No option to skip Firecrawl in `node_modules/@librechat/agents/src/tools/search/search.ts`

[nicholas-johnson-techxcel]

Firecrawl is not actually needed - search works properly without it. Yes, we can self-host it but that does not change the fact that I find that the API be extremely unreliable and poorly documented

It incorrectly asserts:

    throw new Error('Firecrawl scraper instance is required');

And this not being in the same repo as LibreChat, it requires us to bypass these issues with middleware handlers, rather than it just accepting a null scraper and skipping that step.