feat: add tests

docs/core-concepts/Testing.md

@@ -1,41 +0,0 @@
----
-title: crewAI Testing
-description: Learn how to test your crewAI Crew and evaluate their performance.
----
-
-## Introduction
-
-Testing is a crucial part of the development process, and it is essential to ensure that your crew is performing as expected. And with crewAI, you can easily test your crew and evaluate its performance using the built-in testing capabilities.
-
-### Using the Testing Feature
-
-We added the CLI command `crewai test` to make it easy to test your crew. This command will run your crew for a specified number of iterations and provide detailed performance metrics.
-The parameters are `n_iterations` and `model` which are optional and default to 2 and `gpt-4o-mini` respectively. For now the only provider available is OpenAI.
-
-```bash
-crewai test
-```
-
-If you want to run more iterations or use a different model, you can specify the parameters like this:
-
-```bash
-crewai test --n_iterations 5 --model gpt-4o
-```
-
-What happens when you run the `crewai test` command is that the crew will be executed for the specified number of iterations, and the performance metrics will be displayed at the end of the run.
-
-A table of scores at the end will show the performance of the crew in terms of the following metrics:
-```
-                Task Scores
-          (1-10 Higher is better)
-┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
-┃ Tasks/Crew ┃ Run 1 ┃ Run 2 ┃ Avg. Total ┃
-┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
-│ Task 1     │ 10.0  │ 9.0   │ 9.5        │
-│ Task 2     │ 9.0   │ 9.0   │ 9.0        │
-│ Crew       │ 9.5   │ 9.0   │ 9.2        │
-└────────────┴───────┴───────┴────────────┘
-```
-
-The example above shows the test results for two runs of the crew with two tasks, with the average total score for each task and the crew as a whole.
-

mkdocs.yml

@@ -129,7 +129,6 @@ nav:
     - Training: 'core-concepts/Training-Crew.md'
     - Memory: 'core-concepts/Memory.md'
     - Planning: 'core-concepts/Planning.md'
-    - Testing: 'core-concepts/Testing.md'
     - Using LangChain Tools: 'core-concepts/Using-LangChain-Tools.md'
     - Using LlamaIndex Tools: 'core-concepts/Using-LlamaIndex-Tools.md'
   - How to Guides:

src/crewai/cli/templates/main.py

@@ -48,7 +48,7 @@ def test():
         "topic": "AI LLMs"
     }
     try:
-        {{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), openai_model_name=sys.argv[2], inputs=inputs)
+        {{crew_name}}Crew().crew().test(n_iterations=int(sys.argv[1]), model=sys.argv[2], inputs=inputs)
 
     except Exception as e:
         raise Exception(f"An error occurred while replaying the crew: {e}")

src/crewai/crew.py

@@ -37,7 +37,6 @@ from crewai.utilities.constants import (
     TRAINED_AGENTS_DATA_FILE,
     TRAINING_DATA_FILE,
 )
-from crewai.utilities.evaluators.crew_evaluator_handler import CrewEvaluator
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.formatter import (
     aggregate_raw_outputs_from_task_outputs,
@@ -271,6 +270,20 @@ class Crew(BaseModel):
 
         return self
 
+    @model_validator(mode="after")
+    def check_tasks_in_hierarchical_process_not_async(self):
+        """Validates that the tasks in hierarchical process are not flagged with async_execution."""
+        if self.process == Process.hierarchical:
+            for task in self.tasks:
+                if task.async_execution:
+                    raise PydanticCustomError(
+                        "async_execution_in_hierarchical_process",
+                        "Hierarchical process error: Tasks cannot be flagged with async_execution.",
+                        {},
+                    )
+
+        return self
+
     @model_validator(mode="after")
     def validate_end_with_at_most_one_async_task(self):
         """Validates that the crew ends with at most one asynchronous task."""
@@ -593,7 +606,7 @@ class Crew(BaseModel):
     def _run_hierarchical_process(self) -> CrewOutput:
         """Creates and assigns a manager agent to make sure the crew completes the tasks."""
         self._create_manager_agent()
-        return self._execute_tasks(self.tasks)
+        return self._execute_tasks(self.tasks, self.manager_agent)
 
     def _create_manager_agent(self):
         i18n = I18N(prompt_file=self.prompt_file)
@@ -617,6 +630,7 @@ class Crew(BaseModel):
     def _execute_tasks(
         self,
         tasks: List[Task],
+        manager: Optional[BaseAgent] = None,
         start_index: Optional[int] = 0,
         was_replayed: bool = False,
     ) -> CrewOutput:
@@ -644,13 +658,13 @@ class Crew(BaseModel):
                         last_sync_output = task.output
                 continue
 
