style: resolve linter issues

src/crewai/evaluation/__init__.py

@@ -1,4 +1,3 @@
-# First, import the core base classes without AgentEvaluator
 from crewai.evaluation.base_evaluator import (
     BaseEvaluator,
     EvaluationScore,
@@ -6,7 +5,6 @@ from crewai.evaluation.base_evaluator import (
     AgentEvaluationResult
 )
 
-# Now import the evaluators which depend on base classes
 from crewai.evaluation.metrics.semantic_quality_metrics import (
     SemanticQualityEvaluator
 )
@@ -26,7 +24,6 @@ from crewai.evaluation.metrics.tools_metrics import (
     ToolInvocationEvaluator
 )
 
-# Next import integration which uses the base classes but not AgentEvaluator
 from crewai.evaluation.evaluation_listener import (
     EvaluationTraceCallback,
     create_evaluation_callbacks
@@ -36,4 +33,21 @@ from crewai.evaluation.evaluation_listener import (
 from crewai.evaluation.agent_evaluator import (
     AgentEvaluator,
     create_default_evaluator
-)
+)
+
+__all__ = [
+    "BaseEvaluator",
+    "EvaluationScore",
+    "MetricCategory",
+    "AgentEvaluationResult",
+    "SemanticQualityEvaluator",
+    "GoalAlignmentEvaluator",
+    "ReasoningEfficiencyEvaluator",
+    "ToolSelectionEvaluator",
+    "ParameterExtractionEvaluator",
+    "ToolInvocationEvaluator",
+    "EvaluationTraceCallback",
+    "create_evaluation_callbacks",
+    "AgentEvaluator",
+    "create_default_evaluator"
+]

src/crewai/evaluation/agent_evaluator.py

@@ -1,15 +1,12 @@
-from crewai.evaluation.base_evaluator import AgentEvaluationResult, AgentAggregatedEvaluationResult, AggregationStrategy
-from crewai.utilities.events.base_event_listener import BaseEventListener
+from crewai.evaluation.base_evaluator import AgentEvaluationResult, AggregationStrategy
 from crewai.agent import Agent
 from crewai.task import Task
-from crewai.utilities.llm_utils import create_llm
 from crewai.evaluation.evaluation_display import EvaluationDisplayFormatter
 
-from typing import List, Optional, Dict, Any, Tuple
+from typing import List, Optional, Dict, Any
 from collections import defaultdict
-from crewai.evaluation import EvaluationScore, BaseEvaluator, create_evaluation_callbacks
+from crewai.evaluation import BaseEvaluator, create_evaluation_callbacks
 from crewai.crew import Crew
-from rich.table import Table
 from crewai.utilities.events.crewai_event_bus import crewai_event_bus
 from crewai.utilities.events.utils.console_formatter import ConsoleFormatter
 

src/crewai/evaluation/evaluation_display.py

@@ -340,5 +340,5 @@ class EvaluationDisplayFormatter:
 
             return response
 
-        except Exception as e:
+        except Exception:
             return "Synthesized from multiple tasks: " + "\n\n".join([f"- {fb[:500]}..." for fb in feedbacks])

src/crewai/evaluation/metrics/goal_metrics.py

@@ -56,7 +56,7 @@ Evaluate how well the agent's output aligns with the assigned task goal.
                 feedback=evaluation_data.get("feedback", response),
                 raw_response=response
             )
-        except Exception as e:
+        except Exception:
             return EvaluationScore(
                 score=None,
                 feedback=f"Failed to parse evaluation. Raw response: {response}",

src/crewai/evaluation/metrics/reasoning_metrics.py

@@ -14,7 +14,6 @@ import numpy as np
 
 from crewai.agent import Agent
 from crewai.task import Task
-from crewai.llm import BaseLLM, LLM
 
 from crewai.evaluation.base_evaluator import BaseEvaluator, EvaluationScore, MetricCategory
 from crewai.evaluation.json_parser import extract_json_from_llm_response
@@ -60,7 +59,7 @@ class ReasoningEfficiencyEvaluator(BaseEvaluator):
                 try:
                     interval = end_time - start_time
                     time_intervals.append(interval.total_seconds() if hasattr(interval, 'total_seconds') else 0)
-                except:
+                except Exception:
                     has_reliable_timing = False
             else:
                 has_reliable_timing = False
@@ -241,7 +240,7 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
             if start_time and end_time:
                 try:
                     response_times.append(end_time - start_time)
-                except:
+                except Exception:
                     pass
 
         avg_length = np.mean(call_lengths) if call_lengths else 0
@@ -293,7 +292,7 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                 normalized_slope = slope / max_possible_slope
                 return max(min(normalized_slope, 1.0), -1.0)
             return 0.0
-        except:
+        except Exception:
             return 0.0
 
