Arjun in #general: "Hi team, I've been stuck on this for a while. Here's my issue. I've an agent called "head" that assigns work to other subagents each responsible for ..." | Archestra Community | Archestra

Star us on GitHub ⭐

Star us on GitHub ⭐

Messages in #general

Arjun — February 12, 2026

Hi team, I've been stuck on this for a while. Here's my issue. I've an agent called "head" that assigns work to other subagents each responsible for certain MCP tooling. There subagents are working perfectly and I have no qualms with their chats or their MCP tooling. Now, when I try to go to "head" and send a message to try and use the subagents, it throws an error. {"code":"unknown","message":"An unexpected error occurred. Please try again.","isRetryable":false,"originalError":{"provider":"cerebras","message":"Error: LLM Provider API key not configured. Please configure it in Chat Settings.","type":"Error","raw":{}}} For additional context, keys are already configured in the following places -> the main settings, each agent setting also has the API key selected (including "head" itself). Remediation tried -> docker restart, change API keys, clear out the cache, check env, do the whole thing again from scratch. Am I using subagents wrong? As per my general understanding of subagents this is how it's supposed to be. There is nothing to say otherwise in the docs as well. Of course, I can get my project to work by putting all the tools in a single chat (and it does) but that doesn't fully calm my curiosity. Appreciate what you guys do, cheers.

Arjun — February 12, 2026

Additionally, I would like to add that head works without the tool calling. So no issues from the API key end here.

Innokentii Konstantinov (archestra team) — February 12, 2026

What version of archestra are you running? You should see it at the very bottom of archestra Also, you are using cerebras provider, right? Are there any other api keys confugured?

Arjun — February 12, 2026

Archestra - Version: 1.0.42 No other keys configured.

Innokentii Konstantinov (archestra team) — February 12, 2026

Could you please send a screenshots of your keys page and how subagent is configured? Of course if it's comfortable for you

Innokentii Konstantinov (archestra team) — February 12, 2026

Also, I would be happy to jump on a call with you ti debug this

Innokentii Konstantinov (archestra team) — February 12, 2026

In the meanwhile, while I'm investigating the problem, try to set ARCHESTRA_CHAT_CEREBRAS_API_KEY env var, it might help

Arjun — February 12, 2026

attached - keys page, head agent, one of the subagents (analyst), agent builder I ran the below command, still the same issue. docker pull archestra/platform:latest; docker run -p 9000:9000 -p 3000:3000 \ -e ARCHESTRA_QUICKSTART=true \ -e ARCHESTRA_CHAT_CEREBRAS_API_KEY="key" \ -v /var/run/docker.sock:/var/run/docker.sock \ -v archestra-postgres-data:/var/lib/postgresql/data \ -v archestra-app-data:/app/data \ archestra/platform;

Innokentii Konstantinov (archestra team) — February 12, 2026

I think I found a root cause, will release a fix in a hour

Arjun — February 12, 2026

wow that's rapid, do let me in on this.

Innokentii Konstantinov (archestra team) — February 12, 2026

sure, I'll ping you once it's live

Innokentii Konstantinov (archestra team) — February 12, 2026

Release 1.0.43 is here. It should fix this problem. We inferred provider from model name incorrectly for cerebras and were failing to resolve an API key. Please, give it a try 🙂

Arjun — February 12, 2026

yes, fixed!

#general

Feb 11February 12, 2026Feb 13 Latest

Thursday, February 12

akash6:46 AMOpen in Slack

Hi is any other way to deploy the application just the chat bot or agents part not deploying the whole application

Arjun10:34 AMOpen in Slack

Hi team, I've been stuck on this for a while. Here's my issue.

I've an agent called "head" that assigns work to other subagents each responsible for certain MCP tooling. There subagents are working perfectly and I have no qualms with their chats or their MCP tooling.

Now, when I try to go to "head" and send a message to try and use the subagents, it throws an error.

{"code":"unknown","message":"An unexpected error occurred. Please try again.","isRetryable":false,"originalError":{"provider":"cerebras","message":"Error: LLM Provider API key not configured. Please configure it in Chat Settings.","type":"Error","raw":{}}}

For additional context, keys are already configured in the following places -> the main settings, each agent setting also has the API key selected (including "head" itself).

Remediation tried -> docker restart, change API keys, clear out the cache, check env, do the whole thing again from scratch.

Am I using subagents wrong? As per my general understanding of subagents this is how it's supposed to be. There is nothing to say otherwise in the docs as well.

Of course, I can get my project to work by putting all the tools in a single chat (and it does) but that doesn't fully calm my curiosity. Appreciate what you guys do, cheers.

veer adyani11:40 AMOpen in Slack

Hello everyone

The project submission link is live on the website

❤️1

Have a look

Pathan Aymaan12:21 PMOpen in Slack

Hi Archestra team — I’m running archestra/platform:latest via Docker and hitting an error when trying to create a Personal Token and call an A2A agent endpoint.

Issue: Personal token creation fails and A2A auth doesn’t work.

