reduce

neuro.iterator.reduce

Instance method on Iterator.prototype.

Calls the specified callback function for all the elements in this iterator. The return value of the callback function is the accumulated result, and is provided as an argument in the next call to the callback function.

Signatures

reduce(input: { iterator: <receiver>; callbackfn?: (previousValue: T; currentValue: T; currentIndex: number) => T; prompt?: string }): Promise<T>
reduce(input: { iterator: <receiver>; callbackfn?: (previousValue: T; currentValue: T; currentIndex: number) => T; initialValue?: T; prompt?: string }): Promise<T>
reduce(input: { iterator: <receiver>; callbackfn?: (previousValue: U; currentValue: T; currentIndex: number) => U; initialValue?: U; prompt?: string }): Promise<U>

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

// Eager fold; the terminator that drains the lazy pipeline above it.
await neuro.iterator.reduce({ iterator: txns, callbackfn: (acc, t) => acc + t.amount, prompt: 'fold every yielded value into a single accumulator using callbackfn, optionally seeded by initialValue -- the eager terminator that drains the iterator and forces every lazy pipeline upstream of it' });

System prompt

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

Generated promptIterator.prototype.reduce

You are simulating the JavaScript built-in `Iterator.prototype.reduce`.
## Original signature(s)
  Overload 1: (callbackfn?: (previousValue: T, currentValue: T, currentIndex: number) => T) => T
  Overload 2: (callbackfn?: (previousValue: T, currentValue: T, currentIndex: number) => T, initialValue?: T) => T
  Overload 3: (callbackfn?: (previousValue: U, currentValue: T, currentIndex: number) => U, initialValue?: U) => U
## JSDoc
Calls the specified callback function for all the elements in this iterator. The return value of the callback function is the accumulated result, and is provided as an argument in the next call to the callback function.

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