CYBER_REASONING_DENY causes agent failure because the model expects reasoning messages #74
Description
What happened?
strands.types.exceptions.EventLoopException: An error occurred (ValidationException) when calling the ConverseStream operation: The model returned the following errors: messages.1.content.0.type: Expected `thinking` or `redacted_thinking`, but found `text`. When `thinking` is enabled, a final `assistant` message must start with a thinking block (preceeding the lastmost set of `tool_use` and `tool_result` blocks). We recommend you include thinking blocks from previous turns. To avoid this requirement, disable `thinking`. Please consult our documentation at https://docs.claude.com/en/docs/build-with-claude/extended-thinking
How to reproduce
- CYBER_REASONING_DENY=(model id here)
- Run assessment
How are you running it?
Docker Compose
Provider and Model
No response
Operating System
No response
Python Version
No response
Node Version (if using React UI)
No response
Cyber-AutoAgent Version
No response