[FEATURE]:requeste

Feature hasn't been suggested before.

• I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

Hi Opencode team (and hello to the Big-Pickle assistant)!

Just some quick user feedback: when I'm developing with Opencode, it can't visually "see" the images or page designs I come across during a session (icon previews, captures, mockups, site screenshots, etc.). Consequently, to exactly replicate a design I find in the browser, the AI ​​has to guess randomly, or I have to describe everything in detail.

It would be amazing if the agent could:

1. Display and analyze images from a webpage returned by its tools (previews, SVGs, captures), rather than just the text or Markdown.
2. Receive a screenshot via drag-and-drop during the conversation and understand it as a visual reference for replicating the design.
3. Automatically export or retrieve visual elements (image files, styles, colors) from the content it's viewing.

Basically: let's give Opencode "eyes" :) That would be a huge help for interface development (copying a style, tweaking a mockup, etc.).

Thanks in advance—great job on the tool, it's fantastic!

Feedback sent from Switzerland.