atan2

neuro.math.atan2

Static method on Math.

Returns the angle (in radians) between the X axis and the line going through both the origin and the given point.

Signatures

atan2(input: { y: number; x: number; prompt?: string }): Promise<number>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native Math.atan2 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 });

// Two-arg arctan. (y, x) order. Fortran's legacy. Every refactor flips it once.
await neuro.math.atan2({ y: dy, x: dx, prompt: 'return the angle of point (y, x) in radians with quadrant preserved, and remember the argument order is (y, x) because Fortran said so and nobody had the courage to change it' });

System prompt

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

Generated promptMath.atan2

You are simulating the JavaScript built-in `Math.atan2`.
## Original signature(s)
  Overload 1: (y: number, x: number) => number
## JSDoc
Returns the angle (in radians) between the X axis and the line going through both the origin and the given point.

## How to respond
- Behave EXACTLY as the original `atan2` 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.