feat: add crew Testing/Evaluating feature (#998)

* feat: add crew Testing/evalauting feature

* feat: add docs and add unit test

* feat: improve testing output table

* feat: add tests

* feat: fix type checking issue

* feat: add raise ValueError when testing if output is not the expected

* docs: add docs for Testing

* feat: improve tests and fix some issue

* feat: back to sync

* feat: change opdeai model

* feat: fix test

tests/crew_test.py

@@ -8,6 +8,7 @@ from unittest.mock import MagicMock, patch
 
 import pydantic_core
 import pytest
+
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -2499,3 +2500,34 @@ def test_conditional_should_execute():
         assert condition_mock.call_count == 1
         assert condition_mock() is True
         assert mock_execute_sync.call_count == 2
+
+
+@mock.patch("crewai.crew.CrewEvaluator")
+@mock.patch("crewai.crew.Crew.kickoff")
+def test_crew_testing_function(mock_kickoff, crew_evaluator):
+    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.",
+        expected_output="5 bullet points with a paragraph for each idea.",
+        agent=researcher,
+    )
+
+    crew = Crew(
+        agents=[researcher],
+        tasks=[task],
+    )
+    n_iterations = 2
+    crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
+
+    assert len(mock_kickoff.mock_calls) == n_iterations
+    mock_kickoff.assert_has_calls(
+        [mock.call(inputs={"topic": "AI"}), mock.call(inputs={"topic": "AI"})]
+    )
+
+    crew_evaluator.assert_has_calls(
+        [
+            mock.call(crew, "gpt-4o-mini"),
+            mock.call().set_iteration(1),
+            mock.call().set_iteration(2),
+            mock.call().print_crew_evaluation_result(),
+        ]
+    )

tests/utilities/evaluators/test_crew_evaluator_handler.py

@@ -0,0 +1,113 @@
+from unittest import mock
+
+import pytest
+
+from crewai.agent import Agent
+from crewai.crew import Crew
+from crewai.task import Task
+from crewai.tasks.task_output import TaskOutput
+from crewai.utilities.evaluators.crew_evaluator_handler import (
+    CrewEvaluator,
+    TaskEvaluationPydanticOutput,
+)
+
+
+class TestCrewEvaluator:
+    @pytest.fixture
+    def crew_planner(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])
+
+        return CrewEvaluator(crew, openai_model_name="gpt-4o-mini")
+
+    def test_setup_for_evaluating(self, crew_planner):
+        crew_planner._setup_for_evaluating()
+        assert crew_planner.crew.tasks[0].callback == crew_planner.evaluate
+
+    def test_set_iteration(self, crew_planner):
+        crew_planner.set_iteration(1)
+        assert crew_planner.iteration == 1
+
+    def test_evaluator_agent(self, crew_planner):
+        agent = crew_planner._evaluator_agent()
+        assert agent.role == "Task Execution Evaluator"
+        assert (
+            agent.goal
+            == "Your goal is to evaluate the performance of the agents in the crew based on the tasks they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
+        )
+        assert (
+            agent.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"
+        )
+        assert agent.verbose is False
+        assert agent.llm.model_name == "gpt-4o-mini"
+
+    def test_evaluation_task(self, crew_planner):
+        evaluator_agent = Agent(
+            role="Evaluator Agent",
+            goal="Evaluate the performance of the agents in the crew",
+            backstory="Master in Evaluation",
+        )
+        task_to_evaluate = Task(
+            description="Task 1",
+            expected_output="Output 1",
+            agent=Agent(role="Agent 1", goal="Goal 1", backstory="Backstory 1"),
+        )
+        task_output = "Task Output 1"
+        task = crew_planner._evaluation_task(
+            evaluator_agent, task_to_evaluate, task_output
+        )
+
+        assert task.description.startswith(
+            "Based on the task description and the expected output, compare and evaluate the performance of the agents in the crew based on the Task Output they have performed using score from 1 to 10 evaluating on completion, quality, and overall performance."
+        )
+
+        assert task.agent == evaluator_agent
+        assert (
+            task.description
+            == "Based on the task description and the expected output, compare and evaluate "
+            "the performance of the agents in the crew based on the Task Output they have "
+            "performed using score from 1 to 10 evaluating on completion, quality, and overall "
+            "performance.task_description: Task 1 task_expected_output: Output 1 "
+            "agent: Agent 1 agent_goal: Goal 1 Task Output: Task Output 1"
+        )
+
+    @mock.patch("crewai.utilities.evaluators.crew_evaluator_handler.Console")
+    @mock.patch("crewai.utilities.evaluators.crew_evaluator_handler.Table")
+    def test_print_crew_evaluation_result(self, table, console, crew_planner):
+        crew_planner.tasks_scores = {
+            1: [10, 9, 8],
+            2: [9, 8, 7],
+        }
+
+        crew_planner.print_crew_evaluation_result()
+
+        table.assert_has_calls(
+            [
+                mock.call(title="Tasks Scores \n (1-10 Higher is better)"),
+                mock.call().add_column("Tasks/Crew"),
+                mock.call().add_column("Run 1"),
+                mock.call().add_column("Run 2"),
+                mock.call().add_column("Avg. Total"),
+                mock.call().add_row("Task 1", "10", "9", "9.5"),
+                mock.call().add_row("Task 2", "9", "8", "8.5"),
+                mock.call().add_row("Task 3", "8", "7", "7.5"),
+                mock.call().add_row("Crew", "9.0", "8.0", "8.5"),
+            ]
+        )
+        console.assert_has_calls([mock.call(), mock.call().print(table())])
+
+    def test_evaluate(self, crew_planner):
+        task_output = TaskOutput(
+            description="Task 1", agent=str(crew_planner.crew.agents[0])
+        )
+
+        with mock.patch.object(Task, "execute_sync") as execute:
+            execute().pydantic = TaskEvaluationPydanticOutput(quality=9.5)
+            crew_planner.evaluate(task_output)
+            assert crew_planner.tasks_scores[0] == [9.5]