chore: update version and dependencies to 0.201.0 (#3593 )

- Bump CrewAI version to 0.201.0 in __init__.py - Update dependency versions in pyproject.toml for crew, flow, and tool templates to require CrewAI 0.201.0 - Remove unnecessary blank line in pyproject.toml
feat: upgrade chromadb to v1.1.0, improve types
2026-01-01 04:08:30 +00:00 · 2025-09-25 18:04:12 -07:00 · 2025-09-25 20:48:37 -04:00 · 2025-09-25 18:28:39 -04:00 · 2025-09-24 14:42:18 -04:00 · 2025-09-24 11:41:33 -04:00
284 changed files with 12025 additions and 7874 deletions
--- a/docs/en/changelog.mdx
+++ b/docs/en/changelog.mdx
@@ -5,6 +5,82 @@ icon: "clock"
 mode: "wide"
 ---

+<Update label="Sep 20, 2025">
+  ## v0.193.2
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.2)
+
+  ## What's Changed
+
+  - Updated pyproject templates to use the right version
+
+</Update>
+
+<Update label="Sep 20, 2025">
+  ## v0.193.1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.1)
+
+  ## What's Changed
+
+  - Series of minor fixes and linter improvements
+
+</Update>
+
+<Update label="Sep 19, 2025">
+  ## v0.193.0
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.0)
+
+  ## Core Improvements & Fixes
+  
+  - Fixed handling of the `model` parameter during OpenAI adapter initialization  
+  - Resolved test duration cache issues in CI workflows  
+  - Fixed flaky test related to repeated tool usage by agents  
+  - Added missing event exports to `__init__.py` for consistent module behavior  
+  - Dropped message storage from metadata in Mem0 to reduce bloat  
+  - Fixed L2 distance metric support for backward compatibility in vector search  
+
+  ## New Features & Enhancements
+  
+  - Introduced thread-safe platform context management  
+  - Added test duration caching for optimized `pytest-split` runs  
+  - Added ephemeral trace improvements for better trace control  
+  - Made search parameters for RAG, knowledge, and memory fully configurable  
+  - Enabled ChromaDB to use OpenAI API for embedding functions  
+  - Added deeper observability tools for user-level insights  
+  - Unified RAG storage system with instance-specific client support  
+
+  ## Documentation & Guides
+  
+  - Updated `RagTool` references to reflect CrewAI native RAG implementation  
+  - Improved internal docs for `langgraph` and `openai` agent adapters with type annotations and docstrings  
+
+</Update>
+
+<Update label="Sep 11, 2025">
+  ## v0.186.1
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.186.1)
+
+  ## What's Changed
+
+  - Fixed version not being found and silently failing reversion  
+  - Bumped CrewAI version to 0.186.1 and updated dependencies in the CLI  
+
+</Update>
+
+<Update label="Sep 10, 2025">
+  ## v0.186.0
+
+  [View release on GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.186.0)
+
+  ## What's Changed
+
+  - Refer to the GitHub release notes for detailed changes
+
+</Update>
+
 <Update label="Sep 04, 2025">
  ## v0.177.0

--- a/docs/en/concepts/cli.mdx
+++ b/docs/en/concepts/cli.mdx
@@ -404,6 +404,10 @@ crewai config reset
 After resetting configuration, re-run `crewai login` to authenticate again.
 </Tip>

+<Tip>
+CrewAI CLI handles authentication to the Tool Repository automatically when adding packages to your project. Just append `crewai` before any `uv` command to use it. E.g. `crewai uv add requests`. For more information, see [Tool Repository](https://docs.crewai.com/enterprise/features/tool-repository) docs.
+</Tip>
+
 <Note>
 Configuration settings are stored in `~/.config/crewai/settings.json`. Some settings like organization name and UUID are read-only and managed through authentication and organization commands. Tool repository related settings are hidden and cannot be set directly by users.
 </Note>
--- a/docs/en/enterprise/features/tool-repository.mdx
+++ b/docs/en/enterprise/features/tool-repository.mdx
@@ -52,6 +52,36 @@ researcher = Agent(
 )
 ```

+## Adding other packages after installing a tool
+
+After installing a tool from the CrewAI Enterprise Tool Repository, you need to use the `crewai uv` command to add other packages to your project.
+Using pure `uv` commands will fail due to authentication to tool repository being handled by the CLI. By using the `crewai uv` command, you can add other packages to your project without having to worry about authentication.
+Any `uv` command can be used with the `crewai uv` command, making it a powerful tool for managing your project's dependencies without the hassle of managing authentication through environment variables or other methods.
+
+Say that you have installed a custom tool from the CrewAI Enterprise Tool Repository called "my-tool":
+
+```bash
+crewai tool install my-tool
+```
+
+And now you want to add another package to your project, you can use the following command:
+
+```bash
+crewai uv add requests
+```
+
+Other commands like `uv sync` or `uv remove` can also be used with the `crewai uv` command:
+
+```bash
+crewai uv sync
+```
+
+```bash
+crewai uv remove requests
+```
+
+This will add the package to your project and update `pyproject.toml` accordingly.
+
 ## Creating and Publishing Tools

 To create a new tool project:
--- a/docs/en/quickstart.mdx
+++ b/docs/en/quickstart.mdx
@@ -27,7 +27,7 @@ Follow the steps below to get Crewing! 🚣‍♂️
  <Step title="Navigate to your new crew project">
    <CodeGroup>
      ```shell Terminal
-      cd latest-ai-development
+      cd latest_ai_development
      ```
    </CodeGroup>
  </Step>
--- a/docs/en/tools/ai-ml/ragtool.mdx
+++ b/docs/en/tools/ai-ml/ragtool.mdx
@@ -9,7 +9,7 @@ mode: "wide"

 ## Description

-The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through EmbedChain.
+The `RagTool` is designed to answer questions by leveraging the power of Retrieval-Augmented Generation (RAG) through CrewAI's native RAG system.
 It provides a dynamic knowledge base that can be queried to retrieve relevant information from various data sources.
 This tool is particularly useful for applications that require access to a vast array of information and need to provide contextually relevant answers.

@@ -76,8 +76,8 @@ The `RagTool` can be used with a wide variety of data sources, including:
 The `RagTool` accepts the following parameters:

 - **summarize**: Optional. Whether to summarize the retrieved content. Default is `False`.
- **adapter**: Optional. A custom adapter for the knowledge base. If not provided, an EmbedchainAdapter will be used.
- **config**: Optional. Configuration for the underlying EmbedChain App.
+- **adapter**: Optional. A custom adapter for the knowledge base. If not provided, a CrewAIRagAdapter will be used.
+- **config**: Optional. Configuration for the underlying CrewAI RAG system.

 ## Adding Content

@@ -130,44 +130,23 @@ from crewai_tools import RagTool

 # Create a RAG tool with custom configuration
 config = {
-    "app": {
-        "name": "custom_app",
-    },
-    "llm": {
-        "provider": "openai",
+    "vectordb": {
+        "provider": "qdrant",
        "config": {
-            "model": "gpt-4",
+            "collection_name": "my-collection"
        }
    },
    "embedding_model": {
        "provider": "openai",
        "config": {
-            "model": "text-embedding-ada-002"
+            "model": "text-embedding-3-small"
        }
-    },
-    "vectordb": {
-        "provider": "elasticsearch",
-        "config": {
-            "collection_name": "my-collection",
-            "cloud_id": "deployment-name:xxxx",
-            "api_key": "your-key",
-            "verify_certs": False
-        }
-    },
-    "chunker": {
-        "chunk_size": 400,
-        "chunk_overlap": 100,
-        "length_function": "len",
-        "min_chunk_size": 0
    }
 }

 rag_tool = RagTool(config=config, summarize=True)
 ```

-The internal RAG tool utilizes the Embedchain adapter, allowing you to pass any configuration options that are supported by Embedchain.
-You can refer to the [Embedchain documentation](https://docs.embedchain.ai/components/introduction) for details.
-Make sure to review the configuration options available in the .yaml file.

 ## Conclusion
 The `RagTool` provides a powerful way to create and query knowledge bases from various data sources. By leveraging Retrieval-Augmented Generation, it enables agents to access and retrieve relevant information efficiently, enhancing their ability to provide accurate and contextually appropriate responses.
--- a/docs/ko/changelog.mdx
+++ b/docs/ko/changelog.mdx
@@ -5,6 +5,82 @@ icon: "clock"
 mode: "wide"
 ---

+<Update label="2025년 9월 20일">
+  ## v0.193.2
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/0.193.2)
+
+  ## 변경 사항
+  
+  - 올바른 버전을 사용하도록 pyproject 템플릿 업데이트
+
+</Update>
+
+<Update label="2025년 9월 20일">
+  ## v0.193.1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/0.193.1)
+
+  ## 변경 사항
+  
+  - 일련의 사소한 수정 및 린터 개선
+
+</Update>
+
+<Update label="2025년 9월 19일">
+  ## v0.193.0
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/0.193.0)
+
+  ## 핵심 개선 사항 및 수정 사항
+  
+  - OpenAI 어댑터 초기화 중 `model` 매개변수 처리 수정  
+  - CI 워크플로에서 테스트 소요 시간 캐시 문제 해결  
+  - 에이전트의 반복 도구 사용과 관련된 불안정한 테스트 수정  
+  - 일관된 모듈 동작을 위해 누락된 이벤트 내보내기를 `__init__.py`에 추가  
+  - 메타데이터 부하를 줄이기 위해 Mem0에서 메시지 저장 제거  
+  - 벡터 검색의 하위 호환성을 위해 L2 거리 메트릭 지원 수정  
+
+  ## 새로운 기능 및 향상 사항
+  
+  - 스레드 안전한 플랫폼 컨텍스트 관리 도입  
+  - `pytest-split` 실행 최적화를 위한 테스트 소요 시간 캐싱 추가  
+  - 더 나은 추적 제어를 위한 일시적(trace) 개선  
+  - RAG, 지식, 메모리 검색 매개변수를 완전 구성 가능하게 변경  
+  - ChromaDB가 임베딩 함수에 OpenAI API를 사용할 수 있도록 지원  
+  - 사용자 수준 인사이트를 위한 심화된 관찰 가능성 도구 추가  
+  - 인스턴스별 클라이언트를 지원하는 통합 RAG 스토리지 시스템  
+
+  ## 문서 및 가이드
+  
+  - CrewAI 네이티브 RAG 구현을 반영하도록 `RagTool` 참조 업데이트  
+  - 타입 주석과 도크스트링을 포함해 `langgraph` 및 `openai` 에이전트 어댑터 내부 문서 개선  
+
+</Update>
+
+<Update label="2025년 9월 11일">
+  ## v0.186.1
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/0.186.1)
+
+  ## 변경 사항
+  
+  - 버전을 찾지 못해 조용히 되돌리는(reversion) 문제 수정  
+  - CLI에서 CrewAI 버전을 0.186.1로 올리고 의존성 업데이트  
+
+</Update>
+
+<Update label="2025년 9월 10일">
+  ## v0.186.0
+
+  [GitHub 릴리스 보기](https://github.com/crewAIInc/crewAI/releases/tag/0.186.0)
+
+  ## 변경 사항
+  
+  - 자세한 변경 사항은 GitHub 릴리스 노트를 참조하세요
+
+</Update>
+
 <Update label="2025년 9월 4일">
  ## v0.177.0

--- a/docs/ko/quickstart.mdx
+++ b/docs/ko/quickstart.mdx
@@ -27,7 +27,7 @@ mode: "wide"
  <Step title="새로운 crew 프로젝트로 이동하기">
    <CodeGroup>
      ```shell Terminal
-      cd latest-ai-development
+      cd latest_ai_development
      ```
    </CodeGroup>
  </Step>
--- a/docs/pt-BR/changelog.mdx
+++ b/docs/pt-BR/changelog.mdx
@@ -5,6 +5,82 @@ icon: "clock"
 mode: "wide"
 ---

+<Update label="20 set 2025">
+  ## v0.193.2
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.2)
+
+  ## O que Mudou
+
+  - Atualizados templates do pyproject para usar a versão correta
+
+</Update>
+
+<Update label="20 set 2025">
+  ## v0.193.1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.1)
+
+  ## O que Mudou
+
+  - Série de pequenas correções e melhorias de linter
+
+</Update>
+
+<Update label="19 set 2025">
+  ## v0.193.0
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.193.0)
+
+  ## Melhorias e Correções Principais
+  
+  - Corrigido manuseio do parâmetro `model` durante a inicialização do adaptador OpenAI  
+  - Resolvidos problemas de cache da duração de testes nos fluxos de CI  
+  - Corrigido teste instável relacionado ao uso repetido de ferramentas pelos agentes  
+  - Adicionadas exportações de eventos ausentes no `__init__.py` para comportamento consistente do módulo  
+  - Removido armazenamento de mensagem dos metadados no Mem0 para reduzir inchaço  
+  - Corrigido suporte à métrica de distância L2 para compatibilidade retroativa na busca vetorial  
+
+  ## Novos Recursos e Melhorias
+  
+  - Introduzida gestão de contexto de plataforma com segurança de threads  
+  - Adicionado cache da duração de testes para execuções otimizadas do `pytest-split`  
+  - Melhorias de traces efêmeros para melhor controle de rastreamento  
+  - Parâmetros de busca para RAG, conhecimento e memória totalmente configuráveis  
+  - Habilitado ChromaDB para usar a OpenAI API para funções de embedding  
+  - Adicionadas ferramentas de observabilidade mais profundas para insights ao nível do usuário  
+  - Sistema de armazenamento RAG unificado com suporte a cliente específico por instância  
+
+  ## Documentação e Guias
+  
+  - Atualizadas referências do `RagTool` para refletir a implementação nativa de RAG do CrewAI  
+  - Melhorada documentação interna para adaptadores de agente `langgraph` e `openai` com anotações de tipo e docstrings  
+
+</Update>
+
+<Update label="11 set 2025">
+  ## v0.186.1
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.186.1)
+
+  ## O que Mudou
+
+  - Corrigida falha silenciosa de reversão quando a versão não era encontrada  
+  - Versão do CrewAI atualizada para 0.186.1 e dependências do CLI atualizadas  
+
+</Update>
+
+<Update label="10 set 2025">
+  ## v0.186.0
+
+  [Ver release no GitHub](https://github.com/crewAIInc/crewAI/releases/tag/0.186.0)
+
+  ## O que Mudou
+
+  - Consulte as notas de lançamento no GitHub para detalhes completos
+
+</Update>
+
 <Update label="04 set 2025">
  ## v0.177.0

--- a/docs/pt-BR/quickstart.mdx
+++ b/docs/pt-BR/quickstart.mdx
@@ -27,7 +27,7 @@ Siga os passos abaixo para começar a tripular! 🚣‍♂️
  <Step title="Navegue até o novo projeto da sua tripulação">
    <CodeGroup>
      ```shell Terminal
-      cd latest-ai-development
+      cd latest_ai_development
      ```
    </CodeGroup>
  </Step>
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,7 +9,7 @@ authors = [
 ]
 dependencies = [
    # Core Dependencies
-    "pydantic>=2.4.2",
+    "pydantic>=2.11.9",
    "openai>=1.13.3",
    "litellm==1.74.9",
    "instructor>=1.3.3",
@@ -21,13 +21,12 @@ dependencies = [
    "opentelemetry-sdk>=1.30.0",
    "opentelemetry-exporter-otlp-proto-http>=1.30.0",
    # Data Handling
-    "chromadb>=0.5.23",
+    "chromadb~=1.1.0",
    "tokenizers>=0.20.3",
-    "onnxruntime==1.22.0",
    "openpyxl>=3.1.5",
    "pyvis>=0.3.2",
    # Authentication and Security
-    "python-dotenv>=1.0.0",
+    "python-dotenv>=1.1.1",
    "pyjwt>=2.9.0",
    # Configuration and Utils
    "click>=8.1.7",
@@ -40,6 +39,7 @@ dependencies = [
    "blinker>=1.9.0",
    "json5>=0.10.0",
    "portalocker==2.7.0",
+    "pydantic-settings>=2.10.1",
 ]

 [project.urls]
@@ -48,7 +48,9 @@ Documentation = "https://docs.crewai.com"
 Repository = "https://github.com/crewAIInc/crewAI"

 [project.optional-dependencies]
-tools = ["crewai-tools~=0.71.0"]
+tools = [
+    "crewai-tools>=0.74.0",
+]
 embeddings = [
    "tiktoken~=0.8.0"
 ]
@@ -71,24 +73,30 @@ aisuite = [
 qdrant = [
    "qdrant-client[fastembed]>=1.14.3",
 ]
+aws = [
+    "boto3>=1.40.38",
+]
+watson = [
+    "ibm-watsonx-ai>=1.3.39",
+]
+voyageai = [
+    "voyageai>=0.3.5",
+]

-[tool.uv]
-dev-dependencies = [
-    "ruff>=0.12.11",
-    "mypy>=1.17.1",
+[dependency-groups]
+dev = [
+    "ruff>=0.13.1",
+    "mypy>=1.18.2",
    "pre-commit>=4.3.0",
    "bandit>=1.8.6",
-    "pillow>=10.2.0",
-    "cairosvg>=2.7.1",
-    "pytest>=8.0.0",
-    "python-dotenv>=1.0.0",
-    "pytest-asyncio>=0.23.7",
-    "pytest-subprocess>=1.5.2",
-    "pytest-recording>=0.13.2",
-    "pytest-randomly>=3.16.0",
-    "pytest-timeout>=2.3.1",
-    "pytest-xdist>=3.6.1",
-    "pytest-split>=0.9.0",
+    "pytest>=8.4.2",
+    "pytest-asyncio>=1.2.0",
+    "pytest-subprocess>=1.5.3",
+    "pytest-recording>=0.13.4",
+    "pytest-randomly>=4.0.1",
+    "pytest-timeout>=2.4.0",
+    "pytest-xdist>=3.8.0",
+    "pytest-split>=0.10.0",
    "types-requests==2.32.*",
    "types-pyyaml==6.0.*",
    "types-regex==2024.11.6.*",
@@ -138,6 +146,7 @@ ignore = ["E501"]  # ignore line too long globally

 [tool.mypy]
 exclude = ["src/crewai/cli/templates", "tests/"]
+plugins = ["pydantic.mypy"]


 [tool.bandit]
--- a/src/crewai/init.py
+++ b/src/crewai/init.py
@@ -40,7 +40,7 @@ def _suppress_pydantic_deprecation_warnings() -> None:

 _suppress_pydantic_deprecation_warnings()

-__version__ = "0.186.1"
+__version__ = "0.201.0"
 _telemetry_submitted = False


--- a/src/crewai/agent.py
+++ b/src/crewai/agent.py
@@ -1,17 +1,10 @@
 import shutil
 import subprocess
 import time
+from collections.abc import Callable, Sequence
 from typing import (
    Any,
-    Callable,
-    Dict,
-    List,
    Literal,
-    Optional,
-    Sequence,
-    Tuple,
-    Type,
-    Union,
 )

 from pydantic import Field, InstanceOf, PrivateAttr, model_validator
@@ -19,12 +12,31 @@ from pydantic import Field, InstanceOf, PrivateAttr, model_validator
 from crewai.agents import CacheHandler
 from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.agents.crew_agent_executor import CrewAgentExecutor
+from crewai.events.event_bus import crewai_event_bus
+from crewai.events.types.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionErrorEvent,
+    AgentExecutionStartedEvent,
+)
+from crewai.events.types.knowledge_events import (
+    KnowledgeQueryCompletedEvent,
+    KnowledgeQueryFailedEvent,
+    KnowledgeQueryStartedEvent,
+    KnowledgeRetrievalCompletedEvent,
+    KnowledgeRetrievalStartedEvent,
+    KnowledgeSearchQueryFailedEvent,
+)
+from crewai.events.types.memory_events import (
+    MemoryRetrievalCompletedEvent,
+    MemoryRetrievalStartedEvent,
+)
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.utils.knowledge_utils import extract_knowledge_context
 from crewai.lite_agent import LiteAgent, LiteAgentOutput
 from crewai.llm import BaseLLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
+from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security import Fingerprint
 from crewai.task import Task
 from crewai.tools import BaseTool
@@ -38,24 +50,6 @@ from crewai.utilities.agent_utils import (
 )
 from crewai.utilities.constants import TRAINED_AGENTS_DATA_FILE, TRAINING_DATA_FILE
 from crewai.utilities.converter import generate_model_description
-from crewai.events.types.agent_events import (
-    AgentExecutionCompletedEvent,
-    AgentExecutionErrorEvent,
-    AgentExecutionStartedEvent,
-)
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.types.memory_events import (
-    MemoryRetrievalStartedEvent,
-    MemoryRetrievalCompletedEvent,
-)
-from crewai.events.types.knowledge_events import (
-    KnowledgeQueryCompletedEvent,
-    KnowledgeQueryFailedEvent,
-    KnowledgeQueryStartedEvent,
-    KnowledgeRetrievalCompletedEvent,
-    KnowledgeRetrievalStartedEvent,
-    KnowledgeSearchQueryFailedEvent,
-)
 from crewai.utilities.llm_utils import create_llm
 from crewai.utilities.token_counter_callback import TokenCalcHandler
 from crewai.utilities.training_handler import CrewTrainingHandler
@@ -87,36 +81,36 @@ class Agent(BaseAgent):
    """

    _times_executed: int = PrivateAttr(default=0)
-    max_execution_time: Optional[int] = Field(
+    max_execution_time: int | None = Field(
        default=None,
        description="Maximum execution time for an agent to execute a task",
    )
    agent_ops_agent_name: str = None  # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
    agent_ops_agent_id: str = None  # type: ignore # Incompatible types in assignment (expression has type "None", variable has type "str")
-    step_callback: Optional[Any] = Field(
+    step_callback: Any | None = Field(
        default=None,
        description="Callback to be executed after each step of the agent execution.",
    )
-    use_system_prompt: Optional[bool] = Field(
+    use_system_prompt: bool | None = Field(
        default=True,
        description="Use system prompt for the agent.",
    )
-    llm: Union[str, InstanceOf[BaseLLM], Any] = Field(
+    llm: str | InstanceOf[BaseLLM] | Any = Field(
        description="Language model that will run the agent.", default=None
    )
-    function_calling_llm: Optional[Union[str, InstanceOf[BaseLLM], Any]] = Field(
+    function_calling_llm: str | InstanceOf[BaseLLM] | Any | None = Field(
        description="Language model that will run the agent.", default=None
    )
-    system_template: Optional[str] = Field(
+    system_template: str | None = Field(
        default=None, description="System format for the agent."
    )
-    prompt_template: Optional[str] = Field(
+    prompt_template: str | None = Field(
        default=None, description="Prompt format for the agent."
    )
-    response_template: Optional[str] = Field(
+    response_template: str | None = Field(
        default=None, description="Response format for the agent."
    )
-    allow_code_execution: Optional[bool] = Field(
+    allow_code_execution: bool | None = Field(
        default=False, description="Enable code execution for the agent."
    )
    respect_context_window: bool = Field(
@@ -147,31 +141,31 @@ class Agent(BaseAgent):
        default=False,
        description="Whether the agent should reflect and create a plan before executing a task.",
    )
-    max_reasoning_attempts: Optional[int] = Field(
+    max_reasoning_attempts: int | None = Field(
        default=None,
        description="Maximum number of reasoning attempts before executing the task. If None, will try until ready.",
    )
-    embedder: Optional[Dict[str, Any]] = Field(
+    embedder: EmbedderConfig | None = Field(
        default=None,
        description="Embedder configuration for the agent.",
    )
-    agent_knowledge_context: Optional[str] = Field(
+    agent_knowledge_context: str | None = Field(
        default=None,
        description="Knowledge context for the agent.",
    )
-    crew_knowledge_context: Optional[str] = Field(
+    crew_knowledge_context: str | None = Field(
        default=None,
        description="Knowledge context for the crew.",
    )
-    knowledge_search_query: Optional[str] = Field(
+    knowledge_search_query: str | None = Field(
        default=None,
        description="Knowledge search query for the agent dynamically generated by the agent.",
    )
-    from_repository: Optional[str] = Field(
+    from_repository: str | None = Field(
        default=None,
        description="The Agent's role to be used from your repository.",
    )
-    guardrail: Optional[Union[Callable[[Any], Tuple[bool, Any]], str]] = Field(
+    guardrail: Callable[[Any], tuple[bool, Any]] | str | None = Field(
        default=None,
        description="Function or string description of a guardrail to validate agent output",
    )
@@ -180,7 +174,7 @@ class Agent(BaseAgent):
    )

    @model_validator(mode="before")
-    def validate_from_repository(cls, v):
+    def validate_from_repository(cls, v): # noqa: N805
        if v is not None and (from_repository := v.get("from_repository")):
            return load_agent_from_repository(from_repository) | v
        return v
@@ -208,7 +202,7 @@ class Agent(BaseAgent):
            self.cache_handler = CacheHandler()
        self.set_cache_handler(self.cache_handler)

-    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
+    def set_knowledge(self, crew_embedder: EmbedderConfig | None = None):
        try:
            if self.embedder is None and crew_embedder:
                self.embedder = crew_embedder
@@ -224,7 +218,7 @@ class Agent(BaseAgent):
                    )
                    self.knowledge.add_sources()
        except (TypeError, ValueError) as e:
-            raise ValueError(f"Invalid Knowledge Configuration: {str(e)}")
+            raise ValueError(f"Invalid Knowledge Configuration: {e!s}") from e

    def _is_any_available_memory(self) -> bool:
        """Check if any memory is available."""
@@ -244,8 +238,8 @@ class Agent(BaseAgent):
    def execute_task(
        self,
        task: Task,
-        context: Optional[str] = None,
-        tools: Optional[List[BaseTool]] = None,
+        context: str | None = None,
+        tools: list[BaseTool] | None = None,
    ) -> str:
        """Execute a task with the agent.

@@ -278,11 +272,9 @@ class Agent(BaseAgent):
                task.description += f"\n\nReasoning Plan:\n{reasoning_output.plan.plan}"
            except Exception as e:
                if hasattr(self, "_logger"):
-                    self._logger.log(
-                        "error", f"Error during reasoning process: {str(e)}"
-                    )
+                    self._logger.log("error", f"Error during reasoning process: {e!s}")
                else:
-                    print(f"Error during reasoning process: {str(e)}")
+                    print(f"Error during reasoning process: {e!s}")

        self._inject_date_to_task(task)

@@ -335,7 +327,7 @@ class Agent(BaseAgent):
                agent=self,
                task=task,
            )
-            memory = contextual_memory.build_context_for_task(task, context)
+            memory = contextual_memory.build_context_for_task(task, context)  # type: ignore[arg-type]
            if memory.strip() != "":
                task_prompt += self.i18n.slice("memory").format(memory=memory)

@@ -525,14 +517,14 @@ class Agent(BaseAgent):

            try:
                return future.result(timeout=timeout)
-            except concurrent.futures.TimeoutError:
+            except concurrent.futures.TimeoutError as e:
                future.cancel()
                raise TimeoutError(
                    f"Task '{task.description}' execution timed out after {timeout} seconds. Consider increasing max_execution_time or optimizing the task."
-                )
+                ) from e
            except Exception as e:
                future.cancel()
-                raise RuntimeError(f"Task execution failed: {str(e)}")
+                raise RuntimeError(f"Task execution failed: {e!s}") from e

    def _execute_without_timeout(self, task_prompt: str, task: Task) -> str:
        """Execute a task without a timeout.
@@ -554,14 +546,14 @@ class Agent(BaseAgent):
        )["output"]

    def create_agent_executor(
-        self, tools: Optional[List[BaseTool]] = None, task=None
+        self, tools: list[BaseTool] | None = None, task=None
    ) -> None:
        """Create an agent executor for the agent.

        Returns:
            An instance of the CrewAgentExecutor class.
        """
-        raw_tools: List[BaseTool] = tools or self.tools or []
+        raw_tools: list[BaseTool] = tools or self.tools or []
        parsed_tools = parse_tools(raw_tools)

        prompt = Prompts(
@@ -587,7 +579,7 @@ class Agent(BaseAgent):
            agent=self,
            crew=self.crew,
            tools=parsed_tools,
-            prompt=prompt,
+            prompt=prompt,  # type: ignore[arg-type]
            original_tools=raw_tools,
            stop_words=stop_words,
            max_iter=self.max_iter,
@@ -603,10 +595,9 @@ class Agent(BaseAgent):
            callbacks=[TokenCalcHandler(self._token_process)],
        )

-    def get_delegation_tools(self, agents: List[BaseAgent]):
+    def get_delegation_tools(self, agents: list[BaseAgent]):
        agent_tools = AgentTools(agents=agents)
-        tools = agent_tools.tools()
-        return tools
+        return agent_tools.tools()

    def get_multimodal_tools(self) -> Sequence[BaseTool]:
        from crewai.tools.agent_tools.add_image_tool import AddImageTool
@@ -654,7 +645,7 @@ class Agent(BaseAgent):
                )
        return task_prompt

-    def _render_text_description(self, tools: List[Any]) -> str:
+    def _render_text_description(self, tools: list[Any]) -> str:
        """Render the tool name and description in plain text.

        Output will be in the format of:
@@ -664,15 +655,13 @@ class Agent(BaseAgent):
            search: This tool is used for search
            calculator: This tool is used for math
        """
-        description = "\n".join(
+        return "\n".join(
            [
                f"Tool name: {tool.name}\nTool description:\n{tool.description}"
                for tool in tools
            ]
        )

-        return description
-
    def _inject_date_to_task(self, task):
        """Inject the current date into the task description if inject_date is enabled."""
        if self.inject_date:
@@ -696,13 +685,13 @@ class Agent(BaseAgent):
                if not is_valid:
                    raise ValueError(f"Invalid date format: {self.date_format}")

-                current_date: str = datetime.now().strftime(self.date_format)
+                current_date = datetime.now().strftime(self.date_format)
                task.description += f"\n\nCurrent Date: {current_date}"
            except Exception as e:
                if hasattr(self, "_logger"):
-                    self._logger.log("warning", f"Failed to inject date: {str(e)}")
+                    self._logger.log("warning", f"Failed to inject date: {e!s}")
                else:
-                    print(f"Warning: Failed to inject date: {str(e)}")
+                    print(f"Warning: Failed to inject date: {e!s}")

    def _validate_docker_installation(self) -> None:
        """Check if Docker is installed and running."""
@@ -713,15 +702,15 @@ class Agent(BaseAgent):

        try:
            subprocess.run(
-                ["docker", "info"],
+                ["/usr/bin/docker", "info"],
                check=True,
                stdout=subprocess.PIPE,
                stderr=subprocess.PIPE,
            )
-        except subprocess.CalledProcessError:
+        except subprocess.CalledProcessError as e:
            raise RuntimeError(
                f"Docker is not running. Please start Docker to use code execution with agent: {self.role}"
-            )
+            ) from e

    def __repr__(self):
        return f"Agent(role={self.role}, goal={self.goal}, backstory={self.backstory})"
@@ -796,8 +785,8 @@ class Agent(BaseAgent):

    def kickoff(
        self,
-        messages: Union[str, List[Dict[str, str]]],
-        response_format: Optional[Type[Any]] = None,
+        messages: str | list[dict[str, str]],
+        response_format: type[Any] | None = None,
    ) -> LiteAgentOutput:
        """
        Execute the agent with the given messages using a LiteAgent instance.
@@ -836,8 +825,8 @@ class Agent(BaseAgent):

    async def kickoff_async(
        self,
-        messages: Union[str, List[Dict[str, str]]],
-        response_format: Optional[Type[Any]] = None,
+        messages: str | list[dict[str, str]],
+        response_format: type[Any] | None = None,
    ) -> LiteAgentOutput:
        """
        Execute the agent asynchronously with the given messages using a LiteAgent instance.
--- a/src/crewai/agents/init.py
+++ b/src/crewai/agents/init.py
@@ -1,5 +1,12 @@
 from crewai.agents.cache.cache_handler import CacheHandler
-from crewai.agents.parser import parse, AgentAction, AgentFinish, OutputParserException
+from crewai.agents.parser import AgentAction, AgentFinish, OutputParserError, parse
 from crewai.agents.tools_handler import ToolsHandler

-__all__ = ["CacheHandler", "parse", "AgentAction", "AgentFinish", "OutputParserException", "ToolsHandler"]
+__all__ = [
+    "AgentAction",
+    "AgentFinish",
+    "CacheHandler",
+    "OutputParserError",
+    "ToolsHandler",
+    "parse",
+]
--- a/src/crewai/agents/agent_adapters/base_agent_adapter.py
+++ b/src/crewai/agents/agent_adapters/base_agent_adapter.py
@@ -1,7 +1,7 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
+from typing import Any

-from pydantic import PrivateAttr
+from pydantic import ConfigDict, PrivateAttr

 from crewai.agent import BaseAgent
 from crewai.tools import BaseTool
@@ -16,22 +16,21 @@ class BaseAgentAdapter(BaseAgent, ABC):
    """

    adapted_structured_output: bool = False
-    _agent_config: Optional[Dict[str, Any]] = PrivateAttr(default=None)
+    _agent_config: dict[str, Any] | None = PrivateAttr(default=None)

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)

-    def __init__(self, agent_config: Optional[Dict[str, Any]] = None, **kwargs: Any):
+    def __init__(self, agent_config: dict[str, Any] | None = None, **kwargs: Any):
        super().__init__(adapted_agent=True, **kwargs)
        self._agent_config = agent_config

    @abstractmethod
-    def configure_tools(self, tools: Optional[List[BaseTool]] = None) -> None:
+    def configure_tools(self, tools: list[BaseTool] | None = None) -> None:
        """Configure and adapt tools for the specific agent implementation.

        Args:
            tools: Optional list of BaseTool instances to be configured
        """
-        pass

    def configure_structured_output(self, structured_output: Any) -> None:
        """Configure the structured output for the specific agent implementation.
@@ -39,4 +38,3 @@ class BaseAgentAdapter(BaseAgent, ABC):
        Args:
            structured_output: The structured output to be configured
        """
-        pass
--- a/src/crewai/agents/agent_adapters/base_tool_adapter.py
+++ b/src/crewai/agents/agent_adapters/base_tool_adapter.py
@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, List, Optional
+from typing import Any

 from crewai.tools.base_tool import BaseTool

@@ -12,23 +12,22 @@ class BaseToolAdapter(ABC):
    different frameworks and platforms.
    """

-    original_tools: List[BaseTool]
-    converted_tools: List[Any]
+    original_tools: list[BaseTool]
+    converted_tools: list[Any]

-    def __init__(self, tools: Optional[List[BaseTool]] = None):
+    def __init__(self, tools: list[BaseTool] | None = None):
        self.original_tools = tools or []
        self.converted_tools = []

    @abstractmethod
-    def configure_tools(self, tools: List[BaseTool]) -> None:
+    def configure_tools(self, tools: list[BaseTool]) -> None:
        """Configure and convert tools for the specific implementation.

