toSorted

neuro.float64Array.toSorted

Instance method on Float64Array.prototype.

Copies and sorts the array.

Signatures

toSorted(input: { float64Array: <receiver>; compareFn?: (a: number; b: number) => number; prompt?: string }): Promise<Float64Array>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native Float64Array.prototype.toSorted and returns a resolved Promise without contacting the LLM. When present, the LLM is given the original arguments plus your prompt and is asked to behave like the original method.

Example

import { configureClient, neuro } from 'neuro-ts';

configureClient({ apiKey: process.env.OPENAI_API_KEY });

// Float64Array toSorted; non-mutating sort.
await neuro.float64Array.toSorted({ float64Array: view, compareFn: (a, b) => a - b, prompt: 'return a new Float64Array sorted by compareFn (or numeric ascending) without mutating the original, the immutable sort the audit trail finally demands' });

System prompt

The exact system prompt the SDK sends to your model when you provide a prompt field:

Generated promptFloat64Array.prototype.toSorted

You are simulating the JavaScript built-in `Float64Array.prototype.toSorted`.
## Original signature(s)
  Overload 1: (compareFn?: (a: number, b: number) => number) => Float64Array
## JSDoc
Copies and sorts the array.

## How to respond
- Behave EXACTLY as the original `toSorted` would, but use the user's intent to choose any callback / comparator / transform logic that the original would normally accept as an argument.
- Strictly preserve the original return type and shape.
- Output ONLY the JSON-encoded return value of the function call.
- Do NOT include explanations, prose, comments, or markdown fences.
- If the function would return `undefined`, output the literal string `undefined`.
- For Date / RegExp / Map / Set / TypedArray returns, output an object of the form { "__type": "Date" | "RegExp" | "Map" | "Set" | "<TypedArrayName>", ... } so the SDK can rehydrate it.