> ## 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.

# The GEN pipeline

> How bounded associative fragments enter the Entity’s body context.

Generative Entropic Noise, or GEN, is a configured generation process inside soma. It produces short fragments that can influence later context. It is not the main model's hidden reasoning trace.

```mermaid theme={"theme":"github-light-default"}
flowchart LR
  H[Heartbeat or post-turn trigger] --> G[Noise generation]
  B[Body state and recent events] --> G
  C[Selected conversation and journal context] --> G
  S[Optional external seed] --> G
  G --> F[Bounded fragment buffer]
  F --> E[Ebb and prompt assembly]
```

## Inputs and triggers

The daemon can trigger noise generation during a heartbeat. Committed turns can also refresh it, subject to the configured cadence and Ebb behavior.

Generation receives selected body, event, conversation, journal, and prior-fragment context. It does not receive every stored memory or every raw tool result by default. The fragment buffer is bounded.

## Model selection and GPU impact

`soma.noise.model` selects a dedicated model when configured; otherwise the runtime uses its fallback model. A separate small model can reduce the work per generation, but on a local host it may also require another model load. Measure your actual runtime rather than assuming a second model is cheaper to operate.

The checked-in noise settings enable generation with a 90-second cadence and a 240-token maximum output. The cadence is evaluated at trigger points, so it is not a guarantee of one request every exact 90 seconds.

## Optional seeds

`soma.noise_seeder` can sample inputs such as older episodes, beliefs, knowledge, relationship echoes, journal entries, temporal context, or discovery material. It is disabled in the checked-in defaults. External fetching has a separate opt-in setting.

Seeds are inputs to generation, not verified conclusions. Keep their provenance distinct when fragments later influence beliefs or actions.

## Observe and control

`ngram seeds` and `ngram trace` expose seed and fragment audit information; use their [CLI help](/reference/cli) for filters. Body inspection shows the rendered fragments available to the Entity.

The shared inference pause blocks GEN model requests along with chat and embeddings. For a runtime that remains active, tune `soma.noise.enabled`, cadence, token budget, and Ebb settings in the harness configuration.

Source: [`identity/soma.py`](https://github.com/ngramspatial/ngram/blob/main/ngram/identity/soma.py) and [`identity/noise_seeder.py`](https://github.com/ngramspatial/ngram/blob/main/ngram/identity/noise_seeder.py).