unknown

Ok so I spent like 13 hours yesterday and I have some really fun stuff for Discord from both myself and several contributors. Long list incoming:

⭐ You can now VC with your agents in servers! Use either the /vc command, or set specific channels in your config that your agent will automatically join when you do! This uses the existing voice support in the OpenClaw core, so  if you have something that's not supported with your STT/TTS setup, improvements will benefit both! I tested this one with whisper and OpenAI's TTS, and it wasn't the most real-time yet, but there are some awesome maintainers working on that in the OpenClaw core!

⭐ Discord-connected agents can now have their messages streamed into Discord as well! This is off by default, and a bit slower than Telegram, but has been cool to see.

- You can now have all slash commands respond as ephemeral (only visible by you and not persistant) instead of sitting in the channel forever.

- Your agent can now create and edit the tags on forum channels for better organization.

- Agents will now automatically read the channel topics, letting you provide even more context for it! (This will only happen on new sessions when a session first starts)

- Subagents can now display their progress and updates in a thread off the message that the agent spawned it in, rather than going blind

- The /models command now has a fancy UI with buttons and dropdowns instead of just the wall of text, including recent models

- You can now force specific Discord channels to use specific models! Got a channel you want to always use Minimax in instead of GPT? Sure we can do that

- Lots of cleanup fixes for disconnects, lazy-loading guilds on startup, making components work in DMs, reducing ping spam, and a lot more

If you have any issues or thoughts about these Discord-specific features, come join us in the Discord channel called "#channels" that has a post about the Discord channel plugin. (So easy to understand, I know, I'll accept my medal now)

A tweet teasing Discord-related projects developed over 13 hours with contributions from multiple people, with no further details provided.