Agent Email Patterns

This is architectural guidance for agents that need to send and receive email, not SDK documentation. You get seven opinionated patterns: one inbox per agent (never share), two-way conversation loops using extracted_text to strip quoted replies, human-in-the-loop drafts for high-stakes messages, WebSockets over polling, multi-agent topologies with clear role separation, OTP extraction for verification flows, and labels for workflow state. The security section is brief but covers the critical stuff like prompt injection via inbound email and allow lists for production inboxes. Useful if you're building support bots, notification agents, or anything that needs structured email communication instead of just fire-and-forget sending.