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
More from coding & agent
- uv-scripts/ocr returns to the top of Hugging Face datasets with a JSON model picker — vanstriendaniel · 2026-07-21
- Sonar CEO says a guide-verify-solve loop cuts coding-agent issues by 92% — alex_verem · 2026-07-21
- OpenAI’s Codex app is good enough that one user would pay for it even with open models — drdanielbender · 2026-07-21
- A creator built an Awwwards-style landing page with ChatGPT 5.6 Sol in one conversation — paw_lean · 2026-07-21
- A creator rebuilt a personal website as a Jupyter Notebook with Codex — paw_lean · 2026-07-21
- OpenAI’s Build Week buildathon drew 40 people for 11 hours with Codex — paw_lean · 2026-07-21