Skip to content

Explanation

Understanding-oriented. Read these when you want to know why the template is shaped the way it is.

PageQuestion it answers
ArchitectureHow do the A2A handler, LangGraph runtime, and LiteLLM gateway fit together?
A2A protocolWhat does A2A actually require, and where do naive implementations go wrong?
Cost & trace propagationWhy do we emit cost-v1 and parse a2a.trace, and why that specific shape?
Output protocolWhy <scratch_pad> / <output> instead of whatever the model emits?
LiteLLM gatewayWhy route every call through a gateway instead of the provider SDK?

Part of the protoLabs autonomous development studio.