fix: add ConfigDict for Pydantic model_config and ClassVar annotations

packages/crewai/tests/experimental/evaluation/metrics/test_base_evaluation_metrics.py

@@ -1,5 +1,7 @@
-import pytest
 from unittest.mock import MagicMock
+
+import pytest
+
 from crewai.agent import Agent
 from crewai.task import Task
 

packages/crewai/tests/experimental/evaluation/metrics/test_goal_metrics.py

@@ -1,11 +1,11 @@
-from unittest.mock import patch, MagicMock
-from tests.experimental.evaluation.metrics.test_base_evaluation_metrics import (
-    BaseEvaluationMetricsTest,
-)
+from unittest.mock import MagicMock, patch
 
 from crewai.experimental.evaluation.base_evaluator import EvaluationScore
 from crewai.experimental.evaluation.metrics.goal_metrics import GoalAlignmentEvaluator
 from crewai.utilities.llm_utils import LLM
+from tests.experimental.evaluation.metrics.test_base_evaluation_metrics import (
+    BaseEvaluationMetricsTest,
+)
 
 
 class TestGoalAlignmentEvaluator(BaseEvaluationMetricsTest):

packages/crewai/tests/experimental/evaluation/metrics/test_reasoning_metrics.py

@@ -1,16 +1,17 @@
-import pytest
-from unittest.mock import patch, MagicMock
-from typing import List, Dict, Any
+from typing import Any
+from unittest.mock import MagicMock, patch
 
-from crewai.tasks.task_output import TaskOutput
+import pytest
+
+from crewai.experimental.evaluation.base_evaluator import EvaluationScore
 from crewai.experimental.evaluation.metrics.reasoning_metrics import (
     ReasoningEfficiencyEvaluator,
 )
+from crewai.tasks.task_output import TaskOutput
+from crewai.utilities.llm_utils import LLM
 from tests.experimental.evaluation.metrics.test_base_evaluation_metrics import (
     BaseEvaluationMetricsTest,
 )
-from crewai.utilities.llm_utils import LLM
-from crewai.experimental.evaluation.base_evaluator import EvaluationScore
 
 
 class TestReasoningEfficiencyEvaluator(BaseEvaluationMetricsTest):
@@ -21,7 +22,7 @@ class TestReasoningEfficiencyEvaluator(BaseEvaluationMetricsTest):
         return output
 
     @pytest.fixture
-    def llm_calls(self) -> List[Dict[str, Any]]:
+    def llm_calls(self) -> list[dict[str, Any]]:
         return [
             {
                 "prompt": "How should I approach this task?",

packages/crewai/tests/experimental/evaluation/metrics/test_semantic_quality_metrics.py

@@ -1,13 +1,13 @@
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 from crewai.experimental.evaluation.base_evaluator import EvaluationScore
 from crewai.experimental.evaluation.metrics.semantic_quality_metrics import (
     SemanticQualityEvaluator,
 )
+from crewai.utilities.llm_utils import LLM
 from tests.experimental.evaluation.metrics.test_base_evaluation_metrics import (
     BaseEvaluationMetricsTest,
 )
-from crewai.utilities.llm_utils import LLM
 
 
 class TestSemanticQualityEvaluator(BaseEvaluationMetricsTest):

packages/crewai/tests/experimental/evaluation/metrics/test_tools_metrics.py

@@ -1,9 +1,9 @@
-from unittest.mock import patch, MagicMock
+from unittest.mock import MagicMock, patch
 
 from crewai.experimental.evaluation.metrics.tools_metrics import (
-    ToolSelectionEvaluator,
     ParameterExtractionEvaluator,
     ToolInvocationEvaluator,
+    ToolSelectionEvaluator,
 )
 from crewai.utilities.llm_utils import LLM
 from tests.experimental.evaluation.metrics.test_base_evaluation_metrics import (

