Skip to content

Continue does not support Azure OpenAI o3-mini and o-4mini #5872

@yazon

Description

@yazon

Before submitting your bug report

Relevant environment info

- OS: Windows 10
- Continue version: 1.0.10
- IDE version: VS Code 1.100.2
- Model: Azure OpenAI o3-mini/o4-mini

Description

It looks that Azure OpenAI connection does not support o3-mini and o4-mini models. gpt-4o and gpt-4.1 works well. It may be related to the Responses API instead of Chat Completions API.

To reproduce

Image

Log output

Error handling webview message: {
  "msg": {
    "messageId": "4125bde5-336c-4e88-8b8b-38a8fd0c6342",
    "messageType": "llm/streamChat",
    "data": {
      "completionOptions": {},
      "title": "o4-mini",
      "messages": [
        {
          "role": "system",
          "content": "<important_rules>\n  You are in chat mode.\n\n  If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n  If needed consisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n  When addressing code modification requests, present a concise code snippet that\n  emphasizes only the necessary changes and uses abbreviated placeholders for\n  unmodified sections. For example:\n\n   /path/to/file\n  // ... existing code ...\n\n  {{ modified code here }}\n\n  // ... existing code ...\n\n  {{ another modification }}\n\n  // ... rest of code ...\n  \n\n  In existing files, you should always restate the function or class that the snippet belongs to:\n\n   /path/to/file\n  // ... existing code ...\n\n  function exampleFunction() {\n    // ... existing code ...\n\n    {{ modified code here }}\n\n    // ... rest of function ...\n  }\n\n  // ... rest of code ...\n  \n\n  Since users have access to their complete file, they prefer reading only the\n  relevant modifications. It's perfectly acceptable to omit unmodified portions\n  at the beginning, middle, or end of files using these \"lazy\" comments. Only\n  provide the complete file when explicitly requested. Include a concise explanation\n  of changes unless the user specifically asks for code only.\n\n</important_rules>"
        },
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Hi"
            }
          ]
        },
        {
          "role": "assistant",
          "content": ""
        }
      ]
    }
  }
}

Error: HTTP 400 Bad Request from https://xxxxyyyyyzzz/openai/deployments/o4-mini/chat/completions?api-version=2024-12-01-preview

{
  "error": {
    "message": "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",
    "type": "invalid_request_error",
    "param": "max_tokens",
    "code": "unsupported_parameter"
  }
}

Metadata

Metadata

Assignees

Labels

kind:bugIndicates an unexpected problem or unintended behavior

Type

No type

Projects

Status

Done

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions