correct thinking modes for each model

docs/USER_GUIDE.md

@@ -14,9 +14,10 @@ agent-extension data stay on this Mac.
    and chat data.
 3. Choose **File > New Chat** (`⌘N`). Select a thinking profile and a shell
    permission mode in the composer.
-4. Enter a request and send it. **Thinking** is the DS4 default, **Direct** omits
-   hidden reasoning, and **Think Max** appears only when that model profile has
-   the required long context.
+4. Enter a request and send it. The choices match the selected model: DeepSeek
+   offers **Direct**, **Think Low**, **Think High**, and **Think Max**; GLM 5.2
+   offers **Direct**, **Think High**, and **Think Max**; GLM 5.3 Flash always
+   thinks and offers **Think Low**, **Think High**, and **Think Max**.
 
 The selected model is shared by the app and the optional local HTTP endpoint.
 Preferences are saved locally and generation settings are scoped by model and
@@ -219,6 +220,13 @@ client and do not appear in the sidebar. CORS is off by default; enable it only
 for trusted browser clients on this Mac. Saving changed endpoint settings
 restarts the local listener.
 
+`reasoning_effort` accepts only the selected model's advertised values from
+`GET /v1/models`: DeepSeek accepts `none`, `low`, `high`, or `max`; GLM 5.2
+accepts `none`, `high`, or `max`; GLM 5.3 Flash accepts `low`, `high`, or `max`.
+Omitting it uses the upstream model default: `low` for DeepSeek and `max` for
+both GLM models. Unsupported values and conflicting thinking controls return a
+400 error instead of being converted to another effort.
+
 ### Data and recovery
 
 Application data is under