I'm not able to type anything at the input area after 1 prompt doing the work with all the tasks

### Checks

- [x] I have searched [github.com/aws/amazon-q-developer-cli/issues](https://github.com/aws/amazon-q-developer-cli/issues?q=) and there are no duplicates of my issue
- [x] I have run `q doctor` in the affected terminal session
- [x] I have run `q restart` and replicated the issue again

### Operating system

Linux 6.18.33.2-microsoft-standard-WSL2 - Ubuntu 24.04.1 LTS

### Expected behaviour

Expected behaviour is to allow me to type in the prompt. The context is not full - it shows only 4% of the context of the model.

### Actual behaviour

When I gave a prompt, it has got several tasks and when the tool permissions are requested, it's fine - but after all the tasks are done, I'm not able to input it again. I can switch to the plan mode using Shift + Tab but I can't type it in. I've faced this issue in multiple platfroms - running on windows cli and also on the Ubuntu OS directly

### Steps to reproduce

- Just login to kiro-cli using kiro-cli login (I'm using organization SSO login)
- Type in your prompt or save prompt within the file and refer to that in the prompt
- Wait for the agent to finish the analysis and show the tasks
- Once the tasks are finished, you can't enter the second prompt (sometimes this is observed to be happening after 2nd or 3rd completion of all the tasks within the same session)

### Environment

```yaml

[q-details]
version = "2.16.1"
hash = "74e31715c16bf0e62c17c858dc645b4bdc7e4422"
date = "2026-08-04T03:52:09.070375Z (1d ago)"
variant = "minimal"

[system-info]
chip = "Intel(R) Core(TM) Ultra 5 135U"
total-cores = 7
memory = "7.49 GB"

[system-info.os.linux]
kernel_version = "6.18.33.2-microsoft-standard-WSL2"
id = "ubuntu"
name = "Ubuntu"
pretty_name = "Ubuntu 24.04.1 LTS"
version_id = "24.04"
version = "24.04.1 LTS (Noble Numbat)"

[environment]
cwd = "/home/USER"
cli-path = "/home/USER"
os = "Linux"
shell-path = "/usr/bin/bash"
shell-version = "5.2.21"
install-method = "unknown"
in-wsl = true

[env-vars]
DISPLAY = ":0"
PATH = "/home/USER/.local/bin:/home/USER/.local/bin:/home/USER/.nvm/versions/node/v22.23.1/bin:/home/USER/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/games:/usr/local/games:/usr/lib/wsl/lib:/mnt/c/WINDOWS/system32:/mnt/c/WINDOWS:/mnt/c/WINDOWS/System32/Wbem:/mnt/c/WINDOWS/System32/WindowsPowerShell/v1.0/:/mnt/c/WINDOWS/System32/OpenSSH/:/mnt/c/Program Files/dotnet/:/mnt/c/Program Files/Amazon/AWSCLIV2/:/mnt/c/Program Files/PuTTY/:/mnt/c/Program Files/nodejs/:/mnt/c/Users/santhosh.m/AppData/Local/Microsoft/WindowsApps:/snap/bin"
SHELL = "/bin/bash"
TERM = "xterm-256color"
```

Start by reproducing the issue with the reported login and multi-task prompt flow, using q doctor and q restart as noted. Focus on the terminal input state after task completion and verify that a second prompt can be typed in Windows CLI and Ubuntu, including WSL2; done means prompt entry remains available after each completion.

Written by the indexing model from the issue text.