AI

The two integration patterns, when to use each, and the documentation flow.

Threads, runs, SDK orchestration, and persistence conventions.

Receive run completion and recover when callbacks are missed.

In-process agent structure, barrels, and key dependencies.

ReAct chat agents, StateGraph pipelines, and direct LLM calls.

OpenAI/Azure chat and embedding model selection and rules.

MongoDB Atlas Vector Search setup and query patterns.

Required keys for hosted graphs, LLMs, embeddings, and tracing.

SSE, webhooks, Socket.io, and polling for AI output.

Mandatory PR checklist, observability, and span naming.

Run agents locally, tunnel webhooks, and debug stuck jobs.