Settings 

Provider configuration 

Providers, models and configurations are database-backed and managed in the LLM backend module — not via TypoScript. nr-llm does not read plugin.tx_nrllm TypoScript settings; any such constants/setup have no effect (this is true for both classic TypoScript templates and site sets).

To make the generic chat() / complete() entry points work without pinning a provider per call, set up a default configuration:

1. Open the LLM backend module.
2. Create a Provider (e.g. OpenAI) and store its API key as an nr-vault identifier — see API key protection.
3. Create a Model for that provider.
4. Create a Configuration bundling the model, then mark it active and default.

The Setup Wizard in the module walks through these steps.

Without an active default configuration, generic calls throw "No provider specified and no default provider configured".

Quality benchmark for routing 

Measured quality uses one explicitly selected completion benchmark (Completion benchmark revision). These extension settings are read on every score lookup, including in long-running workers.

After upgrading from an unversioned benchmark, re-evaluate and configure both values. Changing prompts or grading rules produces a new fingerprint; switch the selected revision deliberately after reviewing the measurements.

Model discovery 

Model rounds of an agent run 

An agent run sends the model a request, runs the tools it asks for and sends the result back; each such exchange is a round. The settings are in the extension configuration of nr_llm, section agent (ADR-101). The Governance tab of the LLM overview module shows the values that apply.

A run that reaches its number ends with one more request without tools, which writes the answer. The values are read for every run, so a change applies to the next one. A worker that started before the change applies it from its next start.

The Agent Runs module and the playground continue a run after an approval or an answer inside the web request. Each round can take several seconds, so with a high maximum such a request can outlast a timeout of the web server or a proxy in front of it. If PHP keeps running, completion may later appear in Agent Runs. A PHP-worker timeout, process termination or host failure can instead leave an executing segment unfinished. Inspect the run status and worker lease; use the reaper procedure rather than assuming completion. See Command-line operation.

Background worker 

A queued run reads its provider key in a process without a logged-in backend user (ADR-234). The setting is in the extension configuration of nr_llm, section worker.

EXT:autotranslate 

Used only when autotranslate's own setting translatorClass names nr-llm's translator (Page trees and records in the background). The setting is in the extension configuration of nr_llm, section autotranslate.

Filling empty fields on save 

An installation can have empty fields written by AI after a save (ADR-237). The settings are in the extension configuration of nr_llm, section fieldFill. Nothing happens until fieldFill.fields is set.

When an editor changes and saves a record with such a field empty, a background run is queued and the save ends. A save that changes nothing queues nothing. A worker has to run (Background tasks from the command line and the scheduler). It writes the text as the user who saved, and only while the field is still empty. A failed run writes nothing, and Agent Runs shows what became of each answer.

A save in a draft workspace is filled in that workspace: the run reads the record and its page as the workspace shows them and stores the text as a draft there, which waits for the workspace to be published. Live stays unchanged, wherever the editor works when the worker runs. A table without workspace versions is not filled from a draft (ADR-265).

Nothing is queued for a field the save itself emptied, for a page with hardly any text, for _cli_ or an import, for a copy or a translation made by TYPO3, or for a user who may not use the default configuration. The record's text is sent to the provider of the default configuration.

Vision editor actions 

The editor actions Set alternative text, Update file metadata and Set categories from the image send the image of the file to the model (ADR-235). The settings are in the extension configuration of nr_llm, section vision.

The action is not offered when the default configuration's model declares capabilities without vision. A model with an empty capability field passes. A configuration that selects its model by criteria has to require vision in its criteria. The prompt asks for the language of the backend user.

Environment variables 

# TYPO3 encryption key (used for API key encryption)
TYPO3_CONF_VARS__SYS__encryptionKey=your-key

Security 

if (preg_match('/[\x00-\x08\x0B\x0C\x0E-\x1F\x7F]/', $userInput)) {
    throw new \InvalidArgumentException('Unsupported control character.');
}
$text = trim(strip_tags($userInput));
$response = $llmManager->completeForConfiguration($text, $configuration);

$response = $llmManager->completeForConfiguration($prompt, $configuration);

$safeOutput = htmlspecialchars(
    $response->content, ENT_QUOTES, 'UTF-8'
);

Logging 

use Psr\Log\LogLevel;
use TYPO3\CMS\Core\Log\Writer\FileWriter;

$GLOBALS['TYPO3_CONF_VARS']['LOG']
    ['Netresearch']['NrLlm'] = [
    'writerConfiguration' => [
        LogLevel::DEBUG => [
            FileWriter::class => [
                'logFileInfix' => 'nr_llm',
            ],
        ],
    ],
];

Log files: var/log/typo3_nr_llm_*.log

Caching 

The extension uses TYPO3's caching framework with cache identifier nrllm_responses.

No cache backend is specified — TYPO3 automatically uses the instance's default cache backend. If your instance has Redis, Valkey, or Memcached configured, nr-llm uses it transparently with zero configuration.

• Cache identifier: nrllm_responses
• Cache group: nrllm

The backend's defaultLifetime (3600 seconds) does not enable every cache path. Each producer decides whether to store content and with which TTL:

A cache hit avoids the corresponding provider request and its budget charge. Idempotency is a separate retry contract; it is not this response-cache TTL. The privacy purge removes governed database rows; it does not replace cache expiry or an explicit cache flush. See Configuration parameters and policies.

To override the backend for this cache specifically:

use TYPO3\CMS\Core\Cache\Backend\RedisBackend;

$GLOBALS['TYPO3_CONF_VARS']['SYS']['caching']
    ['cacheConfigurations']['nrllm_responses']
    ['backend'] = RedisBackend::class;

Clear cache:

vendor/bin/typo3 cache:flush --group=nrllm