Ekin

@CommandCodeAI when we will get /goal ? :P

MiMo-V2.5-Pro & MiMo-V2.5 are now ~99% off on Command Code. This is like 100x more usage! Input, output, and cache pricing are all lower. Works on every plan + extra top-ups. Pick the /model and go! Our $1 Go plan with $10 in it is perfect for this. Let's go!

@MrAhmadAwais Looking forward to it!

Last night, I discovered a couple major improvements we can make to open models in Command Code. None of the coding agents have these. Pretty excited to improve and soon share the learnings with all, so everyone can improve not just us.

@vipulgupta2048 I am building a Telegram bot daemon to talk to commandcode from telegram and I am using the headless mode inside the daemon. But headless does not save or expose full context so it makes it really difficult to maintain a session within the bot. I wish it did though

Looking for feedback from the X fam on changelog posts like this? What would you do differently to post updates to your community? cc: DX / DevRel folks

Early versions of the telegram bot I’m building. @CommandCodeAI

I am implementing a Telegram bot to talk to @CommandCodeAI from Telegram and I am loving commandcode so far. But I have a few issues tied to this project:

I would suggest that the headless mode should have an option to at least save the session to a file, and the option to resume from that file. Or maybe the team is considering implementing a server version like opencode has?

- Every tool call context gets lost. Except the agent’s message to the user, everything gets lost. Even if the bot works right now, it just burns tokens and loses context constantly.

- The headless mode does not maintain a session file, so I am forced to maintain my own session file. (Bot uses headless) This would normally not be a huge issue, but the headless mode only outputs the agent’s response to the user.