Add support for GPT-5.4 capabilities in OpenAI provider extensions

app/MindWork AI Studio/Settings/ProviderExtensions.OpenAI.cs

@@ -154,13 +154,36 @@ private static List<Capability> GetModelCapabilitiesOpenAI(Model model)
                 Capability.RESPONSES_API, Capability.CHAT_COMPLETION_API,
             ];
 
+        if(modelName is "gpt-5.3" || modelName.StartsWith("gpt-5.3-"))
+            return
+            [
+                Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
+                Capability.TEXT_OUTPUT,
+
+                Capability.FUNCTION_CALLING, Capability.OPTIONAL_REASONING,
+                Capability.WEB_SEARCH,
+                Capability.RESPONSES_API, Capability.CHAT_COMPLETION_API,
+            ];
+
+        if(modelName is "gpt-5.4" || modelName.StartsWith("gpt-5.4-"))
+            return
+            [
+                Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
+                Capability.TEXT_OUTPUT,
+
+                Capability.FUNCTION_CALLING, Capability.OPTIONAL_REASONING,
+                Capability.WEB_SEARCH,
+                Capability.RESPONSES_API, Capability.CHAT_COMPLETION_API,
+            ];
+
         return
             [
                 Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
                 Capability.TEXT_OUTPUT,
 
                 Capability.FUNCTION_CALLING,
                 Capability.RESPONSES_API,
+                Capability.WEB_SEARCH,
             ];
     }
 }

app/MindWork AI Studio/wwwroot/changelog/v26.3.1.md

@@ -6,6 +6,7 @@
 - Added the ability to load a system prompt from a file when creating or editing chat templates.
 - Added a start-page setting, so AI Studio can now open directly on your preferred page when the app starts. Configuration plugins can also provide and optionally lock this default for organizations.
 - Added math rendering in chats for LaTeX display formulas, including block formats such as `$$ ... $$` and `\[ ... \]`.
+- Added the latest OpenAI models.
 - Released the document analysis assistant after an intense testing phase.
 - Improved enterprise deployment for organizations: administrators can now provide up to 10 centrally managed enterprise configuration slots, use policy files on Linux and macOS, and continue using older configuration formats as a fallback during migration.
 - Improved the profile selection for assistants and the chat. You can now explicitly choose between the app default profile, no profile, or a specific profile.