-            agent_to_use = self._get_agent_to_use(task)
+            agent_to_use = self._get_agent_to_use(task, manager)
             if agent_to_use is None:
                 raise ValueError(
                     f"No agent available for task: {task.description}. Ensure that either the task has an assigned agent or a manager agent is provided."
                 )
 
-            self._prepare_agent_tools(task)
+            self._prepare_agent_tools(task, manager)
             self._log_task_start(task, agent_to_use.role)
 
             if isinstance(task, ConditionalTask):
@@ -716,18 +730,20 @@ class Crew(BaseModel):
             return skipped_task_output
         return None
 
-    def _prepare_agent_tools(self, task: Task):
+    def _prepare_agent_tools(self, task: Task, manager: Optional[BaseAgent]):
         if self.process == Process.hierarchical:
-            if self.manager_agent:
-                self._update_manager_tools(task)
+            if manager:
+                self._update_manager_tools(task, manager)
             else:
                 raise ValueError("Manager agent is required for hierarchical process.")
         elif task.agent and task.agent.allow_delegation:
             self._add_delegation_tools(task)
 
-    def _get_agent_to_use(self, task: Task) -> Optional[BaseAgent]:
+    def _get_agent_to_use(
+        self, task: Task, manager: Optional[BaseAgent]
+    ) -> Optional[BaseAgent]:
         if self.process == Process.hierarchical:
-            return self.manager_agent
+            return manager
         return task.agent
 
     def _add_delegation_tools(self, task: Task):
@@ -763,14 +779,11 @@ class Crew(BaseModel):
         if self.output_log_file:
             self._file_handler.log(agent=role, task=task.description, status="started")
 
-    def _update_manager_tools(self, task: Task):
-        if self.manager_agent:
-            if task.agent:
-                self.manager_agent.tools = task.agent.get_delegation_tools([task.agent])
-            else:
-                self.manager_agent.tools = self.manager_agent.get_delegation_tools(
-                    self.agents
-                )
+    def _update_manager_tools(self, task: Task, manager: BaseAgent):
+        if task.agent:
+            manager.tools = task.agent.get_delegation_tools([task.agent])
+        else:
+            manager.tools = manager.get_delegation_tools(self.agents)
 
     def _get_context(self, task: Task, task_outputs: List[TaskOutput]):
         context = (
@@ -869,7 +882,7 @@ class Crew(BaseModel):
             self.tasks[i].output = task_output
 
         self._logging_color = "bold_blue"
-        result = self._execute_tasks(self.tasks, start_index, True)
+        result = self._execute_tasks(self.tasks, self.manager_agent, start_index, True)
         return result
 
     def copy(self):
@@ -955,19 +968,10 @@ class Crew(BaseModel):
         return total_usage_metrics
 
     def test(
-        self,
-        n_iterations: int,
-        openai_model_name: str,
-        inputs: Optional[Dict[str, Any]] = None,
+        self, n_iterations: int, model: str, inputs: Optional[Dict[str, Any]] = None
     ) -> None:
-        """Test and evaluate the Crew with the given inputs for n iterations."""
-        evaluator = CrewEvaluator(self, openai_model_name)
-
-        for i in range(1, n_iterations + 1):
-            evaluator.set_iteration(i)
-            self.kickoff(inputs=inputs)
-
-        evaluator.print_crew_evaluation_result()
+        """Test the crew with the given inputs."""
+        pass
 
     def __repr__(self):
         return f"Crew(id={self.id}, process={self.process}, number_of_agents={len(self.agents)}, number_of_tasks={len(self.tasks)})"

src/crewai/utilities/crew_pydantic_output_parser.py

@@ -1,5 +1,5 @@
 import json
-from typing import Any, List, Type
+from typing import Any, List, Type, Union
 
 import regex
 from langchain.output_parsers import PydanticOutputParser
@@ -7,24 +7,29 @@ from langchain_core.exceptions import OutputParserException
 from langchain_core.outputs import Generation
 from langchain_core.pydantic_v1 import ValidationError
 from pydantic import BaseModel
+from pydantic.v1 import BaseModel as V1BaseModel
 
 
 class CrewPydanticOutputParser(PydanticOutputParser):
     """Parses the text into pydantic models"""
 
