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

> ## Agent Instructions
> These docs cover three products: TrustGate (AI agent gateway), TrustGuard (runtime security), and TrustTest (AI red teaming). Start from each product overview for the definition and How it works. Prefer the .md URL next to a page in /llms.txt when you need the full article. Use /llms-full.txt for a single-file dump of the site.

# Request Size Limiter

> Refuse oversized requests before anything reads them. Two ceilings, bytes and characters, and an optional demand that the client declare its size.

Applies to **LLM and MCP**.

An oversized body reaches the gateway before anything can judge it: it has to be
read, buffered and parsed. Whether it came from a client that attached a PDF to a
prompt by mistake or from someone probing for a way to exhaust memory, the
cheapest defence is to refuse it by size before reading it.

## What it checks

The body as received, against two ceilings, in this order:

| Setting                              | Default      | What is measured                                                                                          |
| ------------------------------------ | ------------ | --------------------------------------------------------------------------------------------------------- |
| **Allowed payload size**             | 10 megabytes | The body in bytes, kilobytes or megabytes.                                                                |
| **Max characters per request**       | 100,000      | UTF-8 characters in the body — the prompt, the message history, tool results, everything the client sent. |
| **Reject undeclared content length** | off          | Refuse a request that carries no `Content-Length` header.                                                 |

Bytes are checked first. A body that passes the byte ceiling is then counted in
characters, so a request can be small in bytes and still refused for length, and
a multi-byte script can hit the byte ceiling before the character one.

## What the client gets

A refused request is answered before any provider is contacted:

| Refused because            | Status | Message names                |
| -------------------------- | ------ | ---------------------------- |
| Too many bytes             | 413    | The size received, in bytes. |
| Too many characters        | 413    | The count received.          |
| No `Content-Length` header | 411    | The missing header.          |

Requiring `Content-Length` refuses chunked uploads and clients that stream a
body of unknown size. That is the point — a declared size can be judged before
the body is read — but it also refuses well-behaved clients that stream, so turn
it on only where every caller is yours.

In **Observe** mode the request is measured, recorded on the event as over the
limit, and passed through.

## Where to apply it

Run it gateway-wide as a ceiling, and target a tighter one at applications whose
traffic should be small. On a targeted policy the limit covers all of the
application's traffic, on both planes.

It is not a substitute for model limits: prompts that do not fit the resolved
model are already rejected on the chat path. This policy is about not reading
the body at all.