I Let Agents Write My Code. They Got Stuck in a Loop and Argued With Each Other

A follow-up to building a local AI pipeline that reviews its own code I built vexdo — a CLI pipeline that automates the full dev cycle: spec → Codex implementation → reviewer → arbiter → PR. The dream: close my laptop, come back to a reviewed PR. No manual copy-pasting between tools, no being the glue. Then I migrated from local Codex to Codex Cloud. Then I swapped the reviewer from Claude to GitHub Copilot CLI. Then I went to make a coffee and came back to find my pipeline had sent Codex the same feedback four times in a row. This post is about that, and the other ways things broke. Not the happy path — the other one. Quick recap: what vexdo does spec.yaml → Codex (implements) → Reviewer (finds issues) → Arbiter (fix / submit / escalate) → PR ↑___________________________| fix loop v1 ran locally and synchronously. v2 runs Codex Cloud so I can kick off a task and close my laptop. The reviewer is now GitHub Copilot CLI. The arbiter is still Claude. Simple enough in theory. Here's what w