-    pydantic_object: Type[BaseModel]
+    pydantic_object: Union[Type[BaseModel], Type[V1BaseModel]]
 
-    def parse_result(self, result: List[Generation]) -> Any:
+    def parse_result(self, result: List[Generation], *, partial: bool = False) -> Any:
         result[0].text = self._transform_in_valid_json(result[0].text)
 
         # Treating edge case of function calling llm returning the name instead of tool_name
         json_object = json.loads(result[0].text)
-        if "tool_name" not in json_object:
-            json_object["tool_name"] = json_object.get("name", "")
+        json_object["tool_name"] = (
+            json_object["name"]
+            if "tool_name" not in json_object
+            else json_object["tool_name"]
+        )
         result[0].text = json.dumps(json_object)
 
+        json_object = super().parse_result(result)
         try:
-            return self.pydantic_object.model_validate(json_object)
+            return self.pydantic_object.parse_obj(json_object)
         except ValidationError as e:
             name = self.pydantic_object.__name__
             msg = f"Failed to parse {name} from completion {json_object}. Got: {e}"

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,149 +0,0 @@
-from collections import defaultdict
-
-from langchain_openai import ChatOpenAI
-from pydantic import BaseModel, Field
-from rich.console import Console
-from rich.table import Table
-
-from crewai.agent import Agent
-from crewai.task import Task
-from crewai.tasks.task_output import TaskOutput
-
-
-class TaskEvaluationPydanticOutput(BaseModel):
-    quality: float = Field(
-        description="A score from 1 to 10 evaluating on completion, quality, and overall performance from the task_description and task_expected_output to the actual Task Output."
-    )
-
-
-class CrewEvaluator:
-    """
-    A class to evaluate the performance of the agents in the crew based on the tasks they have performed.
-
-    Attributes:
-        crew (Crew): The crew of agents to evaluate.
-        openai_model_name (str): The model to use for evaluating the performance of the agents (for now ONLY OpenAI accepted).
-        tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
-        iteration (int): The current iteration of the evaluation.
-    """
-
-    tasks_scores: defaultdict = defaultdict(list)
-    iteration: int = 0
-
-    def __init__(self, crew, openai_model_name: str):
-        self.crew = crew
-        self.openai_model_name = openai_model_name
-        self._setup_for_evaluating()
-
-    def _setup_for_evaluating(self) -> None:
-        """Sets up the crew for evaluating."""
-        for task in self.crew.tasks:
-            task.callback = self.evaluate
-
-    def set_iteration(self, iteration: int) -> None:
-        self.iteration = iteration
-
-    def _evaluator_agent(self):
-        return Agent(
-            role="Task Execution Evaluator",
-            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."
-            ),
-            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=ChatOpenAI(model=self.openai_model_name),
-        )
-
-    def _evaluation_task(
-        self, evaluator_agent: Agent, task_to_evaluate: Task, task_output: str
-    ) -> Task:
-        return 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."
-                f"task_description: {task_to_evaluate.description} "
-                f"task_expected_output: {task_to_evaluate.expected_output} "
-                f"agent: {task_to_evaluate.agent.role if task_to_evaluate.agent else None} "
-                f"agent_goal: {task_to_evaluate.agent.goal if task_to_evaluate.agent else None} "
-                f"Task Output: {task_output}"
-            ),
-            expected_output="Evaluation Score from 1 to 10 based on the performance of the agents on the tasks",
-            agent=evaluator_agent,
-            output_pydantic=TaskEvaluationPydanticOutput,
-        )
-
-    def print_crew_evaluation_result(self) -> None:
-        """
-        Prints the evaluation result of the crew in a table.
-        A Crew with 2 tasks using the command crewai test -n 2
-        will output the following table:
-
-                        Task Scores
-                    (1-10 Higher is better)
