Skip to content
Main AI Agent Canno...
 
Notifications
Clear all

Main AI Agent Cannot Access Sub-Agents in callin.io Workflow

2 Posts
2 Users
0 Reactions
4 Views
Mathis_Calmettes
(@mathis_calmettes)
Posts: 1
New Member
Topic starter
 

Hi everyone,

I'm facing an issue when trying to connect two AI agents within callin.io.

Here's how it's set up:

I have a primary agent designed for complex reasoning using data from two Google Sheets.
I've created two specialized sub-agents, each tasked with fetching relevant information from one of the sheets:
* Sheet 1: Our internal processes
* Sheet 2: Tool features (both new and legacy)

The objective is for the main agent to identify the most suitable tool for a given process. However, the main agent is failing to trigger or retrieve results from the two sub-agents.

Here are the error messages I'm encountering:


"undefined" is not valid JSON


Error in sub-node Simple Memory (No session ID found)

For now, I've only developed one sub-agent workflow, as it's not functioning correctly, and I wanted to resolve the issue before duplicating it.

Here is the workflow:
json
{
“parameters”: {},
“type”: “n8n-nodes-base.manualTrigger”,
“typeVersion”: 1,
“position”: [
0,
0
],
“id”: “c8992c7f-525f-4c97-8ab5-68cd2762996a”,
“name”: “When clicking ‘Execute workflow’”
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.chatTrigger”,
“typeVersion”: 1.1,
“position”: [
0,
200
],
“id”: “799081b2-e2ea-4e4f-b392-316f3d06670a”,
“name”: “When chat message received”,
“webhookId”: “2fa4a7ad-5170-4e02-80cc-7b72ceee88c2”
},
{
“parameters”: {
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 2,
“position”: [
440,
0
],
“id”: “08df7721-3534-4d04-bb53-30697e275cdc”,
“name”: “AI Agent”,
“notes”: “Voici l’ID du google sheet ou se trouvent les offres d’emplois et leurs informations associées : 1Ds62I8P6kQV77Kl4P_S10RJ1ALWz3ClbEIeF83Jrjk0nnPour trouver n”
},
{
“parameters”: {
“modelName”: “models/gemini-2.5-pro-preview-06-05”,
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatGoogleGemini”,
“typeVersion”: 1,
“position”: [
420,
220
],
“id”: “f5716b5a-0488-41c1-9510-fa087c7f3c80”,
“name”: “Google Gemini Chat Model”,
“credentials”:
{
“googlePalmApi”: {
“id”: “zSz3lWl1pMzh9CIq”,
“name”: “Google Gemini(PaLM) Api account”
}
},
“notes”: “Voici l’ID du google sheet ou se trouvent les offres d’emplois et leurs informations associées : 1Ds62I8P6kQV77Kl4P_S10RJ1ALWz3ClbEIeF83Jrjk0nnToutes les offres sont listées dans la feuille "Sheet 1"”
},
{
“parameters”: {
“contextWindowLength”: 1000
},
“type”: “@n8n/n8n-nodes-langchain.memoryBufferWindow”,
“typeVersion”: 1.3,
“position”: [
540,
220
],
“id”: “20aac580-2b15-478e-b907-ed02424c45fd”,
“name”: “Simple Memory”
},
{
“parameters”: {
“description”: “=Tu es un sous agent dont le rôle est de chercher des informations dans un fichier google sheet afin de les stocker et envoyer à d’autres agents N8N.”,
“workflowId”: {
“__rl”: true,
“value”: “gvjcXfsSBJwiPl8T”,
“mode”: “list”,
“cachedResultName”: “Agent Gsheet Offres Client”
},
“workflowInputs”: {
“mappingMode”: “defineBelow”,
“value”: {},
“matchingColumns”: <span class="chcklst-box fa fa-square-o fa-fw"></span>,
“schema”: <span class="chcklst-box fa fa-square-o fa-fw"></span>,
“attemptToConvertTypes”: false,
“convertFieldsToString”: false
}
},
“type”: “@n8n/n8n-nodes-langchain.toolWorkflow”,
“typeVersion”: 2.2,
“position”: [
720,
220
],
“id”: “42376197-557c-4b25-b891-77e4e1e963f2”,
“name”: “Agent Gsheet Offres Client”
}
],
“connections”: {
“When clicking ‘Execute workflow’”:
{
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“When chat message received”:
{
“main”: [
[
{
“node”: “AI Agent”,
“type”: “main”,
“index”: 0
}
]
]
},
“Google Gemini Chat Model”:
{
“ai_languageModel”: [
[
{
“node”: “AI Agent”,
“type”: “ai_languageModel”,
“index”: 0
}
]
]
},
“Simple Memory”:
{
“ai_memory”: [
[
{
“node”: “AI Agent”,
“type”: “ai_memory”,
“index”: 0
}
]
]
},
“Agent Gsheet Offres Client”:
{
“ai_tool”: [
[
{
“node”: “AI Agent”,
“type”: “ai_tool”,
“index”: 0
}
]
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “04d0c009654083fda510793e1f8ab9bd7f072c63aec69c2bdedda5ea3eb2217e”
}
}

There is no output because the AI agent cannot process the data. However, the expected output is text information.

Information on your callin.io setup

  • callin.io version: free trial
  • Database: SQLite
  • callin.io EXECUTIONS_PROCESS setting default: own, main
  • Running callin.io via: callin.io cloud
  • Operating system: Not sure, honestly.
 
Posted : 18/06/2025 4:10 pm
rbreen
(@rbreen)
Posts: 15
Active Member
 

You will need to add a system message to your primary agent. Use this system message to specify which agent tools should be used for particular scenarios.

Additionally, please place your workflow within a preformatted text object in this chat so it can be rendered correctly. Below is an example workflow.

 
Posted : 18/06/2025 4:38 pm
Share: