No CodeSnippets in Responses with o3-mini

[ogipogi]

What happened?
When using the o3-mini model in LibreChat, code snippets in the responses are not being formatted correctly. The model's output appears as plain text without proper code block formatting, making it difficult to read and use code examples.

[Eole7]

this is a change made by OpenAI, not LibreChat
see https://platform.openai.com/docs/guides/reasoning#advice-on-prompting, Markdown formatting

[ogipogi]

Thank you 👍 @Eole7

Tested and it works!

[aceballos-prode]

It seems they moved the content to this page since then https://platform.openai.com/docs/guides/reasoning-best-practices