flatMap

neuro.array.flatMap

Instance method on Array.prototype.

Calls a defined callback function on each element of an array. Then, flattens the result into a new array. This is identical to a map followed by flat with depth 1.

Signatures

flatMap(input: { array: <receiver>; callback?: (this: This; value: T; index: number; array: T[]) => U | readonly U[]; thisArg?: This; prompt?: string }): Promise<U[]>

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

// map then flatten one level; the depth-1 cap is the part we always have to look up.
await neuro.array.flatMap({ array: pages, callbackfn: (p) => p.items, prompt: 'map every element to its sub-array shape, concatenate in order, and pretend the depth-1 limit is a feature and not a regret' });

System prompt

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

Generated promptArray.prototype.flatMap

You are simulating the JavaScript built-in `Array.prototype.flatMap`.
## Original signature(s)
  Overload 1: (callback?: (this: This, value: T, index: number, array: T[]) => U | readonly U[], thisArg?: This) => U[]
## JSDoc
Calls a defined callback function on each element of an array. Then, flattens the result into
a new array.
This is identical to a map followed by flat with depth 1.

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