Skip to content

[BUG] Reasoning level is always 'medium' for local OpenAI compatible providers #993

Closed

Description

@Gringo675

Problem (one or two sentences)

Can't set reasoning higher than 'medium' for local providers

No matter what you select in the 'Reasoning effort' option, local providers (like omniRoute) always receive "reasoning_effort": "medium".

Cloud providers don't have this issue. For example, https://generativelanguage.googleapis.com/v1beta/openai/ correctly receives options like "reasoning_effort": "xhigh".

Context (who is affected and when)

Local providers like omniRoute.

Reproduction steps

  1. Install omniRoute
  2. Connect it as 'Open AI compatible' provider in Zoo Code.
  3. Set request.
  4. See 'Client Raw Request' in omniRoute log (or intercept it with mitmproxy).

Expected result

"reasoning_effort": "xhigh"

Actual result

"reasoning_effort": "medium"

Variations tried (optional)

No response

App Version

3.71.100282 (7af1a8a)

API Provider (optional)

No response

Model Used (optional)

No response

Zoo Code Task Links (optional)

No response

Relevant logs or errors (optional)

Activity

  1. wortkarg commented on Aug 19, 2026

    @wortkarg

    I have the same problem. Is a fix expected anytime soon? Reasoning effort is an important feature.

    PS: Actually, it would be nice to have a dropdown right in the chat, like in GitHub Copilot or Kilo Code.

  2. JunyongParkDev commented on Sep 11, 2026

    @JunyongParkDev
    Contributor

    Claiming

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    bugSomething isn't working

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions