feat: enable custom LLM support for Crew.test()

- Add llm parameter to Crew.test() that accepts string or LLM instance
- Maintain backward compatibility with openai_model_name parameter
- Update CrewEvaluator to handle any LLM implementation
- Improve docstrings and type hints

Fixes #2080

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

src/crewai/crew.py

@@ -1147,20 +1147,35 @@ class Crew(BaseModel):
 
     def test(
         self,
-        n_iterations: int,
+        n_iterations: int = 1,
         openai_model_name: Optional[str] = None,
+        llm: Optional[Union[str, LLM]] = None,
         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.
+
+        Args:
+            n_iterations: Number of iterations to run the test
+            openai_model_name: OpenAI model name to use for evaluation (deprecated)
+            llm: LLM instance or model name to use for evaluation
+            inputs: Optional dictionary of inputs to pass to the crew
+        """
+        if not llm and not openai_model_name:
+            raise ValueError("Either llm or openai_model_name must be provided")
+        
+        model_to_use = llm or openai_model_name
+        if isinstance(model_to_use, str):
+            model_to_use = LLM(model=model_to_use)
+        
         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(model_to_use.model),  # type: ignore[arg-type]
         )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, model_to_use)
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,4 +1,5 @@
 from collections import defaultdict
+from typing import Union
 
 from pydantic import BaseModel, Field
 from rich.box import HEAVY_EDGE
@@ -6,6 +7,7 @@ from rich.console import Console
 from rich.table import Table
 
 from crewai.agent import Agent
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
@@ -32,9 +34,12 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, llm: Union[str, LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        if isinstance(llm, str):
+            self.llm = LLM(model=llm)
+        else:
+            self.llm = llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +56,7 @@ 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(