MiniMax-AI / MiniMax-AI/minimax-code

[Bug]: 容易忽略图片,而专注于解读文字

Open
#84 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug desktop needs-triage
Dominant language
TypeScript
Stars
1.3k
Forks
141
Avg merge
2h 45m
Merged PRs (30d)
46

Description

Version / 版本号

3.0.42-inside.10.10

Platform / 平台

macOS

OS version / 系统版本

macOS 26.5.1

Issue area / 问题类型

Model output quality

Upload ID / 日志上传 ID

410495106749092

What happened? / 问题描述

比如我文字描述了问题,然后上传了应用的截图。结果点开它折叠的思考,发现它一直在解读我的文字,但是根本没看应用截图。我问它为啥不看截图,然后它才看,然后才正确理解了问题。

Steps to reproduce / 复现步骤

见说明

Expected behavior / 预期行为

有图片应该优先看图片

Actual behavior / 实际行为

有图片应该优先看图片,文字是对于图片问题的描述。你不看图片,只看文字,然后自己瞎猜,怎么能得出正确结论。你连问题都没理解清楚。

Logs or crash report / 日志或崩溃信息

Screenshots / 截图

No response

Before submitting / 提交前确认
  • I have searched existing issues.
  • I am using the latest version available to me.
  • I have removed sensitive information from logs/screenshots.

Contributor guide

Open the contributing guide

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 behavior on macOS 26.5.1 with version 3.0.42-inside.10.10, using the reported upload ID 410495106749092 as context. Trace how an uploaded application screenshot and its accompanying text are passed to the model; done means the model examines the image before relying on the textual description and correctly understands the reported problem.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
ai
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.