        Args:
            tools: List of BaseTool instances to be configured and converted
        """
-        pass

-    def tools(self) -> List[Any]:
+    def tools(self) -> list[Any]:
        """Return all converted tools."""
        return self.converted_tools

--- a/src/crewai/agents/agent_builder/base_agent.py
+++ b/src/crewai/agents/agent_builder/base_agent.py
@@ -1,8 +1,9 @@
 import uuid
 from abc import ABC, abstractmethod
+from collections.abc import Callable
 from copy import copy as shallow_copy
 from hashlib import md5
-from typing import Any, Callable, Dict, List, Optional, TypeVar
+from typing import Any, TypeVar

 from pydantic import (
    UUID4,
@@ -21,11 +22,11 @@ from crewai.agents.tools_handler import ToolsHandler
 from crewai.knowledge.knowledge import Knowledge
 from crewai.knowledge.knowledge_config import KnowledgeConfig
 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
+from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.security.security_config import SecurityConfig
 from crewai.tools.base_tool import BaseTool, Tool
 from crewai.utilities import I18N, Logger, RPMController
 from crewai.utilities.config import process_config
-from crewai.utilities.converter import Converter
 from crewai.utilities.string_utils import interpolate_only

 T = TypeVar("T", bound="BaseAgent")
@@ -81,17 +82,17 @@ class BaseAgent(ABC, BaseModel):

    __hash__ = object.__hash__  # type: ignore
    _logger: Logger = PrivateAttr(default_factory=lambda: Logger(verbose=False))
-    _rpm_controller: Optional[RPMController] = PrivateAttr(default=None)
+    _rpm_controller: RPMController | None = PrivateAttr(default=None)
    _request_within_rpm_limit: Any = PrivateAttr(default=None)
-    _original_role: Optional[str] = PrivateAttr(default=None)
-    _original_goal: Optional[str] = PrivateAttr(default=None)
-    _original_backstory: Optional[str] = PrivateAttr(default=None)
+    _original_role: str | None = PrivateAttr(default=None)
+    _original_goal: str | None = PrivateAttr(default=None)
+    _original_backstory: str | None = PrivateAttr(default=None)
    _token_process: TokenProcess = PrivateAttr(default_factory=TokenProcess)
    id: UUID4 = Field(default_factory=uuid.uuid4, frozen=True)
    role: str = Field(description="Role of the agent")
    goal: str = Field(description="Objective of the agent")
    backstory: str = Field(description="Backstory of the agent")
-    config: Optional[Dict[str, Any]] = Field(
+    config: dict[str, Any] | None = Field(
        description="Configuration for the agent", default=None, exclude=True
    )
    cache: bool = Field(
@@ -100,7 +101,7 @@ class BaseAgent(ABC, BaseModel):
    verbose: bool = Field(
        default=False, description="Verbose mode for the Agent Execution"
    )
-    max_rpm: Optional[int] = Field(
+    max_rpm: int | None = Field(
        default=None,
        description="Maximum number of requests per minute for the agent execution to be respected.",
    )
@@ -108,7 +109,7 @@ class BaseAgent(ABC, BaseModel):
        default=False,
        description="Enable agent to delegate and ask questions among each other.",
    )
-    tools: Optional[List[BaseTool]] = Field(
+    tools: list[BaseTool] | None = Field(
        default_factory=list, description="Tools at agents' disposal"
    )
    max_iter: int = Field(
@@ -122,27 +123,27 @@ class BaseAgent(ABC, BaseModel):
    )
    crew: Any = Field(default=None, description="Crew to which the agent belongs.")
    i18n: I18N = Field(default=I18N(), description="Internationalization settings.")
-    cache_handler: Optional[InstanceOf[CacheHandler]] = Field(
+    cache_handler: InstanceOf[CacheHandler] | None = Field(
        default=None, description="An instance of the CacheHandler class."
    )
    tools_handler: InstanceOf[ToolsHandler] = Field(
        default_factory=ToolsHandler,
        description="An instance of the ToolsHandler class.",
    )
-    tools_results: List[Dict[str, Any]] = Field(
+    tools_results: list[dict[str, Any]] = Field(
        default=[], description="Results of the tools used by the agent."
    )
-    max_tokens: Optional[int] = Field(
+    max_tokens: int | None = Field(
        default=None, description="Maximum number of tokens for the agent's execution."
    )
-    knowledge: Optional[Knowledge] = Field(
+    knowledge: Knowledge | None = Field(
        default=None, description="Knowledge for the agent."
    )
-    knowledge_sources: Optional[List[BaseKnowledgeSource]] = Field(
+    knowledge_sources: list[BaseKnowledgeSource] | None = Field(
        default=None,
        description="Knowledge sources for the agent.",
    )
-    knowledge_storage: Optional[Any] = Field(
+    knowledge_storage: Any | None = Field(
        default=None,
        description="Custom knowledge storage for the agent.",
    )
@@ -150,13 +151,13 @@ class BaseAgent(ABC, BaseModel):
        default_factory=SecurityConfig,
        description="Security configuration for the agent, including fingerprinting.",
    )
-    callbacks: List[Callable] = Field(
+    callbacks: list[Callable] = Field(
        default=[], description="Callbacks to be used for the agent"
    )
    adapted_agent: bool = Field(
        default=False, description="Whether the agent is adapted"
    )
-    knowledge_config: Optional[KnowledgeConfig] = Field(
+    knowledge_config: KnowledgeConfig | None = Field(
        default=None,
        description="Knowledge configuration for the agent such as limits and threshold",
    )
@@ -168,7 +169,7 @@ class BaseAgent(ABC, BaseModel):

    @field_validator("tools")
    @classmethod
-    def validate_tools(cls, tools: List[Any]) -> List[BaseTool]:
+    def validate_tools(cls, tools: list[Any]) -> list[BaseTool]:
        """Validate and process the tools provided to the agent.

        This method ensures that each tool is either an instance of BaseTool
@@ -221,7 +222,7 @@ class BaseAgent(ABC, BaseModel):

    @field_validator("id", mode="before")
    @classmethod
-    def _deny_user_set_id(cls, v: Optional[UUID4]) -> None:
+    def _deny_user_set_id(cls, v: UUID4 | None) -> None:
        if v:
            raise PydanticCustomError(
                "may_not_set_field", "This field is not to be set by the user.", {}
@@ -252,8 +253,8 @@ class BaseAgent(ABC, BaseModel):
    def execute_task(
        self,
        task: Any,
-        context: Optional[str] = None,
-        tools: Optional[List[BaseTool]] = None,
+        context: str | None = None,
+        tools: list[BaseTool] | None = None,
    ) -> str:
        pass

@@ -262,9 +263,8 @@ class BaseAgent(ABC, BaseModel):
        pass

    @abstractmethod
-    def get_delegation_tools(self, agents: List["BaseAgent"]) -> List[BaseTool]:
+    def get_delegation_tools(self, agents: list["BaseAgent"]) -> list[BaseTool]:
        """Set the task tools that init BaseAgenTools class."""
-        pass

    def copy(self: T) -> T:  # type: ignore # Signature of "copy" incompatible with supertype "BaseModel"
        """Create a deep copy of the Agent."""
@@ -309,7 +309,7 @@ class BaseAgent(ABC, BaseModel):

        copied_data = self.model_dump(exclude=exclude)
        copied_data = {k: v for k, v in copied_data.items() if v is not None}
-        copied_agent = type(self)(
+        return type(self)(
            **copied_data,
            llm=existing_llm,
            tools=self.tools,
@@ -318,9 +318,7 @@ class BaseAgent(ABC, BaseModel):
            knowledge_storage=copied_knowledge_storage,
        )

-        return copied_agent
-
-    def interpolate_inputs(self, inputs: Dict[str, Any]) -> None:
+    def interpolate_inputs(self, inputs: dict[str, Any]) -> None:
        """Interpolate inputs into the agent description and backstory."""
        if self._original_role is None:
            self._original_role = self.role
@@ -362,5 +360,5 @@ class BaseAgent(ABC, BaseModel):
            self._rpm_controller = rpm_controller
            self.create_agent_executor()

-    def set_knowledge(self, crew_embedder: Optional[Dict[str, Any]] = None):
+    def set_knowledge(self, crew_embedder: EmbedderConfig | None = None):
        pass
--- a/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
+++ b/src/crewai/agents/agent_builder/base_agent_executor_mixin.py
@@ -1,13 +1,13 @@
 import time
-from typing import TYPE_CHECKING, Dict, List
+from typing import TYPE_CHECKING

+from crewai.events.event_listener import event_listener
 from crewai.memory.entity.entity_memory_item import EntityMemoryItem
 from crewai.memory.long_term.long_term_memory_item import LongTermMemoryItem
 from crewai.utilities import I18N
 from crewai.utilities.converter import ConverterError
 from crewai.utilities.evaluators.task_evaluator import TaskEvaluator
 from crewai.utilities.printer import Printer
-from crewai.events.event_listener import event_listener

 if TYPE_CHECKING:
    from crewai.agents.agent_builder.base_agent import BaseAgent
@@ -21,7 +21,7 @@ class CrewAgentExecutorMixin:
    task: "Task"
    iterations: int
    max_iter: int
-    messages: List[Dict[str, str]]
+    messages: list[dict[str, str]]
    _i18n: I18N
    _printer: Printer = Printer()

@@ -46,7 +46,6 @@ class CrewAgentExecutorMixin:
                    )
            except Exception as e:
                print(f"Failed to add to short term memory: {e}")
-                pass

    def _create_external_memory(self, output) -> None:
        """Create and save a external-term memory item if conditions are met."""
@@ -67,7 +66,6 @@ class CrewAgentExecutorMixin:
                )
            except Exception as e:
                print(f"Failed to add to external memory: {e}")
-                pass

    def _create_long_term_memory(self, output) -> None:
        """Create and save long-term and entity memory items based on evaluation."""
@@ -113,10 +111,8 @@ class CrewAgentExecutorMixin:
                    self.crew._entity_memory.save(entity_memories)
            except AttributeError as e:
                print(f"Missing attributes for long term memory: {e}")
-                pass
            except Exception as e:
                print(f"Failed to add to long term memory: {e}")
-                pass
        elif (
            self.crew
            and self.crew._long_term_memory
--- a/src/crewai/agents/crew_agent_executor.py
+++ b/src/crewai/agents/crew_agent_executor.py
@@ -12,7 +12,7 @@ from crewai.agents.agent_builder.base_agent_executor_mixin import CrewAgentExecu
 from crewai.agents.parser import (
    AgentAction,
    AgentFinish,
-    OutputParserException,
+    OutputParserError,
 )
 from crewai.agents.tools_handler import ToolsHandler
 from crewai.events.event_bus import crewai_event_bus
@@ -228,7 +228,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                self._invoke_step_callback(formatted_answer)
                self._append_message(formatted_answer.text)

-            except OutputParserException as e:
+            except OutputParserError as e:  # noqa: PERF203
                formatted_answer = handle_output_parser_exception(
                    e=e,
                    messages=self.messages,
@@ -251,17 +251,20 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
                        i18n=self._i18n,
                    )
                    continue
-                else:
-                    handle_unknown_error(self._printer, e)
-                    raise e
+                handle_unknown_error(self._printer, e)
+                raise e
            finally:
                self.iterations += 1

        # During the invoke loop, formatted_answer alternates between AgentAction
        # (when the agent is using tools) and eventually becomes AgentFinish
-        # (when the agent reaches a final answer). This assertion confirms we've
+        # (when the agent reaches a final answer). This check confirms we've
        # reached a final answer and helps type checking understand this transition.
-        assert isinstance(formatted_answer, AgentFinish)
+        if not isinstance(formatted_answer, AgentFinish):
+            raise RuntimeError(
+                "Agent execution ended without reaching a final answer. "
+                f"Got {type(formatted_answer).__name__} instead of AgentFinish."
+            )
        self._show_logs(formatted_answer)
        return formatted_answer

@@ -324,9 +327,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
            self.agent,
            AgentLogsStartedEvent(
                agent_role=self.agent.role,
-                task_description=(
-                    getattr(self.task, "description") if self.task else "Not Found"
-                ),
+                task_description=(self.task.description if self.task else "Not Found"),
                verbose=self.agent.verbose
                or (hasattr(self, "crew") and getattr(self.crew, "verbose", False)),
            ),
@@ -415,8 +416,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
        """
        prompt = prompt.replace("{input}", inputs["input"])
        prompt = prompt.replace("{tool_names}", inputs["tool_names"])
-        prompt = prompt.replace("{tools}", inputs["tools"])
-        return prompt
+        return prompt.replace("{tools}", inputs["tools"])

    def _handle_human_feedback(self, formatted_answer: AgentFinish) -> AgentFinish:
        """Process human feedback.
--- a/src/crewai/agents/parser.py
+++ b/src/crewai/agents/parser.py
@@ -7,18 +7,18 @@ AgentAction or AgentFinish objects.

 from dataclasses import dataclass

-from json_repair import repair_json
+from json_repair import repair_json  # type: ignore[import-untyped]

 from crewai.agents.constants import (
+    ACTION_INPUT_ONLY_REGEX,
    ACTION_INPUT_REGEX,
    ACTION_REGEX,
-    ACTION_INPUT_ONLY_REGEX,
    FINAL_ANSWER_ACTION,
    MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE,
    MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
    UNABLE_TO_REPAIR_JSON_RESULTS,
 )
-from crewai.utilities import I18N
+from crewai.utilities.i18n import I18N

 _I18N = I18N()

@@ -43,7 +43,7 @@ class AgentFinish:
    text: str


-class OutputParserException(Exception):
+class OutputParserError(Exception):
    """Exception raised when output parsing fails.

    Attributes:
@@ -51,7 +51,7 @@ class OutputParserException(Exception):
    """

    def __init__(self, error: str) -> None:
-        """Initialize OutputParserException.
+        """Initialize OutputParserError.

        Args:
            error: The error message.
@@ -87,7 +87,7 @@ def parse(text: str) -> AgentAction | AgentFinish:
        AgentAction or AgentFinish based on the content.

    Raises:
-        OutputParserException: If the text format is invalid.
+        OutputParserError: If the text format is invalid.
    """
    thought = _extract_thought(text)
    includes_answer = FINAL_ANSWER_ACTION in text
@@ -104,7 +104,7 @@ def parse(text: str) -> AgentAction | AgentFinish:
                final_answer = final_answer[:-3].rstrip()
        return AgentFinish(thought=thought, output=final_answer, text=text)

-    elif action_match:
+    if action_match:
        action = action_match.group(1)
        clean_action = _clean_action(action)

@@ -118,19 +118,18 @@ def parse(text: str) -> AgentAction | AgentFinish:
        )

    if not ACTION_REGEX.search(text):
-        raise OutputParserException(
+        raise OutputParserError(
            f"{MISSING_ACTION_AFTER_THOUGHT_ERROR_MESSAGE}\n{_I18N.slice('final_answer_format')}",
        )
-    elif not ACTION_INPUT_ONLY_REGEX.search(text):
-        raise OutputParserException(
+    if not ACTION_INPUT_ONLY_REGEX.search(text):
+        raise OutputParserError(
            MISSING_ACTION_INPUT_AFTER_ACTION_ERROR_MESSAGE,
        )
-    else:
-        err_format = _I18N.slice("format_without_tools")
-        error = f"{err_format}"
-        raise OutputParserException(
-            error,
-        )
+    err_format = _I18N.slice("format_without_tools")
+    error = f"{err_format}"
+    raise OutputParserError(
+        error,
+    )


 def _extract_thought(text: str) -> str:
@@ -149,8 +148,7 @@ def _extract_thought(text: str) -> str:
        return ""
    thought = text[:thought_index].strip()
    # Remove any triple backticks from the thought string
-    thought = thought.replace("```", "").strip()
-    return thought
+    return thought.replace("```", "").strip()


 def _clean_action(text: str) -> str:
--- a/src/crewai/agents/tools_handler.py
+++ b/src/crewai/agents/tools_handler.py
@@ -1,8 +1,10 @@
 """Tools handler for managing tool execution and caching."""

+import json
+
+from crewai.agents.cache.cache_handler import CacheHandler
 from crewai.tools.cache_tools.cache_tools import CacheTools
 from crewai.tools.tool_calling import InstructorToolCalling, ToolCalling
-from crewai.agents.cache.cache_handler import CacheHandler


 class ToolsHandler:
@@ -37,8 +39,16 @@ class ToolsHandler:
        """
        self.last_used_tool = calling
        if self.cache and should_cache and calling.tool_name != CacheTools().name:
+            # Convert arguments to string for cache
+            input_str = ""
+            if calling.arguments:
+                if isinstance(calling.arguments, dict):
+                    input_str = json.dumps(calling.arguments)
+                else:
+                    input_str = str(calling.arguments)
+
            self.cache.add(
                tool=calling.tool_name,
-                input=calling.arguments,
+                input=input_str,
                output=output,
            )
--- a/src/crewai/cli/authentication/providers/init.py
+++ b/src/crewai/cli/authentication/providers/init.py
--- a/src/crewai/cli/authentication/providers/auth0.py
+++ b/src/crewai/cli/authentication/providers/auth0.py
@@ -1,5 +1,6 @@
 from crewai.cli.authentication.providers.base_provider import BaseProvider

+
 class Auth0Provider(BaseProvider):
    def get_authorize_url(self) -> str:
        return f"https://{self._get_domain()}/oauth/device/code"
@@ -14,13 +15,20 @@ class Auth0Provider(BaseProvider):
        return f"https://{self._get_domain()}/"

    def get_audience(self) -> str:
-        assert self.settings.audience is not None, "Audience is required"
+        if self.settings.audience is None:
+            raise ValueError(
+                "Audience is required. Please set it in the configuration."
+            )
        return self.settings.audience

    def get_client_id(self) -> str:
-        assert self.settings.client_id is not None, "Client ID is required"
+        if self.settings.client_id is None:
+            raise ValueError(
+                "Client ID is required. Please set it in the configuration."
+            )
        return self.settings.client_id

    def _get_domain(self) -> str:
-        assert self.settings.domain is not None, "Domain is required"
+        if self.settings.domain is None:
+            raise ValueError("Domain is required. Please set it in the configuration.")
        return self.settings.domain
--- a/src/crewai/cli/authentication/providers/base_provider.py
+++ b/src/crewai/cli/authentication/providers/base_provider.py
@@ -1,30 +1,26 @@
 from abc import ABC, abstractmethod
+
 from crewai.cli.authentication.main import Oauth2Settings

+
 class BaseProvider(ABC):
    def __init__(self, settings: Oauth2Settings):
        self.settings = settings

    @abstractmethod
-    def get_authorize_url(self) -> str:
-        ...
+    def get_authorize_url(self) -> str: ...

    @abstractmethod
-    def get_token_url(self) -> str:
-        ...
+    def get_token_url(self) -> str: ...

    @abstractmethod
-    def get_jwks_url(self) -> str:
-        ...
+    def get_jwks_url(self) -> str: ...

    @abstractmethod
-    def get_issuer(self) -> str:
-        ...
+    def get_issuer(self) -> str: ...

    @abstractmethod
-    def get_audience(self) -> str:
-        ...
+    def get_audience(self) -> str: ...

    @abstractmethod
-    def get_client_id(self) -> str:
-        ...
+    def get_client_id(self) -> str: ...
--- a/src/crewai/cli/authentication/providers/okta.py
+++ b/src/crewai/cli/authentication/providers/okta.py
@@ -1,5 +1,6 @@
 from crewai.cli.authentication.providers.base_provider import BaseProvider

+
 class OktaProvider(BaseProvider):
    def get_authorize_url(self) -> str:
        return f"https://{self.settings.domain}/oauth2/default/v1/device/authorize"
@@ -14,9 +15,15 @@ class OktaProvider(BaseProvider):
        return f"https://{self.settings.domain}/oauth2/default"

    def get_audience(self) -> str:
-        assert self.settings.audience is not None
+        if self.settings.audience is None:
+            raise ValueError(
+                "Audience is required. Please set it in the configuration."
+            )
        return self.settings.audience

    def get_client_id(self) -> str:
-        assert self.settings.client_id is not None
+        if self.settings.client_id is None:
+            raise ValueError(
+                "Client ID is required. Please set it in the configuration."
+            )
        return self.settings.client_id
--- a/src/crewai/cli/authentication/providers/workos.py
+++ b/src/crewai/cli/authentication/providers/workos.py
@@ -1,5 +1,6 @@
 from crewai.cli.authentication.providers.base_provider import BaseProvider

+
 class WorkosProvider(BaseProvider):
    def get_authorize_url(self) -> str:
        return f"https://{self._get_domain()}/oauth2/device_authorization"
@@ -17,9 +18,13 @@ class WorkosProvider(BaseProvider):
        return self.settings.audience or ""

    def get_client_id(self) -> str:
-        assert self.settings.client_id is not None, "Client ID is required"
+        if self.settings.client_id is None:
+            raise ValueError(
+                "Client ID is required. Please set it in the configuration."
+            )
        return self.settings.client_id

    def _get_domain(self) -> str:
-        assert self.settings.domain is not None, "Domain is required"
+        if self.settings.domain is None:
+            raise ValueError("Domain is required. Please set it in the configuration.")
        return self.settings.domain
--- a/src/crewai/cli/authentication/utils.py
+++ b/src/crewai/cli/authentication/utils.py
@@ -17,8 +17,6 @@ def validate_jwt_token(
                       missing required claims).
    """

-    decoded_token = None
-
    try:
        jwk_client = PyJWKClient(jwks_url)
        signing_key = jwk_client.get_signing_key_from_jwt(jwt_token)
@@ -26,7 +24,7 @@ def validate_jwt_token(
        _unverified_decoded_token = jwt.decode(
            jwt_token, options={"verify_signature": False}
        )
-        decoded_token = jwt.decode(
+        return jwt.decode(
            jwt_token,
            signing_key.key,
            algorithms=["RS256"],
@@ -40,23 +38,22 @@ def validate_jwt_token(
                "require": ["exp", "iat", "iss", "aud", "sub"],
            },
        )
-        return decoded_token

-    except jwt.ExpiredSignatureError:
-        raise Exception("Token has expired.")
-    except jwt.InvalidAudienceError:
+    except jwt.ExpiredSignatureError as e:
+        raise Exception("Token has expired.") from e
+    except jwt.InvalidAudienceError as e:
        actual_audience = _unverified_decoded_token.get("aud", "[no audience found]")
        raise Exception(
            f"Invalid token audience. Got: '{actual_audience}'. Expected: '{audience}'"
-        )
-    except jwt.InvalidIssuerError:
+        ) from e
+    except jwt.InvalidIssuerError as e:
        actual_issuer = _unverified_decoded_token.get("iss", "[no issuer found]")
        raise Exception(
            f"Invalid token issuer. Got: '{actual_issuer}'. Expected: '{issuer}'"
-        )
+        ) from e
    except jwt.MissingRequiredClaimError as e:
-        raise Exception(f"Token is missing required claims: {str(e)}")
+        raise Exception(f"Token is missing required claims: {e!s}") from e
    except jwt.exceptions.PyJWKClientError as e:
-        raise Exception(f"JWKS or key processing error: {str(e)}")
+        raise Exception(f"JWKS or key processing error: {e!s}") from e
    except jwt.InvalidTokenError as e:
-        raise Exception(f"Invalid token: {str(e)}")
+        raise Exception(f"Invalid token: {e!s}") from e
--- a/src/crewai/cli/cli.py
+++ b/src/crewai/cli/cli.py
@@ -1,13 +1,16 @@
+import os
+import subprocess
 from importlib.metadata import version as get_version
-from typing import Optional

 import click
-from crewai.cli.config import Settings
-from crewai.cli.settings.main import SettingsCommand
+
 from crewai.cli.add_crew_to_flow import add_crew_to_flow
+from crewai.cli.config import Settings
 from crewai.cli.create_crew import create_crew
 from crewai.cli.create_flow import create_flow
 from crewai.cli.crew_chat import run_chat
+from crewai.cli.settings.main import SettingsCommand
+from crewai.cli.utils import build_env_with_tool_repository_credentials, read_toml
 from crewai.memory.storage.kickoff_task_outputs_storage import (
    KickoffTaskOutputsSQLiteStorage,
 )
@@ -34,6 +37,46 @@ def crewai():
    """Top-level command group for crewai."""


+@crewai.command(
+    name="uv",
+    context_settings=dict(
+        ignore_unknown_options=True,
+    ),
+)
+@click.argument("uv_args", nargs=-1, type=click.UNPROCESSED)
+def uv(uv_args):
+    """A wrapper around uv commands that adds custom tool authentication through env vars."""
+    env = os.environ.copy()
+    try:
+        pyproject_data = read_toml()
+        sources = pyproject_data.get("tool", {}).get("uv", {}).get("sources", {})
+
+        for source_config in sources.values():
+            if isinstance(source_config, dict):
+                index = source_config.get("index")
+                if index:
+                    index_env = build_env_with_tool_repository_credentials(index)
+                    env.update(index_env)
+    except (FileNotFoundError, KeyError) as e:
+        raise SystemExit(
+            "Error. A valid pyproject.toml file is required. Check that a valid pyproject.toml file exists in the current directory."
+        ) from e
+    except Exception as e:
+        raise SystemExit(f"Error: {e}") from e
+
+    try:
+        subprocess.run(  # noqa: S603
+            ["uv", *uv_args],  # noqa: S607
+            capture_output=False,
+            env=env,
+            text=True,
+            check=True,
+        )
+    except subprocess.CalledProcessError as e:
+        click.secho(f"uv command failed with exit code {e.returncode}", fg="red")
+        raise SystemExit(e.returncode) from e
+
+
@crewai.command()
@click.argument("type", type=click.Choice(["crew", "flow"]))
@click.argument("name")
@@ -237,13 +280,6 @@ def login():
@crewai.group()
 def deploy():
    """Deploy the Crew CLI group."""
-    pass
-
-
-@crewai.group()
-def tool():
-    """Tool Repository related commands."""
-    pass


@deploy.command(name="create")
@@ -263,7 +299,7 @@ def deploy_list():

@deploy.command(name="push")
@click.option("-u", "--uuid", type=str, help="Crew UUID parameter")
-def deploy_push(uuid: Optional[str]):
+def deploy_push(uuid: str | None):
    """Deploy the Crew."""
    deploy_cmd = DeployCommand()
    deploy_cmd.deploy(uuid=uuid)
@@ -271,7 +307,7 @@ def deploy_push(uuid: Optional[str]):

@deploy.command(name="status")
@click.option("-u", "--uuid", type=str, help="Crew UUID parameter")
-def deply_status(uuid: Optional[str]):
+def deply_status(uuid: str | None):
    """Get the status of a deployment."""
    deploy_cmd = DeployCommand()
    deploy_cmd.get_crew_status(uuid=uuid)
@@ -279,7 +315,7 @@ def deply_status(uuid: Optional[str]):

@deploy.command(name="logs")
@click.option("-u", "--uuid", type=str, help="Crew UUID parameter")
-def deploy_logs(uuid: Optional[str]):
+def deploy_logs(uuid: str | None):
    """Get the logs of a deployment."""
    deploy_cmd = DeployCommand()
    deploy_cmd.get_crew_logs(uuid=uuid)
@@ -287,12 +323,17 @@ def deploy_logs(uuid: Optional[str]):

@deploy.command(name="remove")
@click.option("-u", "--uuid", type=str, help="Crew UUID parameter")
-def deploy_remove(uuid: Optional[str]):
+def deploy_remove(uuid: str | None):
    """Remove a deployment."""
    deploy_cmd = DeployCommand()
    deploy_cmd.remove_crew(uuid=uuid)


+@crewai.group()
+def tool():
+    """Tool Repository related commands."""
+
+
@tool.command(name="create")
@click.argument("handle")
 def tool_create(handle: str):
@@ -327,7 +368,6 @@ def tool_publish(is_public: bool, force: bool):
@crewai.group()
 def flow():
    """Flow related commands."""
-    pass


@flow.command(name="kickoff")
@@ -359,7 +399,7 @@ def chat():
    and using the Chat LLM to generate responses.
    """
    click.secho(
-        "\nStarting a conversation with the Crew\n" "Type 'exit' or Ctrl+C to quit.\n",
+        "\nStarting a conversation with the Crew\nType 'exit' or Ctrl+C to quit.\n",
    )

    run_chat()
@@ -368,7 +408,6 @@ def chat():
@crewai.group(invoke_without_command=True)
 def org():
    """Organization management commands."""
-    pass


@org.command("list")
@@ -396,7 +435,6 @@ def current():
@crewai.group()
 def enterprise():
    """Enterprise Configuration commands."""
-    pass


@enterprise.command("configure")
@@ -410,7 +448,6 @@ def enterprise_configure(enterprise_url: str):
@crewai.group()
 def config():
    """CLI Configuration commands."""
-    pass


@config.command("list")
--- a/src/crewai/cli/config.py
+++ b/src/crewai/cli/config.py
@@ -1,20 +1,61 @@
 import json
+import tempfile
+from logging import getLogger
 from pathlib import Path
-from typing import Optional

 from pydantic import BaseModel, Field

 from crewai.cli.constants import (
-    DEFAULT_CREWAI_ENTERPRISE_URL,
-    CREWAI_ENTERPRISE_DEFAULT_OAUTH2_PROVIDER,
    CREWAI_ENTERPRISE_DEFAULT_OAUTH2_AUDIENCE,
    CREWAI_ENTERPRISE_DEFAULT_OAUTH2_CLIENT_ID,
    CREWAI_ENTERPRISE_DEFAULT_OAUTH2_DOMAIN,
+    CREWAI_ENTERPRISE_DEFAULT_OAUTH2_PROVIDER,
+    DEFAULT_CREWAI_ENTERPRISE_URL,
 )
 from crewai.cli.shared.token_manager import TokenManager

+logger = getLogger(__name__)
+
 DEFAULT_CONFIG_PATH = Path.home() / ".config" / "crewai" / "settings.json"

+
+def get_writable_config_path() -> Path | None:
+    """
+    Find a writable location for the config file with fallback options.
+
+    Tries in order:
+    1. Default: ~/.config/crewai/settings.json
+    2. Temp directory: /tmp/crewai_settings.json (or OS equivalent)
+    3. Current directory: ./crewai_settings.json
+    4. In-memory only (returns None)
+
+    Returns:
+        Path object for writable config location, or None if no writable location found
+    """
+    fallback_paths = [
+        DEFAULT_CONFIG_PATH,  # Default location
+        Path(tempfile.gettempdir()) / "crewai_settings.json",  # Temporary directory
+        Path.cwd() / "crewai_settings.json",  # Current working directory
+    ]
+
+    for config_path in fallback_paths:
+        try:
+            config_path.parent.mkdir(parents=True, exist_ok=True)
+            test_file = config_path.parent / ".crewai_write_test"
+            try:
+                test_file.write_text("test")
+                test_file.unlink()  # Clean up test file
+                logger.info(f"Using config path: {config_path}")
+                return config_path
+            except Exception:  # noqa: S112
+                continue
+
+        except Exception:  # noqa: S112
+            continue
+
+    return None
+
+
 # Settings that are related to the user's account
 USER_SETTINGS_KEYS = [
    "tool_repository_username",
@@ -56,20 +97,20 @@ HIDDEN_SETTINGS_KEYS = [


 class Settings(BaseModel):
-    enterprise_base_url: Optional[str] = Field(
+    enterprise_base_url: str | None = Field(
        default=DEFAULT_CLI_SETTINGS["enterprise_base_url"],
        description="Base URL of the CrewAI Enterprise instance",
    )
-    tool_repository_username: Optional[str] = Field(
+    tool_repository_username: str | None = Field(
        None, description="Username for interacting with the Tool Repository"
    )
-    tool_repository_password: Optional[str] = Field(
+    tool_repository_password: str | None = Field(
        None, description="Password for interacting with the Tool Repository"
    )
-    org_name: Optional[str] = Field(
+    org_name: str | None = Field(
        None, description="Name of the currently active organization"
    )
-    org_uuid: Optional[str] = Field(
+    org_uuid: str | None = Field(
        None, description="UUID of the currently active organization"
    )
    config_path: Path = Field(default=DEFAULT_CONFIG_PATH, frozen=True, exclude=True)
@@ -79,7 +120,7 @@ class Settings(BaseModel):
        default=DEFAULT_CLI_SETTINGS["oauth2_provider"],
    )

-    oauth2_audience: Optional[str] = Field(
+    oauth2_audience: str | None = Field(
        description="OAuth2 audience value, typically used to identify the target API or resource.",
        default=DEFAULT_CLI_SETTINGS["oauth2_audience"],
    )
@@ -94,16 +135,32 @@ class Settings(BaseModel):
        default=DEFAULT_CLI_SETTINGS["oauth2_domain"],
    )

-    def __init__(self, config_path: Path = DEFAULT_CONFIG_PATH, **data):
-        """Load Settings from config path"""
-        config_path.parent.mkdir(parents=True, exist_ok=True)
+    def __init__(self, config_path: Path | None = None, **data):
+        """Load Settings from config path with fallback support"""
+        if config_path is None:
+            config_path = get_writable_config_path()
+
+        # If config_path is None, we're in memory-only mode
+        if config_path is None:
+            merged_data = {**data}
+            # Dummy path for memory-only mode
+            super().__init__(config_path=Path("/dev/null"), **merged_data)
+            return
+
+        try:
+            config_path.parent.mkdir(parents=True, exist_ok=True)
+        except Exception:
+            merged_data = {**data}
+            # Dummy path for memory-only mode
+            super().__init__(config_path=Path("/dev/null"), **merged_data)
+            return

        file_data = {}
        if config_path.is_file():
            try:
                with config_path.open("r") as f:
                    file_data = json.load(f)
-            except json.JSONDecodeError:
+            except Exception:
                file_data = {}

        merged_data = {**file_data, **data}
@@ -123,15 +180,22 @@ class Settings(BaseModel):

    def dump(self) -> None:
        """Save current settings to settings.json"""
-        if self.config_path.is_file():
-            with self.config_path.open("r") as f:
-                existing_data = json.load(f)
-        else:
-            existing_data = {}
+        if str(self.config_path) == "/dev/null":
+            return

-        updated_data = {**existing_data, **self.model_dump(exclude_unset=True)}
-        with self.config_path.open("w") as f:
-            json.dump(updated_data, f, indent=4)
+        try:
+            if self.config_path.is_file():
+                with self.config_path.open("r") as f:
+                    existing_data = json.load(f)
+            else:
+                existing_data = {}
+
+            updated_data = {**existing_data, **self.model_dump(exclude_unset=True)}
+            with self.config_path.open("w") as f:
+                json.dump(updated_data, f, indent=4)
+
+        except Exception:  # noqa: S110
+            pass

    def _reset_user_settings(self) -> None:
        """Reset all user settings to default values"""
--- a/src/crewai/cli/create_crew.py
+++ b/src/crewai/cli/create_crew.py
@@ -16,48 +16,72 @@ from crewai.cli.utils import copy_template, load_env_vars, write_env_file
 def create_folder_structure(name, parent_folder=None):
    import keyword
    import re
-    
-    name = name.rstrip('/')
-    
+
+    name = name.rstrip("/")
+
    if not name.strip():
        raise ValueError("Project name cannot be empty or contain only whitespace")
-    
+
    folder_name = name.replace(" ", "_").replace("-", "_").lower()
-    folder_name = re.sub(r'[^a-zA-Z0-9_]', '', folder_name)
-    
+    folder_name = re.sub(r"[^a-zA-Z0-9_]", "", folder_name)
+
    # Check if the name starts with invalid characters or is primarily invalid
-    if re.match(r'^[^a-zA-Z0-9_-]+', name):
-        raise ValueError(f"Project name '{name}' contains no valid characters for a Python module name")
-    
+    if re.match(r"^[^a-zA-Z0-9_-]+", name):
+        raise ValueError(
+            f"Project name '{name}' contains no valid characters for a Python module name"
+        )
+
    if not folder_name:
-        raise ValueError(f"Project name '{name}' contains no valid characters for a Python module name")
-    
+        raise ValueError(
+            f"Project name '{name}' contains no valid characters for a Python module name"
+        )
+
    if folder_name[0].isdigit():
-        raise ValueError(f"Project name '{name}' would generate folder name '{folder_name}' which cannot start with a digit (invalid Python module name)")
-    
+        raise ValueError(
+            f"Project name '{name}' would generate folder name '{folder_name}' which cannot start with a digit (invalid Python module name)"
+        )
+
    if keyword.iskeyword(folder_name):
-        raise ValueError(f"Project name '{name}' would generate folder name '{folder_name}' which is a reserved Python keyword")
-    
+        raise ValueError(
+            f"Project name '{name}' would generate folder name '{folder_name}' which is a reserved Python keyword"
+        )
+
    if not folder_name.isidentifier():
-        raise ValueError(f"Project name '{name}' would generate invalid Python module name '{folder_name}'")
-    
+        raise ValueError(
+            f"Project name '{name}' would generate invalid Python module name '{folder_name}'"
+        )
+
    class_name = name.replace("_", " ").replace("-", " ").title().replace(" ", "")
-    
-    class_name = re.sub(r'[^a-zA-Z0-9_]', '', class_name)
-    
+
+    class_name = re.sub(r"[^a-zA-Z0-9_]", "", class_name)
+
    if not class_name:
-        raise ValueError(f"Project name '{name}' contains no valid characters for a Python class name")
-    
+        raise ValueError(
+            f"Project name '{name}' contains no valid characters for a Python class name"
+        )
+
    if class_name[0].isdigit():
-        raise ValueError(f"Project name '{name}' would generate class name '{class_name}' which cannot start with a digit")
-    
+        raise ValueError(
+            f"Project name '{name}' would generate class name '{class_name}' which cannot start with a digit"
+        )
+
    # Check if the original name (before title casing) is a keyword
-    original_name_clean = re.sub(r'[^a-zA-Z0-9_]', '', name.replace("_", "").replace("-", "").lower())
-    if keyword.iskeyword(original_name_clean) or keyword.iskeyword(class_name) or class_name in ('True', 'False', 'None'):
-        raise ValueError(f"Project name '{name}' would generate class name '{class_name}' which is a reserved Python keyword")
-    
+    original_name_clean = re.sub(
+        r"[^a-zA-Z0-9_]", "", name.replace("_", "").replace("-", "").lower()
+    )
+    if (
+        keyword.iskeyword(original_name_clean)
+        or keyword.iskeyword(class_name)
+        or class_name in ("True", "False", "None")
+    ):
+        raise ValueError(
+            f"Project name '{name}' would generate class name '{class_name}' which is a reserved Python keyword"
+        )
+
    if not class_name.isidentifier():
-        raise ValueError(f"Project name '{name}' would generate invalid Python class name '{class_name}'")
+        raise ValueError(
+            f"Project name '{name}' would generate invalid Python class name '{class_name}'"
+        )

    if parent_folder:
        folder_path = Path(parent_folder) / folder_name
@@ -172,7 +196,7 @@ def create_crew(name, provider=None, skip_provider=False, parent_folder=None):
            )

        # Check if the selected provider has predefined models
-        if selected_provider in MODELS and MODELS[selected_provider]:
+        if MODELS.get(selected_provider):
            while True:
                selected_model = select_model(selected_provider, provider_models)
                if selected_model is None:  # User typed 'q'
--- a/src/crewai/cli/crew_chat.py
+++ b/src/crewai/cli/crew_chat.py
@@ -5,7 +5,7 @@ import sys
 import threading
 import time
 from pathlib import Path
-from typing import Any, Dict, List, Optional, Set, Tuple
+from typing import Any

 import click
 import tomli
@@ -116,7 +116,7 @@ def show_loading(event: threading.Event):
    print()


-def initialize_chat_llm(crew: Crew) -> Optional[LLM | BaseLLM]:
+def initialize_chat_llm(crew: Crew) -> LLM | BaseLLM | None:
    """Initializes the chat LLM and handles exceptions."""
    try:
        return create_llm(crew.chat_llm)
@@ -157,7 +157,7 @@ def build_system_message(crew_chat_inputs: ChatInputs) -> str:
    )


-def create_tool_function(crew: Crew, messages: List[Dict[str, str]]) -> Any:
+def create_tool_function(crew: Crew, messages: list[dict[str, str]]) -> Any:
    """Creates a wrapper function for running the crew tool with messages."""

    def run_crew_tool_with_messages(**kwargs):
@@ -193,7 +193,7 @@ def chat_loop(chat_llm, messages, crew_tool_schema, available_functions):
                user_input, chat_llm, messages, crew_tool_schema, available_functions
            )

-        except KeyboardInterrupt:
+        except KeyboardInterrupt:  # noqa: PERF203
            click.echo("\nExiting chat. Goodbye!")
            break
        except Exception as e:
@@ -221,9 +221,9 @@ def get_user_input() -> str:
 def handle_user_input(
    user_input: str,
    chat_llm: LLM,
-    messages: List[Dict[str, str]],
-    crew_tool_schema: Dict[str, Any],
-    available_functions: Dict[str, Any],
+    messages: list[dict[str, str]],
+    crew_tool_schema: dict[str, Any],
+    available_functions: dict[str, Any],
 ) -> None:
    if user_input.strip().lower() == "exit":
        click.echo("Exiting chat. Goodbye!")
@@ -281,7 +281,7 @@ def generate_crew_tool_schema(crew_inputs: ChatInputs) -> dict:
    }


-def run_crew_tool(crew: Crew, messages: List[Dict[str, str]], **kwargs):
+def run_crew_tool(crew: Crew, messages: list[dict[str, str]], **kwargs):
    """
    Runs the crew using crew.kickoff(inputs=kwargs) and returns the output.

