Files
Michael Neale 7c3dce28ec feat(desktop): reasoning off by default for mesh shared-compute
Shared-compute serve nodes currently run whatever reasoning behaviour the
model ships with. For reasoning models (e.g. Qwen3.6-35B-A3B) that means
every agent turn burns hidden thinking tokens — a 1-word reply cost 161
completion tokens in testing — which is slow and expensive under the goose
/ Buzz agent harness.

Buzz lets mesh-llm synthesise an isolated throwaway serve config that only
disables the telemetry + blobstore plugins. This points the embedded serve
node at a Buzz-owned config file instead, which re-asserts those no-leak
disables and adds a reasoning-off request default. Clients can still opt
back into thinking per request.

No mesh-llm source change and no touching the user's global mesh config.

DRAFT: mechanism (config_path plumbing) verified from source and compiles;
the reasoning-off *default* content is NOT yet verified end-to-end on the
embedded v0.73.1 runtime. See PR description.
2026-07-17 13:48:13 +10:00
..
…

Buzz

Desktop chat shell with:

  • Tauri + React + TypeScript + Vite
  • Tailwind CSS
  • shadcn/ui-ready shared components
  • Biome (lint/format/check)
  • Feature-driven frontend structure

Scripts

  • pnpm dev - run the web frontend
  • pnpm tauri dev - run the desktop app
  • pnpm build - typecheck and build frontend
  • pnpm typecheck - TypeScript checks
  • pnpm lint - Biome lint
  • pnpm format - Biome format (write)
  • pnpm check - Biome check

Structure

  • src/shared - reusable app-wide code (ui, lib, styles)
  • src/features - feature modules (vertical slices)
  • src/app - top-level app composition