HarnessAgent now accepts image input across all harness adapters

AIVercel says HarnessAgent now supports image input across every harness adapter. Developers can pass images alongside text in the standard AI SDK message format, and each harness's underlying vision model processes them.

Vercel DevelopersOfficial

@vercel_dev

View on X

𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 now supports image input across every harness adapter.

Pass images alongside text in the standard AI SDK message format, and each harness's underlying vision model handles the rest. https://vercel.com/changelog/harness-agent-image-inputs

Agents

Source details

Vercel Developers · x.comPublished Oct 27, 2:06 PM ET · added here 2:13 PM ET

Original title: 𝙷𝚊𝚛𝚗𝚎𝚜𝚜𝙰𝚐𝚎𝚗𝚝 now supports image input across every harness adapter.

Topics

AI agents Multimodal AI Deployment & engineering Product updates