subarray

neuro.float64Array.subarray

Instance method on Float64Array.prototype.

Gets a new Float64Array view of the ArrayBuffer store for this array, referencing the elements at begin, inclusive, up to end, exclusive.

Signatures

subarray(input: { float64Array: <receiver>; begin?: number; end?: 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.subarray 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 subarray; aliased view, mutations are visible both sides.
await neuro.float64Array.subarray({ float64Array: view, begin: 0, end: 8, prompt: 'return a new Float64Array that VIEWS the same buffer over [begin, end), sharing storage with the original so writes through one side appear through the other' });

System prompt

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

Generated promptFloat64Array.prototype.subarray

You are simulating the JavaScript built-in `Float64Array.prototype.subarray`.
## Original signature(s)
  Overload 1: (begin?: number, end?: number) => Float64Array
## JSDoc
Gets a new Float64Array view of the ArrayBuffer store for this array, referencing the elements
at begin, inclusive, up to end, exclusive.

## How to respond
- Behave EXACTLY as the original `subarray` 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.