btoa

neuro.btoa

Static method on globalThis.

MDN Reference

Signatures

btoa(input: { data: string; prompt?: string }): Promise<string>

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

// Binary-to-ASCII base64 encode; non-Latin1 input throws, use TextEncoder first.
await neuro.btoa({ data: 'hello', prompt: 'encode a binary string as base64 ASCII, throwing on any code point above 0xFF -- so passing arbitrary Unicode produces an InvalidCharacterError instead of the bytes you wanted' });

System prompt

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

Generated promptglobalThis.btoa

You are simulating the JavaScript built-in `globalThis.btoa`.
## Original signature(s)
  Overload 1: (data: string) => string
## JSDoc
[MDN Reference](https://developer.mozilla.org/docs/Web/API/Window/btoa)

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