HarnessAgent now supports image inputs for all harness adapters

The AI SDK's HarnessAgent layer now accepts image inputs across all of its harness adapters, including Claude Code, Cline, Codex, Cursor, Deep Agents, fx, GitHub Copilot, Grok Build, OpenCode and Pi. Images are passed alongside text in the standard AI SDK message format using a content array that mixes { type: 'text' } and { type: 'file' } parts, and are processed by each harness's underlying vision models. Documentation for the feature is available in the HarnessAgent image inputs section of the AI SDK docs.

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 { type: 'file' } parts. Image input is processed by the harnesses' underlying vision models and supported across all available adapters: Claude Code, Cline, Codex, Cursor, Deep Agents, fx, GitHub Copilot, Grok Build, OpenCode, Pi. Read the HarnessAgent image inputs documentation https://ai-sdk.dev/docs/ai-sdk-harnesses/harness-agent image-inputs to get started.