# Gotcha of the day: preserve_reasoning on local backends vs. framework overrides

> Source: <https://forum.level1techs.com/t/gotcha-of-the-day-preserve-reasoning-on-local-backends-vs-framework-overrides/258410#post_1>
> Published: 2026-10-12 03:46:30+00:00

Symptom: Qwen3.8-Flash-Next and GLM-5.3-Flash repeat plans in reasoning, rethinking again and again in each block without apparent awareness of prior turns and being slow to progress under Hermes Agent.

Cause: By default, Hermes Agent strips reasoning from assistant replays for custom providers, whatever the backend and the chat template might have set it to. This can cause problems for models that accept (or indeed expect) preserved reasoning. Other frameworks may have similar defaults, though I am not familiar with any specific examples.

Fix: Set `model.reasoning_echo` to`true` in Hermes Agent config.

Just thought this might be non-obvious and useful for anyone else having loopy local models in agentic harnesses. That would be all.