Hi,

Sharing two exact errors I hit today building on Archestra: with *Cerebras, a model call failed with Status: 402, Type: unknown_api_error, Message: "402 status code (no body)" — no further detail in the response. With Groq* (Llama 3.3 70B), even in a fresh chat with a short prompt, I got Status: 413, Type: api_payload_too_large_error, Message: "Request body too large: 0.0 MB (limit 70 MB). Use a smaller attachment, or raise ARCHESTRA_API_BODY_LIMIT." — the reported size (0.0 MB) doesn't match the "too large" error. Posting in case others have hit the same and can point to a cause — happy to share full raw JSON for either if useful.

hey .. actually I got another issue .. after stopping the record and saving the prompt and so on when I try to download it it just says it will be exported once it's ready and you download it but nothing got out to be saved on my device and when I try to submit the thing it says sign in to github and once I press it another screen shows that I didn't define the prompt or whatever even tho that I chose the chat messages about the prompt and cut the recording to 30 secs ... is that normal and is it happening with all or I'm missing smth ?

Hi , I am trying to create an app, but the agent says it has scaffolded the app but it doesnt persist the files. Is anyone else facing this issue ?

Heyy

Hitting persistent rate-limit issues while testing app builds in

Archestra — bounced between OpenRouter (empty responses, then a 402

credits error even though I only asked for a simple test app) and

Gemini free tier (RESOURCE_EXHAUSTED after just ~5 requests). Wondering

if there's a recommended provider/model combo for hackathon use that

has more reasonable free-tier limits for iterative app building, since

retrying a few times during testing burns through quota fast. Any

suggestions?

Hello, is there already a ready-made solution for using ArchestrA in a multi-tenant format? Specifically, we would like a single installation to serve multiple companies within the group. Is this possible yet?

Running into repeated LLM provider issues while building an app in

Archestra — tried OpenRouter (empty responses, then a 402 error saying

it requested 32,768 max_tokens but my free account can only afford

1,600-4,000 depending on the moment), Gemini free tier (rate-limited

after ~5 requests), and OpenAI (empty response with no clear reason).

The OpenRouter 32k max_tokens default seems like it might be worth

lowering for free-tier accounts, or exposing as an easy setting — right

now it silently fails instead of scaling down. Is there a way to

configure max_tokens per-model, or a recommended provider/model combo

that works reliably on free tiers for iterative app building?

Hi

Is archestra.app down right now? Getting repeated Cloudflare 522

"connection timed out" errors when trying to open apps I've built via

the chat — happening consistently across multiple different apps and

LLM providers over the last few hours, so it doesn't seem related to

my setup. App builds succeed in chat, but the preview link always

522s. Anyone else seeing this, or any workaround to view apps while

it's down? so any info helps.