Fix maxOutputTokens too low for gemini-3.5-flash thinking model

gemini-3.5-flash uses thinking tokens that share the same budget as output
tokens. With maxOutputTokens=200 (vision) or 100 (intent), the model would
exhaust the budget on thinking (~288-1043 tokens) and truncate the actual
response to 8-11 tokens, producing garbage output like "040825".

Fix: 2048 for vision (needs full JSON), 1024 for intent, 512 for connection test.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

app/Http/Livewire/Chat/ShowConfiguracionChat.php

@@ -110,7 +110,7 @@ class ShowConfiguracionChat extends Component
                 $inicio   = microtime(true);
                 $body     = [
                     'contents'         => [['parts' => [['text' => 'Responde solo "ok"']]]],
-                    'generationConfig' => ['maxOutputTokens' => 5, 'temperature' => 0],
+                    'generationConfig' => ['maxOutputTokens' => 512, 'temperature' => 0],
                 ];
                 $response = Http::timeout(15)
                     ->withHeaders(['Content-Type' => 'application/json'])

app/Services/GeminiIntentService.php

@@ -27,7 +27,7 @@ class GeminiIntentService
     {
         return [
             'contents'         => $contents,
-            'generationConfig' => array_merge(['temperature' => 0.1, 'maxOutputTokens' => 100], $genConfig),
+            'generationConfig' => array_merge(['temperature' => 0.1, 'maxOutputTokens' => 1024], $genConfig),
         ];
     }
 

app/Services/GeminiVisionService.php

@@ -34,7 +34,7 @@ class GeminiVisionService
 
         $body  = [
             'contents'         => $contents,
-            'generationConfig' => ['temperature' => 0.1, 'maxOutputTokens' => 200],
+            'generationConfig' => ['temperature' => 0.1, 'maxOutputTokens' => 2048],
         ];
 
         $inicio    = microtime(true);