Files
buzz/desktop
Michael Neale 33bcaa7ced fix(desktop): stop abandoning healthy mesh prefills at four minutes
buzz-agent's `BUZZ_AGENT_LLM_TIMEOUT_SECS` defaults to 240s. MeshLLM's
OpenAI frontend gives a backend call 600s
(`OpenAiFrontendConfig::DEFAULT_BACKEND_TIMEOUT`), so on shared compute the
client aborts work the server is still legitimately doing.

Requests to a local mesh are `stream: false`, so a cold multi-ten-thousand
token prefill is one silent request. Measured on an M5 Max serving
Qwen3.8-27B Q4_K_M: an 88,318-token cold prompt returns HTTP 200 after
503s at 176 tok/s prefill. At the 240s default the client gives up at
four minutes, then retries with an escalated budget (240 -> 480 -> 960),
piling load onto a box that is already prefilling the first attempt.

Seat the mesh client budget at 660s, just above the frontend's 600s, so
the mesh's own error surfaces rather than a client abort racing it.
Remote providers are untouched and keep buzz-agent's 240s default. Like
the other mesh seeds this is a default, not policy: an explicit user
value survives via `insert_default_if_unset` plus the copy-forward list
in `relay_mesh_process_env`.

Co-authored-by: Michael Neale <michael.neale@gmail.com>
Signed-off-by: Michael Neale <michael.neale@gmail.com>
2026-08-17 20:59:10 +10:00
..
2026-08-03 21:51:17 -04:00
2026-03-09 13:02:11 -07:00
2026-06-11 15:06:24 +00:00
2026-03-09 13:02:11 -07:00

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