error when sending prompt after installation

### 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

macOS 26.3.1 (25D2128)

### Expected behaviour

after sending a prompt in the cli I should get a response from the model.

### Actual behaviour

request_id: 70844f28-df3e-4422-ac25-9806a796b394, error: An unknown error occurred:
ValidationException

### Steps to reproduce

1. install Kiro
2. run kiro-cli in the terminal
3. type a prompt

### Environment

```yaml

[q-details]
version = "2.0.1"
hash = "4a41569da83e25b6ab94898d7c4c83fa18cb5216"
date = "2026-04-17T02:21:00.156808Z (4d ago)"
variant = "full"

[system-info]
os = "macOS 26.3.1 (25D2128)"
chip = "Apple M4 Pro"
total-cores = 12
memory = "24.00 GB"

[environment]
cwd = "/Users/USER"
cli-path = "/Users/USER"
os = "Mac"
shell-path = "/bin/zsh"
shell-version = "5.9"
terminal = "Ghostty"
install-method = "unknown"

[env-vars]
PATH = "/opt/homebrew/bin:/opt/homebrew/sbin:/usr/local/bin:/System/Cryptexes/App/usr/bin:/usr/bin:/bin:/usr/sbin:/sbin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/local/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/bin:/var/run/com.apple.security.cryptexd/codex.system/bootstrap/usr/appleinternal/bin:/opt/pmk/env/global/bin:/Applications/Ghostty.app/Contents/MacOS:/Users/USER/.local/bin"
QTERM_SESSION_ID = "b71ae4ae4d4143828d85cb6669097961"
Q_SET_PARENT_CHECK = "1"
Q_TERM = "2.0.1"
SHELL = "/bin/zsh"
TERM = "xterm-ghostty"
__CFBundleIdentifier = "com.mitchellh.ghostty"
```

Riproduci il problema installando Kiro, avviando kiro-cli e inviando un prompt; confronta il comportamento prima e dopo l’esecuzione di q doctor e q restart. Usa la versione segnalata 2.0.1, l’ambiente macOS, il request ID e ValidationException per tracciare il problema. L’attività è completata quando un prompt riceve una risposta del modello invece dell’errore di convalida.

Scritto dal modello di indicizzazione a partire dal testo della issue.