LangChain Structured Output & HITL

Malicious tool definition detected

Tool: SKILL.md [1/2] Description: --- name: LangChain Structured Output & HITL description: "INVOKE THIS SKILL when you need structured/typed output from LLMs OR human-in-the-loop approval.

Tool: SKILL.md [2/2] Description: middleware=[ human_in_the_loop_middleware( interrupt_on={ "send_email": {"allowed_decisions": ["approve", "edit", "reject"]}, "delete_email": {"allowed_decisions": ["approve", "reject"]}, # No edit "read_email": False, # No HITL for reading } ) ], ) ``` </python> </ex-multiple-tools-different-policies> <boundaries> ### What You CAN Configure **Structured Output:** - Schema structure: Any valid Pydantic/Zod model - Field validation: Types, ranges, regex, etc.