-            ┏━━━━━━━━━━━━┳━━━━━━━┳━━━━━━━┳━━━━━━━━━━━━┓
-            ┃ Tasks/Crew ┃ Run 1 ┃ Run 2 ┃ Avg. Total ┃
-            ┡━━━━━━━━━━━━╇━━━━━━━╇━━━━━━━╇━━━━━━━━━━━━┩
-            │ Task 1     │ 10.0  │ 9.0   │ 9.5        │
-            │ Task 2     │ 9.0   │ 9.0   │ 9.0        │
-            │ Crew       │ 9.5   │ 9.0   │ 9.2        │
-            └────────────┴───────┴───────┴────────────┘
-        """
-        task_averages = [
-            sum(scores) / len(scores) for scores in zip(*self.tasks_scores.values())
-        ]
-        crew_average = sum(task_averages) / len(task_averages)
-
-        # Create a table
-        table = Table(title="Tasks Scores \n (1-10 Higher is better)")
-
-        # Add columns for the table
-        table.add_column("Tasks/Crew")
-        for run in range(1, len(self.tasks_scores) + 1):
-            table.add_column(f"Run {run}")
-        table.add_column("Avg. Total")
-
-        # Add rows for each task
-        for task_index in range(len(task_averages)):
-            task_scores = [
-                self.tasks_scores[run][task_index]
-                for run in range(1, len(self.tasks_scores) + 1)
-            ]
-            avg_score = task_averages[task_index]
-            table.add_row(
-                f"Task {task_index + 1}", *map(str, task_scores), f"{avg_score:.1f}"
-            )
-
-        # Add a row for the crew average
-        crew_scores = [
-            sum(self.tasks_scores[run]) / len(self.tasks_scores[run])
-            for run in range(1, len(self.tasks_scores) + 1)
-        ]
-        table.add_row("Crew", *map(str, crew_scores), f"{crew_average:.1f}")
-
-        # Display the table in the terminal
-        console = Console()
-        console.print(table)
-
-    def evaluate(self, task_output: TaskOutput):
-        """Evaluates the performance of the agents in the crew based on the tasks they have performed."""
-        current_task = None
-        for task in self.crew.tasks:
-            if task.description == task_output.description:
-                current_task = task
-                break
-
-        if not current_task or not task_output:
-            raise ValueError(
-                "Task to evaluate and task output are required for evaluation"
-            )
-
-        evaluator_agent = self._evaluator_agent()
-        evaluation_task = self._evaluation_task(
-            evaluator_agent, current_task, task_output.raw
-        )
-
-        evaluation_result = evaluation_task.execute_sync()
-
-        if isinstance(evaluation_result.pydantic, TaskEvaluationPydanticOutput):
-            self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
-        else:
-            raise ValueError("Evaluation result is not in the expected format")

src/crewai/utilities/evaluators/task_evaluator.py

@@ -66,11 +66,11 @@ class TaskEvaluator:
             "- Entities extracted from the task output, if any, their type, description, and relationships"
         )
 
-        instructions = "Convert all responses into valid JSON output."
+        instructions = "I'm gonna convert this raw text into valid JSON."
 
         if not self._is_gpt(self.llm):
             model_schema = PydanticSchemaParser(model=TaskEvaluation).get_schema()
-            instructions = f"{instructions}\n\nReturn only valid JSON with the following schema:\n```json\n{model_schema}\n```"
+            instructions = f"{instructions}\n\nThe json should have the following structure, with the following keys:\n{model_schema}"
 
         converter = Converter(
             llm=self.llm,

src/crewai/utilities/pydantic_schema_parser.py

@@ -16,13 +16,11 @@ class PydanticSchemaParser(BaseModel):
         return self._get_model_schema(self.model)
 
     def _get_model_schema(self, model, depth=0) -> str:
-        indent = "    " * depth
-        lines = [f"{indent}{{"]
+        lines = []
         for field_name, field in model.model_fields.items():
             field_type_str = self._get_field_type(field, depth + 1)
-            lines.append(f"{indent}    {field_name}: {field_type_str},")
-        lines[-1] = lines[-1].rstrip(",")  # Remove trailing comma from last item
-        lines.append(f"{indent}}}")
+            lines.append(f"{' ' * 4 * depth}- {field_name}: {field_type_str}")
+
         return "\n".join(lines)
 
