When the AI provider refuses a request, you are told, and not charged

Very rarely, the AI provider's safety filter refuses a request outright and returns nothing. Until now the chat showed an empty reply with no explanation, and the turn was still charged. Both are fixed:

• You are told. The chat now shows a notice that the provider declined the request, and that the cause is usually something earlier in the conversation rather than your last message. The action offered is Undo & rephrase, because sending the same thing again gets the same refusal.
• You are not charged for a refused turn that produced nothing.