On 4/5/2026 at 5:38 AM, Joly0 said:

Btw, just did the latest update with the migration and everything and afterwards the directory /tmp/unraid-aicliagents/work/root/ was empty, so all sessions, configurations, etc were gone. I had to manually copy back those files from the backup location under /boot/config/plugins/unraid-aicliagents/persistence/root

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

On 4/4/2026 at 11:52 AM, nathanmlim said:

I tried this out and CONTINUALLY run into the SQLITE database is full error. It's very annoying. I also can't install all the different agent plugins because I can't seem to expand the agent binary storage past 4GB. I've already tried moving to /mnt/nvme/appdata but still run into problems. Am I doing something wrong?

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?

On 4/5/2026 at 7:47 AM, Joly0 said:

Also another thing i have noticed: When i have to debug mcp servers using npm/npx they do not use the correct paths and usually defualt back to /root/ directory instead of the /tmp/unraid-aicliagents/work/root/. Even when starting them like this /usr/local/emhttp/plugins/unraid-aicliagents/bin/npx it doesnt work either and they still usually place their place under /root/. It would be great here if there was some way to easily get into the same environment as cli´s would run under. I assume you are doing some path shenanigans or something similar

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

19 hours ago, johner said:

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

Yes, trying to from the default unraid shell, would be great if there was a way to do this for testing and debugging (currently trying to troubleshoot working with an claude code to opencode bridge).

Another thing:

This has been running for over an hour, it was stuck for most of the time now at the "Backing up active RAM sessions..." step. Not sure how long it will take for the next step, but this rough for a plugin update

3 hours ago, Joly0 said:

Yes, trying to from the default unraid shell, would be great if there was a way to do this for testing and debugging (currently trying to troubleshoot working with an claude code to opencode bridge).

Another thing:

This has been running for over an hour, it was stuck for most of the time now at the "Backing up active RAM sessions..." step. Not sure how long it will take for the next step, but this rough for a plugin update

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.

3 hours ago, Joly0 said:

Yes, trying to from the default unraid shell, would be great if there was a way to do this for testing and debugging (currently trying to troubleshoot working with an claude code to opencode bridge).

Another thing:

This has been running for over an hour, it was stuck for most of the time now at the "Backing up active RAM sessions..." step. Not sure how long it will take for the next step, but this rough for a plugin update

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.

44 minutes ago, johner said:

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.

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!

Sorry, im' new to running CLI agents - is there no way to use your Google AI Plan account? Only using the Gemini CLI API key? When running Gemini CLI locally, i can choose to use a google account.

On 4/7/2026 at 8:46 PM, xAVx said:

Sorry, im' new to running CLI agents - is there no way to use your Google AI Plan account? Only using the Gemini CLI API key? When running Gemini CLI locally, i can choose to use a google account.

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)

Hi, I'm having trouble with "Failed to mount Home storage for root" errors:

[2026-04-11 12:30:58] [INFO] MAINTENANCE: Unlocking Agent storage (RO -> RW)[2026-04-11 12:30:58] [WARN] Mnt Attempt 1 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:30:59] [WARN] Mnt Attempt 2 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:31:00] [WARN] Mnt Attempt 3 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:31:00] [WARN] STALL: Remount RW failed. Triggering robust repair sequence...[2026-04-11 12:31:00] [WARN] Btrfs Rescue: Processing /mnt/user/appdata/aicli-persistence/aicli-agents.img mounted at /usr/local/emhttp/plugins/unraid-aicliagents/agents[2026-04-11 12:31:01] [INFO] Btrfs Rescue: Success for /mnt/user/appdata/aicli-persistence/aicli-agents.img
[2026-04-11 12:31:44] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:31:44] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:31:57] [INFO] startAICliTerminal called: ID=sz9cv0, Agent=gemini-cli, Path=/mnt/user/appdata[2026-04-11 12:31:57] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:31:57] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:32:01] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata[2026-04-11 12:32:01] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:32:01] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:32:08] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata[2026-04-11 12:32:08] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:32:08] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:35:21] [INFO] startAICliTerminal called: ID=sz9cv0, Agent=gemini-cli, Path=/mnt/user/appdata[2026-04-11 12:35:21] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:35:21] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:35:32] [INFO] startAICliTerminal called: ID=sfrv5k, Agent=gemini-cli, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:35:32] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:35:32] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:36:26] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:36:26] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:36:26] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:43:04] [INFO] startAICliTerminal called: ID=sfrv5k, Agent=gemini-cli, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:43:04] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:43:04] [ERROR] ERROR: Failed to mount Home storage for root.

