--- title: "Administration" manual: "LLM Foundation" version: "0.44" permalink: "https://docs.typo3.org/permalink/netresearch/nr-llm:administration@0.44" source: "Administration/Index.rst" rendered: "2026-11-12T17:35:48+00:00" --- # Administration {#administration} This guide walks you through managing AI providers, models, configurations, and tasks in the TYPO3 backend. It also covers the AI-powered wizards that automate most of the setup. ## The LLM backend module {#administration-backend-module} All AI **management** happens in **AI**; editors run prepared tasks and decide approvals in the separate **AI > AI Tasks** module ([Backend user permissions](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-permissions@0.44)). The **Overview** is a guided starting point: - a **usage & cost** band across the top — 30-day cost, requests and tokens, the per-provider request mix, and a daily-requests sparkline (empty until the first request); - a unified **Set up & manage** grid where each module card carries its own setup state — *green* when it is configured, a blue *Next* flag on the single recommended step, and *Empty* on an optional module with no entries yet — so the next action is always visible without a separate wizard. Each card links to its module; - the **Providers** card shows a live, **token-free** reachability indicator per configured provider (a model-list/health ping, never a completion); - a **For developers** section showing how to call the same configuration from PHP via `LlmServiceManager`. The Overview's docheader carries a **Governance** tab — the read-only **effective policy** readout ([ADR-140](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-140@0.44)). It lists the four governance keys that carry a decision (`privacy.level`, `privacy.retentionDays`, `tools.dataClassEnforcement`, `skills.minTrustLevel`) with the value the runtime applies right now and the class that resolved it. Two things it deliberately does not do: it never changes a value — instance-wide keys are set in the Install Tool under **Settings > Extension Configuration > nr_llm** — and it never shows a value it did not get from a resolver, so a row that cannot be answered reads `unknown` rather than a default. Because the reads go through the runtime resolvers, the tab shows what is *in force*: a mistyped `tools.dataClassEnforcement` reads `enforce`, because the gate is fail-closed ([ADR-113](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-113@0.44)). The keys, their fallbacks and recommended settings are documented under [Effective policy](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-governance@0.44). Two rows say more than their value alone: - `tools.dataClassEnforcement = observe` is annotated as applying to built-in tools only. Tools reached through an MCP server are always enforced against the trust-zone ceiling ([ADR-115](https://docs.typo3.org/permalink/netresearch/nr-llm:adr-115@0.44)), so an MCP tool can be dropped while this row reads `observe`. - Every `privacy.retention.` override that deviates from `privacy.retentionDays` gets its own row underneath it. Categories left at `0` resolve to the global window and are not listed — see [Data retention & purge](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-data-retention@0.44) for the full set. ![The LLM Overview — a usage-and-cost band, a status-coloured module card grid, and a developer section](../Images/backend-dashboard.png) The admin module tree has seventeen sections accessible from the left-hand navigation: - **Overview** — guided dashboard: usage & cost, per-module setup state, and the developer guide - **Providers** — API connections - **Models** — available LLM models - **Configurations** — use-case presets - **Tasks** — one-shot prompt templates - **Snippets** — tagged reusable prompt fragments - **Glossaries** — translation term pairs per site and language pair - **Term lists** — forbidden and required terms that stop generated text - **Get Started** — pick a use case and install a matching pack of configuration, tasks and snippets (admin-only) - **Setup wizard** — guided provider, model and configuration setup (admin-only) - **Skills** — GitHub-hosted `SKILL.md` sources (admin-only) - **Tools** — enable or disable the agent tools (admin-only) - **MCP servers** — configure external MCP servers and import their tool catalogues (admin-only) - **Playground** — run the agent tool loop interactively (admin-only) - **Agent runs** — review and decide runs paused for approval or input (admin-only) - **Analytics** — usage and cost dashboard (admin-only) - **Error hints** — the newest logged errors, with a model's hint on request (admin-only, [Error hints](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-error-hints@0.44)) Editors do not use this tree: their surface is the separate **AI > AI Tasks** module, opened per backend group through the [permission grants](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-permissions@0.44). A head editor who may see the usage of his editors gets the module **AI > AI usage of my groups** the same way ([AI usage of assigned groups](https://docs.typo3.org/permalink/netresearch/nr-llm:administration-group-usage@0.44)). - [Managing providers](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-providers@0.44) - [Managing models](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-models@0.44) - [Managing