接不支持视觉信息的LLM
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 183
- Forks
- 15
- Avg merge
- 8m
- Merged PRs (30d)
- 2
Description
相关逻辑在 agent/backends/planner.py:785。当视觉开启时，它最终生成类似 OpenAI 的多模态消息：
{
"type": "image_url",
"image_url": {
"url": "data:image/png;base64,..."
}
}
DeepSeek 当前这个 endpoint 只接受：
{"type": "text"}
所以返回了：
unknown variant image_url, expected text
原来的问题是：底层虽然有 enable_vision，但 .env 和 TUI 没有暴露这个配置。
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start at agent/backends/planner.py:785 and trace how enable_vision affects the generated message. Then inspect the .env configuration and TUI controls mentioned in the issue. Done means the vision setting is exposed in both places and the DeepSeek endpoint no longer receives image_url content when vision is disabled.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Active
- Clarity
- Mostly clear
- Newbie friendliness
- 72/100