#Openclaw in loop

1 messages · Page 1 of 1 (latest)

ornate tide
#

When I ask my bot in telegram (have to check whether in the openclaw-ui as well), then he generates an answer in a loop and keeps generating the same answer without end. What could be the cause? I am using qwen3.5 self-hosted with llamacpp.

tranquil graniteBOT
#

To help others find answers, you can mark your question as solved via Right click solution message -> Apps -> âś… Mark Solution

karmic salmonBOT
#

That symptom can come from two very different places, and the fix depends on which one you’re actually seeing:

1) It’s “one message that keeps getting edited/extended” (Telegram streaming preview)

On Telegram, OpenClaw can send a temporary preview message and keep editing it while the model streams. If your model never hits EOS / never stops, it looks like an infinite loop.

Common causes with llama.cpp + Qwen:

  • wrong chat template (Qwen needs the Qwen template; the wrong one can prevent proper EOS)
  • llama.cpp running with something like ignore-EOS, or no practical max_tokens / n_predict limit
  • decoding params that encourage repetition (too low temp + weak repeat penalty)

What to try (llama.cpp side):

  • ensure you’re using the correct Qwen chat template
  • ensure generation has a hard cap (max_tokens / n_predict) and you’re not ignoring EOS
  • bump repetition controls (e.g., repeat penalty) so it can’t spiral

2) It’s sending the same finished answer again and again (delivery/session loop)

If Telegram shows multiple separate messages (or the same final answer re-sent repeatedly), that’s usually not the model—it’s OpenClaw replaying a stuck state.