MiniMax-AI / MiniMax-AI/MiniMax-Coding-Plan-MCP

[Bug] understand_image (VLM) API 返回 1033 Gemini API error

Open
#15 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
102
Forks
30
PR merge metrics
No merged PRs in 30d

Description

问题描述

understand_image (图片理解) 功能无法正常使用,API 返回 1033 错误。

环境

  • API Key: Coding Plan (国内版)
  • API Host: https://api.minimaxi.com
  • MCP 版本: minimax-coding-plan-mcp@0.0.4

复现步骤

  1. 调用 /v1/coding_plan/vlm 端点
  2. 发送图片 (HTTP URL 或 base64)
  3. 返回错误

测试结果

功能 状态 说明
search (搜索) ✅ 正常 返回搜索结果
vlm (图片理解) ❌ 错误 返回 1033 错误

请求示例

curl -X POST "https://api.minimaxi.com/v1/coding_plan/vlm" \
  -H "Authorization: Bearer <API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"描述图片","image_url":"https://picsum.photos/200"}'

API 返回

{
  "base_resp": {
    "status_code": 1033,
    "status_msg": "system error, Gemini API error: status 400"
  }
}

调试信息

  • HTTP URL: 返回 invalid image URL
  • base64 data URL: 返回 1033 - Gemini API error: status 400

这说明 MCP 代码实现正确,问题出在 MiniMax 服务端调用 Google Gemini API 时返回了 400 错误。

期望

图片理解功能能正常工作。


注意: 如果需要更详细的调试信息,请告知。

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reproducing the documented POST request to /v1/coding_plan/vlm with both the HTTP URL and base64 data URL inputs. Compare the returned 1033 errors with the working search endpoint and determine whether the repository contains an actionable client-side issue or whether the failure is entirely in the MiniMax/Gemini service. Done means image understanding returns a successful response, or the issue is documented as an upstream service defect.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
api, backend
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.