qwen2.5:7b leaked Chinese/Cyrillic mid-reply despite the OUTPUT_LANGUAGE lock, which was buried mid-prompt. Repeat the lock at the END of the system prompt (recency) and ban specific foreign scripts explicitly.
qwen2.5:7b leaked Chinese/Cyrillic mid-reply despite the OUTPUT_LANGUAGE lock, which was buried mid-prompt. Repeat the lock at the END of the system prompt (recency) and ban specific foreign scripts explicitly.