@_philschmid: The Interactions API introduced background=True to handle long-running, async agent tasks that exceed standard HTTP tim…
Summary
The Interactions API now supports background=True for async agent tasks, allowing long-running operations beyond HTTP timeouts. A guide explains usage, reconnection, and streaming.
View Cached Full Text
Cached at: 06/26/26, 10:16 PM
The Interactions API introduced background=True to handle long-running, async agent tasks that exceed standard HTTP timeout limits. We wrote a guide on how to use it, how to reconnect, stream. https://t.co/gdI6d2FvEd
Similar Articles
All your agents are going async
The article argues that AI agents are shifting from synchronous chat interfaces to asynchronous background workflows, highlighting new features from Anthropic, OpenAI, and Cursor that decouple agent lifetimes from HTTP request-response cycles.
@googledevs: The Interactions API is officially generally available (GA), taking center stage as the primary interface for building …
Google's Interactions API for Gemini models and agents is now generally available, introducing managed agents, background execution for long-running tasks, and upcoming Gemini Omni support.
agents can run in the background now. what keeps the task from drifting?
Google added background execution and remote MCP support to managed agents, raising concerns about task drift and the need for fresh approvals during long-running work.
@googledevs: Most agent tutorials stop at stateless agents. Real workflows run for weeks. Build long-running AI agents that pause fo…
A tutorial from Google on building long-running AI agents that can pause for days, survive restarts, and resume without losing context using the Agent Development Kit (ADK), with code and step-by-step guidance for enterprise workflows like new hire onboarding.
@sydneyrunkle: https://x.com/sydneyrunkle/status/2056419909941522687
Deep Agents v0.6 introduces a code interpreter, harness profiles for per-model tuning, streaming support, DeltaChannel for checkpoint storage, and ContextHubBackend for versioned agent memory, enabling model-agnostic programmatic tool calling and recursive workflows.