LLM summary using local Ollama timeout after 1 minute

**Describe the bug** LLM summary fails to generate using local Ollama after exactly 1 minute timeout and show HTTP 504 error in changedetection.io and HTTP 500 in Ollama logs. I have OpenWebUI hosted and it works fine. **Version** 0.55.3 **How did you install?** Docker **To Reproduce** Steps to reproduce the behavior: 1. Have Ollama installed in Docker 2. Have Change Detection installed in Docker 3. Configure local Ollama provider at http://ip:11434 with installed lightweight models like gemma3, llama3.1, etc. 4. Generate summary for any site watch **Expected behavior** Summary generation. **Screenshots** <img width="329" height="142" alt="Image" src="https://github.com/user-attachments/assets/efccc9bf-a5fd-4b11-b8aa-5ee4ac354c21" /> <img width="815" height="59" alt="Image" src="https://github.com/user-attachments/assets/a72ef783-a22d-4b00-9109-54f8438c5f34" /> **Desktop (please complete the following information):** - OS: Arch Linux **Additional context** -