[建议 / Feature] 内置 Vision MCP(analyze_image)固定 GLM-4.5V,请求升级 GLM-5V 系列或允许自选视觉模型
Open
Nobody has claimed this yet.
priority: P2
- Dominant language
- No language data
- Stars
- 22
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
现状
GLM coding plan 附带的内置 Vision MCP(4_5v_mcp.analyze_image)后端模型固定为 GLM-4.5V:工具没有 model 参数,会话内和客户端设置里都无法切换。主模型(GLM-5.3)为纯文本输入,所有看图需求都只能走这一个委托通道。
问题
- GLM-5V-Turbo 已发布(多模态 coding 基准显著更强),GLM-4.6V 更便宜且支持原生工具调用,但 coding plan 用户在内置链路上用不到,只能自建脚本绕过。
- 委托链路(Read 图片 → 上传 CDN → analyze_image 读 URL)环节多、慢,且模型代差直接决定看图质量上限。
期望
- 服务端将该 MCP 的默认视觉模型升级至 GLM-5V 系列;或
- 给
analyze_image增加 model 参数 / 客户端设置项,允许 plan 用户自选视觉后端。
环境
ZCode 桌面客户端(macOS, Apple Silicon),GLM-5.3 coding plan。
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
The issue identifies the built-in Vision MCP entry point as 4_5v_mcp.analyze_image, but names no repository files or tests. First clarify whether the change belongs in the service or ZCode macOS client, then agree on either a GLM-5V default or a selectable model setting and verify that image analysis uses the chosen backend.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- macos
- Domain
- ai, desktop
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100