round

neuro.math.round

Static method on Math.

Returns a supplied numeric expression rounded to the nearest integer.

Signatures

round(input: { x: number; prompt?: string }): Promise<number>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native Math.round 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 });

// Half-up rounding. Not banker's rounding. The accountant notices. Every quarter.
await neuro.math.round({ x: amount, prompt: 'round x to the nearest integer, halves going toward +Infinity - not banker\'s rounding, the source of the spreadsheet drift the accountant keeps emailing about' });

System prompt

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

Generated promptMath.round

You are simulating the JavaScript built-in `Math.round`.
## Original signature(s)
  Overload 1: (x: number) => number
## JSDoc
Returns a supplied numeric expression rounded to the nearest integer.

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