[Bug] 在GLM不支持多模态的情况下，内置的BrowserUse技能仍然主动截图，导致图片无法读取
Nobody has claimed this yet.
- Dominant language
- No language data
- Stars
- 22
- Forks
- 1
- PR merge metrics
- No merged PRs in 30d
Description
提交前确认 · Pre-submission checklist
- 我已搜索过现有 issue，确认这不是重复 / I searched existing issues and confirmed this isn't a duplicate.
- 我已阅读 CONTRIBUTING.md / I've read CONTRIBUTING.md.
问题类别 · Category
对话 / Agent 交互 · Agent chat
涉及的 Agent 框架 · Agent framework
ZCode Agent（自研）
严重程度 · Severity
阻塞使用 · Blocking (无法使用核心功能 / core function unusable)
复现频率 · Reproducibility
必现 · Always
问题描述 · Description
在GLM不支持多模态的情况下，内置的BrowserUse技能仍然主动截图，导致图片无法读取。
并且我们公司的网络会限制上传文件大小，当图片超出大小限制后，会话无法压缩，也无法继续执行，导致这个会话完全废掉无法恢复。
而且现在GLM也没有一个系统级的Agents.md来约束整体的行为。
复现步骤 · Steps to reproduce
1、进行关于页面相关的开发任务，进行页面标注修改，触发使用BrowserUse
2、使用API Key方式配置GLM模型对接
期望表现 · Expected behavior
直接基于纯文本方式进行页面优化
实际表现 · Actual behavior
对页面进行截图，导致后续任务无法处理。
ZCode 版本 · ZCode version
3.7.7
设备 / 系统 / 浏览器 · Device / OS / Browser
Windows11/Edge
截图 / 录屏 / 日志 · Screenshots / Recordings / Logs
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 by tracing the built-in BrowserUse skill when a GLM API key is configured, focusing on the decision that triggers page screenshots. Check how model multimodal support is represented and how failed or oversized image uploads affect the session. Done means unsupported GLM configurations avoid screenshots and the task can continue using text-only page handling.
Written by the indexing model from the issue text.
Assessment
- Domain
- ai, web-dev
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100