Openai assistant, code interpreter, error: **[ERROR: Unexpected run status completed. Full run info:**

Dear Forum,

i hope you can help me solve this problem:

whenever i call an openai assistant (message an assistant) with the task to use the codeinterpreter i get these error message (regardless of the choosen llm model):

[ERROR: Unexpected run status completed. Full run info:

{ “id”: “run_OpZNilPHy08SkfWIJY1MMKpB”, “object”: “thread.run”, “created_at”: 1745407022, “assistant_id”: “asst_x4U9Yxd3VW4kPdDAfFBSzTVy”, “thread_id”: “thread_TND2rVlqLBc06qfPtOcDHAtM”, “status”: “completed”, “started_at”: 1745407023, “expires_at”: null, “cancelled_at”: null, “failed_at”: null, “completed_at”: 1745407034, “required_action”: null, “last_error”: null, “model”: “gpt-4.1-mini”, “instructions”: “your only task is to generate charts using the code interpreter tool.”, “tools”: [ { “type”: “code_interpreter” } ], “tool_resources”: {}, “metadata”: {}, “temperature”: 1, “top_p”: 1, “reasoning_effort”: null, “max_completion_tokens”: null, “max_prompt_tokens”: null, “truncation_strategy”: { “type”: “auto”, “last_messages”: null }, “incomplete_details”: null, “usage”: { “prompt_tokens”: 3212, “completion_tokens”: 315, “total_tokens”: 3527, “prompt_token_details”: { “cached_tokens”: 0 }, “completion_tokens_details”: { “reasoning_tokens”: 0 } }, “response_format”: { “type”: “text” }, “tool_choice”: “auto”, “parallel_tool_calls”: true }]

The assistant in the background completes the task correctly - i can download the generated files of the codeinterpreter via an http request.

If i call the same assistant without using the codeinterpreter everything is fine.

I hope you can help me to solve this problem.

Information on your n8n setup

  • **n8n version:1.90.1
  • Database (default: SQLite):
  • n8n EXECUTIONS_PROCESS setting (default: own, main):
  • **Running n8n via (Docker, npm, n8n cloud, desktop app): cloud
  • **Operating system: win 10

Can you provide your workflow JSON and pasting into the field that appears when clicking the ‘</>’ here on the forums? Will help provide more context.

Dear ThinkBot :wink:

Many thanks for your reply and sorry for my late answer.

I updated n8n from 1.90.1 to 1.91.1 and the problem is gone.

Anyway - here is the simple workflow;