Claude desktop scheduled tasks stall at permission prompts, breaking unattended runs
arturo-natella · ghdev · 2026-10-14
Issue #101851 on anthropics/claude-code reports that scheduled tasks in the Claude desktop app (Code tab) on macOS often fail to run unattended: a task starts on schedule, then halts at a permission prompt for a tool, folder, or command and waits for human approval that will never come.
The author argues scheduled tasks should run autonomously, with permissions decided at creation time (or via allow rules / "Always allow"), and that ungrantable permissions should fail loudly with a notification instead of hanging. The issue is marked duplicate, related to #47180 where "Always allow" doesn't persist between scheduled runs.
More from coding & agent
- Claude cut a 2.6-hour video export to 20 minutes — but only after being told to rebuild the server — byhewar · 2026-10-23
- 3 flight-booking rules my AI agent checks that I'd never do by hand — Efistoffeles · 2026-10-23
- OpenJet claims Qwen3.8-27B coding runs 1.9x faster than llama.cpp on one RTX 3090 — JeremyCMorgan · 2026-10-23
- Building an autonomous SEO agent in Hermes with three skills: programmatic pages, Keywords Everywhere, DataForSEO — EXM7777 · 2026-10-23
- Building a sports betting AI agent with onchain execution and human approval by default: architecture and lessons — Dry-Comfortable-2678 · 2026-10-23
- How do you audit AI agent decisions in regulated workflows? A field survey — Ok_Way_1993 · 2026-10-23