Add docu on custom request settings (#662)

fixed #661

Signed-off-by: Jonas Helming <jhelming@eclipsesource.com>

src/docs/user_ai.md

@@ -17,6 +17,7 @@ Theia AI features within the Theia IDE are currently disabled by default. See th
   - [Hugging Face](#hugging-face)
   - [LlamaFile](#llamafile-models)
   - [Ollama](#ollama)
+  - [Custom Request Settings](#custom-request-settings)
 - [Current Agents in the Theia IDE](#current-agents-in-the-theia-ide)
   - [Universal (Chat Agent)](#universal-chat-agent)
   - [Orchestrator (Chat Agent)](#orchestrator-chat-agent)
@@ -108,6 +109,36 @@ To connect to models hosted via [Ollama](https://ollama.com/), enter the corresp
 
 <img src="../../ollama-setting.png" alt="Ollama configuration in the Theia IDE" style="max-width: 525px">
 
+### Custom Request Settings
+
+You can define **custom request settings** for specific language models in the Theia IDE to tailor how models handle requests, based on their provider.
+
+Add the settings in `settings.json`:
+
+```json
+"ai-features.modelSettings.requestSettings": [
+    {
+        "modelId": "Qwen/Qwen2.5-Coder-32B-Instruct",
+        "requestSettings": { "max_new_tokens": 2048 },
+        "providerId": "huggingface"
+    },
+    {
+        "modelId": "gemma2",
+        "requestSettings": { "stop": ["<file_sep>"] },
+        "providerId": "ollama"
+    }
+]
+```
+
+Or navigate in the settings view to **`ModelSettings` => `Request Settings`**.
+
+#### Key Fields
+- **`modelId`**: The unique identifier of the model.
+- **`requestSettings`**: Provider-specific options, such as token limits or stopping criteria.
+- **`providerId`**: *(Optional)* Specifies the provider for the settings (e.g., `huggingface`, `ollama`, `openai`). If omitted, settings apply to all providers that match the `modelId`.
+
+Valid options for `requestSettings` depend on the model provider.
+
 ## Current Agents in the Theia IDE
 
 This section provides an overview of the currently available agents in the Theia IDE. Agents marked as “Chat Agents” are available in the global chat, while others are directly integrated into UI elements, such as code completion. You can configure and deactivate agents in the AI Configuration view.