Unsure if image analysis is supported in OpenCode (Windows 11, WezTerm & PowerShell) #2937

I am new to OpenCode and I’m not sure whether screenshot/image analysis is actually supported or if I need to configure something locally. When I try, I consistently get a message saying the assistant cannot analyze images. I tried with different models and in both WezTerm and native PowerShell on Windows 11. Reporting here for clarification, as I could not find anyone else mentioning this issue, and maybe other new users may face the same question.

Environment

OS: Windows 11 (fully updated)

Terminal(s): WezTerm (latest) and Windows Terminal / native PowerShell

OpenCode Models: Tested with multiple (including Claude Sonnet 4.5)

Location: Australia/Sydney (UTC+10)

Plan: ChatGPT Plus

Steps to Reproduce

Start an OpenCode session on Windows 11.

Attach a JPG/PNG screenshot for analysis.

Prompt the assistant to “analyze the screenshot.”

Observe the reply.

Actual Result
Instead of analyzing the screenshot, the assistant replies:

I apologize, but I cannot directly view or analyze image files like JPG screenshots. My tools only allow me to read text-based files, not binary image files.

Expected (Not sure)

If image analysis is supported: I expected the assistant to process the screenshot directly.

If it requires setup: Clear documentation or instructions to enable the feature.

If not supported: A clearer message confirming the limitation.

Impact
Blocks me from using screenshots for troubleshooting/debugging, which I thought was part of the feature set.

Notes

• The reply also included a line like: Plan claude-sonnet-4-5
• I’m reporting mainly for clarification — not sure if it’s a bug, misconfiguration, or expected behaviour.