chore(core): change audio transcription job to use gemini 2.5 pro (#13202)

#### PR Dependency Tree


* **PR #13202** 👈

This tree was auto-generated by
[Charcoal](https://github.com/danerwilliams/charcoal)

<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit

* **New Features**
* Improved the "Transcript audio" text action by updating its default AI
model to "gemini-2.5-pro" for enhanced performance.
* Enhanced audio transcription accuracy by refining audio content
handling with a more specific audio format.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->

---------

Co-authored-by: DarkSky <darksky2048@gmail.com>

packages/backend/server/src/__tests__/mocks/copilot.mock.ts

@@ -111,6 +111,19 @@ export class MockCopilotProvider extends OpenAIProvider {
         },
       ],
     },
+    {
+      id: 'gemini-2.5-pro',
+      capabilities: [
+        {
+          input: [ModelInputType.Text, ModelInputType.Image],
+          output: [
+            ModelOutputType.Text,
+            ModelOutputType.Object,
+            ModelOutputType.Structured,
+          ],
+        },
+      ],
+    },
   ];
 
   override async text(

packages/backend/server/src/__tests__/utils/copilot.ts

@@ -433,7 +433,7 @@ export async function submitAudioTranscription(
   for (const [idx, buffer] of content.entries()) {
     resp = resp.attach(idx.toString(), buffer, {
       filename: fileName,
-      contentType: 'application/octet-stream',
+      contentType: 'audio/opus',
     });
   }
 

packages/backend/server/src/plugins/copilot/prompt/prompts.ts

@@ -303,7 +303,7 @@ const textActions: Prompt[] = [
   {
     name: 'Transcript audio',
     action: 'Transcript audio',
-    model: 'gemini-2.5-flash',
+    model: 'gemini-2.5-pro',
     optionalModels: ['gemini-2.5-flash', 'gemini-2.5-pro'],
     messages: [
       {