Autonomous loop

Let the orchestrator check back and drive tasks on its own

Autonomous loop

By default you drive Foxl Code from the chat. Turn on the autonomous loop and the orchestrator checks back on its own - advancing plans, spawning the next agent, and retrying failures without you in the conversation.

What it does

On a schedule, the loop wakes the orchestrator with the current state of your active Task Documents and lets it:

  • Tick checkboxes as their pull requests land.
  • Spawn missing agents for any confirmed plan that hasn't fanned out yet.
  • Retry a failed subtask once.
  • Complete a Task Document when every subtask reaches a terminal state.

This is what makes a multi-PR plan run start to finish after a single confirmation, instead of dead-ending until your next message.

Settings

SettingWhat it controls
IntervalHow often the loop may check. Default 5 minutes, minimum 1 minute.
Quiet hoursA time range when the loop sleeps (for example 22:00-06:00).
Daily capThe most it may spend per day on autonomous checks. Default $0.50.

The loop only does work when something has actually progressed since the last check - new events, a merged PR, a confirmed-but-unstarted plan. If nothing changed, the tick is a cheap no-op, so an idle account costs nothing.

Cost control

The loop respects every other guardrail in Foxl Code: each agent it spawns still has its own per-task budget, and the daily cap bounds what the autonomous checks themselves can spend. Autonomy is on by default for Foxl Code users; you can disable it or tighten the interval, quiet hours, and cap at any time in Settings.

On this page