Hi, been having this repeated challenge for hours now, even after changing models, see debug error (tried to de-auto-select model but not activating)

Your conversation is too long. Please start a new chat or remove some messages.

Agent: My Assistant

Model: 3cbf7cf2-a4d6-4f99-b73a-348801f7****

Provider: groq

Model source: auto-selected (best available)

Code: contexttoolong

Provider: groq

Status: 413

Type: apipayloadtoolargeerror

Message: Request too large for model llama-3.3-70b-versatile in organization org_01kxd8hjn4f7vtzgf55x2e48x9 service tier on_demand on tokens per minute (TPM): Limit 12000, Requested 35421, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at console.groq.com/settings/billing

Raw Error:

{

"url": "localhost/v1/groq/…/completions",

"statusCode": 413,

"isRetryable": false,

"responseBody": {

"error": {

"message": "Request too large for model llama-3.3-70b-versatile in organization org_01kxd8hjn4f7vtzgf55x2e48x9 service tier on_demand on tokens per minute (TPM): Limit 12000, Requested 35421, please reduce your message size and try again. Need more tokens? Upgrade to Dev Tier today at console.groq.com/settings/billing",

"type": "apipayloadtoolargeerror"

}

}

}

Session: c540c217-e47a-423c-a3a3-11998a0b718a

Trace: e8744659ee4413956dbe0ed71e30c13b

Span: 08758220ccd7eafe

new chat did not fix it

Hi, I only have a RuPay card, and both OpenRouter and OpenAI reject it with "This card type isn't accepted." Gemini now requires prepaid credits in my region. Is there a hackathon API key, sponsored credits, or another recommended provider that participants with RuPay cards can use?

Hi! I have a quick question regarding the submission. Are we allowed to include a voice-over narration in our demo video to explain the project and workflow, or is the submission expected to be screen recording only?

Thank you!

Hey guys! I’ve been testing out Archestra for a week. The main things I want to get working is to provide shared/curated skills with the rest of my team and provide them a way to share internal vibe-coded apps (I understand the feature is still in beta, I have some feedback that I’d love to share!). While testing some skills, in particular skills involving creating some HTML assets, I noticed that my agent uses archestra__run_command to write files. Problem with that is that I always hit a Error: command is too large (> 16384 bytes) error, and it forces the agent to unreliably find workarounds (once it tried rewriting the HTML file in small splits, forcing the content to be rewritten in small pages and links between them, another time it just zipped everything). I got the same when working with Apps, even more brutally given that, well, it’s all about apps. Is my agent misconfigured or is this a current limitation of Archestra?

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'm blocked by what appears to be an Archestra issue.

In a fresh session, even sending "Hello" fails with:

Groq reports ~40,000 requested tokens despite the prompt being only a few characters.

Example:

Has anyone seen this before or is there a way to clear/reset the app context?

When starting a conversation with a model like Gemini, for example, can't I switch to another one, like OpenAI's?

Hi everyone! I’m trying to submit my Archestra Apps Hackathon app, but the “Sign in with GitHub” button in the submission flow isn’t working when I click it. Has anyone faced this issue or knows how to fix it?

Hi @user Archestra is returning my prompt with description rather than building. Any special button to override

Hey Hackathon participants 👋

We’re seeing your submissions come in, and some of the apps look very cool!

Tomorrow is the final day of the Hackathon, so keep building and make sure to submit your app before the deadline.

And don’t forget about the $500 Community Buzz prize: share your app online - the post with the most likes or upvotes wins.

Hey

I'm getting this error on Groq even in a brand-new chat with a one-line prompt:

Request too large. Limit: 8000, Requested: 38458

It seems the system prompt + attached tools (GitHub, Playwright, etc.) exceed the model's context limit before my prompt is added.

Is this a known issue? Is there a way to reduce the tools sent per request or disable unused ones?

Also, I've already tried Gemini, OpenRouter, Cerebras, and ChatGPT. Are there any other free providers/models you recommend that work well with Archestra and tool-heavy workflows?

if I have a ChatGPT Plus/Codex subscription or a Claude Pro/Max subscription, is there any way to use those models inside Archestra without paying separately for API tokens, or do I need to use API keys for Anthropic/OpenAI?

What is this?

Annotations

2 errors

Canceling since a higher priority waiting request for hackathon-review-34 exists

Canceling since a higher priority waiting request for hackathon-review-34 exists

Hey @user ! Thanks for the suggestion 🙌

I tried switching to custom tools and enabled load tools progressively, then restarted Archestra, but the issue is still there.

Even with just "Hello", Groq is still getting a huge request:

Is there a way to fully reset the agent/workspace context or check what is being attached automatically? Seems like some old context/tools/memory might still be included.

Thanks!

hy i had the qiestion where how can we confirm what we had submitted the app correctly

Heads up, 💿 v1.3.19 has just landed and it contains fixes for the :joystick: Apps Hackathon Recorder for most of the issues you've been reporting. Please, update your 🐳 docker image to :latest or explicitly :1.3.19 and restart. :blackrightpointingtrianglewithdoublevertical_bar: Recording and submitting should work fine now.

hello! this message keeps popping up regardless of my prompts: No stream activity has been received for the last40seconds. The connection may have stalled. Stop and retry the response. If this keeps happening and your deployment uses a load balancer, verify that its streaming timeout is at least 5 minutes.Learn more in our documentation

I tried leaving a prompt running for 20 min and still no progress

Hi !! I updated my local Archestra Docker setup to v1.3.19 as suggested, and my previous account and apps are now restored successfully. However, I still don't see the Hackathon Recorder / Record button anywhere in the app, including inside my app.

