MoonshotAI / MoonshotAI/kimi-code
Kimi Code API 支持图片上传
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- TypeScript
- Stars
- 7.5k
- Forks
- 1.2k
- Avg merge
- 11h 53m
- Merged PRs (30d)
- 350
Description
What feature would you like to see?
Kimi Code CLI 已支持拖图分析，但 API 端点（api.kimi.com/coding/v1）不支持图片输入。
编程场景截图是刚需：报错截图、UI 设计稿、架构图、日志截图。第三方工具（Claude Code、Roo Code、Cursor）集成时无法传图，体验断层。
OpenAI、Anthropic、Google 的 Coding API 均支持 vision。建议 Kimi Code API 至少对 K3 开放 image_url 或 base64 图片输入，与开放平台保持一致。
使用模型：k3，订阅：Moderato
Additional information
No response
Contributor guide
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 with the api.kimi.com/coding/v1 endpoint and the existing Kimi Code CLI path that supports drag-and-drop image analysis. Compare the requested image_url and base64 inputs with current API behavior, confirm the K3 scope, and treat successful image input for coding requests as done.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- api
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100