The Bot will not respond to thread messages that do not start an AI conversation from the initial message #15
Comments
spantaleev
added a commit
that referenced
this issue
Oct 1, 2024
…a thread This actually fixes 2 issues. Fixes #14 Fixes #17 When people enable transcribe-only mode and the bot replies outside of a thread, messages will no longer look like this: `> 🦻 Transcribed text`. Instead, they will: - look like this: `Transcribed text` - get an emoji reaction (🦻) sent by the bot itself, to indicate that the message is a transcription --------------------------------------- As #14 discusses, the `> 🦻` prefixing of messages also served the purpose of indicating to the bot that this is not its own message, but rather something it "heard" from a user. Given that out-of-thread replies no longer include this, they could be mistaken for bot messages. Because transcribed messages are posted as notice messages, we can easily tell them apart from regular text-generated messages by the bot itself, so we can (and do) treat them differently. Thankfully, the bot does not yet support building a text-generation conversation from arbitrary messages (something discussed in #15), so these out-of-thread replies having the wrong owner are not an issue for now. If we do land support for this, we'll probably need to make the bot inspect such notice messages posted by it, inspect their reactons and attribute them properly (🦻 -> user message).
|
I've also been considering adding this feature (I need it in a multi-user room), so thank you for bringing it up! This new On-demand involvement feature is part of the 1.2.0 release. On the feature's documentation section you can find some screenshots of how it looks and description of how it behaves (when a user is directly invoking the bot in a thread or reply chain, non-user messages are now intentionally considered as part of the context). |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Thank you to the etke.cc team for developing this excellent tool. Currently, it has replaced almost all the AI Bots I use on Matrix, except for one small feature request:
In a thread message list that doesn't start with a direct conversation with the Bot, @ or !bai doesn't trigger the robot's response. At this time, conversation participants usually need AI to help with temporary tasks, such as translating messages or summarizing thread messages.
I hope the Bot can respond to @ or !bai in any thread to participate in the conversation. It will reply in the thread, and in this thread, it can read the context. After that, unless it continues to be @ or !bai, it won't participate in subsequent conversations (of course, this is only limited to threads that don't start with direct conversations with the Bot).
The text was updated successfully, but these errors were encountered: