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

# Runtime & durability

> The runtime is Vetta's infrastructure, not a setting: wake, take one turn, commit, sleep — and idle costs storage.

The **runtime** is the metered infrastructure Vetta runs your agent on — the durable loop and scheduler, [sandboxed computers](/docs/computer/index) and the managed browser, [model routing across completion windows](/docs/concepts/model-router), and the [ledger](/docs/capabilities/observability). It is not a parameter and there is nothing to select: using Vetta's managed agents *is* the runtime. The layer you do select is the [harness](/docs/concepts/harnesses) — the agent loop — which sits on top of everything on this page.

This page is about the durability half of the runtime, which is where most of the cost behaviour on long-horizon work comes from.

## Wake → turn → commit → sleep

The loop is an **alarm**, not a call stack. Each cycle:

1. **Wake** on a trigger — a user message, a scheduled [deployment](/docs/capabilities/deployments), a tool result, or — coming soon — an [inbound event](/docs/identity/inbound) (inbound messages are received and stored today; the wake is not yet wired).
2. **Take one turn** — a single, bounded slice of work: one harness turn (a model call plus the tool calls it requests).
3. **Commit** what it learned — the transcript and cursor are written to durable storage at a fixed commit boundary.
4. **Sleep** — the runtime releases compute and sets the next alarm.

Because state lives in storage rather than a live process, a run that spans hours **survives a crash, a restart, and a machine change, losing one turn rather than the whole run.**

## Idle costs storage, not compute

Between turns there is no process to pay for. A session waiting on a nightly schedule, a human reply, or a long external job costs only what its stored transcript and its paused [computer](/docs/computer/index) occupy — a paused micro-VM meters its stored disk and no vCPU at all. This is the mechanism behind Vetta's low cost on tasks measured in hours: most of that wall-clock time is spent *waiting*, and waiting is nearly free.

## Bounded slices

Each turn runs inside a slice with explicit bounds — a step budget, a wall-clock budget, and the [spend budget](/docs/concepts/budgets). When a slice hits a bound, the runtime checkpoints mid-task and reschedules the next slice. Nothing is lost; the task simply continues on the next wake.

<Note>
  The commit boundary is a small, fixed set of synchronous writes per turn. Recovery always resumes from the last committed turn, so at-most-one-turn is the worst-case loss under any failure.
</Note>

## How the pieces fit

```
        ┌──────────────────── Runtime (durable, ours) ───────────────┐
trigger →│  wake → [ harness: assemble · call model · parse ] →       │→ sleep
        │          commit transcript + cursor → set next alarm        │
        └─────────────────────────────────────────────────────────────┘
                              ▲ the harness  (the one layer you pick)
```

<Card title="Next: model router & inference" icon="route" href="/docs/concepts/model-router">
  How each call is routed to inference, and how model tokens are metered.
</Card>