#general
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/billingRaw Error:
{
"url": "localhost/v1/groq/β¦/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
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! Iβve 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 Iβd 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, itβs 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:
context_too_longGroq reports ~40,000 requested tokens despite the prompt being only a few characters.
Example:
Request too large for model llama-3.1-8b-instant. Requested 40280 tokens.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?
Read-only live mirror of Archestra.AI Slack
πJoin the discussion withAI enthusiasts!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/billingRaw Error:
{
"url": "localhost/v1/groq/β¦/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
13 replies
Hey Liberty! The error is clear β your conversation hit Groq's free tier token limit (12K TPM, you're requesting 35K). *Quick fixes: 1. Start a new chat β the easiest option, clears the context 2. Use a different provider β switch to OpenAI or Anthropic in your agent settings instead of Groq 3. Upgrade Groq* β if you want to stick with Groq, their Dev Tier has higher limits The "de-auto-select model" won't help here since the issue is the conversation length, not the model choice. A fresh chat should get you going immediately! π€ Slack Agent
fresh chatr did not fix it
Sorry, I encountered an error processing your request. π€ Slack Agent Β· Failed after 3 attempts. Last error: Overloaded
new chat did not fix it
Sorry, I encountered an error processing your request. π€ Slack Agent Β· Failed after 3 attempts. Last error: Overloaded
I also faced this new chat issue and it is not fixing
That's frustrating! If new chat isn't clearing it, could be: 1. *Large system prompt β check if your agent has a very long system prompt eating up tokens 2. Tool outputs β if tools return huge payloads, that counts toward the limit 3. Caching issue β try hard refresh (Ctrl+Shift+R) or clear browser cache Quickest workaround:* Switch provider from Groq to OpenAI or Anthropic in your agent's model settings β they have much higher token limits. Can you share which agent you're using? π€ Slack Agent
:mute:1
Happy to help! Could you please provide info on the Archestra version you were running when experienced this issue?
@user @user ^
Fix is in latest main. Please, update your local archestra repo to the last main and the issue should be gone π
P.S. These free Groq models indeed have fairly limited context window, so be careful with tools you load, and your context management in general when using them.
@user @user ^
@user and @user: Hi Mark,
I updated to the latest main and restarted Archestra.
The token count dropped slightly (from 40k to 38k), but the issue still occurs.
Even with a prompt containing only "Hello", Groq reports:
Requested 38405 tokens
Session: 5d94567c-ef3f-4cd9-a892-26cff43f02de
Agent: My Assistant
Is there a way to inspect what context is being attached to the request or completely reset the agent/workspace state?
I'm wondering if there may be old project context, tools, or memory still being included automatically.
Replied in dm
Got it β thanks for following up directly with Attharva, Mark! π€ Slack Agent
:mute:1