# Gemini API Managed Agents: 3.6 Flash, hooks, and more

Source: [Google](https://blog.google/innovation-and-ai/technology/developers-tools/expanding-managed-agents-gemini-api-3-6-flash-hooks/)  
Feed7 permalink: https://feed7.dev/p/expanding-managed-agents-gemini-api-3-6-flash-hooks-0xce1pm  
Published: 2026-07-28T16:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Gemini Managed Agents now add model selection, sandbox hooks, token caps, schedules, and free-tier access, covering several controls needed for unattended coding work.

## Source Summary

Gemini Managed Agents now default to **Gemini 3.6 Flash**. The service adds pre- and post-tool hooks, explicit model selection, scheduled triggers, free-tier access, environment management, and persistent files across scheduled runs.

## Practical Implication

Add hooks where tool calls need policy checks, linting, or audit output, and set **max_total_tokens** on autonomous loops. A capped run pauses as incomplete while preserving its environment, so it can resume with a new budget and previous interaction ID.

## Agent-Ready Context

Gemini Managed Agents now default to **Gemini 3.6 Flash**. The service adds pre- and post-tool hooks, explicit model selection, scheduled triggers, free-tier access, environment management, and persistent files across scheduled runs.

Add hooks where tool calls need policy checks, linting, or audit output, and set **max_total_tokens** on autonomous loops. A capped run pauses as incomplete while preserving its environment, so it can resume with a new budget and previous interaction ID.

The agent remains a preview identified as antigravity-preview-05-2026. Scheduled runs reuse a sandbox, which is useful for stateful work but makes cleanup, state drift, and hook failure behavior important operational concerns.

## Connected Context

Feed7 judgment across 262 accumulated Signals:

This extends Gemini Managed Agents from asynchronous tool execution into a more governable recurring runtime: hooks add policy and audit boundaries, token caps bound loops, and paused runs retain resumable state. Persistent scheduled sandboxes reinforce the value of stateful agents while narrowing the operational requirement to explicit cleanup, drift control, and hook-failure handling; the preview status still limits production confidence.

- [Expanding Managed Agents in Gemini API: background tasks, remote MCP and more](https://feed7.dev/p/expanding-managed-agents-gemini-api-1idue29) — It builds on the earlier background-task and persistent-sandbox capabilities with scheduling, hooks, explicit model choice, and resumable token budgets.
- [From fork() to Fleet: Designing an Agent Sandbox Cloud — Abhishek Bhardwaj, OpenAI](https://feed7.dev/p/from-fork-to-fleet-designing-an-agent-sandbox-cloud-abhishek-bhardwaj-op-0np9ki3) — Persistent scheduled environments reinforce the need for the isolation and recovery properties described for long-running sandbox fleets.
- [Scaling Managed Agents: Decoupling the brain from the hands](https://feed7.dev/p/managed-agents-00zpz67) — Both support long-horizon work with persistent execution environments, while Google’s update adds user-facing controls for interception, budgeting, scheduling, and resumption.
- [Vercel MCP can now deploy code](https://feed7.dev/p/vercel-mcp-can-now-deploy-code-1292qsq) — Pre- and post-tool hooks provide a concrete place to add the review, authorization, completion, and audit checks that production-changing deployment tools require.

## Context Map

- Layer: tools
- Domains: coding, security
- Topics: cloud-agents, sandboxing, tool-use

## Uncertainty

- The agent remains a preview identified as antigravity-preview-05-2026. Scheduled runs reuse a sandbox, which is useful for stateful work but makes cleanup, state drift, and hook failure behavior important operational concerns.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.