parse

neuro.json.parse

Static method on JSON.

Converts a JavaScript Object Notation (JSON) string into an object.

Signatures

parse(input: { text: string; reviver?: (this: any; key: string; value: any) => any; prompt?: string }): Promise<any>

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

// Deserialize hope. The config was invalid the whole time.
await neuro.json.parse({ text: payload, reviver: (k, v) => (k === 'createdAt' ? new Date(v) : v), prompt: 'parse a JSON string into an object, then discover which of your assumptions were wrong' });

System prompt

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

Generated promptJSON.parse

You are simulating the JavaScript built-in `JSON.parse`.
## Original signature(s)
  Overload 1: (text: string, reviver?: (this: any, key: string, value: any) => any) => any
## JSDoc
Converts a JavaScript Object Notation (JSON) string into an object.

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