The plugin page looks like this:

I'm using Gemini if that matters.

Here's my settings page:

Any help would be amazing.

Thanks!

On 4/12/2026 at 2:48 AM, RevelRob said:

Hi, I'm having trouble with "Failed to mount Home storage for root" errors:

[2026-04-11 12:30:58] [INFO] MAINTENANCE: Unlocking Agent storage (RO -> RW)[2026-04-11 12:30:58] [WARN] Mnt Attempt 1 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:30:59] [WARN] Mnt Attempt 2 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:31:00] [WARN] Mnt Attempt 3 failed: mount: /usr/local/emhttp/plugins/unraid-aicliagents/agents: cannot remount /dev/loop4 read-write, is write-protected.        dmesg(1) may have more information after failed mount system call.[2026-04-11 12:31:00] [WARN] STALL: Remount RW failed. Triggering robust repair sequence...[2026-04-11 12:31:00] [WARN] Btrfs Rescue: Processing /mnt/user/appdata/aicli-persistence/aicli-agents.img mounted at /usr/local/emhttp/plugins/unraid-aicliagents/agents[2026-04-11 12:31:01] [INFO] Btrfs Rescue: Success for /mnt/user/appdata/aicli-persistence/aicli-agents.img
[2026-04-11 12:31:44] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:31:44] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:31:57] [INFO] startAICliTerminal called: ID=sz9cv0, Agent=gemini-cli, Path=/mnt/user/appdata[2026-04-11 12:31:57] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:31:57] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:32:01] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata[2026-04-11 12:32:01] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:32:01] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:32:08] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata[2026-04-11 12:32:08] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:32:08] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:35:21] [INFO] startAICliTerminal called: ID=sz9cv0, Agent=gemini-cli, Path=/mnt/user/appdata[2026-04-11 12:35:21] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:35:21] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:35:32] [INFO] startAICliTerminal called: ID=sfrv5k, Agent=gemini-cli, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:35:32] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:35:32] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:36:26] [INFO] startAICliTerminal called: ID=temp-terminal, Agent=terminal, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:36:26] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:36:26] [ERROR] ERROR: Failed to mount Home storage for root.[2026-04-11 12:43:04] [INFO] startAICliTerminal called: ID=sfrv5k, Agent=gemini-cli, Path=/mnt/user/appdata/crafty-4[2026-04-11 12:43:04] [INFO] Mounting Btrfs Home (RAM) for root...[2026-04-11 12:43:04] [ERROR] ERROR: Failed to mount Home storage for root.

The plugin page looks like this:

I'm using Gemini if that matters.

Here's my settings page:

Any help would be amazing.

Thanks!

Hi, sorry I’ve been busy refactoring and uplifting the storage architecture, it will be a lot more standard and reliable. It’s nearly done, there are a lot of test cases to work through! Likely another day or so.

OK... new version out with LOTS of fixes and changes.

Let me know if any issues and any features you want to see.

On 3/31/2026 at 1:48 AM, Unraider_ said:

Hi,

just updated the plugin and all my VMs went off, afterwards also my server rebooted. Mmh..

It was directly during the update and my server is normally very, very stable…

Can you check that?

Thanks

hi, can you check the latest version and see if it still happens please?

There are now per agent settings in the store tab to restrict the memory per agent, default is 4gb.

