Claude Code cloud routines start refusing scheduled runs after July 13 bug report
bishnudg · ghdev · 2026-07-16
A GitHub issue reports that Anthropic’s Claude Code cloud routines started refusing to run after July 13, 2026, even though the same daily scheduled trigger had worked for seven days straight.
- The routine was created through the /v1/code/triggers API and ran successfully from July 6 to July 12.
- From July 13 onward, every firing was declined because the prompt began arriving with a SYSTEM NOTIFICATION — NOT USER INPUT disclaimer, making the model treat its own scheduled prompt as untrusted injected content.
- The reporter says manual human intervention is now required every day, which defeats unattended automation.
More from coding & agent
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- Dev mixes Claude specs with abliterated GLM to build SS7 threat detector — l4rz · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- GitHub Next's Chopin prototype explores real-time multiplayer agentic planning — max__drake · 2026-10-27
- Veynod: An Open-Source Shared Workspace Where AI Agents Collaborate Like a Team — TKOWNS · 2026-10-27
- TMLR paper: enforced thinking doesn't reliably make LLM agents disclose key info to users — SharonYixuanLi · 2026-10-27