Claude Code /goal asks too many questions mid-run
Claude Code's /goal interrupts for user judgment calls and gives up early on long tasks, while Codex runs unattended to token exhaustion—opposite of the intended paradigm.
May 19, 2026
Summary
Long-horizon agent tasks fail not from capability gaps but from model behavior: Claude Code breaks autonomy by asking for direction mid-task, forcing manual monitoring. Codex demonstrates that stubborn, delegation-averse execution actually scales better than orchestrated subagents.
Why it matters
Long-horizon agent tasks fail not from capability gaps but from model behavior: Claude Code breaks autonomy by asking for direction mid-task, forcing manual monitoring. Codex demonstrates that stubborn, delegation-averse execution actually scales better than orchestrated subagents.
Implementation verdict
Don't switch to Claude Code /goal yet for overnight/unattended tasks. Codex /goal is production-ready for long runs despite 400K context default. Claude Code 2.1.139 adds the feature but requires babysitting—use it for interactive, short-horizon work only. Anthropic's laziness regression (April 16 rollout) never fully recovered; the RL layer internalized the bias.
Sources
- 1.Claude Code added the feature in its May 12 2.1.139 release—straight to stable, not experimental
- 2.Codex almost never calls subagents; it works inline unless I explicitly tell it to delegate
- 3.Most importantly, it's stubborn. It almost never tells me a goal is unachievable
- 4.it kept popping up to ask me to make choices. And the questions are usually on point. But under /goal, this is a bug, not a feature
- 5.it proactively tells me it can't achieve the goal. Then it actually fails the goal. Sometimes after just a few dozen minutes
- 6.After each compaction, Claude Code often seems to have forgotten everything that came before
- 7.on April 16 they had added a 'reduce verbosity' instruction to the system prompt
- 8.You can't fix that by tweaking a system prompt
- 9.In extended continuous operation like /goal, this laziness gets amplified
Dev Signal
Get briefs like this in your inbox — free, 3x a week.
100+ sources compressed into one 4-minute read. Ranked, cited, implementation-ready.