Also, I have a second plugin, 'zram' it sets up an in memory compress swap, this has helped my poor old 12gb server instance a lot! install that and set to 75% of your memory. You sacriffice CPU for compression/decompression but can get upto 3x more memory. You can now also get it to set up a fall back to ssd if you have one that meets the criteria, so you should never run out of memory forcing VMs to be shutdown.

Missing goose cli agent support https://github.com/aaif-goose/goose

On 4/18/2026 at 4:48 PM, pires said:

Missing goose cli agent support https://github.com/aaif-goose/goose

The plugin currently only supports NPM installers, as it's embedded in the versioning etc. solution. I have claude and gemini helping with a more generic feature, i'll test it on Goose first :-) given me a week or so as I'm still building out automated test cases, so testing all the moving parts takes time. Will you be willing to test it out?

Updated to latest, was on a fork but seems to have issues with Paths:

[2026-04-30 16:18:43] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents

[2026-04-30 16:18:43] [INFO] [MIGRATION] ERROR: Persistence path failed validation: /mnt/scratch_old/aicliagents

[2026-04-30 16:21:37] [INFO] [AICliAgents] Initializing AICliAgents Plugin (v1.0)...

[2026-04-30 16:21:38] [INFO] [StorageMountService] Mounting Home Stack for root

[2026-04-30 16:21:38] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:21:38] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:21:38] [ERR!] [StorageMountService] Mount script FAILED for home root:

[2026-04-30 16:21:38] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

PERSIST_PATH outside of allowed prefixes a bug?

From a fresh install:

[2026-04-30 16:30:33] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [StorageMountService] Mount script FAILED for agent gemini-cli:

[2026-04-30 16:30:33] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [InstallerService] Failed to mount storage stack for gemini-cli

[2026-04-30 16:30:33] [ERR!] [AICliAgents] Background Install Job FAILED for gemini-cli: Could not mount agent storage

[2026-04-30 16:30:34] [INFO] [COMMIT] No changes to commit for home root

[2026-04-30 16:30:34] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [StorageMountService] Mount script FAILED for agent claude-code:

[2026-04-30 16:30:34] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [InstallerService] Failed to mount storage stack for claude-code

[2026-04-30 16:30:34] [ERR!] [AICliAgents] Background Install Job FAILED for claude-code: Could not mount agent storage

Seems to try and force me to use the usb / fixed paths?

Edited April 30Apr 30 by scs3jb

On 5/1/2026 at 2:24 AM, scs3jb said:

Updated to latest, was on a fork but seems to have issues with Paths:

[2026-04-30 16:18:43] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents

[2026-04-30 16:18:43] [INFO] [MIGRATION] ERROR: Persistence path failed validation: /mnt/scratch_old/aicliagents

[2026-04-30 16:21:37] [INFO] [AICliAgents] Initializing AICliAgents Plugin (v1.0)...

[2026-04-30 16:21:38] [INFO] [StorageMountService] Mounting Home Stack for root

[2026-04-30 16:21:38] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:21:38] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:21:38] [ERR!] [StorageMountService] Mount script FAILED for home root:

[2026-04-30 16:21:38] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

PERSIST_PATH outside of allowed prefixes a bug?

From a fresh install:

[2026-04-30 16:30:33] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [StorageMountService] Mount script FAILED for agent gemini-cli:

[2026-04-30 16:30:33] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:33] [ERR!] [InstallerService] Failed to mount storage stack for gemini-cli

[2026-04-30 16:30:33] [ERR!] [AICliAgents] Background Install Job FAILED for gemini-cli: Could not mount agent storage

[2026-04-30 16:30:34] [INFO] [COMMIT] No changes to commit for home root

[2026-04-30 16:30:34] [ERR!] [guard_path] PERSIST_PATH outside allowed prefixes: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [StorageMountService] Mount script FAILED for agent claude-code:

[2026-04-30 16:30:34] [ERR!] [MOUNT] Persistence path failed validation: /mnt/scratch_old/aicliagents/persistence

[2026-04-30 16:30:34] [ERR!] [InstallerService] Failed to mount storage stack for claude-code

[2026-04-30 16:30:34] [ERR!] [AICliAgents] Background Install Job FAILED for claude-code: Could not mount agent storage

Seems to try and force me to use the usb / fixed paths?

