Why does “Continue (using error output)” on OpenAI v2 not pass the full error body to the next node?

[Jelle]

Describe the problem/error/question

I’m using the OpenAI v2 node with On Error → Continue (using error output).
In the execution UI I can see the detailed error under Error details → From OpenAI as:

{
  "errorMessage": "Bad request - please check your parameters",
  "errorDescription": "Your input exceeds the context window of this model. Please adjust your input and try again.",
  "errorDetails": {
    "rawErrorMessage": [
      "400 - {\"error\":{\"message\":\"Your input exceeds the context window of this model. Please adjust your input and try again.\",\"type\":\"invalid_request_error\",\"param\":\"input\",\"code\":\"context_length_exceeded\"}}"
    ],
    "httpCode": "400"
  }
}

However, what actually reaches the next node as {{ $json }} in my workflow is only:

{
  "error": "Bad request - please check your parameters"
}

There are no other fields like errorMessage, errorDescription, errorDetails, or the original OpenAI error object. This means I can only do:

{{ $json.error === 'Bad request - please check your parameters' }}

but I cannot check for the OpenAI error code (for example context_length_exceeded), because that information is not present in the item that is passed on.

I would like to have the full OpenAI error body (including the code field) available in the error item that is sent to the next node, so that I can do something like:

{{ $json.errorDetails.rawErrorMessage.code === 'context_length_exceeded' }}

Is there a way to have the full OpenAI error body (including the code field) available in $json of the error item, instead of just a single error string?

Share the output returned by the last node

{
  "errorMessage": "Bad request - please check your parameters",
  "errorDescription": "Your input exceeds the context window of this model. Please adjust your input and try again.",
  "errorDetails": {
    "rawErrorMessage": [
      "400 - {\"error\":{\"message\":\"Your input exceeds the context window of this model. Please adjust your input and try again.\",\"type\":\"invalid_request_error\",\"param\":\"input\",\"code\":\"context_length_exceeded\"}}"
    ],
    "httpCode": "400"
  },
  "n8nDetails": {
    "nodeName": "Text1",
    "nodeType": "@n8n/n8n-nodes-langchain.openAi",
    "nodeVersion": 2,
    "resource": "text",
    "operation": "response",
    "itemIndex": 0,
    "time": "17-11-2025, 11:21:32",
    "n8nVersion": "1.119.2 (Self Hosted)",
    "binaryDataMode": "default",
    "stackTrace": [
      "NodeApiError: Bad request - please check your parameters",
      "    at ExecuteContext.requestWithAuthentication (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_@[email protected]_@[email protected]_08b575bec2313d5d8a4cc75358971443/node_modules/n8n-core/src/execution-engine/node-execution-context/utils/request-helper-functions.ts:1498:10)",
      "    at processTicksAndRejections (node:internal/process/task_queues:105:5)",
      "    at ExecuteContext.requestWithAuthentication (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_@[email protected]_@[email protected]_08b575bec2313d5d8a4cc75358971443/node_modules/n8n-core/src/execution-engine/node-execution-context/utils/request-helper-functions.ts:1798:11)",
      "    at ExecuteContext.apiRequest (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/@n8n+n8n-nodes-langchain@file+packages+@n8n+nodes-langchain_ec7fbe0da3d2dc5c86e61be805f9ba74/node_modules/@n8n/n8n-nodes-langchain/nodes/vendors/OpenAi/transport/index.ts:56:9)",
      "    at ExecuteContext.execute (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/@n8n+n8n-nodes-langchain@file+packages+@n8n+nodes-langchain_ec7fbe0da3d2dc5c86e61be805f9ba74/node_modules/@n8n/n8n-nodes-langchain/nodes/vendors/OpenAi/v2/actions/text/response.operation.ts:607:18)",
      "    at ExecuteContext.router (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/@n8n+n8n-nodes-langchain@file+packages+@n8n+nodes-langchain_ec7fbe0da3d2dc5c86e61be805f9ba74/node_modules/@n8n/n8n-nodes-langchain/nodes/vendors/OpenAi/v2/actions/router.ts:58:25)",
      "    at ExecuteContext.execute (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/@n8n+n8n-nodes-langchain@file+packages+@n8n+nodes-langchain_ec7fbe0da3d2dc5c86e61be805f9ba74/node_modules/@n8n/n8n-nodes-langchain/nodes/vendors/OpenAi/v2/OpenAiV2.node.ts:89:10)",
      "    at WorkflowExecute.executeNode (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_@[email protected]_@[email protected]_08b575bec2313d5d8a4cc75358971443/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1093:8)",
      "    at WorkflowExecute.runNode (/usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_@[email protected]_@[email protected]_08b575bec2313d5d8a4cc75358971443/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1274:11)",
      "    at /usr/local/lib/node_modules/n8n/node_modules/.pnpm/n8n-core@file+packages+core_@[email protected]_@[email protected]_08b575bec2313d5d8a4cc75358971443/node_modules/n8n-core/src/execution-engine/workflow-execute.ts:1708:27"
    ]
  }
}

Information on your n8n setup

• n8n version: 1.119.2 (Self Hosted)
• Running n8n via: Docker

[mohamed3nan]

Hello @Jelle

@Jelle

I would like to have the full OpenAI error body (including the code field) available in the error item that is sent to the next node

@Jelle

Is there a way to have the full OpenAI error body (including the code field) available in $json of the error item, instead of just a single error string?

In this case, you’ll probably want to use On Error → Continue, then use an IF/Switch node to check whether an error occurred and parse the complete error message afterward.

[Jelle]

Hello @mohamed3nan,

On Error → Continue or On Error → Continue (using error output) gives the same minimal output:

[
  {
    "error": "Bad request - please check your parameters"
  }
]

[mohamed3nan]

Hi @Jelle

Yes indeed, I thought this would work until I tested it myself.

So as far as I know, there are two possible solutions I’m thinking of right now:

1. Use the HTTP Request node to call the OpenAI API, enable the “Never Error” option, then parse the response as described here:

How to get full HTTP request error message?

I had the exact same issue but with various other nodes. It seems that it is not specifically linked to the Xero API, but a limitation of how the nodes based on HTTP requests are handling the error messages when the error is caused by a HTTP response code (4xx, 5xx,…). Somehow, it does not return the full response but perform some sort of parsing and only provide some parts of the HTTP response body. This typically occur when the JSON returned by the query contain more than one message key or w…

2. Continue using the OpenAI node but use it in a sub-workflow, and set its On Error setting to “Stop Workflow”:

Then, in the main workflow, configure the sub-workflow’s setting On Error > Continue (using error output), then get the execution ID of the sub-workflow, use it to get execution information, and extract the full error object so that you can parse it as desired.

here is an example:

I know it seems like a complicated workaround, but this is what came to mind until there is a simpler built-in feature for this..