[Bug] Claude model intermittently becomes unavailable within the same session

[heyuan110]

Checks

• I have searched github.com/aws/amazon-q-developer-cli/issues and there are no duplicates of my issue
• I have run q doctor in the affected terminal session
• I have run q restart and replicated the issue again

Operating system

macOS 26.5.2 (25F84)

Expected behaviour

Claude Opus works successfully in the same Kiro IDE/CLI session,
but a few seconds later the next request fails with:

"The model 'claude-opus-x' is not available."

No model switch, logout, region change, or client restart occurred.

This happens intermittently in both Kiro IDE and Kiro CLI.

This does not look like a permanent entitlement or region issue,
because the same model succeeds immediately before failing.

Actual behaviour

The selected Claude model intermittently becomes unavailable during the same active session.

For example, Claude Opus works normally for one request and returns a valid response. Then, only a few seconds later, without changing the model, account, region, configuration, or restarting the client, the next request fails with:

The model 'claude-opus-4.8' is not available.

I have also observed the same behavior with claude-opus-5 in Kiro CLI.

The issue is intermittent: the model may become available again later without any configuration changes.

This happens in both Kiro IDE and Kiro CLI, so it appears to be related to model availability/routing rather than a local client configuration issue.

Screenshots are attached showing a successful Claude request followed immediately by a "model not available" error in the same session.

Example request IDs:

• 6273cb42-7dec-4a24-95f1-394c55bdbbea
• cf554955-134b-4c29-86ce-cd26a6bc68b7
• 36c6f7fa-c53b-48ad-8437-df54409a55d6

Steps to reproduce

1. Open Kiro IDE or Kiro CLI.

2. Select a Claude model, for example claude-opus-4.8 or claude-opus-5.

3. Send a prompt and confirm that the model responds successfully.

4. Continue using the same session and the same model.

5. Send another prompt a few seconds or minutes later.

6. Intermittently, the request fails with:

   The model 'claude-opus-x' is not available.

7. Retry later without changing any configuration, and the same model may work again.

The issue is not consistently reproducible on every request, but occurs frequently enough to interrupt normal usage.

Environment

<This will be visible to anyone. Do not include personal or sensitive information>

[q-details]
version = "2.24.0"
hash = "240642df93e76b55141520bb767a757f4434d006"
date = "2026-09-23T20:12:52.807706Z (2d ago)"
variant = "full"

[system-info]
os = "macOS 26.5.2 (25F84)"
chip = "Apple M5"
total-cores = 10
memory = "16.00 GB"

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

[env-vars]
PATH = "/Users/USER/.local/bin:/opt/homebrew/opt/mysql-client/bin:/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/homebrew/bin:/opt/homebrew/sbin:/Users/USER/.local/bin:/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:/pkg/env/global/bin:/Library/Apple/usr/bin"
SHELL = "/bin/zsh"
TERM = "xterm-256color"
__CFBundleIdentifier = "com.github.wez.wezterm"