run
+            llm: Language model to use for evaluation. Can be either a model name string (e.g. "gpt-4") 
+                 or an LLM instance for custom implementations
+            inputs: Optional dictionary of input values to use for task execution
+            
+        Example:
+            ```python
+            # Using model name string
+            crew.test(n_iterations=3, llm="gpt-4")
+            
+            # Using custom LLM implementation
+            custom_llm = LLM(model="custom-model")
+            crew.test(n_iterations=3, llm=custom_llm)
+            ```
+        """
         test_crew = self.copy()
 
         self._test_execution_span = test_crew._telemetry.test_execution_span(
             test_crew,
             n_iterations,
             inputs,
-            openai_model_name,  # type: ignore[arg-type]
+            str(llm) if isinstance(llm, LLM) else llm,
-        )  # type: ignore[arg-type]
+        )
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, llm)
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,10 +1,16 @@
 from collections import defaultdict
+from typing import Any, Dict, List, Optional, TypeVar, Union
+from typing import DefaultDict  # Separate import to avoid circular imports
 
 from pydantic import BaseModel, Field
 from rich.box import HEAVY_EDGE
 from rich.console import Console
 from rich.table import Table
 
+from crewai.llm import LLM
+
+T = TypeVar('T', bound=LLM)
+
 from crewai.agent import Agent
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
@@ -28,14 +34,47 @@ class CrewEvaluator:
         iteration (int): The current iteration of the evaluation.
     """
 
-    tasks_scores: defaultdict = defaultdict(list)
+    _tasks_scores: DefaultDict[int, List[float]] = Field(
-    run_execution_times: defaultdict = defaultdict(list)
+        default_factory=lambda: defaultdict(list))
+    _run_execution_times: DefaultDict[int, List[float]] = Field(
+        default_factory=lambda: defaultdict(list))
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    @property
+    def tasks_scores(self) -> DefaultDict[int, List[float]]:
+        return self._tasks_scores
+
+    @tasks_scores.setter
+    def tasks_scores(self, value: Dict[int, List[float]]) -> None:
+        self._tasks_scores = defaultdict(list, value)
+
+    @property
+    def run_execution_times(self) -> DefaultDict[int, List[float]]:
+        return self._run_execution_times
+
+    @run_execution_times.setter
+    def run_execution_times(self, value: Dict[int, List[float]]) -> None:
+        self._run_execution_times = defaultdict(list, value)
+
+    def __init__(self, crew, llm: Union[str, T]):
+        """Initialize the CrewEvaluator.
+        
+        Args:
+            crew: The Crew instance to evaluate
+            llm: Language model to use for evaluation. Can be either a model name string
+                or an LLM instance for custom implementations
+                
+        Raises:
+            ValueError: If llm is None or invalid
+        """
+        if not llm:
+            raise ValueError("Invalid LLM configuration")
+            
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = LLM(model=llm) if isinstance(llm, str) else llm
         self._telemetry = Telemetry()
+        self._tasks_scores = defaultdict(list)
+        self._run_execution_times = defaultdict(list)
         self._setup_for_evaluating()
 
     def _setup_for_evaluating(self) -> None:
@@ -51,7 +90,7 @@ class CrewEvaluator:
             ),
             backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
             verbose=False,
-            llm=self.openai_model_name,
+            llm=self.llm,
         )
 
     def _evaluation_task(
@@ -181,11 +220,19 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task._execution_time,
-                self.openai_model_name,
+                self._get_llm_identifier(),
             )
-            self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
+            self._tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
-            self.run_execution_times[self.iteration].append(
+            self._run_execution_times[self.iteration].append(
                 current_task._execution_time
             )
         else:
             raise ValueError("Evaluation result is not in the expected format")
+
+    def _get_llm_identifier(self) -> str:
+        """Get a string identifier for the LLM instance.
+        
+        Returns:
+            String representation of the LLM for telemetry
+        """
+        return str(self.llm) if isinstance(self.llm, LLM) else self.llm

tests/crew_test.py

@@ -10,6 +10,7 @@ import instructor
 import pydantic_core
 import pytest
 
+from crewai.llm import LLM
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -1123,7 +1124,7 @@ 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."""
 
@@ -2828,7 +2829,7 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     copy_mock.return_value = crew
 
     n_iterations = 2
-    crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
+    crew.test(n_iterations, llm="gpt-4o-mini", inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
     kickoff_mock.assert_has_calls(
@@ -2844,6 +2845,32 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
         ]
     )
 
+@mock.patch("crewai.crew.CrewEvaluator")
+@mock.patch("crewai.crew.Crew.copy")
+@mock.patch("crewai.crew.Crew.kickoff")
+def test_crew_testing_with_custom_llm(kickoff_mock, copy_mock, crew_evaluator):
+    task = Task(
+        description="Test task",
+        expected_output="Test output",
+        agent=researcher,
+    )
+    crew = Crew(agents=[researcher], tasks=[task])
+    copy_mock.return_value = crew
+    custom_llm = LLM(model="gpt-4")
+    
+    crew.test(2, llm=custom_llm, inputs={"topic": "AI"})
+    
+    kickoff_mock.assert_has_calls([
+        mock.call(inputs={"topic": "AI"}),
+        mock.call(inputs={"topic": "AI"})
+    ])
+    crew_evaluator.assert_has_calls([
+        mock.call(crew, custom_llm),
+        mock.call().set_iteration(1),
+        mock.call().set_iteration(2),
+        mock.call().print_crew_evaluation_result(),
+    ])
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_verbose_manager_agent():
@@ -3125,4 +3152,4 @@ 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

@@ -2,6 +2,7 @@ from unittest import mock
 
 import pytest
 
+from crewai.llm import LLM
 from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.task import Task
@@ -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()
@@ -47,6 +48,25 @@ class TestCrewEvaluator:
         assert agent.verbose is False
         assert agent.llm.model == "gpt-4o-mini"
 
+    @pytest.mark.parametrize("llm_input,expected_model", [
+        (LLM(model="gpt-4"), "gpt-4"),
+        ("gpt-4", "gpt-4"),
+    ])
+    def test_evaluator_with_llm_types(self, crew_planner, llm_input, expected_model):
+        evaluator = CrewEvaluator(crew_planner.crew, llm_input)
+        agent = evaluator._evaluator_agent()
+        assert agent.llm.model == expected_model
+        
+    def test_evaluator_with_invalid_llm(self, crew_planner):
+        with pytest.raises(ValueError, match="Invalid LLM configuration"):
+            CrewEvaluator(crew_planner.crew, None)
+
+    def test_evaluator_with_string_llm(self, crew_planner):
+        evaluator = CrewEvaluator(crew_planner.crew, "gpt-4")
+        agent = evaluator._evaluator_agent()
+        assert isinstance(agent.llm, LLM)
+        assert agent.llm.model == "gpt-4"
+
     def test_evaluation_task(self, crew_planner):
         evaluator_agent = Agent(
             role="Evaluator Agent",