[V1] Protocols - Content Blocks

[pgrayy]

Summary

Add support for missing content block input types (e.g., ImageContent) to enable multimodal agent interactions.

Usage

⚠️ Agent-generated example - This is a preliminary API sketch and has not been finalized.

import { Agent, ImageContent, TextContent } from '@strands-agents/sdk'

const agent = new Agent({ model })

const result = await agent.invoke([
  new TextContent('What is in this image?'),
  new ImageContent({
    source: {
      type: 'base64',
      mediaType: 'image/png',
      data: base64ImageData,
    },
  }),
])

Documentation

https://strandsagents.com/latest/documentation/docs/user-guide/concepts/agents/prompts/

Reference

https://github.com/strands-agents/sdk-python/blob/main/src/strands/types/content.py

[dbschmigelski]

Image, Video, and Document Content Blocks are supported.

The one missing one is Citations which will be introduced to close our this issue.