Checks
Operating system
Ubuntu 22.04.5 LTS
Expected behaviour
I expected kiro-cli to respond to my message with a response corresponding to my input.
Actual behaviour
Step 5. Sending any message will trigger a message similar to the following
The model 'auto' is not available. Please use '/model' to select a different model and try again. (request_id:
3rd-randomly-generated-request-ID)
However, upon attempting to switch models using the /model command, the operation subsequently failed once more.
/model
No options available for /model
From this point, the message changed to the following:
The model '' is not available. Please use '/model' to select a different model and try again. (request_id:
4th-randomly-generated-request-ID)
Steps to reproduce
Step1: My Kiro(kiro-cli) has been working fine for monthes.
However, yesterday it suddenly started showing the following error, no matter what I entered into it
request_id: a-randomly-generated-request-ID, error: An unknown error occurred: ValidationException
request_id: another-randomly-generated-request-ID, error: An unknown error occurred: ValidationException
Step2: I have upgraded the kiro-cli to current version.
$ curl -fsSL https://cli.kiro.dev/install -o install.sh
curl: (35) OpenSSL SSL_connect: SSL_ERROR_ZERO_RETURN in connection to cli.kiro.dev:443
# I have added the TLS 1.3 option to the official command line because of the above error.
$ curl --tlsv1.3 -fsSL https://cli.kiro.dev/install -o install.sh
# I replace all occurrences of `curl -fsSL` with `curl --tlsv1.3 -fsSL`
$ bash install.sh
Kiro CLI installer:
Downloading package...
✓ Downloaded and extracted
⚠️ Existing Kiro CLI installation found
Do you want to replace it? (y/N):y <Enter>
✓ Existing installation removed
✓ Package installed successfully
🎉 Installation complete! Happy coding!
Next steps:
Use the command "kiro-cli" to get started!
Step3: Logout previous session
$ kiro-cli logout
You are now logged out
Run kiro-cli login to log back in to Kiro CLI
Step4: Log back in
$ kiro-cli login --use-device-flow
✔ Select login method · Use with Your Organization
✔ Enter Start URL · https://my.Organization.domain/start
✔ Enter Region · Organization.region
Confirm the following code in the browser
Code: RANDOM-CODE
Open this URL: https://my.Organization.domain/start/#/device?user_code=RANDOM-CODE
Device authorized
Logged in successfully
Step 5. Sending any message will trigger a message similar to the following
The model 'auto' is not available. Please use '/model' to select a different model and try again. (request_id:
3rd-randomly-generated-request-ID)
However, upon attempting to switch models using the /model command, the operation subsequently failed once more.
/model
No options available for /model
From this point, the message changed to the following:
The model '' is not available. Please use '/model' to select a different model and try again. (request_id:
4th-randomly-generated-request-ID)
I have run q doctor in the affected terminal session
The q command is not available on my system.
q doctor
Command 'q' not found, but can be installed with:
snap install q # version 1.6.3-1, or
apt install python3-q-text-as-data # version 3.1.6-1
See 'snap info q' for additional versions.
I have run q restart and replicated the issue again
q restart
Command 'q' not found, but can be installed with:
snap install q # version 1.6.3-1, or
apt install python3-q-text-as-data # version 3.1.6-1
See 'snap info q' for additional versions.
So I ran similar sub-commands for kiro-cli
$kiro-cli doctor
✘ sshd config: SSHD config is not set up correctly
The /etc/ssh/sshd_config file needs to have the following line:
AcceptEnv Q_SET_PARENT
AllowStreamLocalForwarding yes
If your sshd_config is already configured correctly then:
1. Restart sshd, if using systemd: `sudo systemctl restart sshd`
2. Disconnect from the remote host
3. Run `kiro-cli integrations install ssh` on the local machine
4. Reconnect to the remote host and run `kiro-cli doctor` again
✘ Doctor found errors. Please fix them and try again.
If you are not sure how to fix it, please open an issue with `kiro-cli` issue to let us know!
Regarding the above suggestion, I am a normal users to the server, so I have no permission to change the configuration system-wide.
Is it mandatory?
$ kiro-cli restart
error: Please restart Kiro CLI from your host machine
Environment
[q-details]
version = "2.16.2"
hash = "b43b3506cf009fadc655eb9f189dcc2b849db53d"
date = "2026-08-06T04:47:01.105053Z (5d ago)"
variant = "minimal"
[system-info]
chip = "Intel(R) Xeon(R) CPU E5-2620 v4 @ 2.10GHz"
total-cores = 16
memory = "125.79 GB"
[system-info.os.linux]
kernel_version = "6.8.0-88-generic"
id = "ubuntu"
name = "Ubuntu"
pretty_name = "Ubuntu 22.04.5 LTS"
version_id = "22.04"
version = "22.04.5 LTS (Jammy Jellyfish)"
[environment]
cwd = "/WORK_DIR_BASE/kiro_cli_dir"
cli-path = "/WORK_DIR_BASE/kiro_cli_dir"
os = "Linux"
shell-path = "/usr/bin/bash"
shell-version = "5.1.16"
install-method = "unknown"
in-ssh = true
[env-vars]
PATH = "/WORK_DIR_BASE/myusr/usr/bin:/WORK_DIR_BASE/myusr/bin:/WORK_DIR_BASE/hkmc/wassp_run:$HOME/local/usr/bin:$HOME/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/snap/bin:$HOME/.local/bin"
Q_SET_PARENT_CHECK = "1"
SHELL = "/bin/bash"
TERM = "xterm"
XDG_SESSION_TYPE = "tty"
Checks
q doctorin the affected terminal sessionq restartand replicated the issue againOperating system
Ubuntu 22.04.5 LTS
Expected behaviour
I expected
kiro-clito respond to my message with a response corresponding to my input.Actual behaviour
Step 5. Sending any message will trigger a message similar to the following
However, upon attempting to switch models using the
/modelcommand, the operation subsequently failed once more.From this point, the message changed to the following:
Steps to reproduce
Step1: My Kiro(kiro-cli) has been working fine for monthes.
However, yesterday it suddenly started showing the following error, no matter what I entered into it
Step2: I have upgraded the
kiro-clito current version.Step3: Logout previous session
Step4: Log back in
Step 5. Sending any message will trigger a message similar to the following
However, upon attempting to switch models using the
/modelcommand, the operation subsequently failed once more.From this point, the message changed to the following:
I have run
q doctorin the affected terminal sessionThe
qcommand is not available on my system.I have run
q restartand replicated the issue againSo I ran similar sub-commands for
kiro-cliRegarding the above suggestion, I am a normal users to the server, so I have no permission to change the configuration system-wide.
Is it mandatory?
Environment