configurations](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-configurations@0.44) - [Site settings](https://docs.typo3.org/permalink/netresearch/nr-llm:site-settings@0.44) - [Choosing a record from a list](https://docs.typo3.org/permalink/netresearch/nr-llm:choosing-a-record-from-a-list@0.44) - [Managing tasks](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-tasks@0.44) - [Managing prompt snippets](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-prompt-snippets@0.44) - [Managing translation glossaries](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-translation-glossaries@0.44) - [Term lists](https://docs.typo3.org/permalink/netresearch/nr-llm:term-lists@0.44) - [Rule-set judge](https://docs.typo3.org/permalink/netresearch/nr-llm:rule-set-judge@0.44) - [Get Started: use-case packs](https://docs.typo3.org/permalink/netresearch/nr-llm:get-started-use-case-packs@0.44) - [Managing skills](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-skills@0.44) - [Importing and reviewing skill sources](https://docs.typo3.org/permalink/netresearch/nr-llm:importing-and-reviewing-skill-sources@0.44) - [Authoring local skills](https://docs.typo3.org/permalink/netresearch/nr-llm:authoring-local-skills@0.44) - [Approving and revoking skill versions](https://docs.typo3.org/permalink/netresearch/nr-llm:approving-and-revoking-skill-versions@0.44) - [Attaching and loading skills](https://docs.typo3.org/permalink/netresearch/nr-llm:attaching-and-loading-skills@0.44) - [Skill trust and integrity controls](https://docs.typo3.org/permalink/netresearch/nr-llm:skill-trust-and-integrity-controls@0.44) - [Running tools](https://docs.typo3.org/permalink/netresearch/nr-llm:running-tools@0.44) - [Managing enabled tools and groups](https://docs.typo3.org/permalink/netresearch/nr-llm:managing-enabled-tools-and-groups@0.44) - [Editor action catalogue and batches](https://docs.typo3.org/permalink/netresearch/nr-llm:editor-action-catalogue-and-batches@0.44) - [Using the Tool Playground](https://docs.typo3.org/permalink/netresearch/nr-llm:using-the-tool-playground@0.44) - [Tools, languages and workspaces](https://docs.typo3.org/permalink/netresearch/nr-llm:tools-languages-and-workspaces@0.44) - [Read and interaction tool catalogue](https://docs.typo3.org/permalink/netresearch/nr-llm:read-and-interaction-tool-catalogue@0.44) - [Write-tool authorization and previews](https://docs.typo3.org/permalink/netresearch/nr-llm:write-tool-authorization-and-previews@0.44) - [Redirects and cache tools](https://docs.typo3.org/permalink/netresearch/nr-llm:redirects-and-cache-tools@0.44) - [Tool network policy and external pages](https://docs.typo3.org/permalink/netresearch/nr-llm:tool-network-policy-and-external-pages@0.44) - [Skill tool grants](https://docs.typo3.org/permalink/netresearch/nr-llm:skill-tool-grants@0.44) - [Registering tools](https://docs.typo3.org/permalink/netresearch/nr-llm:registering-tools@0.44) - [MCP servers](https://docs.typo3.org/permalink/netresearch/nr-llm:mcp-servers@0.44) - [A2A remote agents](https://docs.typo3.org/permalink/netresearch/nr-llm:a2a-remote-agents@0.44) - [AI-powered wizards](https://docs.typo3.org/permalink/netresearch/nr-llm:ai-powered-wizards@0.44) - [Per-user AI budgets](https://docs.typo3.org/permalink/netresearch/nr-llm:per-user-ai-budgets@0.44) - [Backend user permissions](https://docs.typo3.org/permalink/netresearch/nr-llm:backend-user-permissions@0.44) - [Verifying the specialized services](https://docs.typo3.org/permalink/netresearch/nr-llm:verifying-the-specialized-services@0.44) - [Translating with autotranslate](https://docs.typo3.org/permalink/netresearch/nr-llm:translating-with-autotranslate@0.44) - [Usage analytics](https://docs.typo3.org/permalink/netresearch/nr-llm:usage-analytics@0.44) - [Monthly billing and export](https://docs.typo3.org/permalink/netresearch/nr-llm:monthly-billing-and-export@0.44) - [Provider health diagnostics](https://docs.typo3.org/permalink/netresearch/nr-llm:provider-health-diagnostics@0.44) - [AI usage of assigned groups](https://docs.typo3.org/permalink/netresearch/nr-llm:ai-usage-of-assigned-groups@0.44) - [Error hints](https://docs.typo3.org/permalink/netresearch/nr-llm:error-hints@0.44) - [Agent runs](https://docs.typo3.org/permalink/netresearch/nr-llm:agent-runs@0.44) - [Queues and background answers](https://docs.typo3.org/permalink/netresearch/nr-llm:queues-and-background-answers@0.44) - [Batch actions](https://docs.typo3.org/permalink/netresearch/nr-llm:batch-actions@0.44) - [Recovery and run expiry](https://docs.typo3.org/permalink/netresearch/nr-llm:recovery-and-run-expiry@0.44) - [Data retention & purge](https://docs.typo3.org/permalink/netresearch/nr-llm:data-retention-purge@0.44) - [Command-line operation](https://docs.typo3.org/permalink/netresearch/nr-llm:command-line-operation@0.44) - [Effective policy](https://docs.typo3.org/permalink/netresearch/nr-llm:effective-policy@0.44) - [Policy profiles and retention overrides](https://docs.typo3.org/permalink/netresearch/nr-llm:policy-profiles-and-retention-overrides@0.44) - [Inspecting the effective policy](https://docs.typo3.org/permalink/netresearch/nr-llm:inspecting-the-effective-policy@0.44) - [Routing and request diagnostics](https://docs.typo3.org/permalink/netresearch/nr-llm:routing-and-request-diagnostics@0.44) - [AI-written record marker](https://docs.typo3.org/permalink/netresearch/nr-llm:ai-written-record-marker@0.44)