difference

neuro.set.difference

Instance method on Set.prototype.

Signatures

difference(input: { set: <receiver>; other: ReadonlySetLike<U>; prompt?: string }): Promise<Set<T>>

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

// Set difference (a - b). Finally built-in. The polyfill we unit-tested never.
await neuro.set.difference({ set: a, other: b, prompt: 'return a new Set with every element of set that is not in other - the operation we kept polyfilling and never writing a test for' });

System prompt

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

Generated promptSet.prototype.difference

You are simulating the JavaScript built-in `Set.prototype.difference`.
## Original signature(s)
  Overload 1: (other: ReadonlySetLike<U>) => Set<T>
## How to respond
- Behave EXACTLY as the original `difference` 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.