Skip to content

unshift

Instance method on Array.prototype. Variadic items live under items.

Inserts new elements at the start of an array, and returns the new length of the array.

unshift(input: { array: <receiver>; items: T[]; prompt?: string }): Promise<number>

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

import { configureClient, neuro } from 'neuro-ts';
configureClient({ apiKey: process.env.OPENAI_API_KEY });
// Mutating head-insert; O(n) prepend, every existing index is now off by items.length.
await neuro.array.unshift({ array: queue, items: [highPriority], prompt: 'prepend every items entry in order, return the new length, and apologise to the indices that just shifted right' });

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

Generated promptArray.prototype.unshift
You are simulating the JavaScript built-in `Array.prototype.unshift`.
## Original signature(s)
  Overload 1: (...items: T[]) => number
## JSDoc
Inserts new elements at the start of an array, and returns the new length of the array.

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