Installation
@langchain/core >= 0.2.0.
Three-line setup
VaneCallbackHandler
Extends LangChain’s BaseCallbackHandler. Attach it to any LLM, chain, or agent executor.
Constructor options
What gets attested
Chat models go through
handleChatModelStart (not handleLLMStart). Both paths are covered — you will always get an llm-call record regardless of whether you use a chat model or a completion model.
Error handling
Attestation calls are fire-and-forget. If the Vane server is unavailable, the error is logged toconsole.error and the LangChain execution continues uninterrupted. Attestation failures never block or crash your agent.