Claude Code and Codex still copy shell history UX that clashes with agent workflows

ZeroStateReflex · x · 2026-07-21

A post argues that Claude Code and Codex CLI/TUI should not behave like standard shell programs: users usually want to say “try again, but…” rather than scroll back through prior utterances. The critique is that current scrollwheel/history behavior copies Unix shell conventions too literally, even though conversational coding agents are a different interaction model. The thread’s core point is about interface design for coding agents: - shell-style history recall often mismatches how people revise prompts - repeated attempts should be treated as new instructions, not replayed chat history - the right mental model is a moderately sapient collaborator, not a normal CLI - tool UX should adapt to agentic workflows instead of inheriting terminal defaults blindly

Original post →

More from coding & agent

coding & agent channel →