Describe the problem/error/question
Running a workflow in live triggered by a WebHook provides an error, when I execute a test it works fine, but automations after live breaks.
What is the error message (if any)?
{
“errorMessage”: “Bad request - please check your parameters”,
“errorDescription”: “We could not parse the JSON body of your request. (HINT: This likely means you aren’t using your HTTP library correctly. The OpenAI API expects a JSON payload, but what was sent was not valid JSON. If you have trouble figuring out how to fix this, please contact us through our help center at help.openai.com.)”,
“errorDetails”: {},
“n8nDetails”: {
“time”: “2/5/2025, 10:09:57 AM”,
“n8nVersion”: “1.76.2 (Self Hosted)”,
“binaryDataMode”: “default”,
“cause”: {
“status”: 400,
“headers”: {
“alt-svc”: “h3=”:443"; ma=86400",
“cf-cache-status”: “DYNAMIC”,
“cf-ray”: “90d482d6a9f4ebed-SJC”,
“connection”: “keep-alive”,
“content-length”: “443”,
“content-type”: “application/json; charset=utf-8”,
“date”: “Wed, 05 Feb 2025 17:09:57 GMT”,
“server”: “cloudflare”,
“set-cookie”: “__cf_bm=JGfwy1fwj2WtUw8kFKT_91UY27XiWd05EQT4J6TEhVs-1738775397-1.0.1.1-Ds28tL59SaY4Yg3bvJ.SPYVt2aOVCofRlL4avtuI.oPlWrcAbdKg77kf2TfTyTlhFybbmM6oV4XibiuFVY.uOw; path=/; expires=Wed, 05-Feb-25 17:39:57 GMT; domain=.api.openai.com; HttpOnly; Secure; SameSite=None, _cfuvid=knWkElZNHUao4JW_pZo_uM3aBpXmlcZ8dU7_0nky5Jk-1738775397017-0.0.1.1-604800000; path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None”,
“strict-transport-security”: “max-age=31536000; includeSubDomains; preload”,
“vary”: “Origin”,
“x-content-type-options”: “nosniff”,
“x-request-id”: “req_0e94df1c9b6a8afa43d98799f22efada”
},
“request_id”: “req_0e94df1c9b6a8afa43d98799f22efada”,
“error”: {
“message”: “We could not parse the JSON body of your request. (HINT: This likely means you aren’t using your HTTP library correctly. The OpenAI API expects a JSON payload, but what was sent was not valid JSON. If you have trouble figuring out how to fix this, please contact us through our help center at help.openai.com.)”,
“type”: “invalid_request_error”,
“param”: null,
“code”: null
},
“code”: null,
“param”: null,
“type”: “invalid_request_error”,
“attemptNumber”: 1,
“retriesLeft”: 2
}
}
}
Please share your workflow/screenshots/recording
(Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.)
⚠️ WARNING ⚠️ If you have sensitive data in your workflow (like API keys), please remove it before sharing.
{
“nodes”: [
{
“parameters”: {
“promptType”: “define”,
“text”: “=Name of the Book: {{ $json[‘Idea (from Book)’][0] }}\nThe research data you need for the book: {{ $json[‘Research (from Book)’][0] }}\n\n=== CHAPTER ====\nName of the chapter: {{ $json[‘Chapter Name’] }}\n\nResearch about the chapter: {{ $json.Research }}\n\n========= PERFECT NOW WRITE THE CONTENT FOR THE CHAPTER\n”,
“options”: {
“systemMessage”: “=You’re a world class book writer with half a century of experience weaving words that connects with people, you’ll be given specific tasks to write chapters for books, you’ll be given research and the idea, description of the chapter, and you’ll have to comeup with the adecuate anount of content necesary to sake the chapter gold, you*ll filter through all the information and will write the chapter as it connects.\n\nWrite the content in markdown, It’s should be a long chapter and you’ll have to do your word magic to write the chapter in this book.”
}
},
“type”: “@n8n/n8n-nodes-langchain.agent”,
“typeVersion”: 1.7,
“position”: [
740,
580
],
“id”: “1e05e577-248e-4229-8a7b-4a2447da868f”,
“name”: “AI Agent2”
}
],
“connections”: {
“AI Agent2”: {
“main”: [
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “dad6575cdc9fb918369bf30cc4905e540fd7e5a48ee08d02082f1e7d7a2abd1c”
}
}
{
“nodes”: [
{
“parameters”: {
“model”: {
“__rl”: true,
“value”: “gpt-4o”,
“mode”: “list”,
“cachedResultName”: “gpt-4o”
},
“options”: {}
},
“type”: “@n8n/n8n-nodes-langchain.lmChatOpenAi”,
“typeVersion”: 1.2,
“position”: [
340,
780
],
“id”: “cd5f4690-5a64-41ba-9329-6f3b7faf692f”,
“name”: “ChatGPT LGE”,
“credentials”: {
“openAiApi”: {
“id”: “lMR6ozBbqztOHaBi”,
“name”: “OpenAi V2 - LGE”
}
}
}
],
“connections”: {
“ChatGPT LGE”: {
“ai_languageModel”: [
]
}
},
“pinData”: {},
“meta”: {
“templateCredsSetupCompleted”: true,
“instanceId”: “dad6575cdc9fb918369bf30cc4905e540fd7e5a48ee08d02082f1e7d7a2abd1c”
}
}
Share the output returned by the last node
Debug info
core
- n8nVersion: 1.76.2
- platform: docker (self-hosted)
- nodeJsVersion: 20.18.2
- database: postgres
- executionMode: scaling
- concurrency: -1
- license: enterprise (production)
storage
- success: all
- error: all
- progress: false
- manual: true
- binaryMode: memory
pruning
- enabled: true
- maxAge: 336 hours
- maxCount: 10000 executions
client
- userAgent: mozilla/5.0 (macintosh; intel mac os x 10_15_7) applewebkit/537.36 (khtml, like gecko) chrome/132.0.0.0 safari/537.36
- isTouchDevice: false
Log on Railways show:
Worker started execution 379 (job 55)
400 We could not parse the JSON body of your request. (HINT: This likely means you aren’t using your HTTP library correctly. The OpenAI API expects a JSON payload, but what was sent was not valid JSON. If you have trouble figuring out how to fix this, please contact us through our help center at help.openai.com.)
n8n Version: 1.76.3
Database: Postgres
n8n EXECUTIONS_PROCESS setting: own
Running n8n via Railway.com
Operating system: Linux