@@ -304,9 +304,8 @@ def run_crew_tool(crew: Crew, messages: List[Dict[str, str]], **kwargs):
        crew_output = crew.kickoff(inputs=kwargs)

        # Convert CrewOutput to a string to send back to the user
-        result = str(crew_output)
+        return str(crew_output)

-        return result
    except Exception as e:
        # Exit the chat and show the error message
        click.secho("An error occurred while running the crew:", fg="red")
@@ -314,7 +313,7 @@ def run_crew_tool(crew: Crew, messages: List[Dict[str, str]], **kwargs):
        sys.exit(1)


-def load_crew_and_name() -> Tuple[Crew, str]:
+def load_crew_and_name() -> tuple[Crew, str]:
    """
    Loads the crew by importing the crew class from the user's project.

@@ -351,15 +350,17 @@ def load_crew_and_name() -> Tuple[Crew, str]:
    try:
        crew_module = __import__(crew_module_name, fromlist=[crew_class_name])
    except ImportError as e:
-        raise ImportError(f"Failed to import crew module {crew_module_name}: {e}")
+        raise ImportError(
+            f"Failed to import crew module {crew_module_name}: {e}"
+        ) from e

    # Get the crew class from the module
    try:
        crew_class = getattr(crew_module, crew_class_name)
-    except AttributeError:
+    except AttributeError as e:
        raise AttributeError(
            f"Crew class {crew_class_name} not found in module {crew_module_name}"
-        )
+        ) from e

    # Instantiate the crew
    crew_instance = crew_class().crew()
@@ -395,7 +396,7 @@ def generate_crew_chat_inputs(crew: Crew, crew_name: str, chat_llm) -> ChatInput
    )


-def fetch_required_inputs(crew: Crew) -> Set[str]:
+def fetch_required_inputs(crew: Crew) -> set[str]:
    """
    Extracts placeholders from the crew's tasks and agents.

@@ -405,8 +406,8 @@ def fetch_required_inputs(crew: Crew) -> Set[str]:
    Returns:
        Set[str]: A set of placeholder names.
    """
-    placeholder_pattern = re.compile(r"\{(.+?)\}")
-    required_inputs: Set[str] = set()
+    placeholder_pattern = re.compile(r"\{(.+?)}")
+    required_inputs: set[str] = set()

    # Scan tasks
    for task in crew.tasks:
@@ -435,7 +436,7 @@ def generate_input_description_with_ai(input_name: str, crew: Crew, chat_llm) ->
    """
    # Gather context from tasks and agents where the input is used
    context_texts = []
-    placeholder_pattern = re.compile(r"\{(.+?)\}")
+    placeholder_pattern = re.compile(r"\{(.+?)}")

    for task in crew.tasks:
        if (
@@ -479,9 +480,7 @@ def generate_input_description_with_ai(input_name: str, crew: Crew, chat_llm) ->
        f"{context}"
    )
    response = chat_llm.call(messages=[{"role": "user", "content": prompt}])
-    description = response.strip()
-
-    return description
+    return response.strip()


 def generate_crew_description_with_ai(crew: Crew, chat_llm) -> str:
@@ -497,7 +496,7 @@ def generate_crew_description_with_ai(crew: Crew, chat_llm) -> str:
    """
    # Gather context from tasks and agents
    context_texts = []
-    placeholder_pattern = re.compile(r"\{(.+?)\}")
+    placeholder_pattern = re.compile(r"\{(.+?)}")

    for task in crew.tasks:
        # Replace placeholders with input names
@@ -531,6 +530,4 @@ def generate_crew_description_with_ai(crew: Crew, chat_llm) -> str:
        f"{context}"
    )
    response = chat_llm.call(messages=[{"role": "user", "content": prompt}])
-    crew_description = response.strip()
-
-    return crew_description
+    return response.strip()
--- a/src/crewai/cli/git.py
+++ b/src/crewai/cli/git.py
@@ -14,11 +14,15 @@ class Repository:

        self.fetch()

-    def is_git_installed(self) -> bool:
+    @staticmethod
+    def is_git_installed() -> bool:
        """Check if Git is installed and available in the system."""
        try:
            subprocess.run(
-                ["git", "--version"], capture_output=True, check=True, text=True
+                ["git", "--version"],  # noqa: S607
+                capture_output=True,
+                check=True,
+                text=True,
            )
            return True
        except (subprocess.CalledProcessError, FileNotFoundError):
@@ -26,22 +30,26 @@ class Repository:

    def fetch(self) -> None:
        """Fetch latest updates from the remote."""
-        subprocess.run(["git", "fetch"], cwd=self.path, check=True)
+        subprocess.run(["git", "fetch"], cwd=self.path, check=True)  # noqa: S607

    def status(self) -> str:
        """Get the git status in porcelain format."""
        return subprocess.check_output(
-            ["git", "status", "--branch", "--porcelain"],
+            ["git", "status", "--branch", "--porcelain"],  # noqa: S607
            cwd=self.path,
            encoding="utf-8",
        ).strip()

-    @lru_cache(maxsize=None)
+    @lru_cache(maxsize=None)  # noqa: B019
    def is_git_repo(self) -> bool:
-        """Check if the current directory is a git repository."""
+        """Check if the current directory is a git repository.
+
+        Notes:
+          - TODO: This method is cached to avoid redundant checks, but using lru_cache on methods can lead to memory leaks
+        """
        try:
            subprocess.check_output(
-                ["git", "rev-parse", "--is-inside-work-tree"],
+                ["git", "rev-parse", "--is-inside-work-tree"],  # noqa: S607
                cwd=self.path,
                encoding="utf-8",
            )
@@ -64,14 +72,13 @@ class Repository:
        """Return True if the Git repository is fully synced with the remote, False otherwise."""
        if self.has_uncommitted_changes() or self.is_ahead_or_behind():
            return False
-        else:
-            return True
+        return True

    def origin_url(self) -> str | None:
        """Get the Git repository's remote URL."""
        try:
            result = subprocess.run(
-                ["git", "remote", "get-url", "origin"],
+                ["git", "remote", "get-url", "origin"],  # noqa: S607
                cwd=self.path,
                capture_output=True,
                text=True,
--- a/src/crewai/cli/install_crew.py
+++ b/src/crewai/cli/install_crew.py
@@ -12,8 +12,8 @@ def install_crew(proxy_options: list[str]) -> None:
    Install the crew by running the UV command to lock and install.
    """
    try:
-        command = ["uv", "sync"] + proxy_options
-        subprocess.run(command, check=True, capture_output=False, text=True)
+        command = ["uv", "sync", *proxy_options]
+        subprocess.run(command, check=True, capture_output=False, text=True)  # noqa: S603

    except subprocess.CalledProcessError as e:
        click.echo(f"An error occurred while running the crew: {e}", err=True)
--- a/src/crewai/cli/plus_api.py
+++ b/src/crewai/cli/plus_api.py
@@ -1,11 +1,10 @@
-from typing import List, Optional
 from urllib.parse import urljoin

 import requests

 from crewai.cli.config import Settings
-from crewai.cli.version import get_crewai_version
 from crewai.cli.constants import DEFAULT_CREWAI_ENTERPRISE_URL
+from crewai.cli.version import get_crewai_version


 class PlusAPI:
@@ -56,9 +55,9 @@ class PlusAPI:
        handle: str,
        is_public: bool,
        version: str,
-        description: Optional[str],
+        description: str | None,
        encoded_file: str,
-        available_exports: Optional[List[str]] = None,
+        available_exports: list[str] | None = None,
    ):
        params = {
            "handle": handle,
@@ -167,3 +166,13 @@ class PlusAPI:
            json=payload,
            timeout=30,
        )
+
+    def mark_trace_batch_as_failed(
+        self, trace_batch_id: str, error_message: str
+    ) -> requests.Response:
+        return self._make_request(
+            "PATCH",
+            f"{self.TRACING_RESOURCE}/batches/{trace_batch_id}",
+            json={"status": "failed", "failure_reason": error_message},
+            timeout=30,
+        )
--- a/src/crewai/cli/provider.py
+++ b/src/crewai/cli/provider.py
@@ -1,10 +1,10 @@
-import os
-import certifi
 import json
+import os
 import time
 from collections import defaultdict
 from pathlib import Path

+import certifi
 import click
 import requests

@@ -25,7 +25,7 @@ def select_choice(prompt_message, choices):

    provider_models = get_provider_data()
    if not provider_models:
-        return
+        return None
    click.secho(prompt_message, fg="cyan")
    for idx, choice in enumerate(choices, start=1):
        click.secho(f"{idx}. {choice}", fg="cyan")
@@ -67,7 +67,7 @@ def select_provider(provider_models):
    all_providers = sorted(set(predefined_providers + list(provider_models.keys())))

    provider = select_choice(
-        "Select a provider to set up:", predefined_providers + ["other"]
+        "Select a provider to set up:", [*predefined_providers, "other"]
    )
    if provider is None:  # User typed 'q'
        return None
@@ -102,10 +102,9 @@ def select_model(provider, provider_models):
        click.secho(f"No models available for provider '{provider}'.", fg="red")
        return None

-    selected_model = select_choice(
+    return select_choice(
        f"Select a model to use for {provider.capitalize()}:", available_models
    )
-    return selected_model


 def load_provider_data(cache_file, cache_expiry):
@@ -165,7 +164,7 @@ def fetch_provider_data(cache_file):
    Returns:
    - dict or None: The fetched provider data or None if the operation fails.
    """
-    ssl_config = os.environ['SSL_CERT_FILE'] = certifi.where()
+    ssl_config = os.environ["SSL_CERT_FILE"] = certifi.where()

    try:
        response = requests.get(JSON_URL, stream=True, timeout=60, verify=ssl_config)
--- a/src/crewai/cli/run_crew.py
+++ b/src/crewai/cli/run_crew.py
@@ -1,6 +1,5 @@
 import subprocess
 from enum import Enum
-from typing import List, Optional

 import click
 from packaging import version
@@ -57,7 +56,7 @@ def execute_command(crew_type: CrewType) -> None:
    command = ["uv", "run", "kickoff" if crew_type == CrewType.FLOW else "run_crew"]

    try:
-        subprocess.run(command, capture_output=False, text=True, check=True)
+        subprocess.run(command, capture_output=False, text=True, check=True)  # noqa: S603

    except subprocess.CalledProcessError as e:
        handle_error(e, crew_type)
--- a/src/crewai/cli/shared/token_manager.py
+++ b/src/crewai/cli/shared/token_manager.py
@@ -3,7 +3,7 @@ import os
 import sys
 from datetime import datetime
 from pathlib import Path
-from typing import Optional
+
 from cryptography.fernet import Fernet


@@ -49,7 +49,7 @@ class TokenManager:
        encrypted_data = self.fernet.encrypt(json.dumps(data).encode())
        self.save_secure_file(self.file_path, encrypted_data)

-    def get_token(self) -> Optional[str]:
+    def get_token(self) -> str | None:
        """
        Get the access token if it is valid and not expired.

@@ -113,7 +113,7 @@ class TokenManager:
        # Set appropriate permissions (read/write for owner only)
        os.chmod(file_path, 0o600)

-    def read_secure_file(self, filename: str) -> Optional[bytes]:
+    def read_secure_file(self, filename: str) -> bytes | None:
        """
        Read the content of a secure file.

--- a/src/crewai/cli/templates/crew/pyproject.toml
+++ b/src/crewai/cli/templates/crew/pyproject.toml
@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.186.1,<1.0.0"
+    "crewai[tools]>=0.201.0,<1.0.0"
 ]

 [project.scripts]
--- a/src/crewai/cli/templates/flow/pyproject.toml
+++ b/src/crewai/cli/templates/flow/pyproject.toml
@@ -5,7 +5,7 @@ description = "{{name}} using crewAI"
 authors = [{ name = "Your Name", email = "you@example.com" }]
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.186.1,<1.0.0",
+    "crewai[tools]>=0.201.0,<1.0.0",
 ]

 [project.scripts]
--- a/src/crewai/cli/templates/tool/pyproject.toml
+++ b/src/crewai/cli/templates/tool/pyproject.toml
@@ -5,7 +5,7 @@ description = "Power up your crews with {{folder_name}}"
 readme = "README.md"
 requires-python = ">=3.10,<3.14"
 dependencies = [
-    "crewai[tools]>=0.186.1"
+    "crewai[tools]>=0.201.0"
 ]

 [tool.crewai]
--- a/src/crewai/cli/tools/main.py
+++ b/src/crewai/cli/tools/main.py
@@ -12,6 +12,7 @@ from crewai.cli import git
 from crewai.cli.command import BaseCommand, PlusAPIMixin
 from crewai.cli.config import Settings
 from crewai.cli.utils import (
+    build_env_with_tool_repository_credentials,
    extract_available_exports,
    get_project_description,
    get_project_name,
@@ -42,8 +43,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        if project_root.exists():
            click.secho(f"Folder {folder_name} already exists.", fg="red")
            raise SystemExit
-        else:
-            os.makedirs(project_root)
+        os.makedirs(project_root)

        click.secho(f"Creating custom tool {folder_name}...", fg="green", bold=True)

@@ -56,7 +56,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        os.chdir(project_root)
        try:
            self.login()
-            subprocess.run(["git", "init"], check=True)
+            subprocess.run(["git", "init"], check=True)  # noqa: S607
            console.print(
                f"[green]Created custom tool [bold]{folder_name}[/bold]. Run [bold]cd {project_root}[/bold] to start working.[/green]"
            )
@@ -76,10 +76,10 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
            raise SystemExit()

        project_name = get_project_name(require=True)
-        assert isinstance(project_name, str)
+        assert isinstance(project_name, str)  # noqa: S101

        project_version = get_project_version(require=True)
-        assert isinstance(project_version, str)
+        assert isinstance(project_version, str)  # noqa: S101

        project_description = get_project_description(require=False)
        encoded_tarball = None
@@ -94,8 +94,8 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        self._print_current_organization()

        with tempfile.TemporaryDirectory() as temp_build_dir:
-            subprocess.run(
-                ["uv", "build", "--sdist", "--out-dir", temp_build_dir],
+            subprocess.run(  # noqa: S603
+                ["uv", "build", "--sdist", "--out-dir", temp_build_dir],  # noqa: S607
                check=True,
                capture_output=False,
            )
@@ -146,7 +146,7 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
                style="bold red",
            )
            raise SystemExit
-        elif get_response.status_code != 200:
+        if get_response.status_code != 200:
            console.print(
                "Failed to get tool details. Please try again later.", style="bold red"
            )
@@ -196,10 +196,10 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
        else:
            add_package_command.extend(["--index", index, tool_handle])

-        add_package_result = subprocess.run(
+        add_package_result = subprocess.run(  # noqa: S603
            add_package_command,
            capture_output=False,
-            env=self._build_env_with_credentials(repository_handle),
+            env=build_env_with_tool_repository_credentials(repository_handle),
            text=True,
            check=True,
        )
@@ -221,20 +221,6 @@ class ToolCommand(BaseCommand, PlusAPIMixin):
            )
            raise SystemExit

-    def _build_env_with_credentials(self, repository_handle: str):
-        repository_handle = repository_handle.upper().replace("-", "_")
-        settings = Settings()
-
-        env = os.environ.copy()
-        env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(
-            settings.tool_repository_username or ""
-        )
-        env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(
-            settings.tool_repository_password or ""
-        )
-
-        return env
-
    def _print_current_organization(self) -> None:
        settings = Settings()
        if settings.org_uuid:
--- a/src/crewai/cli/utils.py
+++ b/src/crewai/cli/utils.py
@@ -5,12 +5,13 @@ import sys
 from functools import reduce
 from inspect import getmro, isclass, isfunction, ismethod
 from pathlib import Path
-from typing import Any, Dict, List, get_type_hints
+from typing import Any, get_type_hints

 import click
 import tomli
 from rich.console import Console

+from crewai.cli.config import Settings
 from crewai.cli.constants import ENV_VARS
 from crewai.crew import Crew
 from crewai.flow import Flow
@@ -41,8 +42,7 @@ def copy_template(src, dst, name, class_name, folder_name):
 def read_toml(file_path: str = "pyproject.toml"):
    """Read the content of a TOML file and return it as a dictionary."""
    with open(file_path, "rb") as f:
-        toml_dict = tomli.load(f)
-    return toml_dict
+        return tomli.load(f)


 def parse_toml(content):
@@ -77,7 +77,7 @@ def get_project_description(


 def _get_project_attribute(
-    pyproject_path: str, keys: List[str], require: bool
+    pyproject_path: str, keys: list[str], require: bool
 ) -> Any | None:
    """Get an attribute from the pyproject.toml file."""
    attribute = None
@@ -96,16 +96,20 @@ def _get_project_attribute(
    except FileNotFoundError:
        console.print(f"Error: {pyproject_path} not found.", style="bold red")
    except KeyError:
-        console.print(f"Error: {pyproject_path} is not a valid pyproject.toml file.", style="bold red")
-    except tomllib.TOMLDecodeError if sys.version_info >= (3, 11) else Exception as e:  # type: ignore
        console.print(
-            f"Error: {pyproject_path} is not a valid TOML file."
-            if sys.version_info >= (3, 11)
-            else f"Error reading the pyproject.toml file: {e}",
+            f"Error: {pyproject_path} is not a valid pyproject.toml file.",
            style="bold red",
        )
    except Exception as e:
-        console.print(f"Error reading the pyproject.toml file: {e}", style="bold red")
+        # Handle TOML decode errors for Python 3.11+
+        if sys.version_info >= (3, 11) and isinstance(e, tomllib.TOMLDecodeError):  # type: ignore
+            console.print(
+                f"Error: {pyproject_path} is not a valid TOML file.", style="bold red"
+            )
+        else:
+            console.print(
+                f"Error reading the pyproject.toml file: {e}", style="bold red"
+            )

    if require and not attribute:
        console.print(
@@ -117,7 +121,7 @@ def _get_project_attribute(
    return attribute


-def _get_nested_value(data: Dict[str, Any], keys: List[str]) -> Any:
+def _get_nested_value(data: dict[str, Any], keys: list[str]) -> Any:
    return reduce(dict.__getitem__, keys, data)


@@ -296,7 +300,10 @@ def get_crews(crew_path: str = "crew.py", require: bool = False) -> list[Crew]:
                                try:
                                    crew_instances.extend(fetch_crews(module_attr))
                                except Exception as e:
-                                    console.print(f"Error processing attribute {attr_name}: {e}", style="bold red")
+                                    console.print(
+                                        f"Error processing attribute {attr_name}: {e}",
+                                        style="bold red",
+                                    )
                                    continue

                            # If we found crew instances, break out of the loop
@@ -304,12 +311,15 @@ def get_crews(crew_path: str = "crew.py", require: bool = False) -> list[Crew]:
                                break

                        except Exception as exec_error:
-                            console.print(f"Error executing module: {exec_error}", style="bold red")
+                            console.print(
+                                f"Error executing module: {exec_error}",
+                                style="bold red",
+                            )

                    except (ImportError, AttributeError) as e:
                        if require:
                            console.print(
-                                f"Error importing crew from {crew_path}: {str(e)}",
+                                f"Error importing crew from {crew_path}: {e!s}",
                                style="bold red",
                            )
                        continue
@@ -325,9 +335,9 @@ def get_crews(crew_path: str = "crew.py", require: bool = False) -> list[Crew]:
    except Exception as e:
        if require:
            console.print(
-                f"Unexpected error while loading crew: {str(e)}", style="bold red"
+                f"Unexpected error while loading crew: {e!s}", style="bold red"
            )
-            raise SystemExit
+            raise SystemExit from e
    return crew_instances


@@ -348,8 +358,7 @@ def get_crew_instance(module_attr) -> Crew | None:

    if isinstance(module_attr, Crew):
        return module_attr
-    else:
-        return None
+    return None


 def fetch_crews(module_attr) -> list[Crew]:
@@ -402,11 +411,26 @@ def extract_available_exports(dir_path: str = "src"):
        return available_exports

    except Exception as e:
-        console.print(f"[red]Error: Could not extract tool classes: {str(e)}[/red]")
+        console.print(f"[red]Error: Could not extract tool classes: {e!s}[/red]")
        console.print(
            "Please ensure your project contains valid tools (classes inheriting from BaseTool or functions with @tool decorator)."
        )
-        raise SystemExit(1)
+        raise SystemExit(1) from e
+
+
+def build_env_with_tool_repository_credentials(repository_handle: str):
+    repository_handle = repository_handle.upper().replace("-", "_")
+    settings = Settings()
+
+    env = os.environ.copy()
+    env[f"UV_INDEX_{repository_handle}_USERNAME"] = str(
+        settings.tool_repository_username or ""
+    )
+    env[f"UV_INDEX_{repository_handle}_PASSWORD"] = str(
+        settings.tool_repository_password or ""
+    )
+
+    return env


 def _load_tools_from_init(init_file: Path) -> list[dict[str, Any]]:
@@ -440,8 +464,8 @@ def _load_tools_from_init(init_file: Path) -> list[dict[str, Any]]:
        ]

    except Exception as e:
-        console.print(f"[red]Warning: Could not load {init_file}: {str(e)}[/red]")
-        raise SystemExit(1)
+        console.print(f"[red]Warning: Could not load {init_file}: {e!s}[/red]")
+        raise SystemExit(1) from e

    finally:
        sys.modules.pop("temp_module", None)
--- a/src/crewai/crew.py
+++ b/src/crewai/crew.py
@@ -59,6 +59,7 @@ from crewai.memory.external.external_memory import ExternalMemory
 from crewai.memory.long_term.long_term_memory import LongTermMemory
 from crewai.memory.short_term.short_term_memory import ShortTermMemory
 from crewai.process import Process
+from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.rag.types import SearchResult
 from crewai.security import Fingerprint, SecurityConfig
 from crewai.task import Task
@@ -168,7 +169,7 @@ class Crew(FlowTrackable, BaseModel):
        default=None,
        description="An Instance of the ExternalMemory to be used by the Crew",
    )
-    embedder: dict | None = Field(
+    embedder: EmbedderConfig | None = Field(
        default=None,
        description="Configuration for the embedder to be used for the crew.",
    )
@@ -622,7 +623,8 @@ class Crew(FlowTrackable, BaseModel):
                        training_data=training_data, agent_id=str(agent.id)
                    )
                    CrewTrainingHandler(filename).save_trained_data(
-                        agent_id=str(agent.role), trained_data=result.model_dump()
+                        agent_id=str(agent.role),
+                        trained_data=result.model_dump(),  # type: ignore[arg-type]
                    )

            crewai_event_bus.emit(
@@ -1057,7 +1059,10 @@ class Crew(FlowTrackable, BaseModel):
    def _log_task_start(self, task: Task, role: str = "None"):
        if self.output_log_file:
            self._file_handler.log(
-                task_name=task.name, task=task.description, agent=role, status="started"
+                task_name=task.name,  # type: ignore[arg-type]
+                task=task.description,
+                agent=role,
+                status="started",
            )

    def _update_manager_tools(
@@ -1086,7 +1091,7 @@ class Crew(FlowTrackable, BaseModel):
        role = task.agent.role if task.agent is not None else "None"
        if self.output_log_file:
            self._file_handler.log(
-                task_name=task.name,
+                task_name=task.name,  # type: ignore[arg-type]
                task=task.description,
                agent=role,
                status="completed",
--- a/src/crewai/crews/crew_output.py
+++ b/src/crewai/crews/crew_output.py
@@ -1,5 +1,5 @@
 import json
-from typing import Any, Dict, Optional
+from typing import Any

 from pydantic import BaseModel, Field

@@ -12,19 +12,21 @@ class CrewOutput(BaseModel):
    """Class that represents the result of a crew."""

    raw: str = Field(description="Raw output of crew", default="")
-    pydantic: Optional[BaseModel] = Field(
+    pydantic: BaseModel | None = Field(
        description="Pydantic output of Crew", default=None
    )
-    json_dict: Optional[Dict[str, Any]] = Field(
+    json_dict: dict[str, Any] | None = Field(
        description="JSON dict output of Crew", default=None
    )
    tasks_output: list[TaskOutput] = Field(
        description="Output of each task", default=[]
    )
-    token_usage: UsageMetrics = Field(description="Processed token summary", default={})
+    token_usage: UsageMetrics = Field(
+        description="Processed token summary", default_factory=UsageMetrics
+    )

    @property
-    def json(self) -> Optional[str]:
+    def json(self) -> str | None:  # type: ignore[override]
        if self.tasks_output[-1].output_format != OutputFormat.JSON:
            raise ValueError(
                "No JSON output found in the final task. Please make sure to set the output_json property in the final task in your crew."
@@ -32,7 +34,7 @@ class CrewOutput(BaseModel):

        return json.dumps(self.json_dict)

-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
        """Convert json_output and pydantic_output to a dictionary."""
        output_dict = {}
        if self.json_dict:
@@ -44,10 +46,9 @@ class CrewOutput(BaseModel):
    def __getitem__(self, key):
        if self.pydantic and hasattr(self.pydantic, key):
            return getattr(self.pydantic, key)
-        elif self.json_dict and key in self.json_dict:
+        if self.json_dict and key in self.json_dict:
            return self.json_dict[key]
-        else:
-            raise KeyError(f"Key '{key}' not found in CrewOutput.")
+        raise KeyError(f"Key '{key}' not found in CrewOutput.")

    def __str__(self):
        if self.pydantic:
--- a/src/crewai/events/base_events.py
+++ b/src/crewai/events/base_events.py
@@ -1,5 +1,6 @@
 from datetime import datetime, timezone
-from typing import Any, Dict, Optional
+from typing import Any
+
 from pydantic import BaseModel, Field

 from crewai.utilities.serialization import to_serializable
@@ -10,11 +11,11 @@ class BaseEvent(BaseModel):

    timestamp: datetime = Field(default_factory=lambda: datetime.now(timezone.utc))
    type: str
-    source_fingerprint: Optional[str] = None  # UUID string of the source entity
-    source_type: Optional[str] = (
+    source_fingerprint: str | None = None  # UUID string of the source entity
+    source_type: str | None = (
        None  # "agent", "task", "crew", "memory", "entity_memory", "short_term_memory", "long_term_memory", "external_memory"
    )
-    fingerprint_metadata: Optional[Dict[str, Any]] = None  # Any relevant metadata
+    fingerprint_metadata: dict[str, Any] | None = None  # Any relevant metadata

    def to_json(self, exclude: set[str] | None = None):
        """
@@ -28,13 +29,13 @@ class BaseEvent(BaseModel):
        """
        return to_serializable(self, exclude=exclude)

-    def _set_task_params(self, data: Dict[str, Any]):
+    def _set_task_params(self, data: dict[str, Any]):
        if "from_task" in data and (task := data["from_task"]):
            self.task_id = task.id
            self.task_name = task.name or task.description
            self.from_task = None

-    def _set_agent_params(self, data: Dict[str, Any]):
+    def _set_agent_params(self, data: dict[str, Any]):
        task = data.get("from_task", None)
        agent = task.agent if task else data.get("from_agent", None)

