TextMentionTermination should not check all messages

[OnePaiGu]

As is known, Autogen Studio currently does not support turn-by-turn dialogue. Within the same session, each run is independent. I want to develop a feature that allows runs within the same session to be aware of each other.

My idea is to load previous messages into the task before starting each run. However, I encountered an issue with Autogen's TextMentionTermination mechanism, which checks all messages for the presence of specified text. This causes the new run to terminate immediately when previous messages are loaded, which is not the desired effect.

My question is, why doesn’t TextMentionTermination check each message as it is produced, instead of checking all messages every time? This way, even if historical messages contain specific TextTermination, my new task won’t end directly.

here is the source code:

    async def __call__(self, messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> StopMessage | None:
        if self._terminated:
            raise TerminatedException("Termination condition has already been reached")
        for message in messages:
            if self._sources is not None and message.source not in self._sources:
                continue

            content = message.to_text()
            if self._termination_text in content:
                self._terminated = True
                return StopMessage(
                    content=f"Text '{self._termination_text}' mentioned", source="TextMentionTermination"
                )
        return None

I want to change the code to look like this:

    async def __call__(self, messages: Sequence[BaseAgentEvent | BaseChatMessage]) -> StopMessage | None:
        if self._terminated:
            raise TerminatedException("Termination condition has already been reached")
        current_message =  messages[-1]
        if self._sources is not None and current_message.source not in self._sources:
            return None

        content = current_message.to_text()
        if self._termination_text in content:
            self._terminated = True
            return StopMessage(
                content=f"Text '{self._termination_text}' mentioned", source="TextMentionTermination"
            )
        return None

Is there any problem if I change this?