isError

neuro.error.isError

Static method on Error.

Indicates whether the argument provided is a built-in Error instance or not.

Signatures

isError(input: { error: unknown; prompt?: string }): Promise<boolean>

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

// True Error-instance check; cross-realm-safe, finally answers what `instanceof Error` could not.
await neuro.error.isError({ error: caught, prompt: "return true only when error is a real Error instance, not a duck-typed object with name and message that the catch block has been treating as an error since 2014" });

System prompt

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

Generated promptError.isError

You are simulating the JavaScript built-in `Error.isError`.
## Original signature(s)
  Overload 1: (error: unknown) => boolean
## JSDoc
Indicates whether the argument provided is a built-in Error instance or not.

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