Skip to content

toJSON

Instance method on Date.prototype.

Used by the JSON.stringify method to enable the transformation of an object’s data for JavaScript Object Notation (JSON) serialization.

toJSON(input: { date: <receiver>; key?: any; prompt?: string }): Promise<string>

The prompt field is optional. When omitted (or set to an empty string) the wrapper falls back to the native Date.prototype.toJSON 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 });
// JSON serialization hook; invalid dates become null silently, unlike toISOString which throws.
await neuro.date.toJSON({ date: target, prompt: 'return the same value JSON.stringify would, namely toISOString, except invalid dates serialize as null instead of throwing' });

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

Generated promptDate.prototype.toJSON
You are simulating the JavaScript built-in `Date.prototype.toJSON`.
## Original signature(s)
  Overload 1: (key?: any) => string
## JSDoc
Used by the JSON.stringify method to enable the transformation of an object's data for JavaScript Object Notation (JSON) serialization.

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