> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ngram.space/llms.txt
> Use this file to discover all available pages before exploring further.

# Work between conversations

> Bounded wake conditions, session budgets, delivery, and explicit operator control.

Autonomous wake lets the Entity act without a new human message. The daemon evaluates configured conditions, constructs wake context, and runs bounded cognition with the Entity's tools and memory.

## Triggers and limits

Wake conditions can include elapsed time, impulses, drives, conflicts, or synthesized desires. Silence thresholds and cooldowns reduce overlap with active conversation. Optional noise-triggered waking is separately configurable.

The checked-in configuration enables autonomy with a 600-second minimum gap, at most four cycles per hour, and at most two outgoing messages per cycle. These limits concern the wake engine; independent body and memory mechanisms can still make model requests.

## Sustained wake sessions

`wake_session_max_rounds` controls how many cognition rounds a wake may chain. It defaults to one. Wall-time, per-round message, and additional tool-step budgets constrain longer sessions. The Entity can end a wake session before reaching its cap.

Longer sessions can complete more work but also consume more inference and produce more external effects. Enable them after confirming tool permissions and delivery routes.

## Per-Entity autonomy overrides

The Entity loader merges top-level `autonomy` settings onto the harness configuration:

```yaml theme={"theme":"github-light-default"}
autonomy:
  enabled: true
  min_cycle_gap_seconds: 1800
  max_cycles_per_hour: 2
  messages_per_cycle: 1
  wake_session_max_rounds: 1
```

This example lowers wake frequency and visible output. It does not impose a total provider spending limit.

## Delivery and observability

Wake output uses configured presence routes. The worker can record structured events and a detailed transcript, while chat settings decide how much activity appears to the user.

Telegram `/wakequiet on` suppresses visible wake activity. It does not disable the wake engine or model calls.

## Disabling autonomous wake

Set `autonomy.enabled: false` to disable the wake engine. In v1, a legacy initiative path can still run when this flag is false, and body, memory, and routine jobs are separate.

Use **Pause inference** or Telegram `/pause` when your intent is to stop all new model requests for the Entity. The shared provider control covers those other paths too. See [usage and controls](/guides/usage-and-controls).

Source: [`presence/wake_cycle.py`](https://github.com/ngramspatial/ngram/blob/main/ngram/presence/wake_cycle.py) and [`presence/daemon.py`](https://github.com/ngramspatial/ngram/blob/main/ngram/presence/daemon.py).