Error returned:

{

"jsonrpc": "2.0",

"id": 1,

"error": {

"code": -32603,

"message": "Failed query: insert into \"usertoken\" (\"id\", \"organizationid\", \"userid\", \"name\", \"secretid\", \"tokenstart\", \"createdat\", \"lastusedat\") values (default, $1, $2, $3, $4, $5, default, default) returning \"id\", \"organizationid\", \"userid\", \"name\", \"secretid\", \"tokenstart\", \"createdat\", \"lastusedat\"\nparams: default-org,system,Personal Token,7aff233b-0062-4f29-9464-74d09078023a,archestra81fa"

}

}

Archestra App12:35 PMOpen in Slack

New release! 🚀🚀🚀

1.0.43 (2026-02-12)

Bug Fixes

do not rely on model name in a2a executor (#2758) (22cc91c)

Innokentii Konstantinov (archestra team)1:21 PMOpen in Slack

⚠️ Quick Announcement ⚠️ Update to version 1.0.43 if you had issues with calling subagents from the parent agent.

We’ve fixed the issue when calling subagent from parent agent resulted in LLM Provider API key not configured. Please configure it in Chat Settings error.

Thanks everyone for reporting this bug!

🚀4❤️1🙌1

Pathan Aymaan3:36 PMOpen in Slack

Hi team — I'm testing an A2A *sub-agent* locally and getting an empty response from message/send.

The request succeeds and returns a messageId, but parts.text is empty in the result.

Endpoint: <http://localhost:9000/v1/a2a/333c740d-7abe-4c8e-b624-17f7dc4beb46>

I’m attaching a screenshot of the request/response.

Is there any additional config or step required for sub-agents to return text output?

Response:

{

"jsonrpc": "2.0",

"id": 1,

"result": {

"messageId": "msg-1770910322166-4ok4ag8",

"role": "agent",

"parts": [

{

"kind": "text",

"text": ""

}

]

}

}

Join Slack to see the image

sufyaan khateeb6:35 PMOpen in Slack

We are trying to configure archestra with ollama llm but we are getting an error, any idea how to resolve this

sufyaan khateeb9:02 PMOpen in Slack

Getting this error when trying to add any mcp in the mcp registry

Join Slack to see the image

Read-only live mirror of Archestra.AI Slack

👋Join the discussion withAI enthusiasts!

Thread

Arjun10:34 AMOpen in Slack

Hi team, I've been stuck on this for a while. Here's my issue.

I've an agent called "head" that assigns work to other subagents each responsible for certain MCP tooling. There subagents are working perfectly and I have no qualms with their chats or their MCP tooling.

Now, when I try to go to "head" and send a message to try and use the subagents, it throws an error.

{"code":"unknown","message":"An unexpected error occurred. Please try again.","isRetryable":false,"originalError":{"provider":"cerebras","message":"Error: LLM Provider API key not configured. Please configure it in Chat Settings.","type":"Error","raw":{}}}

For additional context, keys are already configured in the following places -> the main settings, each agent setting also has the API key selected (including "head" itself).

Remediation tried -> docker restart, change API keys, clear out the cache, check env, do the whole thing again from scratch.

Am I using subagents wrong? As per my general understanding of subagents this is how it's supposed to be. There is nothing to say otherwise in the docs as well.

Of course, I can get my project to work by putting all the tools in a single chat (and it does) but that doesn't fully calm my curiosity. Appreciate what you guys do, cheers.

12 replies

Arjun10:39 AMOpen in Slack

Additionally, I would like to add that head works without the tool calling. So no issues from the API key end here.

Innokentii Konstantinov (archestra team)10:42 AMOpen in Slack

What version of archestra are you running? You should see it at the very bottom of archestra

Also, you are using cerebras provider, right? Are there any other api keys confugured?

Join Slack to see the image

Arjun10:42 AMOpen in Slack

Archestra - Version: 1.0.42

No other keys configured.

Innokentii Konstantinov (archestra team)10:56 AMOpen in Slack

Could you please send a screenshots of your keys page and how subagent is configured? Of course if it's comfortable for you

Innokentii Konstantinov (archestra team)10:58 AMOpen in Slack

Also, I would be happy to jump on a call with you ti debug this

Innokentii Konstantinov (archestra team)10:59 AMOpen in Slack

In the meanwhile, while I'm investigating the problem, try to set ARCHESTRACHATCEREBRASAPIKEY env var, it might help

Arjun12:05 PMOpen in Slack

attached - keys page, head agent, one of the subagents (analyst), agent builder

I ran the below command, still the same issue.

docker pull archestra/platform:latest;

docker run -p 9000:9000 -p 3000:3000 \

-e ARCHESTRA_QUICKSTART=true \

-e ARCHESTRACHATCEREBRASAPIKEY="key" \

-v /var/run/docker.sock:/var/run/docker.sock \

-v archestra-postgres-data:/var/lib/postgresql/data \

-v archestra-app-data:/app/data \

archestra/platform;

Join Slack to see the image

Innokentii Konstantinov (archestra team)12:05 PMOpen in Slack

I think I found a root cause, will release a fix in a hour

Arjun12:08 PMOpen in Slack

wow that's rapid, do let me in on this.

Innokentii Konstantinov (archestra team)12:08 PMOpen in Slack

sure, I'll ping you once it's live

Innokentii Konstantinov (archestra team)12:46 PMOpen in Slack

Release 1.0.43 is here. It should fix this problem. We inferred provider from model name incorrectly for cerebras and were failing to resolve an API key.

Please, give it a try 🙂

Arjun1:07 PMOpen in Slack

yes, fixed!

🙌1