Firstly, let me just say I get it this is very new so I understand there will be issues and the devs are trying their best.
I’ve been trying to get the prototyper chat to work but it’s not working, in the little drop down menu it says this:
[GoogleGenerativeAI Error]: Error fetching from https://monospace-pa.googleapis.com/v1/models/gemini-2.5-pro-preview-03-25:streamGenerateContent?alt=sse: [400 Bad Request] Request contains text fields that are too large.
My app also utilizes gemini and it won’t work anymore (maybe related) and it says this:
It’s not finding the model, even though it’s clearly visible in genkit.ts:
import { genkit } from 'genkit';
import { googleAI } from '@genkit-ai/googleai';
export const ai = genkit({
plugins: [googleAI()],
model: 'gemini-1.5-flash-latest',
});
I’ve tried different models but with no luck.
To be clear, I don’t know if the two are related, I’m just trying to give as much context as possible.
- My gemini api key is correct
- my environment variables are correct
- I’ve tried caching, different browser
- I’ve tried reset VM
- The server log just tells me the model is wrong, but no specifics on why or what to use instead.
Before the prototyper chat died, I did put a long message in it which was the first crash, so that aligns with the error message at the top, but follow up smaller messages are also getting treated the same.
I’ve seen a lot of people with this problem and I know there’s no official fix right now, just wanted to share that I’m also having a problem with the prototyper chat.