Gemini API Managed Agents: 3.6 Flash, hooks, and more
Gemini Managed Agents now add model selection, sandbox hooks, token caps, schedules, and free-tier access, covering several controls needed for unattended coding work.
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.
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.
This turns the earlier Managed Agents expansion into a more governable operating model: hooks add control points around tool use, explicit models and token caps bound autonomous runs, and schedules plus persistent files support recurring stateful work. It also sharpens the operational risk already implied by persistent sandboxes, because resumed and scheduled runs require cleanup, drift management, and reliable hook behavior.