--- a/src/crewai/events/event_bus.py
+++ b/src/crewai/events/event_bus.py
@@ -1,8 +1,9 @@
 from __future__ import annotations

 import threading
+from collections.abc import Callable
 from contextlib import contextmanager
-from typing import Any, Callable, Dict, List, Type, TypeVar, cast
+from typing import Any, TypeVar, cast

 from blinker import Signal

@@ -25,17 +26,17 @@ class CrewAIEventsBus:
        if cls._instance is None:
            with cls._lock:
                if cls._instance is None:  # prevent race condition
-                    cls._instance = super(CrewAIEventsBus, cls).__new__(cls)
+                    cls._instance = super().__new__(cls)
                    cls._instance._initialize()
        return cls._instance

    def _initialize(self) -> None:
        """Initialize the event bus internal state"""
        self._signal = Signal("crewai_event_bus")
-        self._handlers: Dict[Type[BaseEvent], List[Callable]] = {}
+        self._handlers: dict[type[BaseEvent], list[Callable]] = {}

    def on(
-        self, event_type: Type[EventT]
+        self, event_type: type[EventT]
    ) -> Callable[[Callable[[Any, EventT], None]], Callable[[Any, EventT], None]]:
        """
        Decorator to register an event handler for a specific event type.
@@ -61,6 +62,18 @@ class CrewAIEventsBus:

        return decorator

+    @staticmethod
+    def _call_handler(
+        handler: Callable, source: Any, event: BaseEvent, event_type: type
+    ) -> None:
+        """Call a single handler with error handling."""
+        try:
+            handler(source, event)
+        except Exception as e:
+            print(
+                f"[EventBus Error] Handler '{handler.__name__}' failed for event '{event_type.__name__}': {e}"
+            )
+
    def emit(self, source: Any, event: BaseEvent) -> None:
        """
        Emit an event to all registered handlers
@@ -72,17 +85,12 @@ class CrewAIEventsBus:
        for event_type, handlers in self._handlers.items():
            if isinstance(event, event_type):
                for handler in handlers:
-                    try:
-                        handler(source, event)
-                    except Exception as e:
-                        print(
-                            f"[EventBus Error] Handler '{handler.__name__}' failed for event '{event_type.__name__}': {e}"
-                        )
+                    self._call_handler(handler, source, event, event_type)

        self._signal.send(source, event=event)

    def register_handler(
-        self, event_type: Type[EventTypes], handler: Callable[[Any, EventTypes], None]
+        self, event_type: type[EventTypes], handler: Callable[[Any, EventTypes], None]
    ) -> None:
        """Register an event handler for a specific event type"""
        if event_type not in self._handlers:
--- a/src/crewai/events/event_listener.py
+++ b/src/crewai/events/event_listener.py
@@ -1,15 +1,30 @@
 from __future__ import annotations

 from io import StringIO
-from typing import Any, Dict
+from typing import Any

 from pydantic import Field, PrivateAttr
-from crewai.llm import LLM
-from crewai.task import Task
-from crewai.telemetry.telemetry import Telemetry
-from crewai.utilities import Logger
-from crewai.utilities.constants import EMITTER_COLOR
+
 from crewai.events.base_event_listener import BaseEventListener
+from crewai.events.types.agent_events import (
+    AgentExecutionCompletedEvent,
+    AgentExecutionStartedEvent,
+    LiteAgentExecutionCompletedEvent,
+    LiteAgentExecutionErrorEvent,
+    LiteAgentExecutionStartedEvent,
+)
+from crewai.events.types.crew_events import (
+    CrewKickoffCompletedEvent,
+    CrewKickoffFailedEvent,
+    CrewKickoffStartedEvent,
+    CrewTestCompletedEvent,
+    CrewTestFailedEvent,
+    CrewTestResultEvent,
+    CrewTestStartedEvent,
+    CrewTrainCompletedEvent,
+    CrewTrainFailedEvent,
+    CrewTrainStartedEvent,
+)
 from crewai.events.types.knowledge_events import (
    KnowledgeQueryCompletedEvent,
    KnowledgeQueryFailedEvent,
@@ -25,34 +40,21 @@ from crewai.events.types.llm_events import (
    LLMStreamChunkEvent,
 )
 from crewai.events.types.llm_guardrail_events import (
-    LLMGuardrailStartedEvent,
    LLMGuardrailCompletedEvent,
-)
-from crewai.events.utils.console_formatter import ConsoleFormatter
-
-from crewai.events.types.agent_events import (
-    AgentExecutionCompletedEvent,
-    AgentExecutionStartedEvent,
-    LiteAgentExecutionCompletedEvent,
-    LiteAgentExecutionErrorEvent,
-    LiteAgentExecutionStartedEvent,
+    LLMGuardrailStartedEvent,
 )
 from crewai.events.types.logging_events import (
-    AgentLogsStartedEvent,
    AgentLogsExecutionEvent,
+    AgentLogsStartedEvent,
 )
-from crewai.events.types.crew_events import (
-    CrewKickoffCompletedEvent,
-    CrewKickoffFailedEvent,
-    CrewKickoffStartedEvent,
-    CrewTestCompletedEvent,
-    CrewTestFailedEvent,
-    CrewTestResultEvent,
-    CrewTestStartedEvent,
-    CrewTrainCompletedEvent,
-    CrewTrainFailedEvent,
-    CrewTrainStartedEvent,
-)
+from crewai.events.utils.console_formatter import ConsoleFormatter
+from crewai.llm import LLM
+from crewai.task import Task
+from crewai.telemetry.telemetry import Telemetry
+from crewai.utilities import Logger
+from crewai.utilities.constants import EMITTER_COLOR
+
+from .listeners.memory_listener import MemoryListener
 from .types.flow_events import (
    FlowCreatedEvent,
    FlowFinishedEvent,
@@ -61,26 +63,24 @@ from .types.flow_events import (
    MethodExecutionFinishedEvent,
    MethodExecutionStartedEvent,
 )
+from .types.reasoning_events import (
+    AgentReasoningCompletedEvent,
+    AgentReasoningFailedEvent,
+    AgentReasoningStartedEvent,
+)
 from .types.task_events import TaskCompletedEvent, TaskFailedEvent, TaskStartedEvent
 from .types.tool_usage_events import (
    ToolUsageErrorEvent,
    ToolUsageFinishedEvent,
    ToolUsageStartedEvent,
 )
-from .types.reasoning_events import (
-    AgentReasoningStartedEvent,
-    AgentReasoningCompletedEvent,
-    AgentReasoningFailedEvent,
-)
-
-from .listeners.memory_listener import MemoryListener


 class EventListener(BaseEventListener):
    _instance = None
    _telemetry: Telemetry = PrivateAttr(default_factory=lambda: Telemetry())
    logger = Logger(verbose=True, default_color=EMITTER_COLOR)
-    execution_spans: Dict[Task, Any] = Field(default_factory=dict)
+    execution_spans: dict[Task, Any] = Field(default_factory=dict)
    next_chunk = 0
    text_stream = StringIO()
    knowledge_retrieval_in_progress = False
--- a/src/crewai/events/event_types.py
+++ b/src/crewai/events/event_types.py
@@ -1,11 +1,10 @@
-from typing import Union
-
 from crewai.events.types.agent_events import (
    AgentExecutionCompletedEvent,
    AgentExecutionErrorEvent,
    AgentExecutionStartedEvent,
    LiteAgentExecutionCompletedEvent,
 )
+
 from .types.crew_events import (
    CrewKickoffCompletedEvent,
    CrewKickoffFailedEvent,
@@ -24,6 +23,14 @@ from .types.flow_events import (
    MethodExecutionFinishedEvent,
    MethodExecutionStartedEvent,
 )
+from .types.knowledge_events import (
+    KnowledgeQueryCompletedEvent,
+    KnowledgeQueryFailedEvent,
+    KnowledgeQueryStartedEvent,
+    KnowledgeRetrievalCompletedEvent,
+    KnowledgeRetrievalStartedEvent,
+    KnowledgeSearchQueryFailedEvent,
+)
 from .types.llm_events import (
    LLMCallCompletedEvent,
    LLMCallFailedEvent,
@@ -34,6 +41,21 @@ from .types.llm_guardrail_events import (
    LLMGuardrailCompletedEvent,
    LLMGuardrailStartedEvent,
 )
+from .types.memory_events import (
+    MemoryQueryCompletedEvent,
+    MemoryQueryFailedEvent,
+    MemoryQueryStartedEvent,
+    MemoryRetrievalCompletedEvent,
+    MemoryRetrievalStartedEvent,
+    MemorySaveCompletedEvent,
+    MemorySaveFailedEvent,
+    MemorySaveStartedEvent,
+)
+from .types.reasoning_events import (
+    AgentReasoningCompletedEvent,
+    AgentReasoningFailedEvent,
+    AgentReasoningStartedEvent,
+)
 from .types.task_events import (
    TaskCompletedEvent,
    TaskFailedEvent,
@@ -44,77 +66,53 @@ from .types.tool_usage_events import (
    ToolUsageFinishedEvent,
    ToolUsageStartedEvent,
 )
-from .types.reasoning_events import (
-    AgentReasoningStartedEvent,
-    AgentReasoningCompletedEvent,
-    AgentReasoningFailedEvent,
-)
-from .types.knowledge_events import (
-    KnowledgeRetrievalStartedEvent,
-    KnowledgeRetrievalCompletedEvent,
-    KnowledgeQueryStartedEvent,
-    KnowledgeQueryCompletedEvent,
-    KnowledgeQueryFailedEvent,
-    KnowledgeSearchQueryFailedEvent,
-)

-from .types.memory_events import (
-    MemorySaveStartedEvent,
-    MemorySaveCompletedEvent,
-    MemorySaveFailedEvent,
-    MemoryQueryStartedEvent,
-    MemoryQueryCompletedEvent,
-    MemoryQueryFailedEvent,
-    MemoryRetrievalStartedEvent,
-    MemoryRetrievalCompletedEvent,
+EventTypes = (
+    CrewKickoffStartedEvent
+    | CrewKickoffCompletedEvent
+    | CrewKickoffFailedEvent
+    | CrewTestStartedEvent
+    | CrewTestCompletedEvent
+    | CrewTestFailedEvent
+    | CrewTrainStartedEvent
+    | CrewTrainCompletedEvent
+    | CrewTrainFailedEvent
+    | AgentExecutionStartedEvent
+    | AgentExecutionCompletedEvent
+    | LiteAgentExecutionCompletedEvent
+    | TaskStartedEvent
+    | TaskCompletedEvent
+    | TaskFailedEvent
+    | FlowStartedEvent
+    | FlowFinishedEvent
+    | MethodExecutionStartedEvent
+    | MethodExecutionFinishedEvent
+    | MethodExecutionFailedEvent
+    | AgentExecutionErrorEvent
+    | ToolUsageFinishedEvent
+    | ToolUsageErrorEvent
+    | ToolUsageStartedEvent
+    | LLMCallStartedEvent
+    | LLMCallCompletedEvent
+    | LLMCallFailedEvent
+    | LLMStreamChunkEvent
+    | LLMGuardrailStartedEvent
+    | LLMGuardrailCompletedEvent
+    | AgentReasoningStartedEvent
+    | AgentReasoningCompletedEvent
+    | AgentReasoningFailedEvent
+    | KnowledgeRetrievalStartedEvent
+    | KnowledgeRetrievalCompletedEvent
+    | KnowledgeQueryStartedEvent
+    | KnowledgeQueryCompletedEvent
+    | KnowledgeQueryFailedEvent
+    | KnowledgeSearchQueryFailedEvent
+    | MemorySaveStartedEvent
+    | MemorySaveCompletedEvent
+    | MemorySaveFailedEvent
+    | MemoryQueryStartedEvent
+    | MemoryQueryCompletedEvent
+    | MemoryQueryFailedEvent
+    | MemoryRetrievalStartedEvent
+    | MemoryRetrievalCompletedEvent
 )
-
-EventTypes = Union[
-    CrewKickoffStartedEvent,
-    CrewKickoffCompletedEvent,
-    CrewKickoffFailedEvent,
-    CrewTestStartedEvent,
-    CrewTestCompletedEvent,
-    CrewTestFailedEvent,
-    CrewTrainStartedEvent,
-    CrewTrainCompletedEvent,
-    CrewTrainFailedEvent,
-    AgentExecutionStartedEvent,
-    AgentExecutionCompletedEvent,
-    LiteAgentExecutionCompletedEvent,
-    TaskStartedEvent,
-    TaskCompletedEvent,
-    TaskFailedEvent,
-    FlowStartedEvent,
-    FlowFinishedEvent,
-    MethodExecutionStartedEvent,
-    MethodExecutionFinishedEvent,
-    MethodExecutionFailedEvent,
-    AgentExecutionErrorEvent,
-    ToolUsageFinishedEvent,
-    ToolUsageErrorEvent,
-    ToolUsageStartedEvent,
-    LLMCallStartedEvent,
-    LLMCallCompletedEvent,
-    LLMCallFailedEvent,
-    LLMStreamChunkEvent,
-    LLMGuardrailStartedEvent,
-    LLMGuardrailCompletedEvent,
-    AgentReasoningStartedEvent,
-    AgentReasoningCompletedEvent,
-    AgentReasoningFailedEvent,
-    KnowledgeRetrievalStartedEvent,
-    KnowledgeRetrievalCompletedEvent,
-    KnowledgeQueryStartedEvent,
-    KnowledgeQueryCompletedEvent,
-    KnowledgeQueryFailedEvent,
-    KnowledgeSearchQueryFailedEvent,
-    MemorySaveStartedEvent,
-    MemorySaveCompletedEvent,
-    MemorySaveFailedEvent,
-    MemoryQueryStartedEvent,
-    MemoryQueryCompletedEvent,
-    MemoryQueryFailedEvent,
-    MemoryRetrievalStartedEvent,
-    MemoryRetrievalCompletedEvent,
-]
--- a/src/crewai/events/listeners/init.py
+++ b/src/crewai/events/listeners/init.py
@@ -2,4 +2,4 @@

 This module contains various event listener implementations
 for handling memory, tracing, and other event-driven functionality.
-"""
+"""
--- a/src/crewai/events/listeners/memory_listener.py
+++ b/src/crewai/events/listeners/memory_listener.py
@@ -1,12 +1,12 @@
 from crewai.events.base_event_listener import BaseEventListener
 from crewai.events.types.memory_events import (
+    MemoryQueryCompletedEvent,
+    MemoryQueryFailedEvent,
    MemoryRetrievalCompletedEvent,
    MemoryRetrievalStartedEvent,
-    MemoryQueryFailedEvent,
-    MemoryQueryCompletedEvent,
-    MemorySaveStartedEvent,
    MemorySaveCompletedEvent,
    MemorySaveFailedEvent,
+    MemorySaveStartedEvent,
 )


--- a/src/crewai/events/listeners/tracing/first_time_trace_handler.py
+++ b/src/crewai/events/listeners/tracing/first_time_trace_handler.py
@@ -1,5 +1,4 @@
 import logging
-import os
 import uuid
 import webbrowser
 from pathlib import Path
@@ -95,7 +94,7 @@ class FirstTimeTraceHandler:
                # Enable tracing for future runs by updating .env file
                try:
                    _update_or_create_env_file()
-                except Exception as e:
+                except Exception:  # noqa: S110
                    pass

                if self.ephemeral_url:
@@ -163,7 +162,7 @@ class FirstTimeTraceHandler:

        try:
            webbrowser.open(self.ephemeral_url)
-        except Exception as e:
+        except Exception:  # noqa: S110
            pass

        panel_content = f"""
--- a/src/crewai/events/listeners/tracing/trace_batch_manager.py
+++ b/src/crewai/events/listeners/tracing/trace_batch_manager.py
@@ -200,6 +200,9 @@ class TraceBatchManager:
        if self.event_buffer:
            events_sent_to_backend_status = self._send_events_to_backend()
            if events_sent_to_backend_status == 500:
+                self.plus_api.mark_trace_batch_as_failed(
+                    self.trace_batch_id, "Error sending events to backend"
+                )
                return None
        self._finalize_backend_batch()

@@ -273,10 +276,13 @@ class TraceBatchManager:
                logger.error(
                    f"❌ Failed to finalize trace batch: {response.status_code} - {response.text}"
                )
+                self.plus_api.mark_trace_batch_as_failed(
+                    self.trace_batch_id, response.text
+                )

        except Exception as e:
            logger.error(f"❌ Error finalizing trace batch: {e}")
-            # TODO: send error to app marking as failed
+            self.plus_api.mark_trace_batch_as_failed(self.trace_batch_id, str(e))

    def _cleanup_batch_data(self):
        """Clean up batch data after successful finalization to free memory"""
--- a/src/crewai/events/listeners/tracing/types.py
+++ b/src/crewai/events/listeners/tracing/types.py
@@ -1,7 +1,7 @@
-from dataclasses import dataclass, field, asdict
-from datetime import datetime, timezone
-from typing import Dict, Any
 import uuid
+from dataclasses import asdict, dataclass, field
+from datetime import datetime, timezone
+from typing import Any


@dataclass
@@ -13,7 +13,7 @@ class TraceEvent:
        default_factory=lambda: datetime.now(timezone.utc).isoformat()
    )
    type: str = ""
-    event_data: Dict[str, Any] = field(default_factory=dict)
+    event_data: dict[str, Any] = field(default_factory=dict)

-    def to_dict(self) -> Dict[str, Any]:
+    def to_dict(self) -> dict[str, Any]:
        return asdict(self)
--- a/src/crewai/events/listeners/tracing/utils.py
+++ b/src/crewai/events/listeners/tracing/utils.py
@@ -54,44 +54,164 @@ def _get_machine_id() -> str:
            [f"{(uuid.getnode() >> b) & 0xFF:02x}" for b in range(0, 12, 2)][::-1]
        )
        parts.append(mac)
-    except Exception:
-        logger.warning("Error getting machine id for fingerprinting")
+    except Exception:  # noqa: S110
+        pass

-    sysname = platform.system()
-    parts.append(sysname)
+    try:
+        sysname = platform.system()
+        parts.append(sysname)
+    except Exception:
+        sysname = "unknown"
+        parts.append(sysname)

    try:
        if sysname == "Darwin":
-            res = subprocess.run(
-                ["/usr/sbin/system_profiler", "SPHardwareDataType"],
-                capture_output=True,
-                text=True,
-                timeout=2,
-            )
-            m = re.search(r"Hardware UUID:\s*([A-Fa-f0-9\-]+)", res.stdout)
-            if m:
-                parts.append(m.group(1))
-        elif sysname == "Linux":
            try:
-                parts.append(Path("/etc/machine-id").read_text().strip())
-            except Exception:
-                parts.append(Path("/sys/class/dmi/id/product_uuid").read_text().strip())
+                res = subprocess.run(
+                    ["/usr/sbin/system_profiler", "SPHardwareDataType"],
+                    capture_output=True,
+                    text=True,
+                    timeout=2,
+                )
+                m = re.search(r"Hardware UUID:\s*([A-Fa-f0-9\-]+)", res.stdout)
+                if m:
+                    parts.append(m.group(1))
+            except Exception:  # noqa: S110
+                pass
+
+        elif sysname == "Linux":
+            linux_id = _get_linux_machine_id()
+            if linux_id:
+                parts.append(linux_id)
+
        elif sysname == "Windows":
-            res = subprocess.run(
-                ["C:\\Windows\\System32\\wbem\\wmic.exe", "csproduct", "get", "UUID"],
-                capture_output=True,
-                text=True,
-                timeout=2,
-            )
-            lines = [line.strip() for line in res.stdout.splitlines() if line.strip()]
-            if len(lines) >= 2:
-                parts.append(lines[1])
-    except Exception:
-        logger.exception("Error getting machine ID")
+            try:
+                res = subprocess.run(
+                    [
+                        "C:\\Windows\\System32\\wbem\\wmic.exe",
+                        "csproduct",
+                        "get",
+                        "UUID",
+                    ],
+                    capture_output=True,
+                    text=True,
+                    timeout=2,
+                )
+                lines = [
+                    line.strip() for line in res.stdout.splitlines() if line.strip()
+                ]
+                if len(lines) >= 2:
+                    parts.append(lines[1])
+            except Exception:  # noqa: S110
+                pass
+        else:
+            generic_id = _get_generic_system_id()
+            if generic_id:
+                parts.append(generic_id)
+
+    except Exception:  # noqa: S110
+        pass
+
+    if len(parts) <= 1:
+        try:
+            import socket
+
+            parts.append(socket.gethostname())
+        except Exception:  # noqa: S110
+            pass
+
+        try:
+            parts.append(getpass.getuser())
+        except Exception:  # noqa: S110
+            pass
+
+        try:
+            parts.append(platform.machine())
+            parts.append(platform.processor())
+        except Exception:  # noqa: S110
+            pass
+
+    if not parts:
+        parts.append("unknown-system")
+        parts.append(str(uuid.uuid4()))

    return hashlib.sha256("".join(parts).encode()).hexdigest()


+def _get_linux_machine_id() -> str | None:
+    linux_id_sources = [
+        "/etc/machine-id",
+        "/sys/class/dmi/id/product_uuid",
+        "/proc/sys/kernel/random/boot_id",
+        "/sys/class/dmi/id/board_serial",
+        "/sys/class/dmi/id/chassis_serial",
+    ]
+
+    for source in linux_id_sources:
+        try:
+            path = Path(source)
+            if path.exists() and path.is_file():
+                content = path.read_text().strip()
+                if content and content.lower() not in [
+                    "unknown",
+                    "to be filled by o.e.m.",
+                    "",
+                ]:
+                    return content
+        except Exception:  # noqa: S112, PERF203
+            continue
+
+    try:
+        import socket
+
+        hostname = socket.gethostname()
+        arch = platform.machine()
+        if hostname and arch:
+            return f"{hostname}-{arch}"
+    except Exception:  # noqa: S110
+        pass
+
+    return None
+
+
+def _get_generic_system_id() -> str | None:
+    try:
+        parts = []
+
+        try:
+            import socket
+
+            hostname = socket.gethostname()
+            if hostname:
+                parts.append(hostname)
+        except Exception:  # noqa: S110
+            pass
+
+        try:
+            parts.append(platform.machine())
+            parts.append(platform.processor())
+            parts.append(platform.architecture()[0])
+        except Exception:  # noqa: S110
+            pass
+
+        try:
+            container_id = os.environ.get(
+                "HOSTNAME", os.environ.get("CONTAINER_ID", "")
+            )
+            if container_id:
+                parts.append(container_id)
+        except Exception:  # noqa: S110
+            pass
+
+        if parts:
+            return "-".join(filter(None, parts))
+
+    except Exception:  # noqa: S110
+        pass
+
+    return None
+
+
 def _user_data_file() -> Path:
    base = Path(db_storage_path())
    base.mkdir(parents=True, exist_ok=True)
--- a/src/crewai/events/types/init.py
+++ b/src/crewai/events/types/init.py
@@ -2,4 +2,4 @@

 This module contains all event types used throughout the CrewAI system
 for monitoring and extending agent, crew, task, and tool execution.
-"""
+"""
--- a/src/crewai/events/types/agent_events.py
+++ b/src/crewai/events/types/agent_events.py
@@ -2,14 +2,15 @@

 from __future__ import annotations

-from typing import Any, Dict, List, Optional, Sequence, Union
+from collections.abc import Sequence
+from typing import Any

-from pydantic import model_validator
+from pydantic import ConfigDict, model_validator

 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.events.base_events import BaseEvent
 from crewai.tools.base_tool import BaseTool
 from crewai.tools.structured_tool import CrewStructuredTool
-from crewai.events.base_events import BaseEvent


 class AgentExecutionStartedEvent(BaseEvent):
@@ -17,11 +18,11 @@ class AgentExecutionStartedEvent(BaseEvent):

    agent: BaseAgent
    task: Any
-    tools: Optional[Sequence[Union[BaseTool, CrewStructuredTool]]]
+    tools: Sequence[BaseTool | CrewStructuredTool] | None
    task_prompt: str
    type: str = "agent_execution_started"

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)

    @model_validator(mode="after")
    def set_fingerprint_data(self):
@@ -45,7 +46,7 @@ class AgentExecutionCompletedEvent(BaseEvent):
    output: str
    type: str = "agent_execution_completed"

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)

    @model_validator(mode="after")
    def set_fingerprint_data(self):
@@ -69,7 +70,7 @@ class AgentExecutionErrorEvent(BaseEvent):
    error: str
    type: str = "agent_execution_error"

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)

    @model_validator(mode="after")
    def set_fingerprint_data(self):
@@ -89,18 +90,18 @@ class AgentExecutionErrorEvent(BaseEvent):
 class LiteAgentExecutionStartedEvent(BaseEvent):
    """Event emitted when a LiteAgent starts executing"""

-    agent_info: Dict[str, Any]
-    tools: Optional[Sequence[Union[BaseTool, CrewStructuredTool]]]
-    messages: Union[str, List[Dict[str, str]]]
+    agent_info: dict[str, Any]
+    tools: Sequence[BaseTool | CrewStructuredTool] | None
+    messages: str | list[dict[str, str]]
    type: str = "lite_agent_execution_started"

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)


 class LiteAgentExecutionCompletedEvent(BaseEvent):
    """Event emitted when a LiteAgent completes execution"""

-    agent_info: Dict[str, Any]
+    agent_info: dict[str, Any]
    output: str
    type: str = "lite_agent_execution_completed"

@@ -108,7 +109,7 @@ class LiteAgentExecutionCompletedEvent(BaseEvent):
 class LiteAgentExecutionErrorEvent(BaseEvent):
    """Event emitted when a LiteAgent encounters an error during execution"""

-    agent_info: Dict[str, Any]
+    agent_info: dict[str, Any]
    error: str
    type: str = "lite_agent_execution_error"

--- a/src/crewai/events/types/crew_events.py
+++ b/src/crewai/events/types/crew_events.py
@@ -1,4 +1,4 @@
-from typing import TYPE_CHECKING, Any, Dict, Optional, Union
+from typing import TYPE_CHECKING, Any

 from crewai.events.base_events import BaseEvent

@@ -11,8 +11,8 @@ else:
 class CrewBaseEvent(BaseEvent):
    """Base class for crew events with fingerprint handling"""

-    crew_name: Optional[str]
-    crew: Optional[Crew] = None
+    crew_name: str | None
+    crew: Crew | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -38,7 +38,7 @@ class CrewBaseEvent(BaseEvent):
 class CrewKickoffStartedEvent(CrewBaseEvent):
    """Event emitted when a crew starts execution"""

-    inputs: Optional[Dict[str, Any]]
+    inputs: dict[str, Any] | None
    type: str = "crew_kickoff_started"


@@ -62,7 +62,7 @@ class CrewTrainStartedEvent(CrewBaseEvent):

    n_iterations: int
    filename: str
-    inputs: Optional[Dict[str, Any]]
+    inputs: dict[str, Any] | None
    type: str = "crew_train_started"


@@ -85,8 +85,8 @@ class CrewTestStartedEvent(CrewBaseEvent):
    """Event emitted when a crew starts testing"""

    n_iterations: int
-    eval_llm: Optional[Union[str, Any]]
-    inputs: Optional[Dict[str, Any]]
+    eval_llm: str | Any | None
+    inputs: dict[str, Any] | None
    type: str = "crew_test_started"


--- a/src/crewai/events/types/flow_events.py
+++ b/src/crewai/events/types/flow_events.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, Optional, Union
+from typing import Any

 from pydantic import BaseModel, ConfigDict

@@ -16,7 +16,7 @@ class FlowStartedEvent(FlowEvent):
    """Event emitted when a flow starts execution"""

    flow_name: str
-    inputs: Optional[Dict[str, Any]] = None
+    inputs: dict[str, Any] | None = None
    type: str = "flow_started"


@@ -32,8 +32,8 @@ class MethodExecutionStartedEvent(FlowEvent):

    flow_name: str
    method_name: str
-    state: Union[Dict[str, Any], BaseModel]
-    params: Optional[Dict[str, Any]] = None
+    state: dict[str, Any] | BaseModel
+    params: dict[str, Any] | None = None
    type: str = "method_execution_started"


@@ -43,7 +43,7 @@ class MethodExecutionFinishedEvent(FlowEvent):
    flow_name: str
    method_name: str
    result: Any = None
-    state: Union[Dict[str, Any], BaseModel]
+    state: dict[str, Any] | BaseModel
    type: str = "method_execution_finished"


@@ -62,7 +62,7 @@ class FlowFinishedEvent(FlowEvent):
    """Event emitted when a flow completes execution"""

    flow_name: str
-    result: Optional[Any] = None
+    result: Any | None = None
    type: str = "flow_finished"


--- a/src/crewai/events/types/knowledge_events.py
+++ b/src/crewai/events/types/knowledge_events.py
@@ -1,6 +1,5 @@
-from crewai.events.base_events import BaseEvent
-
 from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.events.base_events import BaseEvent


 class KnowledgeRetrievalStartedEvent(BaseEvent):
--- a/src/crewai/events/types/llm_events.py
+++ b/src/crewai/events/types/llm_events.py
@@ -1,5 +1,5 @@
 from enum import Enum
-from typing import Any, Dict, List, Optional, Union
+from typing import Any

 from pydantic import BaseModel

@@ -7,14 +7,14 @@ from crewai.events.base_events import BaseEvent


 class LLMEventBase(BaseEvent):
-    task_name: Optional[str] = None
-    task_id: Optional[str] = None
+    task_name: str | None = None
+    task_id: str | None = None

-    agent_id: Optional[str] = None
-    agent_role: Optional[str] = None
+    agent_id: str | None = None
+    agent_role: str | None = None

-    from_task: Optional[Any] = None
-    from_agent: Optional[Any] = None
+    from_task: Any | None = None
+    from_agent: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -38,11 +38,11 @@ class LLMCallStartedEvent(LLMEventBase):
    """

    type: str = "llm_call_started"
-    model: Optional[str] = None
-    messages: Optional[Union[str, List[Dict[str, Any]]]] = None
-    tools: Optional[List[dict[str, Any]]] = None
-    callbacks: Optional[List[Any]] = None
-    available_functions: Optional[Dict[str, Any]] = None
+    model: str | None = None
+    messages: str | list[dict[str, Any]] | None = None
+    tools: list[dict[str, Any]] | None = None
+    callbacks: list[Any] | None = None
+    available_functions: dict[str, Any] | None = None


 class LLMCallCompletedEvent(LLMEventBase):
@@ -52,7 +52,7 @@ class LLMCallCompletedEvent(LLMEventBase):
    messages: str | list[dict[str, Any]] | None = None
    response: Any
    call_type: LLMCallType
-    model: Optional[str] = None
+    model: str | None = None


 class LLMCallFailedEvent(LLMEventBase):
@@ -64,13 +64,13 @@ class LLMCallFailedEvent(LLMEventBase):

 class FunctionCall(BaseModel):
    arguments: str
-    name: Optional[str] = None
+    name: str | None = None


 class ToolCall(BaseModel):
-    id: Optional[str] = None
+    id: str | None = None
    function: FunctionCall
-    type: Optional[str] = None
+    type: str | None = None
    index: int


@@ -79,4 +79,4 @@ class LLMStreamChunkEvent(LLMEventBase):

    type: str = "llm_stream_chunk"
    chunk: str
-    tool_call: Optional[ToolCall] = None
+    tool_call: ToolCall | None = None
--- a/src/crewai/events/types/llm_guardrail_events.py
+++ b/src/crewai/events/types/llm_guardrail_events.py
@@ -1,5 +1,6 @@
+from collections.abc import Callable
 from inspect import getsource
-from typing import Any, Callable, Optional, Union
+from typing import Any

 from crewai.events.base_events import BaseEvent

@@ -13,12 +14,12 @@ class LLMGuardrailStartedEvent(BaseEvent):
    """

    type: str = "llm_guardrail_started"
-    guardrail: Union[str, Callable]
+    guardrail: str | Callable
    retry_count: int

    def __init__(self, **data):
-        from crewai.tasks.llm_guardrail import LLMGuardrail
        from crewai.tasks.hallucination_guardrail import HallucinationGuardrail
+        from crewai.tasks.llm_guardrail import LLMGuardrail

        super().__init__(**data)

@@ -41,5 +42,5 @@ class LLMGuardrailCompletedEvent(BaseEvent):
    type: str = "llm_guardrail_completed"
    success: bool
    result: Any
-    error: Optional[str] = None
+    error: str | None = None
    retry_count: int
--- a/src/crewai/events/types/logging_events.py
+++ b/src/crewai/events/types/logging_events.py
@@ -1,6 +1,8 @@
 """Agent logging events that don't reference BaseAgent to avoid circular imports."""

-from typing import Any, Optional
+from typing import Any
+
+from pydantic import ConfigDict

 from crewai.events.base_events import BaseEvent

@@ -9,7 +11,7 @@ class AgentLogsStartedEvent(BaseEvent):
    """Event emitted when agent logs should be shown at start"""

    agent_role: str
-    task_description: Optional[str] = None
+    task_description: str | None = None
    verbose: bool = False
    type: str = "agent_logs_started"

@@ -22,4 +24,4 @@ class AgentLogsExecutionEvent(BaseEvent):
    verbose: bool = False
    type: str = "agent_logs_execution"

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)
--- a/src/crewai/events/types/memory_events.py
+++ b/src/crewai/events/types/memory_events.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, Optional
+from typing import Any

 from crewai.events.base_events import BaseEvent

@@ -7,12 +7,12 @@ class MemoryBaseEvent(BaseEvent):
    """Base event for memory operations"""

    type: str
-    task_id: Optional[str] = None
-    task_name: Optional[str] = None
-    from_task: Optional[Any] = None
-    from_agent: Optional[Any] = None
-    agent_role: Optional[str] = None
-    agent_id: Optional[str] = None
+    task_id: str | None = None
+    task_name: str | None = None
+    from_task: Any | None = None
+    from_agent: Any | None = None
+    agent_role: str | None = None
+    agent_id: str | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -26,7 +26,7 @@ class MemoryQueryStartedEvent(MemoryBaseEvent):
    type: str = "memory_query_started"
    query: str
    limit: int
-    score_threshold: Optional[float] = None
+    score_threshold: float | None = None


 class MemoryQueryCompletedEvent(MemoryBaseEvent):
@@ -36,7 +36,7 @@ class MemoryQueryCompletedEvent(MemoryBaseEvent):
    query: str
    results: Any
    limit: int
-    score_threshold: Optional[float] = None
+    score_threshold: float | None = None
    query_time_ms: float


@@ -46,7 +46,7 @@ class MemoryQueryFailedEvent(MemoryBaseEvent):
    type: str = "memory_query_failed"
    query: str
    limit: int
-    score_threshold: Optional[float] = None
+    score_threshold: float | None = None
    error: str


@@ -54,9 +54,9 @@ class MemorySaveStartedEvent(MemoryBaseEvent):
    """Event emitted when a memory save operation is started"""

    type: str = "memory_save_started"
-    value: Optional[str] = None
-    metadata: Optional[Dict[str, Any]] = None
-    agent_role: Optional[str] = None
+    value: str | None = None
+    metadata: dict[str, Any] | None = None
+    agent_role: str | None = None


 class MemorySaveCompletedEvent(MemoryBaseEvent):
@@ -64,8 +64,8 @@ class MemorySaveCompletedEvent(MemoryBaseEvent):

    type: str = "memory_save_completed"
    value: str
-    metadata: Optional[Dict[str, Any]] = None
-    agent_role: Optional[str] = None
+    metadata: dict[str, Any] | None = None
+    agent_role: str | None = None
    save_time_ms: float


@@ -73,9 +73,9 @@ class MemorySaveFailedEvent(MemoryBaseEvent):
    """Event emitted when a memory save operation fails"""

    type: str = "memory_save_failed"
-    value: Optional[str] = None
-    metadata: Optional[Dict[str, Any]] = None
-    agent_role: Optional[str] = None
+    value: str | None = None
+    metadata: dict[str, Any] | None = None
+    agent_role: str | None = None
    error: str


@@ -83,13 +83,13 @@ class MemoryRetrievalStartedEvent(MemoryBaseEvent):
    """Event emitted when memory retrieval for a task prompt starts"""

    type: str = "memory_retrieval_started"
-    task_id: Optional[str] = None
+    task_id: str | None = None


 class MemoryRetrievalCompletedEvent(MemoryBaseEvent):
    """Event emitted when memory retrieval for a task prompt completes successfully"""

    type: str = "memory_retrieval_completed"
-    task_id: Optional[str] = None
+    task_id: str | None = None
    memory_content: str
    retrieval_time_ms: float
--- a/src/crewai/events/types/reasoning_events.py
+++ b/src/crewai/events/types/reasoning_events.py
@@ -1,5 +1,6 @@
+from typing import Any
+
 from crewai.events.base_events import BaseEvent
-from typing import Any, Optional


 class ReasoningEvent(BaseEvent):
@@ -9,10 +10,10 @@ class ReasoningEvent(BaseEvent):
    attempt: int = 1
    agent_role: str
    task_id: str
-    task_name: Optional[str] = None
-    from_task: Optional[Any] = None
-    agent_id: Optional[str] = None
-    from_agent: Optional[Any] = None
+    task_name: str | None = None
+    from_task: Any | None = None
+    agent_id: str | None = None
+    from_agent: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
--- a/src/crewai/events/types/task_events.py
+++ b/src/crewai/events/types/task_events.py
@@ -1,15 +1,15 @@
-from typing import Any, Optional
+from typing import Any

-from crewai.tasks.task_output import TaskOutput
 from crewai.events.base_events import BaseEvent
+from crewai.tasks.task_output import TaskOutput


 class TaskStartedEvent(BaseEvent):
    """Event emitted when a task starts"""

    type: str = "task_started"
-    context: Optional[str]
-    task: Optional[Any] = None
+    context: str | None
+    task: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -29,7 +29,7 @@ class TaskCompletedEvent(BaseEvent):

    output: TaskOutput
    type: str = "task_completed"
-    task: Optional[Any] = None
+    task: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -49,7 +49,7 @@ class TaskFailedEvent(BaseEvent):

    error: str
    type: str = "task_failed"
-    task: Optional[Any] = None
+    task: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
@@ -69,7 +69,7 @@ class TaskEvaluationEvent(BaseEvent):

    type: str = "task_evaluation"
    evaluation_type: str
-    task: Optional[Any] = None
+    task: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
--- a/src/crewai/events/types/tool_usage_events.py
+++ b/src/crewai/events/types/tool_usage_events.py
@@ -1,5 +1,8 @@
+from collections.abc import Callable
 from datetime import datetime
-from typing import Any, Callable, Dict, Optional
+from typing import Any
+
+from pydantic import ConfigDict

 from crewai.events.base_events import BaseEvent

@@ -7,21 +10,21 @@ from crewai.events.base_events import BaseEvent
 class ToolUsageEvent(BaseEvent):
    """Base event for tool usage tracking"""

-    agent_key: Optional[str] = None
-    agent_role: Optional[str] = None
-    agent_id: Optional[str] = None
+    agent_key: str | None = None
+    agent_role: str | None = None
+    agent_id: str | None = None
    tool_name: str
-    tool_args: Dict[str, Any] | str
-    tool_class: Optional[str] = None
+    tool_args: dict[str, Any] | str
+    tool_class: str | None = None
    run_attempts: int | None = None
    delegations: int | None = None
-    agent: Optional[Any] = None
-    task_name: Optional[str] = None
-    task_id: Optional[str] = None
-    from_task: Optional[Any] = None
-    from_agent: Optional[Any] = None
+    agent: Any | None = None
+    task_name: str | None = None
+    task_id: str | None = None
+    from_task: Any | None = None
+    from_agent: Any | None = None

