---
title: "Term lists"
manual: "LLM Foundation"
version: "0.43"
permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:administration-term-lists@0.43"
source: "Administration/TermLists.rst"
rendered: "2026-11-04T13:45:29+00:00"
---

# Term lists {#administration-term-lists}

A term list stops generated text. A forbidden term must not appear in it, and a
required term must. The editor does not get the text and reads which term
stopped it. [ADR-238](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-238@0.43) records the decisions.

Open **AI > Authoring > Term Lists** to see the lists. The module is for
administrators, like its neighbours. To let an editor group maintain lists,
store the records on a page in that group's web mount and grant the table under
**Tables (modify)**. The group then edits them in the list module.

## Where a list applies {#administration-term-lists-scope}

-   ****Configurations****

    Required. Text from calls made with these configurations is checked. Calls
    made with any other configuration are not, and neither is a call with no
    configuration. A fallback does not change that: the configuration the call
    asked for decides. Without a list naming a configuration, nothing changes
    for it.

-   ****Site****

    Optional. A caller can state the site through the metadata key
    `ProviderCallContext::METADATA_SITE`. A list bound to a site stays out
    of calls that name another site. When a call names no site, the forbidden
    terms of the list still apply and the required terms do not. The modules of
    nr-llm state no site or language, so this only tells callers apart that do.

-   ****Language****

    Optional, two letters. It works like the site, through
    `ProviderCallContext::METADATA_LANGUAGE`.

A configuration's selection of allowed guardrails cannot switch a term list off.

## How terms match {#administration-term-lists-matching}

One term per line.

-   Case is ignored. `ß` and `ss` stay different letters.
-   A term matches whole words. `Kunde` does not match `Kundenkonto`.
-   A space in a term matches any white space, including a line break.
-   There is no inflection. `Rabatt` does not match `Rabatte`. List each form,
    or end the term with `*`, which takes any letters and digits after it:
    `Rabatt*` matches `Rabatte`, `Rabattaktion` and `Rabatt2026`. It
    matches nothing in front of the term.
-   HTML does not hide a term. `Ra<b>batt</b>` and `Pr&uuml;fung` are found.
-   A typographic hyphen or apostrophe equals the plain one.

Synonyms, misspellings and paraphrases are not found.

Forbidden terms are searched in the text of the answer, in the arguments of
every tool call, and in image descriptions.

A chat is the exception. In an agent run that offers tools, as the AI chat does,
the list checks what a writing tool would store: the arguments of each tool call
that does not declare a read. The text of the chat stays free and appears as it
is written, and a search for a forbidden term runs. A forbidden term can
therefore appear in a chat answer and be copied by hand. A tool that declares
nothing is treated as writing, and so is an imported MCP tool, a search included.
An editor action counts as such a run. A queued task and a field fill do not:
they have no tools, and their answer is the text that is stored.

Required terms are searched in the text of the answer. They are not asked of an
answer of fewer than 30 words, of JSON, of an image description, or of anything
in an agent run: language detection, scores, labels, wizard settings and
alternative texts run on the same configurations as the texts a list means, and
an agent run writes through tools, so its closing note is no output. Words are
counted between spaces and punctuation, so Chinese or Japanese text rarely
reaches 30.

## What a block does {#administration-term-lists-block}

The output is not delivered and not cached, and a tool call in it does not run.
In a chat, no approval card offers the write, and the turn ends with a message
that says the change was not proposed.
The message names the list and the terms, followed by the message of the list.
It is written in the language of the backend user. The block appears as a
governance event.

On a configuration a list names, a stream is held back and checked as a whole,
so the editor sees no text growing. A chat is not held.

When the check itself fails, for example because the database cannot be read,
the output is blocked and the message says the check could not run. The one
exception is the table not existing yet: until the database schema update ran,
the output passes and a warning is logged.

Not screened are DeepL translations, generated images, speech and embeddings.
A language model that revises a DeepL translation is screened, and a block
there stops the translation.