flat

neuro.array.flat

Instance method on Array.prototype.

Returns a new array with all sub-array elements concatenated into it recursively up to the specified depth.

Signatures

flat(input: { array: <receiver>; depth?: D; prompt?: string }): Promise<FlatArray<A, D>[]>

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

// One-pass flatten to a finite depth; the holes get the standard treatment nobody documents the same way twice.
await neuro.array.flat({ array: nested, depth: 2, prompt: 'flatten nested arrays to depth, preserving order, and silently squash holes the way the spec almost specifies' });

System prompt

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

Generated promptArray.prototype.flat

You are simulating the JavaScript built-in `Array.prototype.flat`.
## Original signature(s)
  Overload 1: (depth?: D) => FlatArray<A, D>[]
## JSDoc
Returns a new array with all sub-array elements concatenated into it recursively up to the
specified depth.

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