johner

yes this is how i run. When you first run the gemini cli tool, you select the first option (Sign in with Google), it will then displace a web link, you click that, it'll open the google sign in page in you browser, and once you've given it permission, you copy the code, go back to Unriad AI CLI TAB and paste in the code, it will then persist this in the home storage for gemini cli for all worksapces you use it on. So on launch you'll see this, if not type /auth and select sign out and relaunch Then you'll get: You should be able to click the HTTPS link Click and sign in then: Click copy, and paste in the terminal (see first screenshot)

Ok so I think the best I can do is use a similar approach to limetech, and use squashFS, it'll give a similar outcome to a compressed btrfs loopdevice without the complexity. I'll split the agents across files to minimise risk of hitting the 4gb fat32 limit on the USB. I'll need to figure this all out!

The latest version should have a small terminal icon button on the little drawer tab to launch a pop up terminal with the home set and workspace path ready to go.

if you have the unassigned devices plugin you should be able to see if it's 'writing' to flash, which is what sloooows it down. I've tried a few different approaches, I'm moving any file operations into the runtime out of the plugin install/upgrade script, it'll take some time to then get it reliable while not in a focused upgrade session. You should be able to close the window and it'll run in the background. Ultimately I think the only real way to improve this is to avoid the USB and RAM drives, which means array and the problems that brings if down, or an unassigned device which isn't guarenteed. I'll see if I can find a better/more creative way! Thx for your patience.

Are you dropping into the unraid shell? as the cli tab doesn't allow dropping into the shell. I might add this option as the home path in the unriad shell is different (the default for root), it's automatically overridden in the cli tab. You might be able to temporarily override the unraid shell home path, google came up with: export HOME=/mnt/user/your_new_path cd $HOME

Hi, there is a 4gb limit on fat32 devices like the USB stick. Your /mnt/nvme/appdata is this an 'unassigned devices' direct disk mapping location or an array location? I've yet to test unassigned devices as I need to find or but one to put in, let me accellerate that! What agent(s) are you using?

ok I'll check the migration logic, thanks for letting me know and I'm glad you resolved it manually!

so in the new version there is a dedicated loop back file called agent.img on the USB (by default), it is mounted /usr/local/emhttp/plugins/unraid-aicliagents/agents

because I need it to run when the array is offline, which is the reason to not use docker. I've nearly finished testing an upgrade that allows a user to run agents from usb (read only) and home in ram and occasionally backed up to USB to (deltas) to minimise USB wear. With it a user will be able to move the agent store and/or home to arrary (if you don't mind it not being available when stopped), or ideally to an unassigned device mount which will still be available when the array is stopped.

I’ve nearly finished a version which changes the approach to avoid these issues, I’m about to sleep, so will work on it tomorrow, should be available in about 12-18h hopefully if no major issues.

Hi, Yes I had a similar issue with VMs stopping. There is a chance the RAM disk got exhausted, I’m working on moving the installers back to usb / alternative. In the interim, if you google ‘Unraid increase RAM disk’ or the like, you should be able to give it some breathing room. Else/and uninstall any agents you’re not using often until I fix. Thanks for reporting.

Sounds like a bug or two! I’ll try and fix those.

Is this in Claude? In Gemini I had to change a setting to use alt screen buffer. Have a google to see if something similar on the Linux version of Claude. I’ll review the other response too.

Hi, Try the new version. You should now be able to drop into the normal unraid shell (top right icon) or ssh: The commands are mapped to your persistant home and aliased, so you should now be able to run claude mcp add etc. Let me know how you go Thanks John

can you send a screen shot please? I'm not familiar with what the left side menu is, i'll go investigate though as curious now! UPDATE: I had a quick check of settings, and a google search, it appears you're using a custom theme - is that right? If not, can you point me to where the setting is please? This is how it renders on mine with the regular menu: The tab on the left to open the drawer can be moved up and down.

Hi Sanjay. I have updated the plugin, quite a few changes, a couple for you to test: 1) Gemini CLI now installs via npm like the others, you might need to uninstall then reinstall. Hopefully the docs are now there - i'm not sure what to look for to test. 2) I changed the active location for home to be /tmp/... this gives the highest performance, removes the wear concern, but you'll lose it on reboot 3) The plugin will allow you to manually back up on click of a button in settings, on a schedule, or automatically when all workspaces are closed. It backs up to usb as on reboot it will restore back into ram. 4) currently you can't change the home path due to the above changes, if you really want to make it editable again, let me know, but using the array defeats the point of the plugin of being there to help when you have array, or docker issues etc. Thanks John

Hi, I changed the approach to use npm yesterday, I haven’t pushed to GitHub yet as working through a couple defects on new features. I’ll try and get it out tonight or tomorrow (I’m in Australia). I can change the default but I wanted it to work with the array down and didn’t want to risk losing anything. I’ll get Gemini to add a backup feature :-) The location can be changed on the settings page. Thanks for your feedback!

haha using llms.txt could be a fund way to cause havoc with openclaw instances

wow this is exactly what we need. Assuming you lead the charge, have you tried to get support from @limetech to endorse this? I'd love to take this and convert to a skill and workflow (or a set of) for AI coding agents, and then publish them. In the interim, have you considered adding a https://llmstxt.org/ Thanks John

sure objections welcomed. This is not about code review, I hear your point though, however if one doesn't know what is right or wrong as the information is scattered in unofficial sources, a self assessment/review doesn't help, my point was more it's about quality/security checks pre-publish, given once a repo is added plugins and dockers are not automatically added implies someone is approving something against a check list I assume? I don't have time to stab in the dark, I'm using AI to help analyse existing plugins and unraid frmaework code, but it wont capture everything. I'll totally be research the slackware topic and caching and adding to my standards for agents to follow.

thank you for the feedback! I've really struggled to find the standards, I tried following the forum posts but it's just too difficult. Is there a dev portal/wiki with all of this valuable standards based info in? I'm building out a set of agent files to capture the standards, so far they have been reverse engineering from the Unraid web gui public repo that has both the ui framework (obviosuly) and example/system plugins. The future is agentic coding of these, I assumed the unraid team review them prior to adding them to the CA App Store? There's a lot of utility in these agents, Limetech and the community shold be embracing them - I really hope limetech come up with a formal set of skills and workflows so I can replace mine! Docker vs Plugin - for me I wanted to be able to use these tools to manage the server, if docker is disabled then understandably these wouldn't be available. I think I cover root as you can change the user (I didn't add the feature to auto create a new user, I have this on my list) and caching - updates follow a similar approach to plugins, where on the settings page it performs a check, then enables the upgrade option if the user wants to perform it. I'll double check old cahced versions get removed - a simple change if not. I spent a lot of time on the uninstaller to ensure everything gets clean up, with the exception of settings/home directory contents. I was thinking of adding an archive feature to auto archive then delete the working folders.

Ha! we had a similar idea! I got gemini and claude to add a tab with the terminal embedded for those that don't want to manually SSH/use the standard root one which times our and destroys the session. AI coding agents makes making plugins soooo easy now.

I'm using Gemini CLI, it's been such a great experience building plugin's with it, there is no way I would have had the time to do so before, so they would never have materialised. It does all the hard work of figuring out how to make useful stuff work with Unraids framework.

Thanks for the feedback! Let me know if you need any changes/features added.

hi @Squid I think this thread is ready to move to the plugin support area, is that something I can do myself? if not, would you do the honours please?