-    model_config = {"arbitrary_types_allowed": True}
+    model_config = ConfigDict(arbitrary_types_allowed=True)

    def __init__(self, **data):
        super().__init__(**data)
@@ -81,9 +84,9 @@ class ToolExecutionErrorEvent(BaseEvent):
    error: Any
    type: str = "tool_execution_error"
    tool_name: str
-    tool_args: Dict[str, Any]
+    tool_args: dict[str, Any]
    tool_class: Callable
-    agent: Optional[Any] = None
+    agent: Any | None = None

    def __init__(self, **data):
        super().__init__(**data)
--- a/src/crewai/events/utils/console_formatter.py
+++ b/src/crewai/events/utils/console_formatter.py
@@ -1,25 +1,25 @@
-from typing import Any, Dict, Optional
+from typing import Any, ClassVar

 from rich.console import Console
+from rich.live import Live
 from rich.panel import Panel
+from rich.syntax import Syntax
 from rich.text import Text
 from rich.tree import Tree
-from rich.live import Live
-from rich.syntax import Syntax


 class ConsoleFormatter:
-    current_crew_tree: Optional[Tree] = None
-    current_task_branch: Optional[Tree] = None
-    current_agent_branch: Optional[Tree] = None
-    current_tool_branch: Optional[Tree] = None
-    current_flow_tree: Optional[Tree] = None
-    current_method_branch: Optional[Tree] = None
-    current_lite_agent_branch: Optional[Tree] = None
-    tool_usage_counts: Dict[str, int] = {}
-    current_reasoning_branch: Optional[Tree] = None  # Track reasoning status
+    current_crew_tree: Tree | None = None
+    current_task_branch: Tree | None = None
+    current_agent_branch: Tree | None = None
+    current_tool_branch: Tree | None = None
+    current_flow_tree: Tree | None = None
+    current_method_branch: Tree | None = None
+    current_lite_agent_branch: Tree | None = None
+    tool_usage_counts: ClassVar[dict[str, int]] = {}
+    current_reasoning_branch: Tree | None = None  # Track reasoning status
    _live_paused: bool = False
-    current_llm_tool_tree: Optional[Tree] = None
+    current_llm_tool_tree: Tree | None = None

    def __init__(self, verbose: bool = False):
        self.console = Console(width=None)
@@ -29,7 +29,7 @@ class ConsoleFormatter:
        # instance so the previous render is replaced instead of writing a new one.
        # Once any non-Tree renderable is printed we stop the Live session so the
        # final Tree persists on the terminal.
-        self._live: Optional[Live] = None
+        self._live: Live | None = None

    def create_panel(self, content: Text, title: str, style: str = "blue") -> Panel:
        """Create a standardized panel with consistent styling."""
@@ -45,7 +45,7 @@ class ConsoleFormatter:
        title: str,
        name: str,
        status_style: str = "blue",
-        tool_args: Dict[str, Any] | str = "",
+        tool_args: dict[str, Any] | str = "",
        **fields,
    ) -> Text:
        """Create standardized status content with consistent formatting."""
@@ -70,7 +70,7 @@ class ConsoleFormatter:
        prefix: str,
        name: str,
        style: str = "blue",
-        status: Optional[str] = None,
+        status: str | None = None,
    ) -> None:
        """Update tree label with consistent formatting."""
        label = Text()
@@ -115,7 +115,7 @@ class ConsoleFormatter:
                self._live.update(tree, refresh=True)
            return  # Nothing else to do

-        # Case 2: blank line while a live session is running – ignore so we
+        # Case 2: blank line while a live session is running - ignore so we
        # don't break the in-place rendering behaviour
        if len(args) == 0 and self._live:
            return
@@ -156,7 +156,7 @@ class ConsoleFormatter:

    def update_crew_tree(
        self,
-        tree: Optional[Tree],
+        tree: Tree | None,
        crew_name: str,
        source_id: str,
        status: str = "completed",
@@ -196,7 +196,7 @@ class ConsoleFormatter:

        self.print_panel(content, title, style)

-    def create_crew_tree(self, crew_name: str, source_id: str) -> Optional[Tree]:
+    def create_crew_tree(self, crew_name: str, source_id: str) -> Tree | None:
        """Create and initialize a new crew tree with initial status."""
        if not self.verbose:
            return None
@@ -220,8 +220,8 @@ class ConsoleFormatter:
        return tree

    def create_task_branch(
-        self, crew_tree: Optional[Tree], task_id: str, task_name: Optional[str] = None
-    ) -> Optional[Tree]:
+        self, crew_tree: Tree | None, task_id: str, task_name: str | None = None
+    ) -> Tree | None:
        """Create and initialize a task branch."""
        if not self.verbose:
            return None
@@ -255,11 +255,11 @@ class ConsoleFormatter:

    def update_task_status(
        self,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
        task_id: str,
        agent_role: str,
        status: str = "completed",
-        task_name: Optional[str] = None,
+        task_name: str | None = None,
    ) -> None:
        """Update task status in the tree."""
        if not self.verbose or crew_tree is None:
@@ -306,8 +306,8 @@ class ConsoleFormatter:
        self.print_panel(content, panel_title, style)

    def create_agent_branch(
-        self, task_branch: Optional[Tree], agent_role: str, crew_tree: Optional[Tree]
-    ) -> Optional[Tree]:
+        self, task_branch: Tree | None, agent_role: str, crew_tree: Tree | None
+    ) -> Tree | None:
        """Create and initialize an agent branch."""
        if not self.verbose or not task_branch or not crew_tree:
            return None
@@ -325,9 +325,9 @@ class ConsoleFormatter:

    def update_agent_status(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        agent_role: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
        status: str = "completed",
    ) -> None:
        """Update agent status in the tree."""
@@ -336,7 +336,7 @@ class ConsoleFormatter:
        # altering the tree. Keeping it a no-op avoids duplicate status lines.
        return

-    def create_flow_tree(self, flow_name: str, flow_id: str) -> Optional[Tree]:
+    def create_flow_tree(self, flow_name: str, flow_id: str) -> Tree | None:
        """Create and initialize a flow tree."""
        content = self.create_status_content(
            "Starting Flow Execution", flow_name, "blue", ID=flow_id
@@ -356,7 +356,7 @@ class ConsoleFormatter:

        return flow_tree

-    def start_flow(self, flow_name: str, flow_id: str) -> Optional[Tree]:
+    def start_flow(self, flow_name: str, flow_id: str) -> Tree | None:
        """Initialize a flow execution tree."""
        flow_tree = Tree("")
        flow_label = Text()
@@ -376,7 +376,7 @@ class ConsoleFormatter:

    def update_flow_status(
        self,
-        flow_tree: Optional[Tree],
+        flow_tree: Tree | None,
        flow_name: str,
        flow_id: str,
        status: str = "completed",
@@ -423,11 +423,11 @@ class ConsoleFormatter:

    def update_method_status(
        self,
-        method_branch: Optional[Tree],
-        flow_tree: Optional[Tree],
+        method_branch: Tree | None,
+        flow_tree: Tree | None,
        method_name: str,
        status: str = "running",
-    ) -> Optional[Tree]:
+    ) -> Tree | None:
        """Update method status in the flow tree."""
        if not flow_tree:
            return None
@@ -480,7 +480,7 @@ class ConsoleFormatter:
    def handle_llm_tool_usage_started(
        self,
        tool_name: str,
-        tool_args: Dict[str, Any] | str,
+        tool_args: dict[str, Any] | str,
    ):
        # Create status content for the tool usage
        content = self.create_status_content(
@@ -520,11 +520,11 @@ class ConsoleFormatter:

    def handle_tool_usage_started(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        tool_name: str,
-        crew_tree: Optional[Tree],
-        tool_args: Dict[str, Any] | str = "",
-    ) -> Optional[Tree]:
+        crew_tree: Tree | None,
+        tool_args: dict[str, Any] | str = "",
+    ) -> Tree | None:
        """Handle tool usage started event."""
        if not self.verbose:
            return None
@@ -569,9 +569,9 @@ class ConsoleFormatter:

    def handle_tool_usage_finished(
        self,
-        tool_branch: Optional[Tree],
+        tool_branch: Tree | None,
        tool_name: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle tool usage finished event."""
        if not self.verbose or tool_branch is None:
@@ -600,10 +600,10 @@ class ConsoleFormatter:

    def handle_tool_usage_error(
        self,
-        tool_branch: Optional[Tree],
+        tool_branch: Tree | None,
        tool_name: str,
        error: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle tool usage error event."""
        if not self.verbose:
@@ -631,9 +631,9 @@ class ConsoleFormatter:

    def handle_llm_call_started(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
-    ) -> Optional[Tree]:
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
+    ) -> Tree | None:
        """Handle LLM call started event."""
        if not self.verbose:
            return None
@@ -672,9 +672,9 @@ class ConsoleFormatter:

    def handle_llm_call_completed(
        self,
-        tool_branch: Optional[Tree],
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        tool_branch: Tree | None,
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
    ) -> None:
        """Handle LLM call completed event."""
        if not self.verbose:
@@ -736,7 +736,7 @@ class ConsoleFormatter:
                self.print()

    def handle_llm_call_failed(
-        self, tool_branch: Optional[Tree], error: str, crew_tree: Optional[Tree]
+        self, tool_branch: Tree | None, error: str, crew_tree: Tree | None
    ) -> None:
        """Handle LLM call failed event."""
        if not self.verbose:
@@ -789,7 +789,7 @@ class ConsoleFormatter:

    def handle_crew_test_started(
        self, crew_name: str, source_id: str, n_iterations: int
-    ) -> Optional[Tree]:
+    ) -> Tree | None:
        """Handle crew test started event."""
        if not self.verbose:
            return None
@@ -823,7 +823,7 @@ class ConsoleFormatter:
        return test_tree

    def handle_crew_test_completed(
-        self, flow_tree: Optional[Tree], crew_name: str
+        self, flow_tree: Tree | None, crew_name: str
    ) -> None:
        """Handle crew test completed event."""
        if not self.verbose:
@@ -913,7 +913,7 @@ class ConsoleFormatter:
        self.print_panel(failure_content, "Test Failure", "red")
        self.print()

-    def create_lite_agent_branch(self, lite_agent_role: str) -> Optional[Tree]:
+    def create_lite_agent_branch(self, lite_agent_role: str) -> Tree | None:
        """Create and initialize a lite agent branch."""
        if not self.verbose:
            return None
@@ -935,10 +935,10 @@ class ConsoleFormatter:

    def update_lite_agent_status(
        self,
-        lite_agent_branch: Optional[Tree],
+        lite_agent_branch: Tree | None,
        lite_agent_role: str,
        status: str = "completed",
-        **fields: Dict[str, Any],
+        **fields: dict[str, Any],
    ) -> None:
        """Update lite agent status in the tree."""
        if not self.verbose or lite_agent_branch is None:
@@ -981,7 +981,7 @@ class ConsoleFormatter:
        lite_agent_role: str,
        status: str = "started",
        error: Any = None,
-        **fields: Dict[str, Any],
+        **fields: dict[str, Any],
    ) -> None:
        """Handle lite agent execution events with consistent formatting."""
        if not self.verbose:
@@ -1006,9 +1006,9 @@ class ConsoleFormatter:

    def handle_knowledge_retrieval_started(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
-    ) -> Optional[Tree]:
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
+    ) -> Tree | None:
        """Handle knowledge retrieval started event."""
        if not self.verbose:
            return None
@@ -1034,13 +1034,13 @@ class ConsoleFormatter:

    def handle_knowledge_retrieval_completed(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
        retrieved_knowledge: Any,
    ) -> None:
        """Handle knowledge retrieval completed event."""
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree
@@ -1062,7 +1062,7 @@ class ConsoleFormatter:
                )
                self.print(knowledge_panel)
                self.print()
-            return None
+            return

        knowledge_branch_found = False
        for child in branch_to_use.children:
@@ -1111,18 +1111,18 @@ class ConsoleFormatter:

    def handle_knowledge_query_started(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        task_prompt: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle knowledge query generated event."""
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree
        if branch_to_use is None or tree_to_use is None:
-            return None
+            return

        query_branch = branch_to_use.add("")
        self.update_tree_label(
@@ -1134,9 +1134,9 @@ class ConsoleFormatter:

    def handle_knowledge_query_failed(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        error: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle knowledge query failed event."""
        if not self.verbose:
@@ -1159,18 +1159,18 @@ class ConsoleFormatter:

    def handle_knowledge_query_completed(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
    ) -> None:
        """Handle knowledge query completed event."""
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree

        if branch_to_use is None or tree_to_use is None:
-            return None
+            return

        query_branch = branch_to_use.add("")
        self.update_tree_label(query_branch, "✅", "Knowledge Query Completed", "green")
@@ -1180,9 +1180,9 @@ class ConsoleFormatter:

    def handle_knowledge_search_query_failed(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        error: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle knowledge search query failed event."""
        if not self.verbose:
@@ -1207,10 +1207,10 @@ class ConsoleFormatter:

    def handle_reasoning_started(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        attempt: int,
-        crew_tree: Optional[Tree],
-    ) -> Optional[Tree]:
+        crew_tree: Tree | None,
+    ) -> Tree | None:
        """Handle agent reasoning started (or refinement) event."""
        if not self.verbose:
            return None
@@ -1249,7 +1249,7 @@ class ConsoleFormatter:
        self,
        plan: str,
        ready: bool,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle agent reasoning completed event."""
        if not self.verbose:
@@ -1292,7 +1292,7 @@ class ConsoleFormatter:
    def handle_reasoning_failed(
        self,
        error: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        """Handle agent reasoning failure event."""
        if not self.verbose:
@@ -1329,7 +1329,7 @@ class ConsoleFormatter:
    def handle_agent_logs_started(
        self,
        agent_role: str,
-        task_description: Optional[str] = None,
+        task_description: str | None = None,
        verbose: bool = False,
    ) -> None:
        """Handle agent logs started event."""
@@ -1367,10 +1367,11 @@ class ConsoleFormatter:
        if not verbose:
            return

-        from crewai.agents.parser import AgentAction, AgentFinish
        import json
        import re

+        from crewai.agents.parser import AgentAction, AgentFinish
+
        agent_role = agent_role.partition("\n")[0]

        if isinstance(formatted_answer, AgentAction):
@@ -1473,9 +1474,9 @@ class ConsoleFormatter:

    def handle_memory_retrieval_started(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
-    ) -> Optional[Tree]:
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
+    ) -> Tree | None:
        if not self.verbose:
            return None

@@ -1497,13 +1498,13 @@ class ConsoleFormatter:

    def handle_memory_retrieval_completed(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
        memory_content: str,
        retrieval_time_ms: float,
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree
@@ -1528,7 +1529,7 @@ class ConsoleFormatter:

        if branch_to_use is None or tree_to_use is None:
            add_panel()
-            return None
+            return

        memory_branch_found = False
        for child in branch_to_use.children:
@@ -1565,13 +1566,13 @@ class ConsoleFormatter:

    def handle_memory_query_completed(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        source_type: str,
        query_time_ms: float,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree
@@ -1580,15 +1581,15 @@ class ConsoleFormatter:
            branch_to_use = tree_to_use

        if branch_to_use is None:
-            return None
+            return

        memory_type = source_type.replace("_", " ").title()

        for child in branch_to_use.children:
            if "Memory Retrieval" in str(child.label):
-                for child in child.children:
-                    sources_branch = child
-                    if "Sources Used" in str(child.label):
+                for inner_child in child.children:
+                    sources_branch = inner_child
+                    if "Sources Used" in str(inner_child.label):
                        sources_branch.add(f"✅ {memory_type} ({query_time_ms:.2f}ms)")
                        break
                else:
@@ -1598,13 +1599,13 @@ class ConsoleFormatter:

    def handle_memory_query_failed(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
        error: str,
        source_type: str,
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = self.current_lite_agent_branch or agent_branch
        tree_to_use = branch_to_use or crew_tree
@@ -1613,15 +1614,15 @@ class ConsoleFormatter:
            branch_to_use = tree_to_use

        if branch_to_use is None:
-            return None
+            return

        memory_type = source_type.replace("_", " ").title()

        for child in branch_to_use.children:
            if "Memory Retrieval" in str(child.label):
-                for child in child.children:
-                    sources_branch = child
-                    if "Sources Used" in str(child.label):
+                for inner_child in child.children:
+                    sources_branch = inner_child
+                    if "Sources Used" in str(inner_child.label):
                        sources_branch.add(f"❌ {memory_type} - Error: {error}")
                        break
                else:
@@ -1630,16 +1631,16 @@ class ConsoleFormatter:
                    break

    def handle_memory_save_started(
-        self, agent_branch: Optional[Tree], crew_tree: Optional[Tree]
+        self, agent_branch: Tree | None, crew_tree: Tree | None
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = agent_branch or self.current_lite_agent_branch
        tree_to_use = branch_to_use or crew_tree

        if tree_to_use is None:
-            return None
+            return

        for child in tree_to_use.children:
            if "Memory Update" in str(child.label):
@@ -1655,19 +1656,19 @@ class ConsoleFormatter:

    def handle_memory_save_completed(
        self,
-        agent_branch: Optional[Tree],
-        crew_tree: Optional[Tree],
+        agent_branch: Tree | None,
+        crew_tree: Tree | None,
        save_time_ms: float,
        source_type: str,
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = agent_branch or self.current_lite_agent_branch
        tree_to_use = branch_to_use or crew_tree

        if tree_to_use is None:
-            return None
+            return

        memory_type = source_type.replace("_", " ").title()
        content = f"✅ {memory_type} Memory Saved ({save_time_ms:.2f}ms)"
@@ -1685,19 +1686,19 @@ class ConsoleFormatter:

    def handle_memory_save_failed(
        self,
-        agent_branch: Optional[Tree],
+        agent_branch: Tree | None,
        error: str,
        source_type: str,
-        crew_tree: Optional[Tree],
+        crew_tree: Tree | None,
    ) -> None:
        if not self.verbose:
-            return None
+            return

        branch_to_use = agent_branch or self.current_lite_agent_branch
        tree_to_use = branch_to_use or crew_tree

        if branch_to_use is None or tree_to_use is None:
-            return None
+            return

        memory_type = source_type.replace("_", " ").title()
        content = f"❌ {memory_type} Memory Save Failed"
@@ -1738,7 +1739,7 @@ class ConsoleFormatter:
    def handle_guardrail_completed(
        self,
        success: bool,
-        error: Optional[str],
+        error: str | None,
        retry_count: int,
    ) -> None:
        """Display guardrail evaluation result.
--- a/src/crewai/experimental/init.py
+++ b/src/crewai/experimental/init.py
@@ -1,40 +1,39 @@
 from crewai.experimental.evaluation import (
+    AgentEvaluationResult,
+    AgentEvaluator,
    BaseEvaluator,
    EvaluationScore,
-    MetricCategory,
-    AgentEvaluationResult,
-    SemanticQualityEvaluator,
-    GoalAlignmentEvaluator,
-    ReasoningEfficiencyEvaluator,
-    ToolSelectionEvaluator,
-    ParameterExtractionEvaluator,
-    ToolInvocationEvaluator,
    EvaluationTraceCallback,
-    create_evaluation_callbacks,
-    AgentEvaluator,
-    create_default_evaluator,
-    ExperimentRunner,
-    ExperimentResults,
    ExperimentResult,
+    ExperimentResults,
+    ExperimentRunner,
+    GoalAlignmentEvaluator,
+    MetricCategory,
+    ParameterExtractionEvaluator,
+    ReasoningEfficiencyEvaluator,
+    SemanticQualityEvaluator,
+    ToolInvocationEvaluator,
+    ToolSelectionEvaluator,
+    create_default_evaluator,
+    create_evaluation_callbacks,
 )

-
 __all__ = [
+    "AgentEvaluationResult",
+    "AgentEvaluator",
    "BaseEvaluator",
    "EvaluationScore",
-    "MetricCategory",
-    "AgentEvaluationResult",
-    "SemanticQualityEvaluator",
-    "GoalAlignmentEvaluator",
-    "ReasoningEfficiencyEvaluator",
-    "ToolSelectionEvaluator",
-    "ParameterExtractionEvaluator",
-    "ToolInvocationEvaluator",
    "EvaluationTraceCallback",
-    "create_evaluation_callbacks",
-    "AgentEvaluator",
-    "create_default_evaluator",
-    "ExperimentRunner",
+    "ExperimentResult",
    "ExperimentResults",
-    "ExperimentResult"
-]
+    "ExperimentRunner",
+    "GoalAlignmentEvaluator",
+    "MetricCategory",
+    "ParameterExtractionEvaluator",
+    "ReasoningEfficiencyEvaluator",
+    "SemanticQualityEvaluator",
+    "ToolInvocationEvaluator",
+    "ToolSelectionEvaluator",
+    "create_default_evaluator",
+    "create_evaluation_callbacks",
+]
--- a/src/crewai/experimental/evaluation/init.py
+++ b/src/crewai/experimental/evaluation/init.py
@@ -1,51 +1,47 @@
+from crewai.experimental.evaluation.agent_evaluator import (
+    AgentEvaluator,
+    create_default_evaluator,
+)
 from crewai.experimental.evaluation.base_evaluator import (
+    AgentEvaluationResult,
    BaseEvaluator,
    EvaluationScore,
    MetricCategory,
-    AgentEvaluationResult
 )
-
-from crewai.experimental.evaluation.metrics import (
-    SemanticQualityEvaluator,
-    GoalAlignmentEvaluator,
-    ReasoningEfficiencyEvaluator,
-    ToolSelectionEvaluator,
-    ParameterExtractionEvaluator,
-    ToolInvocationEvaluator
-)
-
 from crewai.experimental.evaluation.evaluation_listener import (
    EvaluationTraceCallback,
-    create_evaluation_callbacks
+    create_evaluation_callbacks,
 )
-
-from crewai.experimental.evaluation.agent_evaluator import (
-    AgentEvaluator,
-    create_default_evaluator
-)
-
 from crewai.experimental.evaluation.experiment import (
-    ExperimentRunner,
+    ExperimentResult,
    ExperimentResults,
-    ExperimentResult
+    ExperimentRunner,
+)
+from crewai.experimental.evaluation.metrics import (
+    GoalAlignmentEvaluator,
+    ParameterExtractionEvaluator,
+    ReasoningEfficiencyEvaluator,
+    SemanticQualityEvaluator,
+    ToolInvocationEvaluator,
+    ToolSelectionEvaluator,
 )

 __all__ = [
+    "AgentEvaluationResult",
+    "AgentEvaluator",
    "BaseEvaluator",
    "EvaluationScore",
-    "MetricCategory",
-    "AgentEvaluationResult",
-    "SemanticQualityEvaluator",
-    "GoalAlignmentEvaluator",
-    "ReasoningEfficiencyEvaluator",
-    "ToolSelectionEvaluator",
-    "ParameterExtractionEvaluator",
-    "ToolInvocationEvaluator",
    "EvaluationTraceCallback",
-    "create_evaluation_callbacks",
-    "AgentEvaluator",
-    "create_default_evaluator",
-    "ExperimentRunner",
+    "ExperimentResult",
    "ExperimentResults",
-    "ExperimentResult"
+    "ExperimentRunner",
+    "GoalAlignmentEvaluator",
+    "MetricCategory",
+    "ParameterExtractionEvaluator",
+    "ReasoningEfficiencyEvaluator",
+    "SemanticQualityEvaluator",
+    "ToolInvocationEvaluator",
+    "ToolSelectionEvaluator",
+    "create_default_evaluator",
+    "create_evaluation_callbacks",
 ]
--- a/src/crewai/experimental/evaluation/agent_evaluator.py
+++ b/src/crewai/experimental/evaluation/agent_evaluator.py
@@ -1,34 +1,36 @@
 import threading
-from typing import Any, Optional
+from collections.abc import Sequence
+from typing import Any

-from crewai.experimental.evaluation.base_evaluator import (
-    AgentEvaluationResult,
-    AggregationStrategy,
-)
 from crewai.agent import Agent
-from crewai.task import Task
-from crewai.experimental.evaluation.evaluation_display import EvaluationDisplayFormatter
+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 (
-    AgentEvaluationStartedEvent,
    AgentEvaluationCompletedEvent,
    AgentEvaluationFailedEvent,
+    AgentEvaluationStartedEvent,
+    LiteAgentExecutionCompletedEvent,
 )
-from crewai.experimental.evaluation import BaseEvaluator, create_evaluation_callbacks
-from collections.abc import Sequence
-from crewai.events.event_bus import crewai_event_bus
-from crewai.events.utils.console_formatter import ConsoleFormatter
 from crewai.events.types.task_events import TaskCompletedEvent
-from crewai.events.types.agent_events import LiteAgentExecutionCompletedEvent
+from crewai.events.utils.console_formatter import ConsoleFormatter
 from crewai.experimental.evaluation.base_evaluator import (
    AgentAggregatedEvaluationResult,
+    AgentEvaluationResult,
+    AggregationStrategy,
+    BaseEvaluator,
    EvaluationScore,
    MetricCategory,
 )
+from crewai.experimental.evaluation.evaluation_display import EvaluationDisplayFormatter
+from crewai.experimental.evaluation.evaluation_listener import (
+    create_evaluation_callbacks,
+)
+from crewai.task import Task


 class ExecutionState:
-    current_agent_id: Optional[str] = None
-    current_task_id: Optional[str] = None
+    current_agent_id: str | None = None
+    current_task_id: str | None = None

    def __init__(self):
        self.traces = {}
@@ -40,10 +42,10 @@ class ExecutionState:
 class AgentEvaluator:
    def __init__(
        self,
-        agents: list[Agent],
+        agents: list[Agent] | list[BaseAgent],
        evaluators: Sequence[BaseEvaluator] | None = None,
    ):
-        self.agents: list[Agent] = agents
+        self.agents: list[Agent] | list[BaseAgent] = agents
        self.evaluators: Sequence[BaseEvaluator] | None = evaluators

        self.callback = create_evaluation_callbacks()
@@ -75,7 +77,8 @@ class AgentEvaluator:
        )

    def _handle_task_completed(self, source: Any, event: TaskCompletedEvent) -> None:
-        assert event.task is not None
+        if event.task is None:
+            raise ValueError("TaskCompletedEvent must have a task")
        agent = event.task.agent
        if (
            agent
@@ -92,9 +95,8 @@ class AgentEvaluator:
            state.current_agent_id = str(agent.id)
            state.current_task_id = str(event.task.id)

-            assert (
-                state.current_agent_id is not None and state.current_task_id is not None
-            )
+            if state.current_agent_id is None or state.current_task_id is None:
+                raise ValueError("Agent ID and Task ID must not be None")
            trace = self.callback.get_trace(
                state.current_agent_id, state.current_task_id
            )
@@ -146,9 +148,8 @@ class AgentEvaluator:
            if not target_agent:
                return

-            assert (
-                state.current_agent_id is not None and state.current_task_id is not None
-            )
+            if state.current_agent_id is None or state.current_task_id is None:
+                raise ValueError("Agent ID and Task ID must not be None")
            trace = self.callback.get_trace(
                state.current_agent_id, state.current_task_id
            )
@@ -244,7 +245,7 @@ class AgentEvaluator:

    def evaluate(
        self,
-        agent: Agent,
+        agent: Agent | BaseAgent,
        execution_trace: dict[str, Any],
        final_output: Any,
        state: ExecutionState,
@@ -255,7 +256,8 @@ class AgentEvaluator:
            task_id=state.current_task_id or (str(task.id) if task else "unknown_task"),
        )

-        assert self.evaluators is not None
+        if self.evaluators is None:
+            raise ValueError("Evaluators must be initialized")
        task_id = str(task.id) if task else None
        for evaluator in self.evaluators:
            try:
@@ -276,7 +278,7 @@ class AgentEvaluator:
                    metric_category=evaluator.metric_category,
                    score=score,
                )
-            except Exception as e:
+            except Exception as e:  # noqa: PERF203
                self.emit_evaluation_failed_event(
                    agent_role=agent.role,
                    agent_id=str(agent.id),
@@ -284,7 +286,7 @@ class AgentEvaluator:
                    error=str(e),
                )
                self.console_formatter.print(
-                    f"Error in {evaluator.metric_category.value} evaluator: {str(e)}"
+                    f"Error in {evaluator.metric_category.value} evaluator: {e!s}"
                )

        return result
@@ -337,14 +339,14 @@ class AgentEvaluator:
        )


-def create_default_evaluator(agents: list[Agent], llm: None = None):
+def create_default_evaluator(agents: list[Agent] | list[BaseAgent], llm: None = None):
    from crewai.experimental.evaluation import (
        GoalAlignmentEvaluator,
-        SemanticQualityEvaluator,
-        ToolSelectionEvaluator,
        ParameterExtractionEvaluator,
-        ToolInvocationEvaluator,
        ReasoningEfficiencyEvaluator,
+        SemanticQualityEvaluator,
+        ToolInvocationEvaluator,
+        ToolSelectionEvaluator,
    )

    evaluators = [
--- a/src/crewai/experimental/evaluation/base_evaluator.py
+++ b/src/crewai/experimental/evaluation/base_evaluator.py
@@ -1,15 +1,17 @@
 import abc
 import enum
 from enum import Enum
-from typing import Any, Dict, List, Optional
+from typing import Any

 from pydantic import BaseModel, Field

 from crewai.agent import Agent
-from crewai.task import Task
+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

+
 class MetricCategory(enum.Enum):
    GOAL_ALIGNMENT = "goal_alignment"
    SEMANTIC_QUALITY = "semantic_quality"
@@ -19,7 +21,7 @@ class MetricCategory(enum.Enum):
    TOOL_INVOCATION = "tool_invocation"

    def title(self):
-        return self.value.replace('_', ' ').title()
+        return self.value.replace("_", " ").title()


 class EvaluationScore(BaseModel):
@@ -27,15 +29,13 @@ class EvaluationScore(BaseModel):
        default=5.0,
        description="Numeric score from 0-10 where 0 is worst and 10 is best, None if not applicable",
        ge=0.0,
-        le=10.0
+        le=10.0,
    )
    feedback: str = Field(
-        default="",
-        description="Detailed feedback explaining the evaluation score"
+        default="", description="Detailed feedback explaining the evaluation score"
    )
    raw_response: str | None = Field(
-        default=None,
-        description="Raw response from the evaluator (e.g., LLM)"
+        default=None, description="Raw response from the evaluator (e.g., LLM)"
    )

    def __str__(self) -> str:
@@ -56,8 +56,8 @@ class BaseEvaluator(abc.ABC):
    @abc.abstractmethod
    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: Any,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -67,9 +67,8 @@ class BaseEvaluator(abc.ABC):
 class AgentEvaluationResult(BaseModel):
    agent_id: str = Field(description="ID of the evaluated agent")
    task_id: str = Field(description="ID of the task that was executed")
-    metrics: Dict[MetricCategory, EvaluationScore] = Field(
-        default_factory=dict,
-        description="Evaluation scores for each metric category"
+    metrics: dict[MetricCategory, EvaluationScore] = Field(
+        default_factory=dict, description="Evaluation scores for each metric category"
    )


@@ -81,33 +80,23 @@ class AggregationStrategy(Enum):


 class AgentAggregatedEvaluationResult(BaseModel):
-    agent_id: str = Field(
-        default="",
-        description="ID of the agent"
-    )
-    agent_role: str = Field(
-        default="",
-        description="Role of the agent"
-    )
+    agent_id: str = Field(default="", description="ID of the agent")
+    agent_role: str = Field(default="", description="Role of the agent")
    task_count: int = Field(
-        default=0,
-        description="Number of tasks included in this aggregation"
+        default=0, description="Number of tasks included in this aggregation"
    )
    aggregation_strategy: AggregationStrategy = Field(
        default=AggregationStrategy.SIMPLE_AVERAGE,
-        description="Strategy used for aggregation"
+        description="Strategy used for aggregation",
    )
-    metrics: Dict[MetricCategory, EvaluationScore] = Field(
-        default_factory=dict,
-        description="Aggregated metrics across all tasks"
+    metrics: dict[MetricCategory, EvaluationScore] = Field(
+        default_factory=dict, description="Aggregated metrics across all tasks"
    )
-    task_results: List[str] = Field(
-        default_factory=list,
-        description="IDs of tasks included in this aggregation"
+    task_results: list[str] = Field(
+        default_factory=list, description="IDs of tasks included in this aggregation"
    )
-    overall_score: Optional[float] = Field(
-        default=None,
-        description="Overall score for this agent"
+    overall_score: float | None = Field(
+        default=None, description="Overall score for this agent"
    )

    def __str__(self) -> str:
@@ -119,7 +108,7 @@ class AgentAggregatedEvaluationResult(BaseModel):
            result += f"\n\n- {category.value.upper()}: {score.score}/10\n"

            if score.feedback:
-                detailed_feedback = "\n  ".join(score.feedback.split('\n'))
+                detailed_feedback = "\n  ".join(score.feedback.split("\n"))
                result += f"  {detailed_feedback}\n"

-        return result
+        return result
--- a/src/crewai/experimental/evaluation/evaluation_display.py
+++ b/src/crewai/experimental/evaluation/evaluation_display.py
@@ -1,16 +1,18 @@
 from collections import defaultdict
-from typing import Dict, Any, List
-from rich.table import Table
-from rich.box import HEAVY_EDGE, ROUNDED
 from collections.abc import Sequence
+from typing import Any
+
+from rich.box import HEAVY_EDGE, ROUNDED
+from rich.table import Table
+
+from crewai.events.utils.console_formatter import ConsoleFormatter
 from crewai.experimental.evaluation.base_evaluator import (
    AgentAggregatedEvaluationResult,
-    AggregationStrategy,
    AgentEvaluationResult,
+    AggregationStrategy,
+    EvaluationScore,
    MetricCategory,
 )
-from crewai.experimental.evaluation import EvaluationScore
-from crewai.events.utils.console_formatter import ConsoleFormatter
 from crewai.utilities.llm_utils import create_llm


@@ -19,7 +21,7 @@ class EvaluationDisplayFormatter:
        self.console_formatter = ConsoleFormatter()

    def display_evaluation_with_feedback(
-        self, iterations_results: Dict[int, Dict[str, List[Any]]]
+        self, iterations_results: dict[int, dict[str, list[Any]]]
    ):
        if not iterations_results:
            self.console_formatter.print(
@@ -99,7 +101,7 @@ class EvaluationDisplayFormatter:

    def display_summary_results(
        self,
-        iterations_results: Dict[int, Dict[str, List[AgentAggregatedEvaluationResult]]],
+        iterations_results: dict[int, dict[str, list[AgentEvaluationResult]]],
    ):
        if not iterations_results:
            self.console_formatter.print(
@@ -280,7 +282,7 @@ class EvaluationDisplayFormatter:
                    feedback_summary = feedbacks[0]

            aggregated_metrics[category] = EvaluationScore(
-                score=avg_score, feedback=feedback_summary
+                score=avg_score, feedback=feedback_summary or ""
            )

        overall_score = None
@@ -304,25 +306,25 @@ class EvaluationDisplayFormatter:
        self,
        agent_role: str,
        metric: str,
-        feedbacks: List[str],
-        scores: List[float | None],
+        feedbacks: list[str],
+        scores: list[float | None],
        strategy: AggregationStrategy,
    ) -> str:
        if len(feedbacks) <= 2 and all(len(fb) < 200 for fb in feedbacks):
            return "\n\n".join(
-                [f"Feedback {i+1}: {fb}" for i, fb in enumerate(feedbacks)]
+                [f"Feedback {i + 1}: {fb}" for i, fb in enumerate(feedbacks)]
            )

        try:
            llm = create_llm()

            formatted_feedbacks = []
-            for i, (feedback, score) in enumerate(zip(feedbacks, scores)):
+            for i, (feedback, score) in enumerate(zip(feedbacks, scores, strict=False)):
                if len(feedback) > 500:
                    feedback = feedback[:500] + "..."
                score_text = f"{score:.1f}" if score is not None else "N/A"
                formatted_feedbacks.append(
-                    f"Feedback #{i+1} (Score: {score_text}):\n{feedback}"
+                    f"Feedback #{i + 1} (Score: {score_text}):\n{feedback}"
                )

            all_feedbacks = "\n\n" + "\n\n---\n\n".join(formatted_feedbacks)
@@ -365,10 +367,9 @@ class EvaluationDisplayFormatter:
                """,
                },
            ]
-            assert llm is not None
-            response = llm.call(prompt)
-
-            return response
+            if llm is None:
+                raise ValueError("LLM must be initialized")
+            return llm.call(prompt)

        except Exception:
            return "Synthesized from multiple tasks: " + "\n\n".join(
--- a/src/crewai/experimental/evaluation/evaluation_listener.py
+++ b/src/crewai/experimental/evaluation/evaluation_listener.py
@@ -1,26 +1,25 @@
-from datetime import datetime
-from typing import Any, Dict, Optional
-
 from collections.abc import Sequence
+from datetime import datetime
+from typing import Any