Hi, ok let me check, I’ve been working on other updates, I’m now away for a few days, so might take a week or so.

Did you get it running by forking it?

Thanks for letting me know.

Edited May 2May 2 by johner

I released a new version, let me know if you have any issues or requests. It's a big release under the covers, I already have a new release planned to fix a couple issues since Unraid 7.3.0. It works though.

On 4/18/2026 at 4:48 PM, pires said:

Missing goose cli agent support https://github.com/aaif-goose/goose

It's there now, I haven't done much to configure and test it, I'd appreciate if you could. If you need to run an initial command to set it up, click the terminal icon in the drawer tab, it'll load a terminal overlay in the same worksapce where you can run what you need.

Having issues with Codex CLI. Wanted to sign in with my ChatGPT account (not api token) but get this error. Any suggestions?

[Agent Binary Missing] The agent binary was not found.

Expected: /usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex

The agent may need reinstalling via the Store card.

Press ENTER to retry...

bash: line 1: /usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex: No such file or directory

node:internal/modules/cjs/loader:1368

throw err;

^

Error: Cannot find module '/usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex'

at Function._resolveFilename (node:internal/modules/cjs/loader:1365:15)

at defaultResolveImpl (node:internal/modules/cjs/loader:1021:19)

at resolveForCJSWithHooks (node:internal/modules/cjs/loader:1026:22)

at Function._load (node:internal/modules/cjs/loader:1175:37)

at TracingChannel.traceSync (node:diagnostics_channel:322:14)

at wrapModuleLoad (node:internal/modules/cjs/loader:235:24)

at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:171:5)

at node:internal/main/run_main_module:36:49 {

code: 'MODULE_NOT_FOUND',

requireStack: []

}

Node.js v22.18.0

[Agent Exited Immediately] The agent exited after 1s — likely missing configuration.

Press ENTER to retry, or close this workspace from the UI.

Edited May 17May 17 by indivinity

6 hours ago, indivinity said:

Having issues with Codex CLI. Wanted to sign in with my ChatGPT account (not api token) but get this error. Any suggestions?

[Agent Binary Missing] The agent binary was not found.

Expected: /usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex

The agent may need reinstalling via the Store card.

Press ENTER to retry...

bash: line 1: /usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex: No such file or directory

node:internal/modules/cjs/loader:1368

throw err;

^

Error: Cannot find module '/usr/local/emhttp/plugins/unraid-aicliagents/agents/codex-cli/node_modules/@openai/codex/vendor/x86_64-unknown-linux-musl/codex/codex'

at Function._resolveFilename (node:internal/modules/cjs/loader:1365:15)

at defaultResolveImpl (node:internal/modules/cjs/loader:1021:19)

at resolveForCJSWithHooks (node:internal/modules/cjs/loader:1026:22)

at Function._load (node:internal/modules/cjs/loader:1175:37)

at TracingChannel.traceSync (node:diagnostics_channel:322:14)

at wrapModuleLoad (node:internal/modules/cjs/loader:235:24)

at Function.executeUserEntryPoint [as runMain] (node:internal/modules/run_main:171:5)

at node:internal/main/run_main_module:36:49 {

code: 'MODULE_NOT_FOUND',

requireStack: []

}

Node.js v22.18.0

[Agent Exited Immediately] The agent exited after 1s — likely missing configuration.

Press ENTER to retry, or close this workspace from the UI.

Should be fixed now, upgrade and let me know please.

19 hours ago, johner said:

Should be fixed now, upgrade and let me know please.

I'm getting stuck at this screen now. Also not sure why but it's locking up my system when I use it. My dashboard and everything stops working for an extended period of time.

4 hours ago, indivinity said:

I'm getting stuck at this screen now. Also not sure why but it's locking up my system when I use it. My dashboard and everything stops working for an extended period of time.

