Backend produced reasoning without actionable content, retrying

[eglia]

LocalAI version:
quay.io/go-skynet/local-ai:v4.1.3-gpu-vulkan@sha256:ab337d593517231464cd50fe81fa4f84ee9bda5be0856e2591cdfd5f020a70bf

Environment, CPU architecture, OS, and Version:
Linux 7997ab623f44 6.19.10+deb13-amd64 #1 SMP PREEMPT_DYNAMIC Debian 6.19.10-1~bpo13+1 (2026-04-02) x86_64 x86_64 x86_64 GNU/Linux
AMD Ryzen 7 3700X
Intel Arc Pro B70

Describe the bug
For some requests, mainly from nextcloud and home assistant, localai does not return any data, with the log showing Backend produced reasoning without actionable content, retrying multiple times. But the backend trace shows a valid response: response I am a helpful AI assistant designed to assist you with a wide range of tasks, from answering questions and searching fo...

To Reproduce
Connect nextcloud to localai, start a chat.

Expected behavior
Localai should return the produced message.

Logs
localai.log

Additional context

[mudler]

@eglia did you upgraded the llama.cpp backend or is this a new installation?

[eglia]

This is a new installation.