Add REASONING_EFFORT configuration and UI support

README.md

@@ -45,6 +45,7 @@ Use these tokens in app arguments:
 - `TOP_P`
 - `TOP_K`
 - `MIN_P`
+- `REASONING_EFFORT`
 - `REASONING_STOP`
 
 Example:
@@ -53,6 +54,11 @@ Example:
 -m MODEL -c CONTEXT_SIZE -t THREADS -ngl GPU_LAYERS --temp TEMP --top-p TOP_P --top-k TOP_K --min-p MIN_P
 ```
 
+For llama-server reasoning controls, configure `--chat-template-kwargs REASONING_EFFORT`.
+The placeholder expands to a single JSON argument such as `{"reasoning_effort": "medium"}`.
+When this placeholder is selected for the current app and model, the model options panel provides
+the presets `none`, `low`, `medium`, `high`, and `xhigh`.
+
 ## Setup
 
 ### lm-launcher.properties