Describe the bug
After upgrading to smolagents 1.13, Azure's content filter is blocking my requests.
This ONLY happens when planning_interval != 0 (ie. is enabled). If planning_interval is not set, everyting works just fine.
It usually complains about "self_harm"

Code to reproduce the error

import os
from smolagents import CodeAgent, AzureOpenAIServerModel

model = AzureOpenAIServerModel(
    model_id = "gpt-4o",
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    api_key=os.getenv("AZURE_OPENAI_API_KEY"),
    api_version=os.getenv("AZURE_OPENAI_API_VERSION"),
)
agent = CodeAgent(
    tools=[],
    model=model,
    planning_interval=2,
)
agent.run("what is e**3?")

Error logs (if any)
Error in generating model output: Error code: 400 - {'error': {'message': "The response was filtered due to the prompt triggering Azure OpenAI's content management policy. Please modify your prompt and retry. To learn more about our content filtering policies please read our documentation: https://go.microsoft.com/fwlink/?linkid=2198766", 'type': None, 'param': 'prompt', 'code': 'content_filter', 'status': 400, 'innererror': {'code': 'ResponsibleAIPolicyViolation', 'content_filter_result': {'hate': {'filtered': False, 'severity': 'safe'}, 'jailbreak': {'filtered': False, 'detected': False}, 'self_harm': {'filtered': True, 'severity': 'high'}, 'sexual': {'filtered': False, 'severity': 'safe'}, 'violence': {'filtered': False, 'severity': 'medium'}}}}}

Expected behavior
I expected the agent to run normally after upgrading versions, both with and without planning.

Packages version:
smolagents==1.13.0