agentscope-ai / agentscope-ai/QwenPaw

[Bug]: 使用内置 MiniMax 供应商且模型选择MiniMax-M3时,图片无法被模型正确识别

Open
#6,362 2 comments 0 reactions 0 assignees View on GitHub
bug
Dominant language
Python
Stars
34.9k
Forks
3.1k
Avg merge
1d 15h
Merged PRs (30d)
225

Description

## QwenPaw Version

QwenPaw, version 2.0.0.post4

## Description

使用 QwenPaw 内置的 MiniMax 供应商(默认走 Anthropic 兼容协议)时,模型完全无法识别上传图片的内容,会返回与图片无关的乱编答案。

## Component(s) Affected

- [x] Core / Backend (app, agents, config, providers, utils, local_models)
- [ ] Console (frontend web UI)
- [ ] Channels (DingTalk, Feishu, QQ, Discord, iMessage, etc.)
- [ ] Skills
- [ ] CLI
- [ ] Documentation (website)
- [ ] Tests
- [ ] CI/CD
- [ ] Scripts / Deploy

## Environment

- **QwenPaw version:** 2.0.0.post4
- **OS:** Windows 11
- **Install method:** 桌面版安装
- **Model:** MiniMax-M3

## Steps to Reproduce

1.打开 QwenPaw,选择内置的 MiniMax 供应商。
2.上传任意一张显示时间日期的截图。
3.发送问题:"图上的年日月时分秒是多少?"。

## Actual vs Expected

- **Actual:** 模型完全无法识别图片内容,返回与图片毫无关系的乱码/编造内容。
- **Expected:** 模型应能正确识别图片中日期。

## Logs / Screenshots

上传的图片:
Image

对话:
Image

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.