Support "minimal" reasoning effort

README.md

@@ -98,7 +98,7 @@ In addition to updating the OpenAI Base URL, you need to:
 
 2. Ensure the toggles for both options are **on**, as shown in the previous image.
 
-3. Add the custom models called exactly `gpt-high`, `gpt-medium`, and `gpt-low`, as shown in the previous image. You don't need to remove other models.
+3. Add the custom models called exactly `gpt-high`, `gpt-medium`, and `gpt-low`, as shown in the previous image. You can also create `gpt-minimal` for minimal reasoning effort. You don't need to remove other models.
 
 <details>
 <summary>Additional steps if you face this error:

app/azure/request_adapter.py

@@ -234,9 +234,9 @@ class RequestAdapter:
         responses_body["stream"] = True
 
         reasoning_effort = inbound_model.replace("gpt-", "").lower()
-        if reasoning_effort not in {"high", "medium", "low"}:
+        if reasoning_effort not in {"high", "medium", "low", "minimal"}:
             raise ValueError(
-                "Model name must be either gpt-high, gpt-medium, or gpt-low"
+                "Model name must be either gpt-high, gpt-medium, gpt-low, or gpt-minimal"
             )
 
         responses_body["reasoning"] = {