Good point, but Happy also has parsers to turn terminal output into "chat bubbles" but with how often Claude Code and Codex change that output, that parser has to be updated every time. With new terminal agents coming into the fray, wouldn't you forever have to parse new agents to make them available?

We use the Claude Agent SDK and the Codex App server, which makes it easier to maintain (we used to parse out the literal terminal when we first launched, which was not maintainable - https://news.ycombinator.com/item?id=44878650). There's also ACP (https://agentclientprotocol.com/get-started/introduction) which we'll probably integrate eventually, which should make it easier to manage all the harnesses.