-from crewai.agent import Agent
-from crewai.task import Task
+from crewai.agents.agent_builder.base_agent import BaseAgent
 from crewai.events.base_event_listener import BaseEventListener
 from crewai.events.event_bus import CrewAIEventsBus
 from crewai.events.types.agent_events import (
-    AgentExecutionStartedEvent,
    AgentExecutionCompletedEvent,
-    LiteAgentExecutionStartedEvent,
+    AgentExecutionStartedEvent,
    LiteAgentExecutionCompletedEvent,
+    LiteAgentExecutionStartedEvent,
 )
+from crewai.events.types.llm_events import LLMCallCompletedEvent, LLMCallStartedEvent
 from crewai.events.types.tool_usage_events import (
-    ToolUsageFinishedEvent,
-    ToolUsageErrorEvent,
    ToolExecutionErrorEvent,
    ToolSelectionErrorEvent,
+    ToolUsageErrorEvent,
+    ToolUsageFinishedEvent,
    ToolValidateInputErrorEvent,
 )
-from crewai.events.types.llm_events import LLMCallStartedEvent, LLMCallCompletedEvent
+from crewai.task import Task


 class EvaluationTraceCallback(BaseEventListener):
@@ -136,7 +135,7 @@ class EvaluationTraceCallback(BaseEventListener):
    def _init_trace(self, trace_key: str, **kwargs: Any):
        self.traces[trace_key] = kwargs

-    def on_agent_start(self, agent: Agent, task: Task):
+    def on_agent_start(self, agent: BaseAgent, task: Task):
        self.current_agent_id = agent.id
        self.current_task_id = task.id

@@ -151,7 +150,7 @@ class EvaluationTraceCallback(BaseEventListener):
            final_output=None,
        )

-    def on_agent_finish(self, agent: Agent, task: Task, output: Any):
+    def on_agent_finish(self, agent: BaseAgent, task: Task, output: Any):
        trace_key = f"{agent.id}_{task.id}"
        if trace_key in self.traces:
            self.traces[trace_key]["final_output"] = output
@@ -253,7 +252,7 @@ class EvaluationTraceCallback(BaseEventListener):
        if hasattr(self, "current_llm_call"):
            self.current_llm_call = {}

-    def get_trace(self, agent_id: str, task_id: str) -> Optional[Dict[str, Any]]:
+    def get_trace(self, agent_id: str, task_id: str) -> dict[str, Any] | None:
        trace_key = f"{agent_id}_{task_id}"
        return self.traces.get(trace_key)

--- a/src/crewai/experimental/evaluation/experiment/init.py
+++ b/src/crewai/experimental/evaluation/experiment/init.py
@@ -1,8 +1,7 @@
+from crewai.experimental.evaluation.experiment.result import (
+    ExperimentResult,
+    ExperimentResults,
+)
 from crewai.experimental.evaluation.experiment.runner import ExperimentRunner
-from crewai.experimental.evaluation.experiment.result import ExperimentResults, ExperimentResult

-__all__ = [
-    "ExperimentRunner",
-    "ExperimentResults",
-    "ExperimentResult"
-]
+__all__ = ["ExperimentResult", "ExperimentResults", "ExperimentRunner"]
--- a/src/crewai/experimental/evaluation/experiment/result.py
+++ b/src/crewai/experimental/evaluation/experiment/result.py
@@ -2,45 +2,60 @@ import json
 import os
 from datetime import datetime, timezone
 from typing import Any
+
 from pydantic import BaseModel

+
 class ExperimentResult(BaseModel):
    identifier: str
    inputs: dict[str, Any]
-    score: int | dict[str, int | float]
-    expected_score: int | dict[str, int | float]
+    score: float | dict[str, float]
+    expected_score: float | dict[str, float]
    passed: bool
    agent_evaluations: dict[str, Any] | None = None

+
 class ExperimentResults:
-    def __init__(self, results: list[ExperimentResult], metadata: dict[str, Any] | None = None):
+    def __init__(
+        self, results: list[ExperimentResult], metadata: dict[str, Any] | None = None
+    ):
        self.results = results
        self.metadata = metadata or {}
        self.timestamp = datetime.now(timezone.utc)

-        from crewai.experimental.evaluation.experiment.result_display import ExperimentResultsDisplay
+        from crewai.experimental.evaluation.experiment.result_display import (
+            ExperimentResultsDisplay,
+        )
+
        self.display = ExperimentResultsDisplay()

    def to_json(self, filepath: str | None = None) -> dict[str, Any]:
        data = {
            "timestamp": self.timestamp.isoformat(),
            "metadata": self.metadata,
-            "results": [r.model_dump(exclude={"agent_evaluations"}) for r in self.results]
+            "results": [
+                r.model_dump(exclude={"agent_evaluations"}) for r in self.results
+            ],
        }

        if filepath:
-            with open(filepath, 'w') as f:
+            with open(filepath, "w") as f:
                json.dump(data, f, indent=2)
            self.display.console.print(f"[green]Results saved to {filepath}[/green]")

        return data

-    def compare_with_baseline(self, baseline_filepath: str, save_current: bool = True, print_summary: bool = False) -> dict[str, Any]:
+    def compare_with_baseline(
+        self,
+        baseline_filepath: str,
+        save_current: bool = True,
+        print_summary: bool = False,
+    ) -> dict[str, Any]:
        baseline_runs = []

        if os.path.exists(baseline_filepath) and os.path.getsize(baseline_filepath) > 0:
            try:
-                with open(baseline_filepath, 'r') as f:
+                with open(baseline_filepath, "r") as f:
                    baseline_data = json.load(f)

                if isinstance(baseline_data, dict) and "timestamp" in baseline_data:
@@ -48,14 +63,18 @@ class ExperimentResults:
                elif isinstance(baseline_data, list):
                    baseline_runs = baseline_data
            except (json.JSONDecodeError, FileNotFoundError) as e:
-                self.display.console.print(f"[yellow]Warning: Could not load baseline file: {str(e)}[/yellow]")
+                self.display.console.print(
+                    f"[yellow]Warning: Could not load baseline file: {e!s}[/yellow]"
+                )

        if not baseline_runs:
            if save_current:
                current_data = self.to_json()
-                with open(baseline_filepath, 'w') as f:
+                with open(baseline_filepath, "w") as f:
                    json.dump([current_data], f, indent=2)
-                self.display.console.print(f"[green]Saved current results as new baseline to {baseline_filepath}[/green]")
+                self.display.console.print(
+                    f"[green]Saved current results as new baseline to {baseline_filepath}[/green]"
+                )
            return {"is_baseline": True, "changes": {}}

        baseline_runs.sort(key=lambda x: x.get("timestamp", ""), reverse=True)
@@ -69,9 +88,11 @@ class ExperimentResults:
        if save_current:
            current_data = self.to_json()
            baseline_runs.append(current_data)
-            with open(baseline_filepath, 'w') as f:
+            with open(baseline_filepath, "w") as f:
                json.dump(baseline_runs, f, indent=2)
-            self.display.console.print(f"[green]Added current results to baseline file {baseline_filepath}[/green]")
+            self.display.console.print(
+                f"[green]Added current results to baseline file {baseline_filepath}[/green]"
+            )

        return comparison

@@ -118,5 +139,5 @@ class ExperimentResults:
            "new_tests": new_tests,
            "missing_tests": missing_tests,
            "total_compared": len(improved) + len(regressed) + len(unchanged),
-            "baseline_timestamp": baseline_run.get("timestamp", "unknown")
+            "baseline_timestamp": baseline_run.get("timestamp", "unknown"),
        }
--- a/src/crewai/experimental/evaluation/experiment/result_display.py
+++ b/src/crewai/experimental/evaluation/experiment/result_display.py
@@ -1,9 +1,12 @@
-from typing import Dict, Any
+from typing import Any
+
 from rich.console import Console
-from rich.table import Table
 from rich.panel import Panel
+from rich.table import Table
+
 from crewai.experimental.evaluation.experiment.result import ExperimentResults

+
 class ExperimentResultsDisplay:
    def __init__(self):
        self.console = Console()
@@ -19,13 +22,19 @@ class ExperimentResultsDisplay:
        table.add_row("Total Test Cases", str(total))
        table.add_row("Passed", str(passed))
        table.add_row("Failed", str(total - passed))
-        table.add_row("Success Rate", f"{(passed / total * 100):.1f}%" if total > 0 else "N/A")
+        table.add_row(
+            "Success Rate", f"{(passed / total * 100):.1f}%" if total > 0 else "N/A"
+        )

        self.console.print(table)

-    def comparison_summary(self, comparison: Dict[str, Any], baseline_timestamp: str):
-        self.console.print(Panel(f"[bold]Comparison with baseline run from {baseline_timestamp}[/bold]",
-                                 expand=False))
+    def comparison_summary(self, comparison: dict[str, Any], baseline_timestamp: str):
+        self.console.print(
+            Panel(
+                f"[bold]Comparison with baseline run from {baseline_timestamp}[/bold]",
+                expand=False,
+            )
+        )

        table = Table(title="Results Comparison")
        table.add_column("Metric", style="cyan")
@@ -34,7 +43,9 @@ class ExperimentResultsDisplay:

        improved = comparison.get("improved", [])
        if improved:
-            details = ", ".join([f"{test_identifier}" for test_identifier in improved[:3]])
+            details = ", ".join(
+                [f"{test_identifier}" for test_identifier in improved[:3]]
+            )
            if len(improved) > 3:
                details += f" and {len(improved) - 3} more"
            table.add_row("✅ Improved", str(len(improved)), details)
@@ -43,7 +54,9 @@ class ExperimentResultsDisplay:

        regressed = comparison.get("regressed", [])
        if regressed:
-            details = ", ".join([f"{test_identifier}" for test_identifier in regressed[:3]])
+            details = ", ".join(
+                [f"{test_identifier}" for test_identifier in regressed[:3]]
+            )
            if len(regressed) > 3:
                details += f" and {len(regressed) - 3} more"
            table.add_row("❌ Regressed", str(len(regressed)), details, style="red")
@@ -58,13 +71,13 @@ class ExperimentResultsDisplay:
            details = ", ".join(new_tests[:3])
            if len(new_tests) > 3:
                details += f" and {len(new_tests) - 3} more"
-            table.add_row("➕ New Tests", str(len(new_tests)), details)
+            table.add_row("+ New Tests", str(len(new_tests)), details)

        missing_tests = comparison.get("missing_tests", [])
        if missing_tests:
            details = ", ".join(missing_tests[:3])
            if len(missing_tests) > 3:
                details += f" and {len(missing_tests) - 3} more"
-            table.add_row("➖ Missing Tests", str(len(missing_tests)), details)
+            table.add_row("- Missing Tests", str(len(missing_tests)), details)

        self.console.print(table)
--- a/src/crewai/experimental/evaluation/experiment/runner.py
+++ b/src/crewai/experimental/evaluation/experiment/runner.py
@@ -2,11 +2,20 @@ from collections import defaultdict
 from hashlib import md5
 from typing import Any

-from crewai import Crew, Agent
+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.experiment.result_display import ExperimentResultsDisplay
-from crewai.experimental.evaluation.experiment.result import ExperimentResults, ExperimentResult
-from crewai.experimental.evaluation.evaluation_display import AgentAggregatedEvaluationResult
+from crewai.experimental.evaluation.evaluation_display import (
+    AgentAggregatedEvaluationResult,
+)
+from crewai.experimental.evaluation.experiment.result import (
+    ExperimentResult,
+    ExperimentResults,
+)
+from crewai.experimental.evaluation.experiment.result_display import (
+    ExperimentResultsDisplay,
+)
+

 class ExperimentRunner:
    def __init__(self, dataset: list[dict[str, Any]]):
@@ -14,11 +23,17 @@ class ExperimentRunner:
        self.evaluator: AgentEvaluator | None = None
        self.display = ExperimentResultsDisplay()

-    def run(self, crew: Crew | None = None, agents: list[Agent] | None = None, print_summary: bool = False) -> ExperimentResults:
+    def run(
+        self,
+        crew: Crew | None = None,
+        agents: list[Agent] | list[BaseAgent] | None = None,
+        print_summary: bool = False,
+    ) -> ExperimentResults:
        if crew and not agents:
            agents = crew.agents

-        assert agents is not None
+        if agents is None:
+            raise ValueError("Agents must be provided either directly or via a crew")
        self.evaluator = create_default_evaluator(agents=agents)

        results = []
@@ -35,21 +50,37 @@ class ExperimentRunner:

        return experiment_results

-    def _run_test_case(self, test_case: dict[str, Any], agents: list[Agent], crew: Crew | None = None) -> ExperimentResult:
+    def _run_test_case(
+        self,
+        test_case: dict[str, Any],
+        agents: list[Agent] | list[BaseAgent],
+        crew: Crew | None = None,
+    ) -> ExperimentResult:
        inputs = test_case["inputs"]
        expected_score = test_case["expected_score"]
-        identifier = test_case.get("identifier") or md5(str(test_case).encode(), usedforsecurity=False).hexdigest()
+        identifier = (
+            test_case.get("identifier")
+            or md5(str(test_case).encode(), usedforsecurity=False).hexdigest()
+        )

        try:
-            self.display.console.print(f"[dim]Running crew with input: {str(inputs)[:50]}...[/dim]")
+            self.display.console.print(
+                f"[dim]Running crew with input: {str(inputs)[:50]}...[/dim]"
+            )
            self.display.console.print("\n")
            if crew:
                crew.kickoff(inputs=inputs)
            else:
                for agent in agents:
-                    agent.kickoff(**inputs)
+                    if isinstance(agent, Agent):
+                        agent.kickoff(**inputs)
+                    else:
+                        raise TypeError(
+                            f"Agent {agent} is not an instance of Agent and cannot be kicked off directly"
+                        )

-            assert self.evaluator is not None
+            if self.evaluator is None:
+                raise ValueError("Evaluator must be initialized")
            agent_evaluations = self.evaluator.get_agent_evaluation()

            actual_score = self._extract_scores(agent_evaluations)
@@ -61,35 +92,38 @@ class ExperimentRunner:
                score=actual_score,
                expected_score=expected_score,
                passed=passed,
-                agent_evaluations=agent_evaluations
+                agent_evaluations=agent_evaluations,
            )

        except Exception as e:
-            self.display.console.print(f"[red]Error running test case: {str(e)}[/red]")
+            self.display.console.print(f"[red]Error running test case: {e!s}[/red]")
            return ExperimentResult(
                identifier=identifier,
                inputs=inputs,
-                score=0,
+                score=0.0,
                expected_score=expected_score,
-                passed=False
+                passed=False,
            )

-    def _extract_scores(self, agent_evaluations: dict[str, AgentAggregatedEvaluationResult]) -> float | dict[str,  float]:
+    def _extract_scores(
+        self, agent_evaluations: dict[str, AgentAggregatedEvaluationResult]
+    ) -> float | dict[str, float]:
        all_scores: dict[str, list[float]] = defaultdict(list)
        for evaluation in agent_evaluations.values():
            for metric_name, score in evaluation.metrics.items():
                if score.score is not None:
                    all_scores[metric_name.value].append(score.score)

-        avg_scores = {m: sum(s)/len(s) for m, s in all_scores.items()}
+        avg_scores = {m: sum(s) / len(s) for m, s in all_scores.items()}

        if len(avg_scores) == 1:
-            return list(avg_scores.values())[0]
+            return next(iter(avg_scores.values()))

        return avg_scores

-    def _assert_scores(self, expected: float | dict[str, float],
-                        actual: float | dict[str, float]) -> bool:
+    def _assert_scores(
+        self, expected: float | dict[str, float], actual: float | dict[str, float]
+    ) -> bool:
        """
        Compare expected and actual scores, and return whether the test case passed.

@@ -122,4 +156,4 @@ class ExperimentRunner:
            # All matching keys must have actual >= expected
            return all(actual[key] >= expected[key] for key in matching_keys)

-        return False
+        return False
--- a/src/crewai/experimental/evaluation/json_parser.py
+++ b/src/crewai/experimental/evaluation/json_parser.py
@@ -13,11 +13,11 @@ def extract_json_from_llm_response(text: str) -> dict[str, Any]:

    json_patterns = [
        # Standard markdown code blocks with json
-        r'```json\s*([\s\S]*?)\s*```',
+        r"```json\s*([\s\S]*?)\s*```",
        # Code blocks without language specifier
-        r'```\s*([\s\S]*?)\s*```',
+        r"```\s*([\s\S]*?)\s*```",
        # Inline code with JSON
-        r'`([{\\[].*[}\]])`',
+        r"`([{\\[].*[}\]])`",
    ]

    for pattern in json_patterns:
@@ -25,6 +25,6 @@ def extract_json_from_llm_response(text: str) -> dict[str, Any]:
        for match in matches:
            try:
                return json.loads(match.strip())
-            except json.JSONDecodeError:
+            except json.JSONDecodeError:  # noqa: PERF203
                continue
    raise ValueError("No valid JSON found in the response")
--- a/src/crewai/experimental/evaluation/metrics/init.py
+++ b/src/crewai/experimental/evaluation/metrics/init.py
@@ -1,26 +1,21 @@
+from crewai.experimental.evaluation.metrics.goal_metrics import GoalAlignmentEvaluator
 from crewai.experimental.evaluation.metrics.reasoning_metrics import (
-    ReasoningEfficiencyEvaluator
+    ReasoningEfficiencyEvaluator,
 )
-
-from crewai.experimental.evaluation.metrics.tools_metrics import (
-    ToolSelectionEvaluator,
-    ParameterExtractionEvaluator,
-    ToolInvocationEvaluator
-)
-
-from crewai.experimental.evaluation.metrics.goal_metrics import (
-    GoalAlignmentEvaluator
-)
-
 from crewai.experimental.evaluation.metrics.semantic_quality_metrics import (
-    SemanticQualityEvaluator
+    SemanticQualityEvaluator,
+)
+from crewai.experimental.evaluation.metrics.tools_metrics import (
+    ParameterExtractionEvaluator,
+    ToolInvocationEvaluator,
+    ToolSelectionEvaluator,
 )

 __all__ = [
-    "ReasoningEfficiencyEvaluator",
-    "ToolSelectionEvaluator",
-    "ParameterExtractionEvaluator",
-    "ToolInvocationEvaluator",
    "GoalAlignmentEvaluator",
-    "SemanticQualityEvaluator"
-]
+    "ParameterExtractionEvaluator",
+    "ReasoningEfficiencyEvaluator",
+    "SemanticQualityEvaluator",
+    "ToolInvocationEvaluator",
+    "ToolSelectionEvaluator",
+]
--- a/src/crewai/experimental/evaluation/metrics/goal_metrics.py
+++ b/src/crewai/experimental/evaluation/metrics/goal_metrics.py
@@ -1,10 +1,15 @@
-from typing import Any, Dict
+from typing import Any

 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.experimental.evaluation.base_evaluator import (
+    BaseEvaluator,
+    EvaluationScore,
+    MetricCategory,
+)
+from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response
 from crewai.task import Task

-from crewai.experimental.evaluation.base_evaluator import BaseEvaluator, EvaluationScore, MetricCategory
-from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response

 class GoalAlignmentEvaluator(BaseEvaluator):
    @property
@@ -13,8 +18,8 @@ class GoalAlignmentEvaluator(BaseEvaluator):

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: Any,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -23,7 +28,9 @@ class GoalAlignmentEvaluator(BaseEvaluator):
            task_context = f"Task description: {task.description}\nExpected output: {task.expected_output}\n"

        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing how well an AI agent's output aligns with its assigned task goal.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing how well an AI agent's output aligns with its assigned task goal.

 Score the agent's goal alignment on a scale from 0-10 where:
 - 0: Complete misalignment, agent did not understand or attempt the task goal
@@ -37,8 +44,11 @@ Consider:
 4. Did the agent provide all requested information or deliverables?

 Return your evaluation as JSON with fields 'score' (number) and 'feedback' (string).
-"""},
-            {"role": "user", "content": f"""
+""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 Agent goal: {agent.goal}
 {task_context}
@@ -47,23 +57,26 @@ Agent's final output:
 {final_output}

 Evaluate how well the agent's output aligns with the assigned task goal.
-"""}
+""",
+            },
        ]
-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
            evaluation_data: dict[str, Any] = extract_json_from_llm_response(response)
-            assert evaluation_data is not None
+            if evaluation_data is None:
+                raise ValueError("Failed to extract evaluation data from LLM response")

            return EvaluationScore(
                score=evaluation_data.get("score", 0),
                feedback=evaluation_data.get("feedback", response),
-                raw_response=response
+                raw_response=response,
            )
        except Exception:
            return EvaluationScore(
                score=None,
                feedback=f"Failed to parse evaluation. Raw response: {response}",
-                raw_response=response
+                raw_response=response,
            )
--- a/src/crewai/experimental/evaluation/metrics/reasoning_metrics.py
+++ b/src/crewai/experimental/evaluation/metrics/reasoning_metrics.py
@@ -8,18 +8,24 @@ This module provides evaluator implementations for:

 import logging
 import re
-from enum import Enum
-from typing import Any, Dict, List, Tuple
-import numpy as np
 from collections.abc import Sequence
+from enum import Enum
+from typing import Any
+
+import numpy as np

 from crewai.agent import Agent
-from crewai.task import Task
-
-from crewai.experimental.evaluation.base_evaluator import BaseEvaluator, EvaluationScore, MetricCategory
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.experimental.evaluation.base_evaluator import (
+    BaseEvaluator,
+    EvaluationScore,
+    MetricCategory,
+)
 from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response
+from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput

+
 class ReasoningPatternType(Enum):
    EFFICIENT = "efficient"  # Good reasoning flow
    LOOP = "loop"  # Agent is stuck in a loop
@@ -35,8 +41,8 @@ class ReasoningEfficiencyEvaluator(BaseEvaluator):

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: TaskOutput | str,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -49,7 +55,7 @@ class ReasoningEfficiencyEvaluator(BaseEvaluator):
        if not llm_calls or len(llm_calls) < 2:
            return EvaluationScore(
                score=None,
-                feedback="Insufficient LLM calls to evaluate reasoning efficiency."
+                feedback="Insufficient LLM calls to evaluate reasoning efficiency.",
            )

        total_calls = len(llm_calls)
@@ -58,12 +64,16 @@ class ReasoningEfficiencyEvaluator(BaseEvaluator):
        time_intervals = []
        has_reliable_timing = True
        for i in range(1, len(llm_calls)):
-            start_time = llm_calls[i-1].get("end_time")
+            start_time = llm_calls[i - 1].get("end_time")
            end_time = llm_calls[i].get("start_time")
            if start_time and end_time and start_time != end_time:
                try:
                    interval = end_time - start_time
-                    time_intervals.append(interval.total_seconds() if hasattr(interval, 'total_seconds') else 0)
+                    time_intervals.append(
+                        interval.total_seconds()
+                        if hasattr(interval, "total_seconds")
+                        else 0
+                    )
                except Exception:
                    has_reliable_timing = False
            else:
@@ -83,14 +93,22 @@ class ReasoningEfficiencyEvaluator(BaseEvaluator):
        if has_reliable_timing and time_intervals:
            efficiency_metrics["avg_time_between_calls"] = np.mean(time_intervals)

-        loop_info = f"Detected {len(loop_details)} potential reasoning loops." if loop_detected else "No significant reasoning loops detected."
+        loop_info = (
+            f"Detected {len(loop_details)} potential reasoning loops."
+            if loop_detected
+            else "No significant reasoning loops detected."
+        )

        call_samples = self._get_call_samples(llm_calls)

-        final_output = final_output.raw if isinstance(final_output, TaskOutput) else final_output
+        final_output = (
+            final_output.raw if isinstance(final_output, TaskOutput) else final_output
+        )

        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing the reasoning efficiency of an AI agent's thought process.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing the reasoning efficiency of an AI agent's thought process.

 Evaluate the agent's reasoning efficiency across these five key subcategories:

@@ -120,8 +138,11 @@ Return your evaluation as JSON with the following structure:
    "feedback": string (general feedback about overall reasoning efficiency),
    "optimization_suggestions": string (concrete suggestions for improving reasoning efficiency),
    "detected_patterns": string (describe any inefficient reasoning patterns you observe)
-}"""},
-            {"role": "user", "content": f"""
+}""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 {task_context}

@@ -140,10 +161,12 @@ Agent's final output:

 Evaluate the reasoning efficiency of this agent based on these interaction patterns.
 Identify any inefficient reasoning patterns and provide specific suggestions for optimization.
-"""}
+""",
+            },
        ]

-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
@@ -156,34 +179,46 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
            conciseness = scores.get("conciseness", 5.0)
            loop_avoidance = scores.get("loop_avoidance", 5.0)

-            overall_score = evaluation_data.get("overall_score", evaluation_data.get("score", 5.0))
+            overall_score = evaluation_data.get(
+                "overall_score", evaluation_data.get("score", 5.0)
+            )
            feedback = evaluation_data.get("feedback", "No detailed feedback provided.")
-            optimization_suggestions = evaluation_data.get("optimization_suggestions", "No specific suggestions provided.")
+            optimization_suggestions = evaluation_data.get(
+                "optimization_suggestions", "No specific suggestions provided."
+            )

            detailed_feedback = "Reasoning Efficiency Evaluation:\n"
-            detailed_feedback += f"• Focus: {focus}/10 - Staying on topic without tangents\n"
-            detailed_feedback += f"• Progression: {progression}/10 - Building on previous thinking\n"
+            detailed_feedback += (
+                f"• Focus: {focus}/10 - Staying on topic without tangents\n"
+            )
+            detailed_feedback += (
+                f"• Progression: {progression}/10 - Building on previous thinking\n"
+            )
            detailed_feedback += f"• Decision Quality: {decision_quality}/10 - Making appropriate decisions\n"
-            detailed_feedback += f"• Conciseness: {conciseness}/10 - Communicating efficiently\n"
+            detailed_feedback += (
+                f"• Conciseness: {conciseness}/10 - Communicating efficiently\n"
+            )
            detailed_feedback += f"• Loop Avoidance: {loop_avoidance}/10 - Avoiding repetitive patterns\n\n"

            detailed_feedback += f"Feedback:\n{feedback}\n\n"
-            detailed_feedback += f"Optimization Suggestions:\n{optimization_suggestions}"
+            detailed_feedback += (
+                f"Optimization Suggestions:\n{optimization_suggestions}"
+            )

            return EvaluationScore(
                score=float(overall_score),
                feedback=detailed_feedback,
-                raw_response=response
+                raw_response=response,
            )
        except Exception as e:
            logging.warning(f"Failed to parse reasoning efficiency evaluation: {e}")
            return EvaluationScore(
                score=None,
                feedback=f"Failed to parse reasoning efficiency evaluation. Raw response: {response[:200]}...",
-                raw_response=response
+                raw_response=response,
            )

-    def _detect_loops(self, llm_calls: List[Dict]) -> Tuple[bool, List[Dict]]:
+    def _detect_loops(self, llm_calls: list[dict]) -> tuple[bool, list[dict]]:
        loop_details = []

        messages = []
@@ -193,9 +228,11 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                messages.append(content)
            elif isinstance(content, list) and len(content) > 0:
                # Handle message list format
-                for msg in content:
-                    if isinstance(msg, dict) and "content" in msg:
-                        messages.append(msg["content"])
+                messages.extend(
+                    msg["content"]
+                    for msg in content
+                    if isinstance(msg, dict) and "content" in msg
+                )

        # Simple n-gram based similarity detection
        # For a more robust implementation, consider using embedding-based similarity
@@ -205,18 +242,20 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                # A more sophisticated approach would use semantic similarity
                similarity = self._calculate_text_similarity(messages[i], messages[j])
                if similarity > 0.7:  # Arbitrary threshold
-                    loop_details.append({
-                        "first_occurrence": i,
-                        "second_occurrence": j,
-                        "similarity": similarity,
-                        "snippet": messages[i][:100] + "..."
-                    })
+                    loop_details.append(
+                        {
+                            "first_occurrence": i,
+                            "second_occurrence": j,
+                            "similarity": similarity,
+                            "snippet": messages[i][:100] + "...",
+                        }
+                    )

        return len(loop_details) > 0, loop_details

    def _calculate_text_similarity(self, text1: str, text2: str) -> float:
-        text1 = re.sub(r'\s+', ' ', text1.lower()).strip()
-        text2 = re.sub(r'\s+', ' ', text2.lower()).strip()
+        text1 = re.sub(r"\s+", " ", text1.lower()).strip()
+        text2 = re.sub(r"\s+", " ", text2.lower()).strip()

        # Simple Jaccard similarity on word sets
        words1 = set(text1.split())
@@ -227,7 +266,7 @@ Identify any inefficient reasoning patterns and provide specific suggestions for

        return intersection / union if union > 0 else 0.0

-    def _analyze_reasoning_patterns(self, llm_calls: List[Dict]) -> Dict[str, Any]:
+    def _analyze_reasoning_patterns(self, llm_calls: list[dict]) -> dict[str, Any]:
        call_lengths = []
        response_times = []

@@ -248,8 +287,8 @@ 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 Exception:
-                    pass
+                except Exception as e:
+                    logging.debug(f"Failed to calculate response time: {e}")

        avg_length = np.mean(call_lengths) if call_lengths else 0
        std_length = np.std(call_lengths) if call_lengths else 0
@@ -267,7 +306,9 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
            details = "Agent is consistently verbose across interactions."
        elif len(llm_calls) > 10 and length_trend > 0.5:
            primary_pattern = ReasoningPatternType.INDECISIVE
-            details = "Agent shows signs of indecisiveness with increasing message lengths."
+            details = (
+                "Agent shows signs of indecisiveness with increasing message lengths."
+            )
        elif std_length / avg_length > 0.8:
            primary_pattern = ReasoningPatternType.SCATTERED
            details = "Agent shows inconsistent reasoning flow with highly variable responses."
@@ -279,8 +320,8 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                "avg_length": avg_length,
                "std_length": std_length,
                "length_trend": length_trend,
-                "loop_score": loop_score
-            }
+                "loop_score": loop_score,
+            },
        }

    def _calculate_trend(self, values: Sequence[float | int]) -> float:
@@ -303,7 +344,9 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
        except Exception:
            return 0.0

-    def _calculate_loop_likelihood(self, call_lengths: Sequence[float], response_times: Sequence[float]) -> float:
+    def _calculate_loop_likelihood(
+        self, call_lengths: Sequence[float], response_times: Sequence[float]
+    ) -> float:
        if not call_lengths or len(call_lengths) < 3:
            return 0.0

@@ -312,7 +355,11 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
        if len(call_lengths) >= 4:
            repeated_lengths = 0
            for i in range(len(call_lengths) - 2):
-                ratio = call_lengths[i] / call_lengths[i + 2] if call_lengths[i + 2] > 0 else 0
+                ratio = (
+                    call_lengths[i] / call_lengths[i + 2]
+                    if call_lengths[i + 2] > 0
+                    else 0
+                )
                if 0.85 <= ratio <= 1.15:
                    repeated_lengths += 1

@@ -324,21 +371,27 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
                std_time = np.std(response_times)
                mean_time = np.mean(response_times)
                if mean_time > 0:
-                    time_consistency = 1.0 - (std_time / mean_time)
-                    indicators.append(max(0, time_consistency - 0.3) * 1.5)
-            except Exception:
-                pass
+                    time_consistency = 1.0 - (float(std_time) / float(mean_time))
+                    indicators.append(max(0.0, float(time_consistency - 0.3)) * 1.5)
+            except Exception as e:
+                logging.debug(f"Time consistency calculation failed: {e}")

-        return np.mean(indicators) if indicators else 0.0
+        return float(np.mean(indicators)) if indicators else 0.0

-    def _get_call_samples(self, llm_calls: List[Dict]) -> str:
+    def _get_call_samples(self, llm_calls: list[dict]) -> str:
        samples = []

        if len(llm_calls) <= 6:
            sample_indices = list(range(len(llm_calls)))
        else:
-            sample_indices = [0, 1, len(llm_calls) // 2 - 1, len(llm_calls) // 2,
-                             len(llm_calls) - 2, len(llm_calls) - 1]
+            sample_indices = [
+                0,
+                1,
+                len(llm_calls) // 2 - 1,
+                len(llm_calls) // 2,
+                len(llm_calls) - 2,
+                len(llm_calls) - 1,
+            ]

        for idx in sample_indices:
            call = llm_calls[idx]
@@ -347,10 +400,11 @@ Identify any inefficient reasoning patterns and provide specific suggestions for
            if isinstance(content, str):
                sample = content
            elif isinstance(content, list) and len(content) > 0:
-                sample_parts = []
-                for msg in content:
-                    if isinstance(msg, dict) and "content" in msg:
-                        sample_parts.append(msg["content"])
+                sample_parts = [
+                    msg["content"]
+                    for msg in content
+                    if isinstance(msg, dict) and "content" in msg
+                ]
                sample = "\n".join(sample_parts)
            else:
                sample = str(content)
--- a/src/crewai/experimental/evaluation/metrics/semantic_quality_metrics.py
+++ b/src/crewai/experimental/evaluation/metrics/semantic_quality_metrics.py
@@ -1,10 +1,15 @@
-from typing import Any, Dict
+from typing import Any

 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.experimental.evaluation.base_evaluator import (
+    BaseEvaluator,
+    EvaluationScore,
+    MetricCategory,
+)
+from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response
 from crewai.task import Task

-from crewai.experimental.evaluation.base_evaluator import BaseEvaluator, EvaluationScore, MetricCategory
-from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response

 class SemanticQualityEvaluator(BaseEvaluator):
    @property
@@ -13,8 +18,8 @@ class SemanticQualityEvaluator(BaseEvaluator):

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: Any,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -22,7 +27,9 @@ class SemanticQualityEvaluator(BaseEvaluator):
        if task is not None:
            task_context = f"Task description: {task.description}"
        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing the semantic quality of an AI agent's output.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing the semantic quality of an AI agent's output.

 Score the semantic quality on a scale from 0-10 where:
 - 0: Completely incoherent, confusing, or logically flawed output
@@ -37,8 +44,11 @@ Consider:
 5. Is the output free from contradictions and logical fallacies?

 Return your evaluation as JSON with fields 'score' (number) and 'feedback' (string).
-"""},
-            {"role": "user", "content": f"""
+""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 {task_context}

@@ -46,23 +56,28 @@ Agent's final output:
 {final_output}

 Evaluate the semantic quality and reasoning of this output.
-"""}
+""",
+            },
        ]

-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
            evaluation_data: dict[str, Any] = extract_json_from_llm_response(response)
-            assert evaluation_data is not None
+            if evaluation_data is None:
+                raise ValueError("Failed to extract evaluation data from LLM response")
            return EvaluationScore(
-                score=float(evaluation_data["score"]) if evaluation_data.get("score") is not None else None,
+                score=float(evaluation_data["score"])
+                if evaluation_data.get("score") is not None
+                else None,
                feedback=evaluation_data.get("feedback", response),
-                raw_response=response
+                raw_response=response,
            )
        except Exception:
            return EvaluationScore(
                score=None,
                feedback=f"Failed to parse evaluation. Raw response: {response}",
-                raw_response=response
-            )
+                raw_response=response,
+            )
--- a/src/crewai/experimental/evaluation/metrics/tools_metrics.py
+++ b/src/crewai/experimental/evaluation/metrics/tools_metrics.py
@@ -1,22 +1,26 @@
 import json
-from typing import Dict, Any
+from typing import Any

-from crewai.experimental.evaluation.base_evaluator import BaseEvaluator, EvaluationScore, MetricCategory
-from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response
 from crewai.agent import Agent
+from crewai.agents.agent_builder.base_agent import BaseAgent
+from crewai.experimental.evaluation.base_evaluator import (
+    BaseEvaluator,
+    EvaluationScore,
+    MetricCategory,
+)
+from crewai.experimental.evaluation.json_parser import extract_json_from_llm_response
 from crewai.task import Task


 class ToolSelectionEvaluator(BaseEvaluator):
-
    @property
    def metric_category(self) -> MetricCategory:
        return MetricCategory.TOOL_SELECTION

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: str,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -26,19 +30,18 @@ class ToolSelectionEvaluator(BaseEvaluator):

        tool_uses = execution_trace.get("tool_uses", [])
        tool_count = len(tool_uses)
-        unique_tool_types = set([tool.get("tool", "Unknown tool") for tool in tool_uses])
+        unique_tool_types = set(
+            [tool.get("tool", "Unknown tool") for tool in tool_uses]
+        )

        if tool_count == 0:
            if not agent.tools:
                return EvaluationScore(
-                    score=None,
-                    feedback="Agent had no tools available to use."
-                )
-            else:
-                return EvaluationScore(
-                    score=None,
-                    feedback="Agent had tools available but didn't use any."
+                    score=None, feedback="Agent had no tools available to use."
                )
+            return EvaluationScore(
+                score=None, feedback="Agent had tools available but didn't use any."
+            )

        available_tools_info = ""
        if agent.tools:
@@ -52,7 +55,9 @@ class ToolSelectionEvaluator(BaseEvaluator):
            tool_types_summary += f"- {tool_type}\n"

        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing if an AI agent selected the most appropriate tools for a given task.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing if an AI agent selected the most appropriate tools for a given task.

