meleki/gott
1
0 Fork 0
Code Activity

Cache Provider-Modelle in models_cache.json statt bei jedem Start von APIs zu laden

Browse Source 
- LoadModelsAsync() prüft zuerst data/models_cache.json
- Bei Cache-Hit: kein API-Call, sofortiger Start
- RefreshModelsFromApis() lädt von APIs + speichert Cache
- POST /api/models/refresh Endpoint für manuellen Refresh
- dataDir an OpenAiService-Konstruktor übergeben
This commit is contained in:
Meleki committed 2026-03-12 08:57:47 +01:00
1 parent 145441fa7b
commit ed6e78de56
3 files changed
+62 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

Program.cs
+1 -1
View File
@@ -70,7 +70,7 @@ builder.Services.AddSingleton<AnthropicService>(sp =>
// OpenAI-kompatibler Service (Nvidia etc.)
builder.Services.AddSingleton<OpenAiService>(sp =>
new OpenAiService(sp.GetRequiredService<IHttpClientFactory>(), dbService, sp.GetRequiredService<ToolService>(), builder.Configuration));
new OpenAiService(sp.GetRequiredService<IHttpClientFactory>(), dbService, sp.GetRequiredService<ToolService>(), builder.Configuration, dataDir));
// Telegram Bot (pro Session – Token aus Session-Config)
var maxIterations = builder.Configuration.GetValue<int>("MaxIterations", 100);