Error: [handleAbortError] AI response error; aborting request: getOpenAIConfig is not a function

[kskkssk]

Hello! I am trying to connect N8N custom endpoint.
The model does show up in the LibreChat UI.
Librechat version: v0.8.1-rc1

LibreChat UI shows: Something went wrong. Here's the specific error message we encountered: An error occurred while processing your request. Please contact the Admin.

Log in ./logs directory is empty. I have this error: [handleAbortError] AI response error; aborting request: getOpenAIConfig is not a function.
As I see, LibreChat doesn't even connect to N8N workflow.

My librechat.yaml:

endpoints:
  custom:
    - name: 'n8n-chat'
      apiKey: '${N8N_CHAT_KEY}'
      baseURL: 'http://host.docker.internal:5678/webhook/v1/chat/completions'
      models:
        default: ['n8n-chat']
        fetch: false
      addParams:
        session_id: "{{user._id}}"
        stream: false
      titleConvo: true
      titleModel: 'n8n-chat'
      modelDisplayLabel: 'n8n-chat'

I have the ${N8N_CHAT_KEY} set in .env.
I have tested request from container, it seems working:

/app # wget -S -O- \
>   --header='Content-Type: application/json' \
>   --header='Authorization: getwebhook' \
>   --post-data='{"model":"n8n-chat","messages":[{"role":"user","content":"Hi"}],"stream":false}' \
>   http://host.docker.internal:5678/webhook/v1/chat/completions

Response
Connecting to host.docker.internal:5678 (192.168.65.254:5678)
HTTP/1.1 200 OK
Content-Type: application/json; charset=utf-8
Vary: Accept-Encoding
Date: Fri, 14 Nov 2025 10:09:25 GMT
Connection: close
Transfer-Encoding: chunked

Is there anything wrong or missing in my librechat.yaml configuration for this kind of custom endpoint?
Any help or pointers would be greatly appreciated, thanks in advance!