 You must evaluate based on these 2 criteria:
 1. Relevance (0-10): Were the tools chosen directly aligned with the task's goals?
@@ -73,8 +78,11 @@ Return your evaluation as JSON with these fields:
 - overall_score: number (average of all scores, 0-10)
 - feedback: string (focused ONLY on tool selection decisions from available tools)
 - improvement_suggestions: string (ONLY suggest better selection from the AVAILABLE tools list, NOT new tools)
-"""},
-            {"role": "user", "content": f"""
+""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 {task_context}

@@ -89,14 +97,17 @@ IMPORTANT:
 - ONLY evaluate selection from tools listed as available
 - DO NOT suggest new tools that aren't in the available tools list
 - DO NOT evaluate tool usage or results
-"""}
+""",
+            },
        ]
-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
            evaluation_data = extract_json_from_llm_response(response)
-            assert evaluation_data is not None
+            if evaluation_data is None:
+                raise ValueError("Failed to extract evaluation data from LLM response")

            scores = evaluation_data.get("scores", {})
            relevance = scores.get("relevance", 5.0)
@@ -105,22 +116,24 @@ IMPORTANT:

            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"
+            feedback += (
+                f"• Coverage: {coverage}/10 - Selection of all necessary tool types\n"
+            )
            if "improvement_suggestions" in evaluation_data:
                feedback += f"Improvement Suggestions:\n{evaluation_data['improvement_suggestions']}"
            else:
-                feedback += evaluation_data.get("feedback", "No detailed feedback available.")
+                feedback += evaluation_data.get(
+                    "feedback", "No detailed feedback available."
+                )

            return EvaluationScore(
-                score=overall_score,
-                feedback=feedback,
-                raw_response=response
+                score=overall_score, feedback=feedback, raw_response=response
            )
        except Exception as e:
            return EvaluationScore(
                score=None,
                feedback=f"Error evaluating tool selection: {e}",
-                raw_response=response
+                raw_response=response,
            )


@@ -131,8 +144,8 @@ class ParameterExtractionEvaluator(BaseEvaluator):

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: str,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -145,19 +158,23 @@ class ParameterExtractionEvaluator(BaseEvaluator):
        if tool_count == 0:
            return EvaluationScore(
                score=None,
-                feedback="No tool usage detected. Cannot evaluate parameter extraction."
+                feedback="No tool usage detected. Cannot evaluate parameter extraction.",
            )

-        validation_errors = []
-        for tool_use in tool_uses:
-            if not tool_use.get("success", True) and tool_use.get("error_type") == "validation_error":
-                validation_errors.append({
-                    "tool": tool_use.get("tool", "Unknown tool"),
-                    "error": tool_use.get("result"),
-                    "args": tool_use.get("args", {})
-                })
+        validation_errors = [
+            {
+                "tool": tool_use.get("tool", "Unknown tool"),
+                "error": tool_use.get("result"),
+                "args": tool_use.get("args", {}),
+            }
+            for tool_use in tool_uses
+            if not tool_use.get("success", True)
+            and tool_use.get("error_type") == "validation_error"
+        ]

-        validation_error_rate = len(validation_errors) / tool_count if tool_count > 0 else 0
+        validation_error_rate = (
+            len(validation_errors) / tool_count if tool_count > 0 else 0
+        )

        param_samples = []
        for i, tool_use in enumerate(tool_uses[:5]):
@@ -168,7 +185,7 @@ class ParameterExtractionEvaluator(BaseEvaluator):

            is_validation_error = error_type == "validation_error"

-            sample = f"Tool use #{i+1} - {tool_name}:\n"
+            sample = f"Tool use #{i + 1} - {tool_name}:\n"
            sample += f"- Parameters: {json.dumps(tool_args, indent=2)}\n"
            sample += f"- Success: {'No' if not success else 'Yes'}"

@@ -187,13 +204,17 @@ class ParameterExtractionEvaluator(BaseEvaluator):
                tool_name = err.get("tool", "Unknown tool")
                error_msg = err.get("error", "Unknown error")
                args = err.get("args", {})
-                validation_errors_info += f"\nValidation Error #{i+1}:\n- Tool: {tool_name}\n- Args: {json.dumps(args, indent=2)}\n- Error: {error_msg}"
+                validation_errors_info += f"\nValidation Error #{i + 1}:\n- Tool: {tool_name}\n- Args: {json.dumps(args, indent=2)}\n- Error: {error_msg}"

            if len(validation_errors) > 3:
-                validation_errors_info += f"\n...and {len(validation_errors) - 3} more validation errors."
+                validation_errors_info += (
+                    f"\n...and {len(validation_errors) - 3} more validation errors."
+                )
        param_samples_text = "\n\n".join(param_samples)
        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing how well an AI agent extracts and formats PARAMETER VALUES for tool calls.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing how well an AI agent extracts and formats PARAMETER VALUES for tool calls.

 Your job is to evaluate ONLY whether the agent used the correct parameter VALUES, not whether the right tools were selected or how the tools were invoked.

@@ -216,8 +237,11 @@ Return your evaluation as JSON with these fields:
 - overall_score: number (average of all scores, 0-10)
 - feedback: string (focused ONLY on parameter value extraction quality)
 - improvement_suggestions: string (concrete suggestions for better parameter VALUE extraction)
-"""},
-            {"role": "user", "content": f"""
+""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 {task_context}

@@ -226,15 +250,18 @@ Parameter extraction examples:
 {validation_errors_info}

 Evaluate the quality of the agent's parameter extraction for this task.
-"""}
+""",
+            },
        ]

-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
            evaluation_data = extract_json_from_llm_response(response)
-            assert evaluation_data is not None
+            if evaluation_data is None:
+                raise ValueError("Failed to extract evaluation data from LLM response")

            scores = evaluation_data.get("scores", {})
            accuracy = scores.get("accuracy", 5.0)
@@ -251,18 +278,18 @@ Evaluate the quality of the agent's parameter extraction for this task.
            if "improvement_suggestions" in evaluation_data:
                feedback += f"Improvement Suggestions:\n{evaluation_data['improvement_suggestions']}"
            else:
-                feedback += evaluation_data.get("feedback", "No detailed feedback available.")
+                feedback += evaluation_data.get(
+                    "feedback", "No detailed feedback available."
+                )

            return EvaluationScore(
-                score=overall_score,
-                feedback=feedback,
-                raw_response=response
+                score=overall_score, feedback=feedback, raw_response=response
            )
        except Exception as e:
            return EvaluationScore(
                score=None,
                feedback=f"Error evaluating parameter extraction: {e}",
-                raw_response=response
+                raw_response=response,
            )


@@ -273,8 +300,8 @@ class ToolInvocationEvaluator(BaseEvaluator):

    def evaluate(
        self,
-        agent: Agent,
-        execution_trace: Dict[str, Any],
+        agent: Agent | BaseAgent,
+        execution_trace: dict[str, Any],
        final_output: str,
        task: Task | None = None,
    ) -> EvaluationScore:
@@ -288,7 +315,7 @@ class ToolInvocationEvaluator(BaseEvaluator):
        if tool_count == 0:
            return EvaluationScore(
                score=None,
-                feedback="No tool usage detected. Cannot evaluate tool invocation."
+                feedback="No tool usage detected. Cannot evaluate tool invocation.",
            )

        for tool_use in tool_uses:
@@ -296,7 +323,7 @@ class ToolInvocationEvaluator(BaseEvaluator):
                error_info = {
                    "tool": tool_use.get("tool", "Unknown tool"),
                    "error": tool_use.get("result"),
-                    "error_type": tool_use.get("error_type", "unknown_error")
+                    "error_type": tool_use.get("error_type", "unknown_error"),
                }
                tool_errors.append(error_info)

@@ -315,9 +342,11 @@ class ToolInvocationEvaluator(BaseEvaluator):
            tool_args = tool_use.get("args", {})
            success = tool_use.get("success", True) and not tool_use.get("error", False)
            error_type = tool_use.get("error_type", "") if not success else ""
-            error_msg = tool_use.get("result", "No error") if not success else "No error"
+            error_msg = (
+                tool_use.get("result", "No error") if not success else "No error"
+            )

-            sample = f"Tool invocation #{i+1}:\n"
+            sample = f"Tool invocation #{i + 1}:\n"
            sample += f"- Tool: {tool_name}\n"
            sample += f"- Parameters: {json.dumps(tool_args, indent=2)}\n"
            sample += f"- Success: {'No' if not success else 'Yes'}\n"
@@ -330,11 +359,13 @@ class ToolInvocationEvaluator(BaseEvaluator):
        if error_types:
            error_type_summary = "Error type breakdown:\n"
            for error_type, count in error_types.items():
-                error_type_summary += f"- {error_type}: {count} occurrences ({(count/tool_count):.1%})\n"
+                error_type_summary += f"- {error_type}: {count} occurrences ({(count / tool_count):.1%})\n"

        invocation_samples_text = "\n\n".join(invocation_samples)
        prompt = [
-            {"role": "system", "content": """You are an expert evaluator assessing how correctly an AI agent's tool invocations are STRUCTURED.
+            {
+                "role": "system",
+                "content": """You are an expert evaluator assessing how correctly an AI agent's tool invocations are STRUCTURED.

 Your job is to evaluate ONLY the structural and syntactical aspects of how the agent called tools, NOT which tools were selected or what parameter values were used.

@@ -359,8 +390,11 @@ Return your evaluation as JSON with these fields:
 - overall_score: number (average of all scores, 0-10)
 - feedback: string (focused ONLY on structural aspects of tool invocation)
 - improvement_suggestions: string (concrete suggestions for better structuring of tool calls)
-"""},
-            {"role": "user", "content": f"""
+""",
+            },
+            {
+                "role": "user",
+                "content": f"""
 Agent role: {agent.role}
 {task_context}

@@ -371,15 +405,18 @@ Tool error rate: {error_rate:.2%} ({len(tool_errors)} errors out of {tool_count}
 {error_type_summary}

 Evaluate the quality of the agent's tool invocation structure during this task.
-"""}
+""",
+            },
        ]

-        assert self.llm is not None
+        if self.llm is None:
+            raise ValueError("LLM must be initialized")
        response = self.llm.call(prompt)

        try:
            evaluation_data = extract_json_from_llm_response(response)
-            assert evaluation_data is not None
+            if evaluation_data is None:
+                raise ValueError("Failed to extract evaluation data from LLM response")
            scores = evaluation_data.get("scores", {})
            structure = scores.get("structure", 5.0)
            error_handling = scores.get("error_handling", 5.0)
@@ -388,23 +425,25 @@ Evaluate the quality of the agent's tool invocation structure during this task.
            overall_score = float(evaluation_data.get("overall_score", 5.0))

            feedback = "Tool Invocation Evaluation:\n"
-            feedback += f"• Structure: {structure}/10 - Following proper syntax and format\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"

            if "improvement_suggestions" in evaluation_data:
                feedback += f"Improvement Suggestions:\n{evaluation_data['improvement_suggestions']}"
            else:
-                feedback += evaluation_data.get("feedback", "No detailed feedback available.")
+                feedback += evaluation_data.get(
+                    "feedback", "No detailed feedback available."
+                )

            return EvaluationScore(
-                score=overall_score,
-                feedback=feedback,
-                raw_response=response
+                score=overall_score, feedback=feedback, raw_response=response
            )
        except Exception as e:
            return EvaluationScore(
                score=None,
                feedback=f"Error evaluating tool invocation: {e}",
-                raw_response=response
+                raw_response=response,
            )
--- a/src/crewai/experimental/evaluation/testing.py
+++ b/src/crewai/experimental/evaluation/testing.py
@@ -1,12 +1,21 @@
 import inspect
+import warnings

 from typing_extensions import Any
-import warnings
-from crewai.experimental.evaluation.experiment import ExperimentResults, ExperimentRunner
-from crewai import Crew, Agent

-def assert_experiment_successfully(experiment_results: ExperimentResults, baseline_filepath: str | None = None) -> None:
-    failed_tests = [result for result in experiment_results.results if not result.passed]
+from crewai import Agent, Crew
+from crewai.experimental.evaluation.experiment import (
+    ExperimentResults,
+    ExperimentRunner,
+)
+
+
+def assert_experiment_successfully(
+    experiment_results: ExperimentResults, baseline_filepath: str | None = None
+) -> None:
+    failed_tests = [
+        result for result in experiment_results.results if not result.passed
+    ]

    if failed_tests:
        detailed_failures: list[str] = []
@@ -14,39 +23,54 @@ def assert_experiment_successfully(experiment_results: ExperimentResults, baseli
        for result in failed_tests:
            expected = result.expected_score
            actual = result.score
-            detailed_failures.append(f"- {result.identifier}: expected {expected}, got {actual}")
+            detailed_failures.append(
+                f"- {result.identifier}: expected {expected}, got {actual}"
+            )

        failure_details = "\n".join(detailed_failures)
        raise AssertionError(f"The following test cases failed:\n{failure_details}")

    baseline_filepath = baseline_filepath or _get_baseline_filepath_fallback()
-    comparison = experiment_results.compare_with_baseline(baseline_filepath=baseline_filepath)
+    comparison = experiment_results.compare_with_baseline(
+        baseline_filepath=baseline_filepath
+    )
    assert_experiment_no_regression(comparison)

+
 def assert_experiment_no_regression(comparison_result: dict[str, list[str]]) -> None:
    regressed = comparison_result.get("regressed", [])
    if regressed:
-        raise AssertionError(f"Regression detected! The following tests that previously passed now fail: {regressed}")
+        raise AssertionError(
+            f"Regression detected! The following tests that previously passed now fail: {regressed}"
+        )

    missing_tests = comparison_result.get("missing_tests", [])
    if missing_tests:
        warnings.warn(
            f"Warning: {len(missing_tests)} tests from the baseline are missing in the current run: {missing_tests}",
-            UserWarning
+            UserWarning,
+            stacklevel=2,
        )

-def run_experiment(dataset: list[dict[str, Any]], crew: Crew | None = None, agents: list[Agent] | None = None, verbose: bool = False) -> ExperimentResults:
+
+def run_experiment(
+    dataset: list[dict[str, Any]],
+    crew: Crew | None = None,
+    agents: list[Agent] | None = None,
+    verbose: bool = False,
+) -> ExperimentResults:
    runner = ExperimentRunner(dataset=dataset)

    return runner.run(agents=agents, crew=crew, print_summary=verbose)

+
 def _get_baseline_filepath_fallback() -> str:
    test_func_name = "experiment_fallback"

    try:
        current_frame = inspect.currentframe()
        if current_frame is not None:
-            test_func_name = current_frame.f_back.f_back.f_code.co_name # type: ignore[union-attr]
+            test_func_name = current_frame.f_back.f_back.f_code.co_name  # type: ignore[union-attr]
    except Exception:
        ...
-    return f"{test_func_name}_results.json"
+    return f"{test_func_name}_results.json"
--- a/src/crewai/flow/init.py
+++ b/src/crewai/flow/init.py
@@ -1,5 +1,4 @@
-from crewai.flow.flow import Flow, start, listen, or_, and_, router
+from crewai.flow.flow import Flow, and_, listen, or_, router, start
 from crewai.flow.persistence import persist

-__all__ = ["Flow", "start", "listen", "or_", "and_", "router", "persist"]
-
+__all__ = ["Flow", "and_", "listen", "or_", "persist", "router", "start"]
--- a/src/crewai/flow/flow_trackable.py
+++ b/src/crewai/flow/flow_trackable.py
@@ -1,5 +1,4 @@
 import inspect
-from typing import Optional

 from pydantic import BaseModel, Field, InstanceOf, model_validator

@@ -14,7 +13,7 @@ class FlowTrackable(BaseModel):
    inspecting the call stack.
    """

-    parent_flow: Optional[InstanceOf[Flow]] = Field(
+    parent_flow: InstanceOf[Flow] | None = Field(
        default=None,
        description="The parent flow of the instance, if it was created inside a flow.",
    )
--- a/src/crewai/flow/flow_visualizer.py
+++ b/src/crewai/flow/flow_visualizer.py
@@ -1,14 +1,13 @@
 # flow_visualizer.py

 import os
-from pathlib import Path

-from pyvis.network import Network
+from pyvis.network import Network  # type: ignore[import-untyped]

 from crewai.flow.config import COLORS, NODE_STYLES
 from crewai.flow.html_template_handler import HTMLTemplateHandler
 from crewai.flow.legend_generator import generate_legend_items_html, get_legend_items
-from crewai.flow.path_utils import safe_path_join, validate_path_exists
+from crewai.flow.path_utils import safe_path_join
 from crewai.flow.utils import calculate_node_levels
 from crewai.flow.visualization_utils import (
    add_edges,
@@ -34,13 +33,13 @@ class FlowPlot:
        ValueError
            If flow object is invalid or missing required attributes.
        """
-        if not hasattr(flow, '_methods'):
+        if not hasattr(flow, "_methods"):
            raise ValueError("Invalid flow object: missing '_methods' attribute")
-        if not hasattr(flow, '_listeners'):
+        if not hasattr(flow, "_listeners"):
            raise ValueError("Invalid flow object: missing '_listeners' attribute")
-        if not hasattr(flow, '_start_methods'):
+        if not hasattr(flow, "_start_methods"):
            raise ValueError("Invalid flow object: missing '_start_methods' attribute")
-            
+
        self.flow = flow
        self.colors = COLORS
        self.node_styles = NODE_STYLES
@@ -65,7 +64,7 @@ class FlowPlot:
        """
        if not filename or not isinstance(filename, str):
            raise ValueError("Filename must be a non-empty string")
-            
+
        try:
            # Initialize network
            net = Network(
@@ -96,32 +95,34 @@ class FlowPlot:
            try:
                node_levels = calculate_node_levels(self.flow)
            except Exception as e:
-                raise ValueError(f"Failed to calculate node levels: {str(e)}")
+                raise ValueError(f"Failed to calculate node levels: {e!s}") from e

            # Compute positions
            try:
                node_positions = compute_positions(self.flow, node_levels)
            except Exception as e:
-                raise ValueError(f"Failed to compute node positions: {str(e)}")
+                raise ValueError(f"Failed to compute node positions: {e!s}") from e

            # Add nodes to the network
            try:
                add_nodes_to_network(net, self.flow, node_positions, self.node_styles)
            except Exception as e:
-                raise RuntimeError(f"Failed to add nodes to network: {str(e)}")
+                raise RuntimeError(f"Failed to add nodes to network: {e!s}") from e

            # Add edges to the network
            try:
                add_edges(net, self.flow, node_positions, self.colors)
            except Exception as e:
-                raise RuntimeError(f"Failed to add edges to network: {str(e)}")
+                raise RuntimeError(f"Failed to add edges to network: {e!s}") from e

            # Generate HTML
            try:
                network_html = net.generate_html()
                final_html_content = self._generate_final_html(network_html)
            except Exception as e:
-                raise RuntimeError(f"Failed to generate network visualization: {str(e)}")
+                raise RuntimeError(
+                    f"Failed to generate network visualization: {e!s}"
+                ) from e

            # Save the final HTML content to the file
            try:
@@ -129,12 +130,16 @@ class FlowPlot:
                    f.write(final_html_content)
                print(f"Plot saved as {filename}.html")
            except IOError as e:
-                raise IOError(f"Failed to save flow visualization to {filename}.html: {str(e)}")
+                raise IOError(
+                    f"Failed to save flow visualization to {filename}.html: {e!s}"
+                ) from e

        except (ValueError, RuntimeError, IOError) as e:
            raise e
        except Exception as e:
-            raise RuntimeError(f"Unexpected error during flow visualization: {str(e)}")
+            raise RuntimeError(
+                f"Unexpected error during flow visualization: {e!s}"
+            ) from e
        finally:
            self._cleanup_pyvis_lib()

@@ -165,7 +170,9 @@ class FlowPlot:
        try:
            # Extract just the body content from the generated HTML
            current_dir = os.path.dirname(__file__)
-            template_path = safe_path_join("assets", "crewai_flow_visual_template.html", root=current_dir)
+            template_path = safe_path_join(
+                "assets", "crewai_flow_visual_template.html", root=current_dir
+            )
            logo_path = safe_path_join("assets", "crewai_logo.svg", root=current_dir)

            if not os.path.exists(template_path):
@@ -179,12 +186,9 @@ class FlowPlot:
            # Generate the legend items HTML
            legend_items = get_legend_items(self.colors)
            legend_items_html = generate_legend_items_html(legend_items)
-            final_html_content = html_handler.generate_final_html(
-                network_body, legend_items_html
-            )
-            return final_html_content
+            return html_handler.generate_final_html(network_body, legend_items_html)
        except Exception as e:
-            raise IOError(f"Failed to generate visualization HTML: {str(e)}")
+            raise IOError(f"Failed to generate visualization HTML: {e!s}") from e

    def _cleanup_pyvis_lib(self):
        """
@@ -197,6 +201,7 @@ class FlowPlot:
            lib_folder = safe_path_join("lib", root=os.getcwd())
            if os.path.exists(lib_folder) and os.path.isdir(lib_folder):
                import shutil
+
                shutil.rmtree(lib_folder)
        except ValueError as e:
            print(f"Error validating lib folder path: {e}")
--- a/src/crewai/flow/html_template_handler.py
+++ b/src/crewai/flow/html_template_handler.py
@@ -1,8 +1,7 @@
 import base64
 import re
-from pathlib import Path

-from crewai.flow.path_utils import safe_path_join, validate_path_exists
+from crewai.flow.path_utils import validate_path_exists


 class HTMLTemplateHandler:
@@ -28,7 +27,7 @@ class HTMLTemplateHandler:
            self.template_path = validate_path_exists(template_path, "file")
            self.logo_path = validate_path_exists(logo_path, "file")
        except ValueError as e:
-            raise ValueError(f"Invalid template or logo path: {e}")
+            raise ValueError(f"Invalid template or logo path: {e}") from e

    def read_template(self):
        """Read and return the HTML template file contents."""
@@ -53,23 +52,23 @@ class HTMLTemplateHandler:
            if "border" in item:
                legend_items_html += f"""
                <div class="legend-item">
-                <div class="legend-color-box" style="background-color: {item['color']}; border: 2px dashed {item['border']};"></div>
-                <div>{item['label']}</div>
+                <div class="legend-color-box" style="background-color: {item["color"]}; border: 2px dashed {item["border"]};"></div>
+                <div>{item["label"]}</div>
                </div>
                """
            elif item.get("dashed") is not None:
                style = "dashed" if item["dashed"] else "solid"
                legend_items_html += f"""
                <div class="legend-item">
-                <div class="legend-{style}" style="border-bottom: 2px {style} {item['color']};"></div>
-                <div>{item['label']}</div>
+                <div class="legend-{style}" style="border-bottom: 2px {style} {item["color"]};"></div>
+                <div>{item["label"]}</div>
                </div>
                """
            else:
                legend_items_html += f"""
                <div class="legend-item">
-                <div class="legend-color-box" style="background-color: {item['color']};"></div>
-                <div>{item['label']}</div>
+                <div class="legend-color-box" style="background-color: {item["color"]};"></div>
+                <div>{item["label"]}</div>
                </div>
                """
        return legend_items_html
@@ -79,15 +78,9 @@ class HTMLTemplateHandler:
        html_template = self.read_template()
        logo_svg_base64 = self.encode_logo()

-        final_html_content = html_template.replace("{{ title }}", title)
-        final_html_content = final_html_content.replace(
-            "{{ network_content }}", network_body
+        return (
+            html_template.replace("{{ title }}", title)
+            .replace("{{ network_content }}", network_body)
+            .replace("{{ logo_svg_base64 }}", logo_svg_base64)
+            .replace("<!-- LEGEND_ITEMS_PLACEHOLDER -->", legend_items_html)
        )
-        final_html_content = final_html_content.replace(
-            "{{ logo_svg_base64 }}", logo_svg_base64
-        )
-        final_html_content = final_html_content.replace(
-            "<!-- LEGEND_ITEMS_PLACEHOLDER -->", legend_items_html
-        )
-
-        return final_html_content
--- a/src/crewai/flow/path_utils.py
+++ b/src/crewai/flow/path_utils.py
@@ -5,12 +5,10 @@ This module provides utilities for secure path handling to prevent directory
 traversal attacks and ensure paths remain within allowed boundaries.
 """

-import os
 from pathlib import Path
-from typing import List, Union


-def safe_path_join(*parts: str, root: Union[str, Path, None] = None) -> str:
+def safe_path_join(*parts: str, root: str | Path | None = None) -> str:
    """
    Safely join path components and ensure the result is within allowed boundaries.

@@ -43,25 +41,25 @@ def safe_path_join(*parts: str, root: Union[str, Path, None] = None) -> str:

        # Establish root directory
        root_path = Path(root).resolve() if root else Path.cwd()
-        
+
        # Join and resolve the full path
        full_path = Path(root_path, *clean_parts).resolve()
-        
+
        # Check if the resolved path is within root
        if not str(full_path).startswith(str(root_path)):
            raise ValueError(
                f"Invalid path: Potential directory traversal. Path must be within {root_path}"
            )
-            
+
        return str(full_path)
-        
+
    except Exception as e:
        if isinstance(e, ValueError):
            raise
-        raise ValueError(f"Invalid path components: {str(e)}")
+        raise ValueError(f"Invalid path components: {e!s}") from e


-def validate_path_exists(path: Union[str, Path], file_type: str = "file") -> str:
+def validate_path_exists(path: str | Path, file_type: str = "file") -> str:
    """
    Validate that a path exists and is of the expected type.

@@ -84,24 +82,24 @@ def validate_path_exists(path: Union[str, Path], file_type: str = "file") -> str
    """
    try:
        path_obj = Path(path).resolve()
-        
+
        if not path_obj.exists():
            raise ValueError(f"Path does not exist: {path}")
-            
+
        if file_type == "file" and not path_obj.is_file():
            raise ValueError(f"Path is not a file: {path}")
-        elif file_type == "directory" and not path_obj.is_dir():
+        if file_type == "directory" and not path_obj.is_dir():
            raise ValueError(f"Path is not a directory: {path}")
-            
+
        return str(path_obj)
-        
+
    except Exception as e:
        if isinstance(e, ValueError):
            raise
-        raise ValueError(f"Invalid path: {str(e)}")
+        raise ValueError(f"Invalid path: {e!s}") from e


-def list_files(directory: Union[str, Path], pattern: str = "*") -> List[str]:
+def list_files(directory: str | Path, pattern: str = "*") -> list[str]:
    """
    Safely list files in a directory matching a pattern.

@@ -126,10 +124,10 @@ def list_files(directory: Union[str, Path], pattern: str = "*") -> List[str]:
        dir_path = Path(directory).resolve()
        if not dir_path.is_dir():
            raise ValueError(f"Not a directory: {directory}")
-            
+
        return [str(p) for p in dir_path.glob(pattern) if p.is_file()]
-        
+
    except Exception as e:
        if isinstance(e, ValueError):
            raise
-        raise ValueError(f"Error listing files: {str(e)}")
+        raise ValueError(f"Error listing files: {e!s}") from e
--- a/src/crewai/flow/persistence/init.py
+++ b/src/crewai/flow/persistence/init.py
@@ -4,7 +4,7 @@ CrewAI Flow Persistence.
 This module provides interfaces and implementations for persisting flow states.
 """

-from typing import Any, Dict, TypeVar, Union
+from typing import Any, TypeVar

 from pydantic import BaseModel

@@ -12,7 +12,7 @@ from crewai.flow.persistence.base import FlowPersistence
 from crewai.flow.persistence.decorators import persist
 from crewai.flow.persistence.sqlite import SQLiteFlowPersistence

-__all__ = ["FlowPersistence", "persist", "SQLiteFlowPersistence"]
+__all__ = ["FlowPersistence", "SQLiteFlowPersistence", "persist"]

-StateType = TypeVar('StateType', bound=Union[Dict[str, Any], BaseModel])
-DictStateType = Dict[str, Any]
+StateType = TypeVar("StateType", bound=dict[str, Any] | BaseModel)
+DictStateType = dict[str, Any]
--- a/src/crewai/flow/persistence/base.py
+++ b/src/crewai/flow/persistence/base.py
@@ -1,53 +1,47 @@
 """Base class for flow state persistence."""

 import abc
-from typing import Any, Dict, Optional, Union
+from typing import Any

 from pydantic import BaseModel


 class FlowPersistence(abc.ABC):
    """Abstract base class for flow state persistence.
-    
+
    This class defines the interface that all persistence implementations must follow.
    It supports both structured (Pydantic BaseModel) and unstructured (dict) states.
    """
-    
+
    @abc.abstractmethod
    def init_db(self) -> None:
        """Initialize the persistence backend.
-        
+
        This method should handle any necessary setup, such as:
        - Creating tables
        - Establishing connections
        - Setting up indexes
        """
-        pass
-    
+
    @abc.abstractmethod
    def save_state(
-        self,
-        flow_uuid: str,
-        method_name: str,
-        state_data: Union[Dict[str, Any], BaseModel]
+        self, flow_uuid: str, method_name: str, state_data: dict[str, Any] | BaseModel
    ) -> None:
        """Persist the flow state after method completion.
-        
+
        Args:
            flow_uuid: Unique identifier for the flow instance
            method_name: Name of the method that just completed
            state_data: Current state data (either dict or Pydantic model)
        """
-        pass
-    
+
    @abc.abstractmethod
-    def load_state(self, flow_uuid: str) -> Optional[Dict[str, Any]]:
+    def load_state(self, flow_uuid: str) -> dict[str, Any] | None:
        """Load the most recent state for a given flow UUID.
-        
+
        Args:
            flow_uuid: Unique identifier for the flow instance
-            
+
        Returns:
            The most recent state as a dictionary, or None if no state exists
        """
-        pass
--- a/src/crewai/flow/persistence/decorators.py
+++ b/src/crewai/flow/persistence/decorators.py
@@ -24,13 +24,10 @@ Example:
 import asyncio
 import functools
 import logging
+from collections.abc import Callable
 from typing import (
    Any,
-    Callable,
-    Optional,
-    Type,
    TypeVar,
-    Union,
    cast,
 )

@@ -48,7 +45,7 @@ LOG_MESSAGES = {
    "save_state": "Saving flow state to memory for ID: {}",
    "save_error": "Failed to persist state for method {}: {}",
    "state_missing": "Flow instance has no state",
-    "id_missing": "Flow state must have an 'id' field for persistence"
+    "id_missing": "Flow state must have an 'id' field for persistence",
 }


@@ -58,7 +55,13 @@ class PersistenceDecorator:
    _printer = Printer()  # Class-level printer instance

    @classmethod
-    def persist_state(cls, flow_instance: Any, method_name: str, persistence_instance: FlowPersistence, verbose: bool = False) -> None:
+    def persist_state(
+        cls,
+        flow_instance: Any,
+        method_name: str,
+        persistence_instance: FlowPersistence,
+        verbose: bool = False,
+    ) -> None:
        """Persist flow state with proper error handling and logging.

        This method handles the persistence of flow state data, including proper
@@ -76,22 +79,24 @@ class PersistenceDecorator:
            AttributeError: If flow instance lacks required state attributes
        """
        try:
-            state = getattr(flow_instance, 'state', None)
+            state = getattr(flow_instance, "state", None)
            if state is None:
                raise ValueError("Flow instance has no state")

-            flow_uuid: Optional[str] = None
+            flow_uuid: str | None = None
            if isinstance(state, dict):
-                flow_uuid = state.get('id')
+                flow_uuid = state.get("id")
            elif isinstance(state, BaseModel):
-                flow_uuid = getattr(state, 'id', None)
+                flow_uuid = getattr(state, "id", None)

            if not flow_uuid:
                raise ValueError("Flow state must have an 'id' field for persistence")

            # Log state saving only if verbose is True
            if verbose:
-                cls._printer.print(LOG_MESSAGES["save_state"].format(flow_uuid), color="cyan")
+                cls._printer.print(
+                    LOG_MESSAGES["save_state"].format(flow_uuid), color="cyan"
+                )
                logger.info(LOG_MESSAGES["save_state"].format(flow_uuid))

            try:
@@ -104,12 +109,12 @@ class PersistenceDecorator:
                error_msg = LOG_MESSAGES["save_error"].format(method_name, str(e))
                cls._printer.print(error_msg, color="red")
                logger.error(error_msg)
-                raise RuntimeError(f"State persistence failed: {str(e)}") from e
-        except AttributeError:
+                raise RuntimeError(f"State persistence failed: {e!s}") from e
+        except AttributeError as e:
            error_msg = LOG_MESSAGES["state_missing"]
            cls._printer.print(error_msg, color="red")
            logger.error(error_msg)
-            raise ValueError(error_msg)
+            raise ValueError(error_msg) from e
        except (TypeError, ValueError) as e:
            error_msg = LOG_MESSAGES["id_missing"]
            cls._printer.print(error_msg, color="red")
@@ -117,7 +122,7 @@ class PersistenceDecorator:
            raise ValueError(error_msg) from e


-def persist(persistence: Optional[FlowPersistence] = None, verbose: bool = False):
+def persist(persistence: FlowPersistence | None = None, verbose: bool = False):
    """Decorator to persist flow state.

