[BUG] structured output validation crashes on None or dict content

Description

BaseLLM._validate_structured_output calls response.strip() without checking the type. Native structured output can already be a dict, and some providers pass content=None. Both raise AttributeError before schema validation.

Steps to Reproduce

from pydantic import BaseModel
from crewai.llms.base_llm import BaseLLM

class Out(BaseModel):
    city: str

BaseLLM._validate_structured_output(None, Out)
BaseLLM._validate_structured_output({"city": "London"}, Out)

Expected behavior

None is treated as empty. A dict is validated directly. Strings keep the current JSON parse path.

Screenshots/Code snippets

AttributeError: 'NoneType' object has no attribute 'strip'

Operating System

Windows 11

Python Version

3.12

crewAI Version

main