feat: OpenAI-kompatibler Provider (Nvidia/g4f.space) mit Tool-Calling und SSE-Streaming

- OpenAiService.cs: Neuer Service für OpenAI-kompatible APIs
  - SSE-Streaming mit text_start/text_delta/text_end Events
  - Tool-Calling: list_files, read_file, write_file, edit_file, delete_file, execute
  - Agentic Loop (max 10 Iterationen)
  - Tool-Use + Tool-Result in DB gespeichert
  - History-Rebuild: Anthropic-Format → OpenAI-Format (tool_use/tool_result korrekt konvertiert)
- ChatContext.cs: Provider-Feld hinzugefügt
- ChatService.cs: OpenAI-Provider-Erkennung in ResolveModelId + PrepareContext
- ChatEndpoint.cs: Provider-Dispatch (nvidia → OpenAiService, sonst → AnthropicService)
- Program.cs: OpenAiService als Singleton registriert
- wwwroot/index.html: nvidia:moonshotai/kimi-k2.5 in Modell-Auswahl

Program.cs

@@ -68,6 +68,10 @@ builder.Services.AddSingleton<AnthropicService>(sp =>
     return svc;
 });
 
+// OpenAI-kompatibler Service (Nvidia etc.)
+builder.Services.AddSingleton<OpenAiService>(sp =>
+    new OpenAiService(sp.GetRequiredService<IHttpClientFactory>(), dbService, sp.GetRequiredService<ToolService>()));
+
 // Telegram Bot (pro Session – Token aus Session-Config)
 var maxIterations = builder.Configuration.GetValue<int>("MaxIterations", 100);
 builder.Services.AddSingleton<TelegramService>(sp =>