I think you may have suffered from a defect where the agent sqlite DB can get corrupted. I've uploaded a new version with this fix.

However, you may need to delete the codex folder from the home path.

How to recover a stuck agent

If your agent gets stuck on the "Waking..." screen or starts but complains about a corrupted database, follow these steps. You'll lose the affected agent's conversation history (which is already broken), but everything else — your workspaces, settings, and other agents — stays intact.

Step 1 — Open a terminal

In Unraid's top-right toolbar, click the >_ terminal icon. A black terminal window opens with a prompt like root@Tower:~#.

Step 2 — Confirm you're looking at the right place

Type each command and press Enter after each:

cd /tmp/unraid-aicliagents/work/root/home

ls -la

You should see directories starting with a dot — .codex, .copilot, .local, etc. Those are the per-agent state folders.

If the cd command fails ("No such file or directory") or ls -la shows an empty list, the plugin's overlay isn't mounted for your user. Open and immediately close the plugin's terminal once in the web UI (this triggers the mount), then re-run the two commands above.

Step 3 — Delete the broken agent's folder

Run one of these commands for the agent that's misbehaving:

┌────────────────┬──────────────────────────────┐

│ Agent │ Command │

├────────────────┼──────────────────────────────┤

│ Codex CLI │ rm -rf .codex │

├────────────────┼──────────────────────────────┤

│ GitHub Copilot │ rm -rf .copilot │

├────────────────┼──────────────────────────────┤

│ Kilo Code │ rm -rf .local/share/kilo │

├────────────────┼──────────────────────────────┤

│ OpenCode │ rm -rf .local/share/opencode │

├────────────────┼──────────────────────────────┤

│ Goose │ rm -rf .local/share/goose │

└────────────────┴──────────────────────────────┘

If you're not sure which agent is at fault, run more than one — each agent rebuilds its folder from scratch the next time it starts. You'll only lose conversation history for the agents you delete; your workspaces, settings, and other agents stay exactly as they were.

Step 4 — Re-launch the agent and verify

1. Back in the plugin's web UI, open a workspace that uses the agent you just cleared.

2. The "Waking..." screen should clear within 5–15 seconds and you should see a normal agent prompt.

3. Type a quick message ("hello") and confirm the agent responds.

4. Close that workspace and re-open it — confirm the hang doesn't come back.

If the problem still happens, please post the last 50 lines of the plugin's debug log to the support thread. You can grab it in the terminal with:

tail -50 /boot/config/plugins/unraid-aicliagents/debug.log

Edited May 18May 18 by johner

Getting an Error

Terminal session not found. Check debug log.

0 SQLite path(s) excluded)...

[2026-05-21 18:35:58] [INFO] [COMMIT] Bake complete: home_root_delta_20260521T173558Z.sqsh

[2026-05-21 18:35:58] [INFO] [COMMIT] Checking for active sessions on /tmp/unraid-aicliagents/work/root/home...

[2026-05-21 18:35:58] [INFO] [COMMIT] Mount is BUSY (open files detected). Skipping ZRAM flush.

[2026-05-21 18:35:58] [INFO] [COMMIT] Data persisted to Flash. ZRAM dirty stats remain until sessions close.

[2026-05-21 18:36:01] [INFO] [COMMIT] Pruning caches before bake...

[2026-05-21 18:36:01] [INFO] [COMMIT] Baking changes to /boot/config/plugins/unraid-aicliagents/persistence/ (atomic delta, 0

0 SQLite path(s) excluded)...

directory /tmp/tmux-0 has unsafe permissions

[2026-05-21 18:36:02] [INFO] [COMMIT] Bake complete: home_root_delta_20260521T173601Z.sqsh

[2026-05-21 18:36:02] [INFO] [COMMIT] Checking for active sessions on /tmp/unraid-aicliagents/work/root/home...

[2026-05-21 18:36:02] [INFO] [COMMIT] Mount is BUSY (open files detected). Skipping ZRAM flush.

