refactor: reorganize agent executor imports and introduce CrewAgentExecutorFlow

- Removed the old import of CrewAgentExecutorFlow and replaced it with the new import from the experimental module.
- Updated relevant references in the codebase to ensure compatibility with the new structure.
- Enhanced the organization of imports in core.py and base_agent.py for better clarity and maintainability.

lib/crewai/src/crewai/agent/core.py

@@ -34,7 +34,6 @@ from crewai.agent.utils import (
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
-from crewai.agents.crew_agent_executor_flow import CrewAgentExecutorFlow
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.knowledge_events import (
     KnowledgeQueryCompletedEvent,
@@ -45,6 +44,7 @@ from crewai.events.types.memory_events import (
     MemoryRetrievalCompletedEvent,
     MemoryRetrievalStartedEvent,
 )
+from crewai.experimental.crew_agent_executor_flow import CrewAgentExecutorFlow
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.lite_agent import LiteAgent

lib/crewai/src/crewai/agents/agent_builder/base_agent.py

@@ -457,7 +457,6 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         if self.cache:
             self.cache_handler = cache_handler
             self.tools_handler.cache = cache_handler
-        # TODO: we should do if agent_executor, then we update as we were re-creating the agent_executor which is not ideal
 
     def set_rpm_controller(self, rpm_controller: RPMController) -> None:
         """Set the rpm controller for the agent.
@@ -467,7 +466,6 @@ class BaseAgent(BaseModel, ABC, metaclass=AgentMeta):
         """
         if not self._rpm_controller:
             self._rpm_controller = rpm_controller
-            # TODO: we should do if agent_executor, then we update as we were re-creating the agent_executor which is not ideal
 
     def set_knowledge(self, crew_embedder: EmbedderConfig | None = None) -> None:
         pass

lib/crewai/src/crewai/experimental/__init__.py

@@ -1,3 +1,4 @@
+from crewai.experimental.crew_agent_executor_flow import CrewAgentExecutorFlow
 from crewai.experimental.evaluation import (
     AgentEvaluationResult,
     AgentEvaluator,
@@ -23,6 +24,7 @@ __all__ = [
     "AgentEvaluationResult",
     "AgentEvaluator",
     "BaseEvaluator",
+    "CrewAgentExecutorFlow",
     "EvaluationScore",
     "EvaluationTraceCallback",
     "ExperimentResult",

lib/crewai/src/crewai/experimental/evaluation/agent_evaluator.py

@@ -1,8 +1,9 @@
+from __future__ import annotations
+
 from collections.abc import Sequence
 import threading
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
-from crewai.agent.core import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.events.event_bus import crewai_event_bus
 from crewai.events.types.agent_events import (
@@ -28,6 +29,10 @@ from crewai.experimental.evaluation.evaluation_listener import (
 from crewai.task import Task
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class ExecutionState:
     current_agent_id: str | None = None
     current_task_id: str | None = None

lib/crewai/src/crewai/experimental/evaluation/base_evaluator.py

@@ -1,17 +1,22 @@
+from __future__ import annotations
+
 import abc
 import enum
 from enum import Enum
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 from pydantic import BaseModel, Field
 
-from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.llm import BaseLLM
 from crewai.task import Task
 from crewai.utilities.llm_utils import create_llm
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class MetricCategory(enum.Enum):
     GOAL_ALIGNMENT = "goal_alignment"
     SEMANTIC_QUALITY = "semantic_quality"

lib/crewai/src/crewai/experimental/evaluation/experiment/runner.py

@@ -1,8 +1,9 @@
+from __future__ import annotations
+
 from collections import defaultdict
 from hashlib import md5
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
-from crewai import Agent, Crew
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.experimental.evaluation import AgentEvaluator, create_default_evaluator
 from crewai.experimental.evaluation.evaluation_display import (
@@ -17,6 +18,11 @@ from crewai.experimental.evaluation.experiment.result_display import (
 )
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+    from crewai.crew import Crew
+
+
 class ExperimentRunner:
     def __init__(self, dataset: list[dict[str, Any]]):
         self.dataset = dataset or []

lib/crewai/src/crewai/experimental/evaluation/metrics/goal_metrics.py

@@ -1,6 +1,7 @@
-from typing import Any
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
 
-from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.experimental.evaluation.base_evaluator import (
     BaseEvaluator,
@@ -12,6 +13,10 @@ from crewai.task import Task
 from crewai.utilities.types import LLMMessage
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class GoalAlignmentEvaluator(BaseEvaluator):
     @property
     def metric_category(self) -> MetricCategory:

lib/crewai/src/crewai/experimental/evaluation/metrics/reasoning_metrics.py

@@ -6,15 +6,16 @@ This module provides evaluator implementations for:
 - Thinking-to-action ratio
 """
 
