dsh-better-reasoning-effort

Usage

1. Configure a third-party provider (API key etc.) on the official Models page.
2. Expand a model row: the editor block sits under the official capacity fields.
   • Check levels (off / minimal / low / medium / high / xhigh / max) and fill the wire values (e.g. give high the spelling ultra, and the gateway receives ultra when you pick High in the composer);
   • Toggle Image input under Input modalities to declare what the model accepts (unchecked with no declaration = inherit the provider default, usually text-only);
   • Click Auto-adapt to fill recommended levels and modalities from the knowledge base / protocol / endpoint listing — reference capacities show up as read-only hints you can copy into the official fields yourself;
   • Any change you make is pending: the block says so, and those changes land when you press the card's own Save. Press Cancel (or reload the page) and they are discarded along with the card's own fields.
3. On a compatible protocol, the Endpoint compatibility section appears at the bottom — set the thinking budget field / vLLM priority on openai-completions, and max_output_tokens handling on openai-responses.
4. All levels off + Save = unset the declaration; only off checked + Save = disable reasoning (false); Clear declaration on the modality row + Save = back to inheriting the provider default.

Declared models are immediately selectable for reasoning effort in the composer's model picker, and image-declared models accept attachments end to end.

Configuration

The host half accepts optional configuration on its profile row (the values below are the defaults):

- insert:
    - id: dsh-better-reasoning-effort
      name: dsh-better-reasoning-effort
      config:
        # Auto-fill undeclared models on boot (the browser half fills session
        # additions once you leave the editing card).
        autofill: true
        # Whether the auto-fill above also fills input-modality declarations.
        modalityAutofill: true
        # Upstream /models probe fetch timeout, in milliseconds.
        probeTimeoutMs: 15000
        # Boot-fill retry backoff schedule; [] means "try exactly once".
        bootRetryDelaysMs: [1000, 2000, 4000, 8000, 16000, 30000]
        # Map effort-less calls on forced-thinking ladders to the vendor default.
        defaultGuard: true

Set autofill: false to disable the silent auto-fill entirely (both the boot pass and the browser half's running complement) — the browser-side Auto-adapt button keeps working.