---
title: "Configuration"
manual: "AI Cowriter for TYPO3"
version: "main"
permalink: "https://docs.typo3.org/permalink/netresearch/t3-cowriter:configuration@main"
source: "Configuration/Index.rst"
rendered: "2026-09-24T09:13:18+00:00"
---

# Configuration {#configuration}

## LLM provider setup {#llm-provider-setup}

The Cowriter extension uses the [nr-llm extension](https://docs.typo3.org/p/netresearch/nr-llm/main/en-us/Index.html#start) for
LLM provider configuration. Configure your preferred provider in the
nr-llm backend module.

### Supported providers {#supported-providers}

-   **OpenAI** \- GPT-5.x series, o-series reasoning models
-   **Anthropic Claude** \- Claude 4.5 Opus, Sonnet, Haiku
-   **Google Gemini** \- Gemini 3 Pro, Flash
-   **OpenRouter** \- Access to 100+ models from multiple providers
-   **Mistral** \- Mistral Large, Medium, and open models
-   **Groq** \- Ultra-fast inference with Llama, Mixtral

### Configuration steps {#configuration-steps}

1.  Navigate to **Admin Tools** \> **LLM Management**
1.  Add a provider (e.g., OpenAI with your API key)
1.  Create a model configuration
1.  Create an LLM configuration and set it as default

> [!TIP]
> See the
> [nr-llm provider configuration](https://docs.typo3.org/p/netresearch/nr-llm/main/en-us/Configuration/ProviderFields.html#configuration-provider)
> for detailed provider configuration options.

## RTE configuration {#rte-configuration}

There are two ways to configure the CKEditor integration:

### Option 1: Using the shipped preset {#option-1-using-the-shipped-preset}

If you don't have a custom RTE configuration, point the RTE at the preset
this extension registers:

1.  Go to your root page
1.  Open **Page Properties** \> **Page TSconfig**
1.  Add this line:

    ```typoscript
    RTE.default.preset = cowriter
    ```

The preset is inherited by every page below, and brings all four toolbar
items with it.

![Page TSconfig configuration in TYPO3 v14](../Images/pagetsconfig.png)

### Option 2: Custom RTE configuration {#option-2-custom-rte-configuration}

If you have your own RTE configuration file
(`your_ext/Configuration/RTE/YourConfig.yaml`), add the Cowriter module:

```yaml
editor:
  config:
    importModules:
      - { module: '@netresearch/t3_cowriter/cowriter', exports: ['Cowriter'] }
    toolbar:
      items:
        - cowriter
        - cowriterVision
        - cowriterTranslate
        - cowriterTemplates
```

The four toolbar items are:

-   **`cowriter`**

    Main dialog — task-based content generation with preview

-   **`cowriterVision`**

    Generate image alt text via LLM vision analysis

-   **`cowriterTranslate`**

    Inline translation dropdown (10 languages)

-   **`cowriterTemplates`**

    Open the Cowriter dialog with a task pre-selected

> [!TIP]
> You can include only the toolbar items you need. For example, if you
> only want the main dialog and translation, omit `cowriterVision`
> and `cowriterTemplates`.

> [!WARNING]
> An explicit `toolbar.items` list REPLACES the toolbar, it does not add
> to it. Importing the module and then listing only `cowriter` gives you
> exactly one button — the other three are registered but have nowhere to
> appear. If buttons are missing, check this list before suspecting the
> extension.

## Task configuration {#task-configuration}

The Cowriter dialog shows [tasks](https://docs.typo3.org/p/netresearch/nr-llm/main/en-us/Configuration/TaskFields.html#configuration-tasks) from
the nr-llm extension with `category = 'content'`. Default tasks
(Improve, Summarize, Extend, Fix Grammar, Translate EN/DE) are seeded
during installation.

### Adding custom tasks {#adding-custom-tasks}

1.  Navigate to **Admin Tools** \> **LLM Management**
1.  Create a new task record with `category = 'content'`
1.  Set a descriptive name and identifier
1.  Write a prompt template using `{{input}}` as the placeholder for
    user content

**Example prompt template**

```text
Rewrite the following text in a more engaging tone, suitable for
a marketing audience. Output ONLY the rewritten text without
explanations.

{{input}}
```

> [!TIP]
> Tasks can have their own LLM configuration. If a task has no
> configuration assigned, the request's configuration or the default
> configuration is used as fallback.

## Rate limiting {#rate-limiting}

The Cowriter enforces a rate limit of 20 requests per minute per
backend user. When the limit is exceeded, the API returns HTTP 429
with a `Retry-After` header.

## Security considerations {#security-considerations}

The Cowriter extension routes all LLM requests through the TYPO3 backend,
ensuring that:

-   API keys are never exposed to the frontend
-   All requests are authenticated via TYPO3's backend session
-   Error conditions are logged for debugging

> [!WARNING]
> Always configure your LLM provider's API key in the backend. Never
> expose API keys in frontend JavaScript or client-accessible files.

## Troubleshooting {#troubleshooting}

### Translation not working {#translation-not-working}

If the translate button shows "Translation failed", check:

1.  An LLM provider is configured and marked as default in
    **Admin Tools** \> **LLM Management**
1.  The provider's API key is valid and not expired
1.  The provider supports the `translation` feature
1.  Check the TYPO3 system log for detailed error messages

### No tasks in dropdown {#no-tasks-in-dropdown}

If the Tasks dropdown shows "No tasks configured":

1.  Navigate to **Admin Tools** \> **LLM Management**
    \> **Tasks**
1.  Create at least one task with `category = 'content'`
1.  Make sure the task record is not hidden or deleted
1.  Reload the page in the browser to refresh the task list

### API key rejected {#api-key-rejected}

If you see "The LLM provider rejected the API key":

1.  Check the provider configuration in the LLM module
1.  Verify the API key is correct and has not been revoked
1.  Some providers require specific permissions or billing setup

### Rate limit exceeded {#rate-limit-exceeded}

The Cowriter allows 20 requests per minute per backend user. If you
hit the limit, wait a moment and try again. The `Retry-After`
response header indicates when the limit resets.