Skip to content

OpenAI API Streaming Error: 400 Invalid parameter #1039

@Roy-GY

Description

@Roy-GY

What happened?

My model is gpt-4o and I'm running command qwen -p "generate a 2048 game" --yolo.

The output is "OpenAI API Streaming Error: 400 Invalid parameter: messages with role 'tool' must be a response to a preceeding message with 'tool_calls''

But when I use deepseek-v3, this problem didn't happen.

What did you expect to happen?

I want to know how to solve this problem.

Client information

Client Information

Run qwen to enter the interactive CLI, then run the /about command.

$ qwen /about
│ CLI Version            0.2.1                                       │
│ Git Commit             e6d08f05                                    │
│ Model                  gpt-4o                                      │
│ Sandbox                no sandbox                                  │
│ OS Platform            linux                                       │
│ OS Arch                x64                                         │
│ OS Release             6.8.0-85-generic                            │
│ Node.js Version        v24.11.1                                    │
│ NPM Version            11.6.2                                      │
│ Session ID             bfbe05d8-6ede-465a-aaad-01aaab5014f7        │
│ Auth Method            openai                                      │
│ Base URL               https://api.chatanywhere.tech/v1            │
│ Memory Usage           219.9 MB  

Login information

No response

Anything else we need to know?

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    priority/P2Medium - Moderately impactful, noticeable problem

    Type

    No fields configured for Bug.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions