AI 精选动态
智能评分 63
交互API正式发布
AI 推荐理由
建议开发者重点关注其后台异步执行和统一工具生态，以评估是否可简化多模态代理的构建与部署。核心解读
Google 宣布 Interactions API 达到 GA，成为模型推理和自主代理的统一接口。新版本提供托管代理（默认 antigravity-preview-05-2026 或自定义指令的安全远程 Linux 沙箱）、线性简化 schema（每个操作为独立步骤）、后台异步执行（background=True），并新增对 Computer Use、File Search、Google Maps、Gemini API Docs MCP、gemini-interactions-api Skill 的原生支持，以及基于 Google Search-grounded Nano Banana 2 的图像生成、Lyria 3 音乐和多说话人 TTS。
全文
The Interactions API is now GA. Featuring a stable schema and new capabilities via a single /interactions endpoint, it is now our standard interface for both model inference and autonomous agents.
Check out the key updates:
— Managed Agents: Spin up a secure, remote Linux sandbox for code execution and browsing via a single API call, using the default antigravity-preview-05-2026 agent or your own custom instructions
— Simplified Schema: Every action is now represented as its own step (from user_input to model_output, etc.) in a simplified, linear flow
— Background Execution: Set background=True to run models and agents asynchronously, letting you poll for results when ready
— Expanded Tool Ecosystem: Native support for Computer Use, File Search, and Google Maps, alongside new agent-building tools like the Gemini API Docs MCP server and gemini-interactions-api Skill
— Media Generation: Image generation via Google Search-grounded Nano Banana 2, music with Lyria 3, and expressive multi-speaker TTS
Read the blog to learn more: https://t.co/ZzfpUGzAvm