packages/crewai/tests/experimental/evaluation/test_agent_evaluator.py

@@ -1,28 +1,27 @@
 import pytest
 
 from crewai.agent import Agent
-from crewai.task import Task
 from crewai.crew import Crew
-from crewai.experimental.evaluation.agent_evaluator import AgentEvaluator
-from crewai.experimental.evaluation.base_evaluator import AgentEvaluationResult
-from crewai.experimental.evaluation import (
-    GoalAlignmentEvaluator,
-    SemanticQualityEvaluator,
-    ToolSelectionEvaluator,
-    ParameterExtractionEvaluator,
-    ToolInvocationEvaluator,
-    ReasoningEfficiencyEvaluator,
-    MetricCategory,
-    EvaluationScore,
-)
-
+from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.agent_events import (
-    AgentEvaluationStartedEvent,
     AgentEvaluationCompletedEvent,
     AgentEvaluationFailedEvent,
+    AgentEvaluationStartedEvent,
 )
-from crewai.events.event_bus import crewai_event_bus
-from crewai.experimental.evaluation import create_default_evaluator
+from crewai.experimental.evaluation import (
+    EvaluationScore,
+    GoalAlignmentEvaluator,
+    MetricCategory,
+    ParameterExtractionEvaluator,
+    ReasoningEfficiencyEvaluator,
+    SemanticQualityEvaluator,
+    ToolInvocationEvaluator,
+    ToolSelectionEvaluator,
+    create_default_evaluator,
+)
+from crewai.experimental.evaluation.agent_evaluator import AgentEvaluator
+from crewai.experimental.evaluation.base_evaluator import AgentEvaluationResult
+from crewai.task import Task
 
 
 class TestAgentEvaluator:
@@ -100,7 +99,7 @@ class TestAgentEvaluator:
         ]
 
         assert len(agent_evaluator.evaluators) == len(expected_types)
-        for evaluator, expected_type in zip(agent_evaluator.evaluators, expected_types):
+        for evaluator, expected_type in zip(agent_evaluator.evaluators, expected_types, strict=False):
             assert isinstance(evaluator, expected_type)
 
     @pytest.mark.vcr(filter_headers=["authorization"])
@@ -254,8 +253,8 @@ class TestAgentEvaluator:
                 events["failed"] = event
 
             # Create a mock evaluator that will raise an exception
-            from crewai.experimental.evaluation.base_evaluator import BaseEvaluator
             from crewai.experimental.evaluation import MetricCategory
+            from crewai.experimental.evaluation.base_evaluator import BaseEvaluator
 
             class FailingEvaluator(BaseEvaluator):
                 metric_category = MetricCategory.GOAL_ALIGNMENT

packages/crewai/tests/experimental/evaluation/test_experiment_result.py

@@ -1,7 +1,11 @@
-import pytest
 from unittest.mock import MagicMock, patch
 
-from crewai.experimental.evaluation.experiment.result import ExperimentResult, ExperimentResults
+import pytest
+
+from crewai.experimental.evaluation.experiment.result import (
+    ExperimentResult,
+    ExperimentResults,
+)
 
 
 class TestExperimentResult:
@@ -108,4 +112,4 @@ class TestExperimentResult:
         assert comparison["regressed"] == ["test-3"]
         assert comparison["unchanged"] == ["test-2", "test-4"]
         assert comparison["new_tests"] == ["test-6"]
-        assert comparison["missing_tests"] == ["test-5"]
+        assert comparison["missing_tests"] == ["test-5"]

packages/crewai/tests/experimental/evaluation/test_experiment_runner.py

@@ -1,11 +1,17 @@
-import pytest
 from unittest.mock import MagicMock, patch
 
+import pytest
+
 from crewai.crew import Crew
-from crewai.experimental.evaluation.experiment.runner import ExperimentRunner
+from crewai.experimental.evaluation.base_evaluator import (
+    EvaluationScore,
+    MetricCategory,
+)
+from crewai.experimental.evaluation.evaluation_display import (
+    AgentAggregatedEvaluationResult,
+)
 from crewai.experimental.evaluation.experiment.result import ExperimentResults
-from crewai.experimental.evaluation.evaluation_display import AgentAggregatedEvaluationResult
-from crewai.experimental.evaluation.base_evaluator import MetricCategory, EvaluationScore
+from crewai.experimental.evaluation.experiment.runner import ExperimentRunner
 
 
 class TestExperimentRunner:
@@ -194,4 +200,4 @@ class TestExperimentRunner:
         assert result.inputs == {"query": "Test query 2"}
         assert isinstance(result.expected_score, dict)
         assert "unknown_metric" in result.expected_score.keys()
-        assert result.passed is False
+        assert result.passed is False