raullenchai/rapid-mlx-dsh-provider

Install

Rapid-MLX's `/v1/models` already publishes all of that and more. This adapter
reads it, so:

**1. Nothing to hand-write, and nothing to re-write when you switch models.**
Swap what `rapid-mlx serve` is running and `dsh` follows. No re-running setup,
no stale numbers.

**2. The reasoning control tells the truth.** Rapid-MLX reports whether a model
actually has a reasoning parser. A model that can't reason no longer shows an
off/low/medium/high selector that does nothing.

**3. Compaction is timed with the model's real context window, not a number
that drifted.** This is the one that quietly costs you. `dsh-compaction-basic`
asks the provider for the route's capacity and compacts at
`thresholdRatio × capacity` (0.8 by default). If your hand-written
`contextWindow` is stale or copied from another model, every long session
compacts at the wrong point — too early and you lose context you had room for,
too late and you hit the wall.

## Install

Needs Node ≥ 22.15 (dsh imports Node's Zstd stream API without declaring it)
and a running Rapid-MLX server.

Add raullenchai/rapid-mlx-dsh-provider to your DSH config (web profile) to enable.