    This decorator can be applied at either the class level or method level.
@@ -144,111 +149,151 @@ def persist(persistence: Optional[FlowPersistence] = None, verbose: bool = False
            def begin(self):
                pass
    """
-    def decorator(target: Union[Type, Callable[..., T]]) -> Union[Type, Callable[..., T]]:
+
+    def decorator(target: type | Callable[..., T]) -> type | Callable[..., T]:
        """Decorator that handles both class and method decoration."""
        actual_persistence = persistence or SQLiteFlowPersistence()

        if isinstance(target, type):
            # Class decoration
-            original_init = getattr(target, "__init__")
+            original_init = target.__init__  # type: ignore[misc]

            @functools.wraps(original_init)
            def new_init(self: Any, *args: Any, **kwargs: Any) -> None:
-                if 'persistence' not in kwargs:
-                    kwargs['persistence'] = actual_persistence
+                if "persistence" not in kwargs:
+                    kwargs["persistence"] = actual_persistence
                original_init(self, *args, **kwargs)

-            setattr(target, "__init__", new_init)
+            target.__init__ = new_init  # type: ignore[misc]

            # Store original methods to preserve their decorators
-            original_methods = {}
-
-            for name, method in target.__dict__.items():
-                if callable(method) and (
-                    hasattr(method, "__is_start_method__") or
-                    hasattr(method, "__trigger_methods__") or
-                    hasattr(method, "__condition_type__") or
-                    hasattr(method, "__is_flow_method__") or
-                    hasattr(method, "__is_router__")
-                ):
-                    original_methods[name] = method
+            original_methods = {
+                name: method
+                for name, method in target.__dict__.items()
+                if callable(method)
+                and (
+                    hasattr(method, "__is_start_method__")
+                    or hasattr(method, "__trigger_methods__")
+                    or hasattr(method, "__condition_type__")
+                    or hasattr(method, "__is_flow_method__")
+                    or hasattr(method, "__is_router__")
+                )
+            }

            # Create wrapped versions of the methods that include persistence
            for name, method in original_methods.items():
                if asyncio.iscoroutinefunction(method):
                    # Create a closure to capture the current name and method
-                    def create_async_wrapper(method_name: str, original_method: Callable):
+                    def create_async_wrapper(
+                        method_name: str, original_method: Callable
+                    ):
                        @functools.wraps(original_method)
-                        async def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
+                        async def method_wrapper(
+                            self: Any, *args: Any, **kwargs: Any
+                        ) -> Any:
                            result = await original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(self, method_name, actual_persistence, verbose)
+                            PersistenceDecorator.persist_state(
+                                self, method_name, actual_persistence, verbose
+                            )
                            return result
+
                        return method_wrapper

                    wrapped = create_async_wrapper(name, method)

                    # Preserve all original decorators and attributes
-                    for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
+                    for attr in [
+                        "__is_start_method__",
+                        "__trigger_methods__",
+                        "__condition_type__",
+                        "__is_router__",
+                    ]:
                        if hasattr(method, attr):
                            setattr(wrapped, attr, getattr(method, attr))
-                    setattr(wrapped, "__is_flow_method__", True)
+                    wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]

                    # Update the class with the wrapped method
                    setattr(target, name, wrapped)
                else:
                    # Create a closure to capture the current name and method
-                    def create_sync_wrapper(method_name: str, original_method: Callable):
+                    def create_sync_wrapper(
+                        method_name: str, original_method: Callable
+                    ):
                        @functools.wraps(original_method)
                        def method_wrapper(self: Any, *args: Any, **kwargs: Any) -> Any:
                            result = original_method(self, *args, **kwargs)
-                            PersistenceDecorator.persist_state(self, method_name, actual_persistence, verbose)
+                            PersistenceDecorator.persist_state(
+                                self, method_name, actual_persistence, verbose
+                            )
                            return result
+
                        return method_wrapper

                    wrapped = create_sync_wrapper(name, method)

                    # Preserve all original decorators and attributes
-                    for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
+                    for attr in [
+                        "__is_start_method__",
+                        "__trigger_methods__",
+                        "__condition_type__",
+                        "__is_router__",
+                    ]:
                        if hasattr(method, attr):
                            setattr(wrapped, attr, getattr(method, attr))
-                    setattr(wrapped, "__is_flow_method__", True)
+                    wrapped.__is_flow_method__ = True  # type: ignore[attr-defined]

                    # Update the class with the wrapped method
                    setattr(target, name, wrapped)

            return target
-        else:
-            # Method decoration
-            method = target
-            setattr(method, "__is_flow_method__", True)
+        # Method decoration
+        method = target
+        method.__is_flow_method__ = True  # type: ignore[attr-defined]

-            if asyncio.iscoroutinefunction(method):
-                @functools.wraps(method)
-                async def method_async_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
-                    method_coro = method(flow_instance, *args, **kwargs)
-                    if asyncio.iscoroutine(method_coro):
-                        result = await method_coro
-                    else:
-                        result = method_coro
-                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence, verbose)
-                    return result
+        if asyncio.iscoroutinefunction(method):

-                for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
-                    if hasattr(method, attr):
-                        setattr(method_async_wrapper, attr, getattr(method, attr))
-                setattr(method_async_wrapper, "__is_flow_method__", True)
-                return cast(Callable[..., T], method_async_wrapper)
-            else:
-                @functools.wraps(method)
-                def method_sync_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
-                    result = method(flow_instance, *args, **kwargs)
-                    PersistenceDecorator.persist_state(flow_instance, method.__name__, actual_persistence, verbose)
-                    return result
+            @functools.wraps(method)
+            async def method_async_wrapper(
+                flow_instance: Any, *args: Any, **kwargs: Any
+            ) -> T:
+                method_coro = method(flow_instance, *args, **kwargs)
+                if asyncio.iscoroutine(method_coro):
+                    result = await method_coro
+                else:
+                    result = method_coro
+                PersistenceDecorator.persist_state(
+                    flow_instance, method.__name__, actual_persistence, verbose
+                )
+                return result

-                for attr in ["__is_start_method__", "__trigger_methods__", "__condition_type__", "__is_router__"]:
-                    if hasattr(method, attr):
-                        setattr(method_sync_wrapper, attr, getattr(method, attr))
-                setattr(method_sync_wrapper, "__is_flow_method__", True)
-                return cast(Callable[..., T], method_sync_wrapper)
+            for attr in [
+                "__is_start_method__",
+                "__trigger_methods__",
+                "__condition_type__",
+                "__is_router__",
+            ]:
+                if hasattr(method, attr):
+                    setattr(method_async_wrapper, attr, getattr(method, attr))
+            method_async_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
+            return cast(Callable[..., T], method_async_wrapper)
+
+        @functools.wraps(method)
+        def method_sync_wrapper(flow_instance: Any, *args: Any, **kwargs: Any) -> T:
+            result = method(flow_instance, *args, **kwargs)
+            PersistenceDecorator.persist_state(
+                flow_instance, method.__name__, actual_persistence, verbose
+            )
+            return result
+
+        for attr in [
+            "__is_start_method__",
+            "__trigger_methods__",
+            "__condition_type__",
+            "__is_router__",
+        ]:
+            if hasattr(method, attr):
+                setattr(method_sync_wrapper, attr, getattr(method, attr))
+        method_sync_wrapper.__is_flow_method__ = True  # type: ignore[attr-defined]
+        return cast(Callable[..., T], method_sync_wrapper)

    return decorator
--- a/src/crewai/flow/persistence/sqlite.py
+++ b/src/crewai/flow/persistence/sqlite.py
@@ -6,7 +6,7 @@ import json
 import sqlite3
 from datetime import datetime, timezone
 from pathlib import Path
-from typing import Any, Dict, Optional, Union
+from typing import Any

 from pydantic import BaseModel

@@ -23,7 +23,7 @@ class SQLiteFlowPersistence(FlowPersistence):

    db_path: str

-    def __init__(self, db_path: Optional[str] = None):
+    def __init__(self, db_path: str | None = None):
        """Initialize SQLite persistence.

        Args:
@@ -70,7 +70,7 @@ class SQLiteFlowPersistence(FlowPersistence):
        self,
        flow_uuid: str,
        method_name: str,
-        state_data: Union[Dict[str, Any], BaseModel],
+        state_data: dict[str, Any] | BaseModel,
    ) -> None:
        """Save the current flow state to SQLite.

@@ -107,7 +107,7 @@ class SQLiteFlowPersistence(FlowPersistence):
                ),
            )

-    def load_state(self, flow_uuid: str) -> Optional[Dict[str, Any]]:
+    def load_state(self, flow_uuid: str) -> dict[str, Any] | None:
        """Load the most recent state for a given flow UUID.

        Args:
--- a/src/crewai/flow/types.py
+++ b/src/crewai/flow/types.py
@@ -5,6 +5,7 @@ the Flow system.
 """

 from typing import Any, TypedDict
+
 from typing_extensions import NotRequired, Required


--- a/src/crewai/flow/utils.py
+++ b/src/crewai/flow/utils.py
@@ -17,10 +17,10 @@ import ast
 import inspect
 import textwrap
 from collections import defaultdict, deque
-from typing import Any, Deque, Dict, List, Optional, Set, Union
+from typing import Any


-def get_possible_return_constants(function: Any) -> Optional[List[str]]:
+def get_possible_return_constants(function: Any) -> list[str] | None:
    try:
        source = inspect.getsource(function)
    except OSError:
@@ -58,12 +58,12 @@ def get_possible_return_constants(function: Any) -> Optional[List[str]]:
                target = node.targets[0]
                if isinstance(target, ast.Name):
                    var_name = target.id
-                    dict_values = []
                    # Extract string values from the dictionary
-                    for val in node.value.values:
-                        if isinstance(val, ast.Constant) and isinstance(val.value, str):
-                            dict_values.append(val.value)
-                        # If non-string, skip or just ignore
+                    dict_values = [
+                        val.value
+                        for val in node.value.values
+                        if isinstance(val, ast.Constant) and isinstance(val.value, str)
+                    ]
                    if dict_values:
                        dict_definitions[var_name] = dict_values
            self.generic_visit(node)
@@ -94,7 +94,7 @@ def get_possible_return_constants(function: Any) -> Optional[List[str]]:
    return list(return_values) if return_values else None


-def calculate_node_levels(flow: Any) -> Dict[str, int]:
+def calculate_node_levels(flow: Any) -> dict[str, int]:
    """
    Calculate the hierarchical level of each node in the flow.

@@ -118,10 +118,10 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
    - Handles both OR and AND conditions for listeners
    - Processes router paths separately
    """
-    levels: Dict[str, int] = {}
-    queue: Deque[str] = deque()
-    visited: Set[str] = set()
-    pending_and_listeners: Dict[str, Set[str]] = {}
+    levels: dict[str, int] = {}
+    queue: deque[str] = deque()
+    visited: set[str] = set()
+    pending_and_listeners: dict[str, set[str]] = {}

    # Make all start methods at level 0
    for method_name, method in flow._methods.items():
@@ -172,7 +172,7 @@ def calculate_node_levels(flow: Any) -> Dict[str, int]:
    return levels


-def count_outgoing_edges(flow: Any) -> Dict[str, int]:
+def count_outgoing_edges(flow: Any) -> dict[str, int]:
    """
    Count the number of outgoing edges for each method in the flow.

@@ -197,7 +197,7 @@ def count_outgoing_edges(flow: Any) -> Dict[str, int]:
    return counts


-def build_ancestor_dict(flow: Any) -> Dict[str, Set[str]]:
+def build_ancestor_dict(flow: Any) -> dict[str, set[str]]:
    """
    Build a dictionary mapping each node to its ancestor nodes.

@@ -211,8 +211,8 @@ def build_ancestor_dict(flow: Any) -> Dict[str, Set[str]]:
    Dict[str, Set[str]]
        Dictionary mapping each node to a set of its ancestor nodes.
    """
-    ancestors: Dict[str, Set[str]] = {node: set() for node in flow._methods}
-    visited: Set[str] = set()
+    ancestors: dict[str, set[str]] = {node: set() for node in flow._methods}
+    visited: set[str] = set()
    for node in flow._methods:
        if node not in visited:
            dfs_ancestors(node, ancestors, visited, flow)
@@ -220,7 +220,7 @@ def build_ancestor_dict(flow: Any) -> Dict[str, Set[str]]:


 def dfs_ancestors(
-    node: str, ancestors: Dict[str, Set[str]], visited: Set[str], flow: Any
+    node: str, ancestors: dict[str, set[str]], visited: set[str], flow: Any
 ) -> None:
    """
    Perform depth-first search to build ancestor relationships.
@@ -265,7 +265,7 @@ def dfs_ancestors(


 def is_ancestor(
-    node: str, ancestor_candidate: str, ancestors: Dict[str, Set[str]]
+    node: str, ancestor_candidate: str, ancestors: dict[str, set[str]]
 ) -> bool:
    """
    Check if one node is an ancestor of another.
@@ -287,7 +287,7 @@ def is_ancestor(
    return ancestor_candidate in ancestors.get(node, set())


-def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:
+def build_parent_children_dict(flow: Any) -> dict[str, list[str]]:
    """
    Build a dictionary mapping parent nodes to their children.

@@ -307,7 +307,7 @@ def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:
    - Maps router methods to their paths and listeners
    - Children lists are sorted for consistent ordering
    """
-    parent_children: Dict[str, List[str]] = {}
+    parent_children: dict[str, list[str]] = {}

    # Map listeners to their trigger methods
    for listener_name, (_, trigger_methods) in flow._listeners.items():
@@ -332,7 +332,7 @@ def build_parent_children_dict(flow: Any) -> Dict[str, List[str]]:


 def get_child_index(
-    parent: str, child: str, parent_children: Dict[str, List[str]]
+    parent: str, child: str, parent_children: dict[str, list[str]]
 ) -> int:
    """
    Get the index of a child node in its parent's sorted children list.
@@ -364,7 +364,7 @@ def process_router_paths(flow, current, current_level, levels, queue):
        paths = flow._router_paths.get(current, [])
        for path in paths:
            for listener_name, (
-                condition_type,
+                _condition_type,
                trigger_methods,
            ) in flow._listeners.items():
                if path in trigger_methods:
--- a/src/crewai/flow/visualization_utils.py
+++ b/src/crewai/flow/visualization_utils.py
@@ -17,7 +17,7 @@ Example

 import ast
 import inspect
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any

 from .utils import (
    build_ancestor_dict,
@@ -56,6 +56,7 @@ def method_calls_crew(method: Any) -> bool:

    class CrewCallVisitor(ast.NodeVisitor):
        """AST visitor to detect .crew() method calls."""
+
        def __init__(self):
            self.found = False

@@ -73,8 +74,8 @@ def method_calls_crew(method: Any) -> bool:
 def add_nodes_to_network(
    net: Any,
    flow: Any,
-    node_positions: Dict[str, Tuple[float, float]],
-    node_styles: Dict[str, Dict[str, Any]]
+    node_positions: dict[str, tuple[float, float]],
+    node_styles: dict[str, dict[str, Any]],
 ) -> None:
    """
    Add nodes to the network visualization with appropriate styling.
@@ -98,6 +99,7 @@ def add_nodes_to_network(
    - Crew methods
    - Regular methods
    """
+
    def human_friendly_label(method_name):
        return method_name.replace("_", " ").title()

@@ -138,10 +140,10 @@ def add_nodes_to_network(

 def compute_positions(
    flow: Any,
-    node_levels: Dict[str, int],
+    node_levels: dict[str, int],
    y_spacing: float = 150,
-    x_spacing: float = 300
-) -> Dict[str, Tuple[float, float]]:
+    x_spacing: float = 300,
+) -> dict[str, tuple[float, float]]:
    """
    Compute the (x, y) positions for each node in the flow graph.

@@ -161,8 +163,8 @@ def compute_positions(
    Dict[str, Tuple[float, float]]
        Dictionary mapping node names to their (x, y) coordinates.
    """
-    level_nodes: Dict[int, List[str]] = {}
-    node_positions: Dict[str, Tuple[float, float]] = {}
+    level_nodes: dict[int, list[str]] = {}
+    node_positions: dict[str, tuple[float, float]] = {}

    for method_name, level in node_levels.items():
        level_nodes.setdefault(level, []).append(method_name)
@@ -180,10 +182,10 @@ def compute_positions(
 def add_edges(
    net: Any,
    flow: Any,
-    node_positions: Dict[str, Tuple[float, float]],
-    colors: Dict[str, str]
+    node_positions: dict[str, tuple[float, float]],
+    colors: dict[str, str],
 ) -> None:
-    edge_smooth: Dict[str, Union[str, float]] = {"type": "continuous"}  # Default value
+    edge_smooth: dict[str, str | float] = {"type": "continuous"}  # Default value
    """
    Add edges to the network visualization with appropriate styling.

@@ -269,7 +271,7 @@ def add_edges(
    for router_method_name, paths in flow._router_paths.items():
        for path in paths:
            for listener_name, (
-                condition_type,
+                _condition_type,
                trigger_methods,
            ) in flow._listeners.items():
                if path in trigger_methods:
--- a/src/crewai/knowledge/knowledge.py
+++ b/src/crewai/knowledge/knowledge.py
@@ -1,10 +1,10 @@
 import os
-from typing import Any

 from pydantic import BaseModel, ConfigDict, Field

 from crewai.knowledge.source.base_knowledge_source import BaseKnowledgeSource
 from crewai.knowledge.storage.knowledge_storage import KnowledgeStorage
+from crewai.rag.embeddings.types import EmbedderConfig
 from crewai.rag.types import SearchResult

 os.environ["TOKENIZERS_PARALLELISM"] = "false"  # removes logging from fastembed
@@ -16,20 +16,20 @@ class Knowledge(BaseModel):
    Args:
        sources: list[BaseKnowledgeSource] = Field(default_factory=list)
        storage: KnowledgeStorage | None = Field(default=None)
-        embedder: dict[str, Any] | None = None
+        embedder: EmbedderConfig | None = None
    """

    sources: list[BaseKnowledgeSource] = Field(default_factory=list)
    model_config = ConfigDict(arbitrary_types_allowed=True)
    storage: KnowledgeStorage | None = Field(default=None)
-    embedder: dict[str, Any] | None = None
+    embedder: EmbedderConfig | None = None
    collection_name: str | None = None

    def __init__(
        self,
        collection_name: str,
        sources: list[BaseKnowledgeSource],
-        embedder: dict[str, Any] | None = None,
+        embedder: EmbedderConfig | None = None,
        storage: KnowledgeStorage | None = None,
        **data,
    ):
--- a/src/crewai/knowledge/source/base_file_knowledge_source.py
+++ b/src/crewai/knowledge/source/base_file_knowledge_source.py
@@ -1,6 +1,5 @@
 from abc import ABC, abstractmethod
 from pathlib import Path
-from typing import Dict, List, Optional, Union

 from pydantic import Field, field_validator

@@ -14,19 +13,19 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
    """Base class for knowledge sources that load content from files."""

    _logger: Logger = Logger(verbose=True)
-    file_path: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+    file_path: Path | list[Path] | str | list[str] | None = Field(
        default=None,
        description="[Deprecated] The path to the file. Use file_paths instead.",
    )
-    file_paths: Optional[Union[Path, List[Path], str, List[str]]] = Field(
+    file_paths: Path | list[Path] | str | list[str] | None = Field(
        default_factory=list, description="The path to the file"
    )
-    content: Dict[Path, str] = Field(init=False, default_factory=dict)
-    storage: Optional[KnowledgeStorage] = Field(default=None)
-    safe_file_paths: List[Path] = Field(default_factory=list)
+    content: dict[Path, str] = Field(init=False, default_factory=dict)
+    storage: KnowledgeStorage | None = Field(default=None)
+    safe_file_paths: list[Path] = Field(default_factory=list)

    @field_validator("file_path", "file_paths", mode="before")
-    def validate_file_path(cls, v, info):
+    def validate_file_path(cls, v, info):  # noqa: N805
        """Validate that at least one of file_path or file_paths is provided."""
        # Single check if both are None, O(1) instead of nested conditions
        if (
@@ -46,9 +45,8 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
        self.content = self.load_content()

    @abstractmethod
-    def load_content(self) -> Dict[Path, str]:
+    def load_content(self) -> dict[Path, str]:
        """Load and preprocess file content. Should be overridden by subclasses. Assume that the file path is relative to the project root in the knowledge directory."""
-        pass

    def validate_content(self):
        """Validate the paths."""
@@ -74,11 +72,11 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
        else:
            raise ValueError("No storage found to save documents.")

-    def convert_to_path(self, path: Union[Path, str]) -> Path:
+    def convert_to_path(self, path: Path | str) -> Path:
        """Convert a path to a Path object."""
        return Path(KNOWLEDGE_DIRECTORY + "/" + path) if isinstance(path, str) else path

-    def _process_file_paths(self) -> List[Path]:
+    def _process_file_paths(self) -> list[Path]:
        """Convert file_path to a list of Path objects."""

        if hasattr(self, "file_path") and self.file_path is not None:
@@ -93,7 +91,7 @@ class BaseFileKnowledgeSource(BaseKnowledgeSource, ABC):
            raise ValueError("Your source must be provided with a file_paths: []")

        # Convert single path to list
-        path_list: List[Union[Path, str]] = (
+        path_list: list[Path | str] = (
            [self.file_paths]
            if isinstance(self.file_paths, (str, Path))
            else list(self.file_paths)
--- a/src/crewai/knowledge/source/base_knowledge_source.py
+++ b/src/crewai/knowledge/source/base_knowledge_source.py
@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, List, Optional
+from typing import Any

 import numpy as np
 from pydantic import BaseModel, ConfigDict, Field
@@ -12,29 +12,27 @@ class BaseKnowledgeSource(BaseModel, ABC):

    chunk_size: int = 4000
    chunk_overlap: int = 200
-    chunks: List[str] = Field(default_factory=list)
-    chunk_embeddings: List[np.ndarray] = Field(default_factory=list)
+    chunks: list[str] = Field(default_factory=list)
+    chunk_embeddings: list[np.ndarray] = Field(default_factory=list)

    model_config = ConfigDict(arbitrary_types_allowed=True)
-    storage: Optional[KnowledgeStorage] = Field(default=None)
-    metadata: Dict[str, Any] = Field(default_factory=dict)  # Currently unused
-    collection_name: Optional[str] = Field(default=None)
+    storage: KnowledgeStorage | None = Field(default=None)
+    metadata: dict[str, Any] = Field(default_factory=dict)  # Currently unused
+    collection_name: str | None = Field(default=None)

    @abstractmethod
    def validate_content(self) -> Any:
        """Load and preprocess content from the source."""
-        pass

    @abstractmethod
    def add(self) -> None:
        """Process content, chunk it, compute embeddings, and save them."""
-        pass

-    def get_embeddings(self) -> List[np.ndarray]:
+    def get_embeddings(self) -> list[np.ndarray]:
        """Return the list of embeddings for the chunks."""
        return self.chunk_embeddings

-    def _chunk_text(self, text: str) -> List[str]:
+    def _chunk_text(self, text: str) -> list[str]:
        """Utility method to split text into chunks."""
        return [
            text[i : i + self.chunk_size]
--- a/src/crewai/knowledge/source/crew_docling_source.py
+++ b/src/crewai/knowledge/source/crew_docling_source.py
@@ -1,13 +1,21 @@
+from collections.abc import Iterator
 from pathlib import Path
-from typing import Iterator, List, Optional, Union
 from urllib.parse import urlparse

 try:
-    from docling.datamodel.base_models import InputFormat
-    from docling.document_converter import DocumentConverter
-    from docling.exceptions import ConversionError
-    from docling_core.transforms.chunker.hierarchical_chunker import HierarchicalChunker
-    from docling_core.types.doc.document import DoclingDocument
+    from docling.datamodel.base_models import (  # type: ignore[import-not-found]
+        InputFormat,
+    )
+    from docling.document_converter import (  # type: ignore[import-not-found]
+        DocumentConverter,
+    )
+    from docling.exceptions import ConversionError  # type: ignore[import-not-found]
+    from docling_core.transforms.chunker.hierarchical_chunker import (  # type: ignore[import-not-found]
+        HierarchicalChunker,
+    )
+    from docling_core.types.doc.document import (  # type: ignore[import-not-found]
+        DoclingDocument,
+    )

    DOCLING_AVAILABLE = True
 except ImportError:
@@ -35,11 +43,11 @@ class CrewDoclingSource(BaseKnowledgeSource):

    _logger: Logger = Logger(verbose=True)

-    file_path: Optional[List[Union[Path, str]]] = Field(default=None)
-    file_paths: List[Union[Path, str]] = Field(default_factory=list)
-    chunks: List[str] = Field(default_factory=list)
-    safe_file_paths: List[Union[Path, str]] = Field(default_factory=list)
-    content: List["DoclingDocument"] = Field(default_factory=list)
+    file_path: list[Path | str] | None = Field(default=None)
+    file_paths: list[Path | str] = Field(default_factory=list)
+    chunks: list[str] = Field(default_factory=list)
+    safe_file_paths: list[Path | str] = Field(default_factory=list)
+    content: list["DoclingDocument"] = Field(default_factory=list)
    document_converter: "DocumentConverter" = Field(
        default_factory=lambda: DocumentConverter(
            allowed_formats=[
@@ -66,7 +74,7 @@ class CrewDoclingSource(BaseKnowledgeSource):
        self.safe_file_paths = self.validate_content()
        self.content = self._load_content()

-    def _load_content(self) -> List["DoclingDocument"]:
+    def _load_content(self) -> list["DoclingDocument"]:
        try:
            return self._convert_source_to_docling_documents()
        except ConversionError as e:
@@ -88,7 +96,7 @@ class CrewDoclingSource(BaseKnowledgeSource):
            self.chunks.extend(list(new_chunks_iterable))
        self._save_documents()

-    def _convert_source_to_docling_documents(self) -> List["DoclingDocument"]:
+    def _convert_source_to_docling_documents(self) -> list["DoclingDocument"]:
        conv_results_iter = self.document_converter.convert_all(self.safe_file_paths)
        return [result.document for result in conv_results_iter]

@@ -97,8 +105,8 @@ class CrewDoclingSource(BaseKnowledgeSource):
        for chunk in chunker.chunk(doc):
            yield chunk.text

-    def validate_content(self) -> List[Union[Path, str]]:
-        processed_paths: List[Union[Path, str]] = []
+    def validate_content(self) -> list[Path | str]:
+        processed_paths: list[Path | str] = []
        for path in self.file_paths:
            if isinstance(path, str):
                if path.startswith(("http://", "https://")):
@@ -108,7 +116,7 @@ class CrewDoclingSource(BaseKnowledgeSource):
                        else:
                            raise ValueError(f"Invalid URL format: {path}")
                    except Exception as e:
-                        raise ValueError(f"Invalid URL: {path}. Error: {str(e)}")
+                        raise ValueError(f"Invalid URL: {path}. Error: {e!s}") from e
                else:
                    local_path = Path(KNOWLEDGE_DIRECTORY + "/" + path)
                    if local_path.exists():
--- a/src/crewai/knowledge/source/csv_knowledge_source.py
+++ b/src/crewai/knowledge/source/csv_knowledge_source.py
@@ -1,6 +1,5 @@
 import csv
 from pathlib import Path
-from typing import Dict, List

 from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledgeSource

@@ -8,7 +7,7 @@ from crewai.knowledge.source.base_file_knowledge_source import BaseFileKnowledge
 class CSVKnowledgeSource(BaseFileKnowledgeSource):
    """A knowledge source that stores and queries CSV file content using embeddings."""

-    def load_content(self) -> Dict[Path, str]:
+    def load_content(self) -> dict[Path, str]:
        """Load and preprocess CSV file content."""
        content_dict = {}
        for file_path in self.safe_file_paths:
@@ -32,7 +31,7 @@ class CSVKnowledgeSource(BaseFileKnowledgeSource):
        self.chunks.extend(new_chunks)
        self._save_documents()

-    def _chunk_text(self, text: str) -> List[str]:
+    def _chunk_text(self, text: str) -> list[str]:
        """Utility method to split text into chunks."""
        return [
            text[i : i + self.chunk_size]
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
Lorenze Jay	b5b10a8cde	chore: update version and dependencies to 0.201.0 (#3593 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Build uv cache / build-cache (3.10) (push) Has been cancelled Details Build uv cache / build-cache (3.11) (push) Has been cancelled Details Build uv cache / build-cache (3.12) (push) Has been cancelled Details Build uv cache / build-cache (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details - Bump CrewAI version to 0.201.0 in __init__.py - Update dependency versions in pyproject.toml for crew, flow, and tool templates to require CrewAI 0.201.0 - Remove unnecessary blank line in pyproject.toml	2025-09-25 18:04:12 -07:00
Greyson LaLonde	2485ed93d6	feat: upgrade chromadb to v1.1.0, improve types - update imports and include handling for chromadb v1.1.0 - fix mypy and typing_compat issues (required, typeddict, voyageai) - refine embedderconfig typing and allow base provider instances - handle mem0 as special case for external memory storage - bump tools and clean up redundant deps	2025-09-25 20:48:37 -04:00
Greyson LaLonde	ce5ea9be6f	feat: add custom embedding types and migrate providers - introduce baseembeddingsprovider and helper for embedding functions - add core embedding types and migrate providers, factory, and storage modules - remove unused type aliases and fix pydantic schema error - update providers with env var support and related fixes	2025-09-25 18:28:39 -04:00
Greyson LaLonde	e070c1400c	feat: update pydantic, add pydantic-settings, migrate to dependency-groups Some checks failed Build uv cache / build-cache (3.10) (push) Has been cancelled Details Build uv cache / build-cache (3.11) (push) Has been cancelled Details Build uv cache / build-cache (3.12) (push) Has been cancelled Details Build uv cache / build-cache (3.13) (push) Has been cancelled Details CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details - Add pydantic-settings>=2.10.1 dependency for configuration management - Update pydantic to 2.11.9 and python-dotenv to 1.1.1 - Migrate from deprecated tool.uv.dev-dependencies to dependency-groups.dev format - Remove unnecessary dev dependencies: pillow, cairosvg - Update all dev tooling to latest versions - Remove duplicate python-dotenv from dev dependencies	2025-09-24 14:42:18 -04:00
Greyson LaLonde	6537e3737d	fix: correct directory name in quickstart documentation	2025-09-24 11:41:33 -04:00
Greyson LaLonde	346faf229f	feat: add pydantic-compatible import validation and deprecate old utilities	2025-09-24 11:36:02 -04:00
Lorenze Jay	a0b757a12c	Lorenze/traces mark as failed (#3586 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details * marking trace batch as failed if its failed * fix test	2025-09-23 22:02:27 -07:00
Greyson LaLonde	1dbe8aab52	fix: add batch_size support to prevent embedder token limit errors - add batch_size field to baseragconfig (default=100) - update chromadb/qdrant clients and factories to use batch_size - extract and filter batch_size from embedder config in knowledgestorage - fix large csv files exceeding embedder token limits (#3574) - remove unneeded conditional for type Co-authored-by: Vini Brasil <vini@hey.com>	2025-09-24 00:05:43 -04:00
Greyson LaLonde	4ac65eb0a6	fix: support nested config format for embedder configuration Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details - support nested config format with embedderconfig typeddict - fix parsing for model/model_name compatibility - add validation, typing_extensions, and improved type hints - enhance embedding factory with env var injection and provider support - add tests for openai, azure, and all embedding providers - misc fixes: test file rename, updated mocking patterns	2025-09-23 11:57:46 -04:00
Greyson LaLonde	3e97393f58	chore: improve typing and consolidate utilities - add type annotations across utility modules - refactor printer system, agent utils, and imports for consistency - remove unused modules, constants, and redundant patterns - improve runtime type checks, exception handling, and guardrail validation - standardize warning suppression and logging utilities - fix llm typing, threading/typing edge cases, and test behavior	2025-09-23 11:33:46 -04:00
Heitor Carvalho	34bed359a6	feat: add `crewai uv` wrapper for `uv` commands (#3581 )	2025-09-23 10:55:15 -04:00
Tony Kipkemboi	feeed505bb	docs(changelog): add releases 0.193.2, 0.193.1, 0.193.0, 0.186.1, 0.186.0 across en/ko/pt-BR (#3577 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details	2025-09-22 16:19:55 -07:00
Greyson LaLonde	cb0efd05b4	chore: fix ruff linting issues in tools module Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details linting, args_schema default, and validator check	2025-09-22 13:13:23 -04:00
Greyson LaLonde	db5f565dea	fix: apply ruff linting fixes to tasks module	2025-09-22 13:09:53 -04:00
Greyson LaLonde	58413b663a	chore: fix ruff linting issues in rag module linting, list embedding handling, and test update	2025-09-22 13:06:22 -04:00
Greyson LaLonde	37636f0dd7	chore: fix ruff linting and mypy issues in flow module	2025-09-22 13:03:06 -04:00
Greyson LaLonde	0e370593f1	chore: resolve all ruff and mypy issues in experimental module resolve linting, typing, and import issues; update Okta test	2025-09-22 12:56:28 -04:00
Vini Brasil	aa8dc9d77f	Add source to LLM Guardrail events (#3572 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details This commit adds the source attribute to LLM Guardrail event calls to identify the Lite Agent or Task that executed the guardrail.	2025-09-22 11:58:00 +09:00
Jonathan Hill	9c1096dbdc	fix: Make 'ready' parameter optional in _create_reasoning_plan function (#3561 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details * fix: Make 'ready' parameter optional in _create_reasoning_plan function This PR fixes Issue #3466 where the _create_reasoning_plan function was missing the 'ready' parameter when called by the LLM. The fix makes the 'ready' parameter optional with a default value of False, which allows the function to be called with only the 'plan' argument. Fixes #3466 * Change default value of 'ready' parameter to True --------- Co-authored-by: João Moura <joaomdmoura@gmail.com>	2025-09-20 22:57:18 -03:00
João Moura	47044450c0	Adding fallback to crew settings (#3562 ) * Adding fallback to crew settings * fix: resolve ruff and mypy issues in cli/config.py --------- Co-authored-by: Greyson Lalonde <greyson.r.lalonde@gmail.com>	2025-09-20 22:54:36 -03:00
João Moura	0ee438c39d	fix version (#3557 )	2025-09-20 17:14:28 -03:00
Joao Moura	cbb9965bf7	preparing new version	2025-09-20 12:27:25 -07:00
João Moura	4951d30dd9	Dix issues with getting id (#3556 ) * fix issues with getting id * ignore linter * fix: resolve ruff linting issues in tracing utils --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-09-20 15:29:25 -03:00
Greyson LaLonde	7426969736	chore: apply ruff linting fixes and type annotations to memory module Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details Co-authored-by: Lorenze Jay <63378463+lorenzejay@users.noreply.github.com>	2025-09-19 22:20:13 -04:00
Greyson LaLonde	d879be8b66	chore: fix ruff linting issues in agents module fix(agents): linting, import paths, cache key alignment, and static method	2025-09-19 22:11:21 -04:00
Greyson LaLonde	24b84a4b68	chore: apply ruff linting fixes to crews module	2025-09-19 22:02:22 -04:00
Greyson LaLonde	8e571ea8a7	chore: fix ruff linting and mypy issues in knowledge module Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Build uv cache / build-cache (3.10) (push) Has been cancelled Details Build uv cache / build-cache (3.11) (push) Has been cancelled Details Build uv cache / build-cache (3.12) (push) Has been cancelled Details Build uv cache / build-cache (3.13) (push) Has been cancelled Details	2025-09-19 21:39:15 -04:00
Greyson LaLonde	2cfc4d37b8	chore: apply ruff linting fixes to events module fix: apply ruff linting to events	2025-09-19 20:10:55 -04:00
Greyson LaLonde	f4abc41235	chore: apply ruff linting fixes to CLI module fix: apply ruff fixes to CLI and update Okta provider test	2025-09-19 19:55:55 -04:00
Greyson LaLonde	de5d3c3ad1	chore: add pydantic.mypy plugin for better type checking	2025-09-19 19:23:33 -04:00
Lorenze Jay	c062826779	chore: update dependencies and versioning for CrewAI 0.193.0 (#3542 ) * chore: update dependencies and versioning for CrewAI - Bump `crewai-tools` dependency version from `0.71.0` to `0.73.0` in `pyproject.toml`. - Update CrewAI version from `0.186.1` to `0.193.0` in `__init__.py`. - Adjust dependency versions in CLI templates for crew, flow, and tool to reflect the new CrewAI version. This update ensures compatibility with the latest features and improvements in CrewAI. * remove embedchain mock * fix: remove last embedchain mocks * fix: remove langchain_openai from tests --------- Co-authored-by: Greyson LaLonde <greyson.r.lalonde@gmail.com>	2025-09-19 16:01:55 -03:00
João Moura	9491fe8334	Adding Ability for user to get deeper observability (#3541 ) Some checks failed CodeQL Advanced / Analyze (actions) (push) Has been cancelled Details CodeQL Advanced / Analyze (python) (push) Has been cancelled Details Notify Downstream / notify-downstream (push) Has been cancelled Details Update Test Durations / update-durations (3.10) (push) Has been cancelled Details Update Test Durations / update-durations (3.11) (push) Has been cancelled Details Update Test Durations / update-durations (3.12) (push) Has been cancelled Details Update Test Durations / update-durations (3.13) (push) Has been cancelled Details Mark stale issues and pull requests / stale (push) Has been cancelled Details * feat(tracing): enhance first-time trace display and auto-open browser * avoinding line breaking * set tracing if user enables it * linted --------- Co-authored-by: lorenzejay <lorenzejaytech@gmail.com>	2025-09-18 21:47:09 -03:00
Greyson LaLonde	6f2ea013a7	docs: update RagTool references from EmbedChain to CrewAI native RAG (#3537 ) * docs: update RagTool references from EmbedChain to CrewAI native RAG * change ref to qdrant * docs: update RAGTool to use Qdrant and add embedding_model example	2025-09-18 16:06:44 -07:00
Greyson LaLonde	39e8792ae5	fix: add l2 distance metric support for backward compatibility (#3540 )	2025-09-18 18:36:33 -04:00