HI Please close PR #45 as well. It was resubmitted before I corrected the description in the updated recorder. I will fix the description and submit once more.

Hi team, what is the exact closing time and time zone for our project submission today

Hi! I asked a few participants who have already submitted their apps, and I found that the people using v1.3.16 were able to use the Record button successfully, while some people on v1.3.18 were experiencing recording issues.

In my case, I initially saw the Record button on an older version, but the recording itself wasn't working. After the team mentioned that the recording issue was fixed in a newer release, I updated my Docker setup. However, after updating, the Record button itself disappeared.

I've since tried v1.3.16, v1.3.18, and the newer version again, but I still can't get the Record button to appear. I've also tried recreating the containers and reusing my existing volumes.

Could this be related to some persisted configuration, feature flag, or frontend state in my Docker volumes? Is there a recommended clean upgrade path or configuration I should follow to restore the Record button?

@user @user It's nice to participate in this hackathon, however, for me, and I guess for many others too, it's more of "navigating" the platform & co, and getting the model to responded as "expected" than actually fine-tuning your app swag. So in a nut shell, it's been platform-centric rather than on app-centric🙏

@user Your dm pls

How much time left for the hackathon?

i had done with my submission but the app was not in gallery

Last day of the Hackathon :unicorn_face:

Dear participants, you have 14 hours left to submit your apps! Submissions close today, July 29, at 23:59 UTC.

Don’t forget to enter the Community Buzz category: share your app online, include a link to it, and tag us so we can see your post.

I've finished building the app, but I'm confused about the submission process. The brief mentions a recording and submission option available within the chat/app interface, but I can't locate it anywhere in the Archestra UI (checked the app view, the "..." menu, and sidebar). Could you point me to where this recording/submission feature is, or clarify whether I should instead record my screen externally (e.g., via Xbox Game Bar/OBS) and submit the video link separately?

Hi mentors, my RouteForge submission is now live in the gallery and PR #45 has been merged:

However, the autogenerated description incorrectly describes it as a customer-support/email-drafting app.

Could you please replace only the description with:

“RouteForge is a privacy-aware MCP gateway that keeps sensitive or routine LLM requests local, redacts private data before permitted cloud processing, and returns an auditable receipt explaining every routing decision.”

The existing recording is correct and should remain unchanged. I have also posted this correction request on PR #45. Thank you!

@user after hitting the STOP BUTTON the recording refuses to load, it just continues in infinite loading.

My experience with Archestra AI has been exciting and insightful. The platform makes it easy to quickly build AI applications, but there are some areas that could be improved. The AI agent sometimes fails to fetch the latest information, and debugging issues can be challenging due to limited error details. Better real-time data handling, clearer logs, and improved troubleshooting support would make the platform more reliable and user-friendly.

Is today the last date of the hackathon? @user @user

Bug Report: Missing Record Option

I noticed that the application does not have a Record option, even though it is required for recording audio directly within the app. Because of this, I am unable to test or use features that depend on voice input.

Please check whether this is a bug or if the feature has not been implemented yet. Adding a Record option would greatly improve usability and allow users to complete voice-based workflows without relying on external tools.

I have a question: when we integrate an agent into Slack, how are its conversations and interactions handled within the system? Do they show up somewhere? Do they become sessions?

Is there anything in Git regarding plans to evolve the apps to support a backend and other languages, like Next.js?

Hi , The Repo Oracle is complete and submitted to the Archestra Apps Hackathon. The source code is available at github.com/jaswanth422/repo-oracle, and submission PR #68 is open and awaiting organizer review: github.com/archestra-ai/apps-gallery/pull/68. Thanks for all the support!

Hello! I have pngs imported into archestra for my game but it appears the recorder isn't capturing them. Can I record using outside tools?

Hi again lol, just wanted to say thank you to the Archestra team for hosting this hackathon! I truly had a wonderful time learning the Archestra platform but I did run into a few issues that slowed development. The biggest problem was that long-running responses would frequently get stuck with the “No stream activity has been received for the last 40 seconds” message, sometimes even for very small file edits, forcing me to restart the Docker container. Once a response got stuck, the chat would often become unusable because stopping or retrying didn’t always work. I also found it confusing to manage files between chat attachments and the workspace, especially when starting a new chat, since I had to reattach source files even though they already existed in the project. Finally, it would be really helpful to have more visibility into what Archestra is doing (reading files, editing, typechecking, rebuilding, etc.) so it’s easier to tell whether it’s still working or actually frozen. Despite these issues, I think the platform has a lot of potential and was genuinely enjoyable to build with!

Also side note, my PR for Tower of Nonsense was approved, but I don’t see it in the public gallery yet. Is there another publishing step or does the gallery take some time to update?

hey @user is it possible to extend the deadline by 12 hr more ?