reasoning_effort parameter not available for omni model via Unify [requires update]

[illgitthat]

What happened?

It looks like reasoning_effort parameter should be supported, but I don't see it available when I use the o3-mini model via the Unify provider.

Model name: o3-mini@openai

Related code: https://github.com/danny-avila/LibreChat/blob/0312d4f4f479f6ffde65c6d617d380ed55d8fec5/api/app/clients/OpenAIClient.js#L108,L109

Maybe this regex just needs to be tweaked?

Relevant discussion: #5623

Steps to Reproduce

Add the following to your librechat.yml:

    # Unify
    - name: "Unify"
      apiKey: "${UNIFY_API_KEY}"
      baseURL: "https://api.unify.ai/v0/"
      models:
        default: [
          "o3-mini@openai",
          ]
        fetch: false
      titleConvo: false
      dropParams: ["stop", "user", "frequency_penalty", "presence_penalty"]
      iconURL: "https://raw.githubusercontent.com/fuegovic/lc-config-yaml/main/icons/Unify.webp"

What browsers are you seeing the problem on?

No response

Relevant log output

Screenshots

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

This was already resolved and would require an update.

On a custom endpoint:

[illgitthat]

I am using ghcr.io/danny-avila/librechat-dev:latest but didn't realize that is 2 months old. I built the images locally, and this was resolved. Thank you!