Claude Code Scheduled Tasks Bug: Silent Failures and False Success Reports
wshallwshall · ghdev · 2026-07-31
A developer reported a critical bug in Claude Code's scheduled-tasks feature. Six sessions attempting to schedule a restart after hitting usage limits all failed in two distinct ways:
- Silently dropped: 3 tasks were never dispatched but remained enabled: true with a nextRunAt timestamp stuck in the past, leaving them permanently armed.
- Killed mid-execution but reported success: 3 tasks were killed mid-tool-call within 15-27 seconds, but the system marked them as enabled: false with lastRunAt set—identical to a successful completion.
The report notes that the underlying scheduling API functions correctly, suggesting the defects lie entirely in dispatch, execution, and state reporting. Additionally, when multiple tasks share the same fire time, only a prefix of the tasks is dispatched while the rest are dropped.
More from coding & agent
- Tencent Releases UI-Mate-27B, a Desktop GUI Agent Model — tencent · 2026-08-24
- Comparing AI Subscriptions: DeepSeek API vs. Claude Pro vs. Local LLMs — Unlikely_Bluejay5392 · 2026-08-24
- Claude Code introduces 'Remote Control' feature to boost coding efficiency — rohanpaul_ai · 2026-08-24
- rauchg lays out fx extension philosophy: MCP, Skills, Plugins and Unix composition — AccBalanced · 2026-08-24
- Netflix details its production LLM judge: hundreds of thousands of recommendations scored weekly — omarsar0 · 2026-08-24
- smolvm passes Simon Willison's Fable 5 agent test as a secure sandbox — yawnxyz · 2026-08-24