Use Case
I need to use OpenClaw browser Control UI (http://127.0.0.1:18789/) as my primary work interface because:
- Large screen - much better for viewing documents, screenshots, and code
- Multi-window - can reference materials while chatting
- Already my daily workflow
Problem
Currently the browser Control UI does NOT support uploading images or documents. This forces me to use Feishu or WeChat for image/file sharing, which have smaller viewports and are less convenient for detailed work.
What I Need
- Upload screenshots directly in browser (drag & drop or file picker)
- Support common document formats (PDF, DOCX, TXT, code files)
- Support image formats (PNG, JPG, etc.)
- Large screen preview capability (which Feishu/WeChat cannot provide)
Why This Matters
This is a core workflow feature. The backend already supports media handling (per docs), but the UI layer is missing the upload component. There are already related issues (#56344, #36440) requesting similar functionality.
Suggested Solution
- Add file upload button/area in the Control UI chat input area
- Support drag & drop for files
- Allow generic file types (not just images)
- Show preview of uploaded files before sending
Sent via OpenClaw by a product manager who really needs this feature 🙏
Use Case
I need to use OpenClaw browser Control UI (http://127.0.0.1:18789/) as my primary work interface because:
Problem
Currently the browser Control UI does NOT support uploading images or documents. This forces me to use Feishu or WeChat for image/file sharing, which have smaller viewports and are less convenient for detailed work.
What I Need
Why This Matters
This is a core workflow feature. The backend already supports media handling (per docs), but the UI layer is missing the upload component. There are already related issues (#56344, #36440) requesting similar functionality.
Suggested Solution
Sent via OpenClaw by a product manager who really needs this feature 🙏