Can't implement guardrails with litellm

[m-hamza-hashim]

Please read this first

• Have you read the docs?Agents SDK docs
• Have you searched for related issues? Others may have faced similar issues.

Describe the bug

A clear and concise description of what the bug is.

Debug information

• Agents SDK version: (e.g. v0.0.3)
• Python version (e.g. Python 3.10)

Repro steps

Ideally provide a minimal python script that can be run to reproduce the bug.

Expected behavior

A clear and concise description of what you expected to happen.

[rm-openai]

Please provide more info/repro steps

[m-hamza-hashim]

when making the agent through LitellmModel and then implementing a guardrail (whether input or ouput) on this agent, a pydantic error is produced "the input should be an integer". However, when the agent is given the model through OpenAIChatCompletionsModel , no such error is being produced and the guardrail is also working.