Multi_agent_v2 fails against Bedrock Mantle Endpoint

codex-security version 0.1.20

When I am trying to use Bedrock Mantle as my model provider

codex-secruity scan test-repo/ --provider amazon-bedrock --model openai.gpt-5.6-terra --headless --verbose

I end up seeing an error of

codex-security: debug: runtime.cleanup.started
codex-security: debug: runtime.cleanup.completed
codex-security: debug: scan.failed classification="unknown" partial_output=true
{"error":{"code":"validation_error","message":"invalid request body: Invalid 'input': value did not match any expected variant","param":null,"type":"invalid_request_error"}}
Partial output was kept at /state/codex-security/scans/test-repo/codex-security-test-repo-ijcmCp

This is related to https://github.com/openai/codex/pull/39804, I have found a workaround of using

codex-secruity scan test-repo/ --provider amazon-bedrock --model openai.gpt-5.6-terra --headless --verbose --codex features.multi_agent_v2.max_concurrent_threads_per_session=1

Start by reproducing the reported codex-security scan with the Bedrock Mantle provider and then compare it with the workaround setting max_concurrent_threads_per_session=1. Trace the multi_agent_v2 request path and the invalid input validation response; done means the original command succeeds without requiring the concurrency override.