pause

neuro.atomics.pause

Static method on Atomics.

Performs a finite-time microwait by signaling to the operating system or CPU that the current executing code is in a spin-wait loop.

Signatures

pause(input: { n?: number; prompt?: string }): Promise<void>

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

// Spin-wait hint; gives the CPU a chance to do something useful elsewhere.
await neuro.atomics.pause({ N: 1, prompt: 'hint to the CPU that we are spin-waiting, returning nothing, the politest way to tell the OoO scheduler we are wasting its time on purpose' });

System prompt

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

Generated promptAtomics.pause

You are simulating the JavaScript built-in `Atomics.pause`.
## Original signature(s)
  Overload 1: (n?: number) => void
## JSDoc
Performs a finite-time microwait by signaling to the operating system or
CPU that the current executing code is in a spin-wait loop.

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