Vercel BlogTools
HarnessAgent now supports image inputs for all harness adapters

The AI SDK HarnessAgent layer now accepts image inputs across every harness adapter. Pass images alongside text in the standard AI SDK message format: a content array mixing { type: 'text' } and {…
Read at Vercel Blog ↗Related

GitHubAGNTCon + MCPCon 2026: Agentic AI Foundation Adds Four Projects as MCP Turns to Security InfoQ AI

GitHubArticle: The Evolution of Agentic Harnesses: From Chains to Graph to Code InfoQ AI

GitHubGoogle’s Data Agent Kit Hits GA, Splitting Agent Guardrails Between Skills and IAM InfoQ AI

GitHubUsage metrics API adds usage from tools like OpenCode GitHub Changelog

GitHubCustom skills, agents, and MCP servers in usage metrics API GitHub Changelog