+from __future__ import annotations
+
 from collections.abc import Sequence
 from enum import Enum
 import logging
 import re
-from typing import Any
+from typing import TYPE_CHECKING, Any
 
 import numpy as np
 
-from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.experimental.evaluation.base_evaluator import (
     BaseEvaluator,
@@ -27,6 +28,10 @@ from crewai.tasks.task_output import TaskOutput
 from crewai.utilities.types import LLMMessage
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class ReasoningPatternType(Enum):
     EFFICIENT = "efficient"  # Good reasoning flow
     LOOP = "loop"  # Agent is stuck in a loop

lib/crewai/src/crewai/experimental/evaluation/metrics/semantic_quality_metrics.py

@@ -1,6 +1,7 @@
-from typing import Any
+from __future__ import annotations
+
+from typing import TYPE_CHECKING, Any
 
-from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.experimental.evaluation.base_evaluator import (
     BaseEvaluator,
@@ -12,6 +13,10 @@ from crewai.task import Task
 from crewai.utilities.types import LLMMessage
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class SemanticQualityEvaluator(BaseEvaluator):
     @property
     def metric_category(self) -> MetricCategory:

lib/crewai/src/crewai/experimental/evaluation/metrics/tools_metrics.py

@@ -1,7 +1,8 @@
-import json
+from __future__ import annotations
-from typing import Any
+
+import json
+from typing import TYPE_CHECKING, Any
 
-from crewai.agent import Agent
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.experimental.evaluation.base_evaluator import (
     BaseEvaluator,
@@ -13,6 +14,10 @@ from crewai.task import Task
 from crewai.utilities.types import LLMMessage
 
 
+if TYPE_CHECKING:
+    from crewai.agent import Agent
+
+
 class ToolSelectionEvaluator(BaseEvaluator):
     @property
     def metric_category(self) -> MetricCategory:

lib/crewai/tests/agents/test_crew_agent_executor_flow.py

@@ -8,7 +8,7 @@ from unittest.mock import Mock, patch
 
 import pytest
 
-from crewai.agents.crew_agent_executor_flow import (
+from crewai.experimental.crew_agent_executor_flow import (
     AgentReActState,
     CrewAgentExecutorFlow,
 )
@@ -233,7 +233,7 @@ class TestCrewAgentExecutorFlow:
             AgentFinish(thought="thinking", output="test", text="final")
         )
 
-    @patch("crewai.agents.crew_agent_executor_flow.handle_output_parser_exception")
+    @patch("crewai.experimental.crew_agent_executor_flow.handle_output_parser_exception")
     def test_recover_from_parser_error(
         self, mock_handle_exception, mock_dependencies
     ):
@@ -252,7 +252,7 @@ class TestCrewAgentExecutorFlow:
         assert executor.state.iterations == initial_iterations + 1
         mock_handle_exception.assert_called_once()
 
-    @patch("crewai.agents.crew_agent_executor_flow.handle_context_length")
+    @patch("crewai.experimental.crew_agent_executor_flow.handle_context_length")
     def test_recover_from_context_length(
         self, mock_handle_context, mock_dependencies
     ):
@@ -321,8 +321,8 @@ class TestFlowErrorHandling:
             "tools_handler": Mock(),
         }
 
-    @patch("crewai.agents.crew_agent_executor_flow.get_llm_response")
+    @patch("crewai.experimental.crew_agent_executor_flow.get_llm_response")
-    @patch("crewai.agents.crew_agent_executor_flow.enforce_rpm_limit")
+    @patch("crewai.experimental.crew_agent_executor_flow.enforce_rpm_limit")
     def test_call_llm_parser_error(
         self, mock_enforce_rpm, mock_get_llm, mock_dependencies
     ):
@@ -338,9 +338,9 @@ class TestFlowErrorHandling:
         assert result == "parser_error"
         assert executor._last_parser_error is not None
 
-    @patch("crewai.agents.crew_agent_executor_flow.get_llm_response")
+    @patch("crewai.experimental.crew_agent_executor_flow.get_llm_response")
-    @patch("crewai.agents.crew_agent_executor_flow.enforce_rpm_limit")
+    @patch("crewai.experimental.crew_agent_executor_flow.enforce_rpm_limit")
-    @patch("crewai.agents.crew_agent_executor_flow.is_context_length_exceeded")
+    @patch("crewai.experimental.crew_agent_executor_flow.is_context_length_exceeded")
     def test_call_llm_context_error(
         self,
         mock_is_context_exceeded,