[FEATURE]: Add image/vision capability info to Go docs models table

[coygeek]

Problem

The Go docs models table lists 12 models with limits and endpoints but no capability info. Users don't know which models support image/vision input, leading to silent failures (#27326, #24454, #29653).

Proposed Solution

Add a "Capabilities" or "Modalities" column to the Go docs models table indicating image/vision support, or add a note clarifying which models are text-only vs multimodal.

• I have checked that this feature has not already been suggested

[github-actions]

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

• This appears to be a documentation feature request, but the title does not start with [FEATURE]: and the feature request template (which includes a verification checkbox confirming the feature hasn't been suggested before) was not used. Please reopen using the Feature Request template, or prefix your title with [FEATURE]: and confirm the feature hasn't been previously requested.

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

---

This issue might be a duplicate of existing issues. Please check:

• [FEATURE]: Show Metadata (e.g. Model Context Limit) while Selecting Models in Opencode CLI Menu #19411: Requests showing model capability metadata (vision, PDF, reasoning) in the model selector — overlapping concern around surfacing vision/modality support to users

If you believe this was flagged incorrectly, please let a maintainer know.

[github-actions]

Thanks for updating the issue! It now follows our contributing guidelines. We'll take a look.