Skip to content

fix(overseer): hide tool-incompatible brain models (gpt-5.6-luna converse 400) #142

Description

@heavygee

Problem

Overseer talk (POST /api/overseer/converse) fails when active model is gpt-5.6-luna:

Function tools with reasoning_effort are not supported for gpt-5.6-luna in /v1/chat/completions. To use function tools, use /v1/responses or set reasoning_effort to 'none'.

Brain shows reachable; converse returns the soft "tool conversation (request error)" reply.

Ask

Overseer always uses chat/completions + function tools. Do not offer models that cannot run that path. Clear/reject an already-persisted incompatible active model.

Notes

Operator dogfood on /overseer 2026-09-07. Optional belt: send reasoning_effort: none when tools are present so recoverable reasoning models work — still keep the picker honest.

Activity

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

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions