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
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11
- Investment Analyst Asks How to Build a Claude-Based Diligence Agent Stack — Careless_Tie2286 · 2026-09-11
- How Do You Catch Behavioral Regressions in LLM Agents Between Releases? — Beautiful_Belt_601 · 2026-09-11
- Treating agents like 50 First Dates: a 3-layer context system so every conversation doesn't start from zero — evielync · 2026-09-11
- Running the Firefox MCP on Android via Termux, ngrok, and mcp-proxy — Nervous-Strain7544 · 2026-09-11
- Run Firefox MCP on Android: Termux + ngrok tunnel tutorial — Nervous-Strain7544 · 2026-09-11