[2026-05-21 18:36:02] [INFO] [COMMIT] Data persisted to Flash. ZRAM dirty stats remain until sessions close.

[2026-05-21 18:36:56] [INFO] [COMMIT] Pruning caches before bake...

[2026-05-21 18:36:56] [INFO] [COMMIT] Baking changes to /boot/config/plugins/unraid-aicliagents/persistence/ (atomic delta, 0

0 SQLite path(s) excluded)...

directory /tmp/tmux-0 has unsafe permissions

[2026-05-21 18:36:56] [INFO] [COMMIT] Bake complete: home_root_delta_20260521T173656Z.sqsh

[2026-05-21 18:36:56] [INFO] [COMMIT] Checking for active sessions on /tmp/unraid-aicliagents/work/root/home...

[2026-05-21 18:36:56] [INFO] [COMMIT] Mount is BUSY (open files detected). Skipping ZRAM flush.

[2026-05-21 18:36:56] [INFO] [COMMIT] Data persisted to Flash. ZRAM dirty stats remain until sessions close.

[2026-05-21 18:38:20] [INFO] [COMMIT] Pruning caches before bake...

[2026-05-21 18:38:20] [INFO] [COMMIT] Baking changes to /boot/config/plugins/unraid-aicliagents/persistence/ (atomic delta, 0

0 SQLite path(s) excluded)...

[2026-05-21 18:38:21] [INFO] [COMMIT] Bake complete: home_root_delta_20260521T173820Z.sqsh

[2026-05-21 18:38:21] [INFO] [COMMIT] Checking for active sessions on /tmp/unraid-aicliagents/work/root/home...

[2026-05-21 18:38:21] [INFO] [COMMIT] Performing selective ZRAM cleanup (per-file mtime + open-fd invariant)...

directory /tmp/tmux-0 has unsafe permissions

[2026-05-21 18:38:31] [INFO] [COMMIT] Refreshing mount stack...

[2026-05-21 18:38:31] [INFO] [MOUNT] Stack mounted at /tmp/unraid-aicliagents/work/root/home (Layers: 8)

[2026-05-21 18:38:32] [INFO] [CONSOLIDATE] Pruning regenerable caches from merged home view before consolidation...

[2026-05-21 18:38:32] [INFO] [CONSOLIDATE] Baking consolidated volume (atomic)...

[2026-05-21 18:38:32] [INFO] [CONSOLIDATE] Consolidated volume written: home_root_consolidated_20260521T173832Z.sqsh

[2026-05-21 18:38:32] [INFO] [CONSOLIDATE] Updating manifest to list only the new consolidated layer (before file deletes)...

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Cleaning up old layers...

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Removed old layer: home_root_consolidated_20260521T172622Z.sqsh

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T172747Z.sqsh

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173550Z.sqsh

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173555Z.sqsh

[2026-05-21 18:38:33] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173558Z.sqsh

[2026-05-21 18:38:34] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173601Z.sqsh

[2026-05-21 18:38:34] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173656Z.sqsh

[2026-05-21 18:38:34] [INFO] [CONSOLIDATE] Removed old layer: home_root_delta_20260521T173820Z.sqsh

[2026-05-21 18:38:34] [INFO] [CONSOLIDATE] Finalizing stack and clearing RAM...

[2026-05-21 18:38:34] [INFO] [CONSOLIDATE] Note: Active agent terminals may log transient I/O errors during remount. This is expected and resolves automatically.

[2026-05-21 18:38:34] [INFO] [MOUNT] Stack mounted at /tmp/unraid-aicliagents/work/root/home (Layers: 1)

Hey, i noticed after a reboot the agent is simply gone. When i try to access it for example through the normal unraid webui terminal and run something like "claude" i get this error:
bash: /usr/local/emhttp/plugins/unraid-aicliagents/agents/claude-code/node_modules/.bin/claude: No such file or directory

The "agent store" says its installed. I either have to uninstall and reinstall or (if available) update to get claude (and others) back working.