wrapCall helper (TypeScript). The wrapper scans your messages before the OpenAI request goes out.
Python
1
Install
2
Decorate the call
llm.py
@guard.wrap_async for an async def function.TypeScript
1
Install
2
Wrap the call
llm.ts
Message format
Benchspan expects messages in standard chat shape:systemandassistantmessages → skippeduserandtoolmessages → scanned (content must be a string)- The
namefield, if present, is passed assourceto the dashboard
Want the raw scan without wrapping?
Python
TypeScript