     def _calculate_loop_likelihood(self, call_lengths: List[float], response_times: List[float]) -> float:
@@ -319,7 +318,7 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                 if mean_time > 0:
                     time_consistency = 1.0 - (std_time / mean_time)
                     indicators.append(max(0, time_consistency - 0.3) * 1.5)
-            except:
+            except Exception:
                 pass
 
         return np.mean(indicators) if indicators else 0.0

src/crewai/evaluation/metrics/semantic_quality_metrics.py

@@ -55,7 +55,7 @@ Evaluate the semantic quality and reasoning of this output.
                 feedback=evaluation_data.get("feedback", response),
                 raw_response=response
             )
-        except Exception as e:
+        except Exception:
             return EvaluationScore(
                 score=None,
                 feedback=f"Failed to parse evaluation. Raw response: {response}",

src/crewai/evaluation/metrics/tools_metrics.py

@@ -97,7 +97,7 @@ IMPORTANT:
             coverage = scores.get("coverage", 5.0)
             overall_score = float(evaluation_data.get("overall_score", 5.0))
 
-            feedback = f"Tool Selection Evaluation:\n"
+            feedback = "Tool Selection Evaluation:\n"
             feedback += f"• Relevance: {relevance}/10 - Selection of appropriate tool types for the task\n"
             feedback += f"• Coverage: {coverage}/10 - Selection of all necessary tool types\n"
             if "improvement_suggestions" in evaluation_data:
@@ -164,7 +164,7 @@ class ParameterExtractionEvaluator(BaseEvaluator):
             sample += f"- Success: {'No' if not success else 'Yes'}"
 
             if is_validation_error:
-                sample += f" (PARAMETER VALIDATION ERROR)\n"
+                sample += " (PARAMETER VALIDATION ERROR)\n"
                 sample += f"- Error: {tool_use.get('result', 'Unknown error')}"
             elif not success:
                 sample += f" (Other error: {error_type})\n"
@@ -231,7 +231,7 @@ Evaluate the quality of the agent's parameter extraction for this task.
 
             overall_score = float(evaluation_data.get("overall_score", 5.0))
 
-            feedback = f"Parameter Extraction Evaluation:\n"
+            feedback = "Parameter Extraction Evaluation:\n"
             feedback += f"• Accuracy: {accuracy}/10 - Correctly identifying required parameters\n"
             feedback += f"• Formatting: {formatting}/10 - Properly formatting parameters for tools\n"
             feedback += f"• Completeness: {completeness}/10 - Including all necessary information\n\n"
@@ -370,7 +370,7 @@ Evaluate the quality of the agent's tool invocation structure during this task.
 
             overall_score = float(evaluation_data.get("overall_score", 5.0))
 
-            feedback = f"Tool Invocation Evaluation:\n"
+            feedback = "Tool Invocation Evaluation:\n"
             feedback += f"• Structure: {structure}/10 - Following proper syntax and format\n"
             feedback += f"• Error Handling: {error_handling}/10 - Appropriately handling tool errors\n"
             feedback += f"• Invocation Patterns: {invocation_patterns}/10 - Proper sequencing and management of calls\n\n"

src/crewai/utilities/events/llm_events.py

@@ -2,7 +2,6 @@ from enum import Enum
 from typing import Any, Dict, List, Optional, Union
 
 from pydantic import BaseModel
-from datetime import datetime
 
 from crewai.utilities.events.base_events import BaseEvent
 

tests/evaluation/metrics/test_goal_metrics.py

@@ -1,4 +1,3 @@
-import pytest
 from unittest.mock import patch, MagicMock
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest
 

tests/evaluation/metrics/test_reasoning_metrics.py

@@ -5,7 +5,6 @@ from typing import List, Dict, Any
 from crewai.tasks.task_output import TaskOutput
 from crewai.evaluation.metrics.reasoning_metrics import (
     ReasoningEfficiencyEvaluator,
-    ReasoningPatternType
 )
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest
 from crewai.utilities.llm_utils import LLM

tests/evaluation/metrics/test_semantic_quality_metrics.py

@@ -1,8 +1,5 @@
-import pytest
-from unittest.mock import patch, MagicMock, ANY
+from unittest.mock import patch, MagicMock
 
-from crewai.agent import Agent
-from crewai.task import Task
 from crewai.evaluation.base_evaluator import EvaluationScore
 from crewai.evaluation.metrics.semantic_quality_metrics import SemanticQualityEvaluator
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest

tests/evaluation/metrics/test_tools_metrics.py

@@ -1,9 +1,5 @@
-import pytest
-from unittest.mock import patch, MagicMock, ANY
+from unittest.mock import patch, MagicMock
 
-from crewai.agent import Agent
-from crewai.task import Task
-from crewai.evaluation.base_evaluator import EvaluationScore
 from crewai.evaluation.metrics.tools_metrics import (
     ToolSelectionEvaluator,
     ParameterExtractionEvaluator,