     def _get_field_type(self, field, depth) -> str:
@@ -37,6 +35,6 @@ class PydanticSchemaParser(BaseModel):
             else:
                 return f"List[{list_item_type.__name__}]"
         elif issubclass(field_type, BaseModel):
-            return self._get_model_schema(field_type, depth)
+            return f"\n{self._get_model_schema(field_type, depth)}"
         else:
             return field_type.__name__

tests/crew_test.py

@@ -8,7 +8,6 @@ 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
@@ -1356,66 +1355,28 @@ def test_hierarchical_crew_creation_tasks_with_agents():
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_crew_creation_tasks_with_async_execution():
-    """
-    Agents are not required for tasks in a hierarchical process but sometimes they are still added
-    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
-    """
     from langchain_openai import ChatOpenAI
 
     task = Task(
-        description="Write one amazing paragraph about AI.",
-        expected_output="A single paragraph with 4 sentences.",
-        agent=writer,
-        async_execution=True,
+        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.",
+        async_execution=True,  # should throw an error
     )
 
-    crew = Crew(
-        tasks=[task],
-        agents=[writer, researcher, ceo],
-        process=Process.hierarchical,
-        manager_llm=ChatOpenAI(model="gpt-4o"),
+    with pytest.raises(pydantic_core._pydantic_core.ValidationError) as exec_info:
+        Crew(
+            tasks=[task],
+            agents=[researcher],
+            process=Process.hierarchical,
+            manager_llm=ChatOpenAI(model="gpt-4o"),
+        )
+
+    assert (
+        exec_info.value.errors()[0]["type"] == "async_execution_in_hierarchical_process"
     )
-
-    crew.kickoff()
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert crew.manager_agent.tools[0].description.startswith(
-        "Delegate a specific task to one of the following coworkers: Senior Writer\n"
-    )
-
-
-@pytest.mark.vcr(filter_headers=["authorization"])
-def test_hierarchical_crew_creation_tasks_with_sync_last():
-    """
-    Agents are not required for tasks in a hierarchical process but sometimes they are still added
-    This test makes sure that the manager still delegates the task to the agent even if the agent is passed in the task
-    """
-    from langchain_openai import ChatOpenAI
-
-    task = Task(
-        description="Write one amazing paragraph about AI.",
-        expected_output="A single paragraph with 4 sentences.",
-        agent=writer,
-        async_execution=True,
-    )
-    task2 = Task(
-        description="Write one amazing paragraph about AI.",
-        expected_output="A single paragraph with 4 sentences.",
-        async_execution=False,
-    )
-
-    crew = Crew(
-        tasks=[task, task2],
-        agents=[writer, researcher, ceo],
-        process=Process.hierarchical,
-        manager_llm=ChatOpenAI(model="gpt-4o"),
-    )
-
-    crew.kickoff()
-    assert crew.manager_agent is not None
-    assert crew.manager_agent.tools is not None
-    assert crew.manager_agent.tools[0].description.startswith(
-        "Delegate a specific task to one of the following coworkers: Senior Writer, Researcher, CEO\n"
+    assert (
+        "Hierarchical process error: Tasks cannot be flagged with async_execution."
+        in exec_info.value.errors()[0]["msg"]
     )
 
 
@@ -2538,34 +2499,3 @@ 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

@@ -1,113 +0,0 @@
-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]

tests/utilities/evaluators/test_task_evaluator.py

@@ -56,7 +56,8 @@ def test_evaluate_training_data(converter_mock):
                 "based on the human feedback\n",
                 model=TrainingTaskEvaluation,
                 instructions="I'm gonna convert this raw text into valid JSON.\n\nThe json should have the "
-                "following structure, with the following keys:\n{\n    suggestions: List[str],\n    quality: float,\n    final_summary: str\n}",
+                "following structure, with the following keys:\n- suggestions: List[str]\n- "
+                "quality: float\n- final_summary: str",
             ),
             mock.call().to_pydantic(),
         ]