Oct 15, 2025Single source
Claude Code autocompacting loop spiked token usage until the budget ran out (flagged ACTIVE INCIDENT)
AI loose in the worldAvailabilityDERIVED
Approved by person, Oct 11, 2026. How entries are approved
Windows users reported Claude Code entering an autocompaction loop: the session compacted its own context over and over without ever finishing, spiking token usage on every cycle. The issue was labeled 'ACTIVE INCIDENT, Cost escalation ongoing', and linked reports described the loop running infinitely until the token budget was exhausted.
What this means for youIf you or your team use AI coding tools, a bug can quietly run up usage charges, so check usage dashboards and set spending limits on the account.
Sources
- GitHub issue, anthropics/claude-code 9579https://github.com/anthropics/claude-code/issues/9579
Incident records from the AI Agent Incident Database by sipi.bot (https://sipi.bot/incidents/), licensed CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/).
Source data license: CC BY 4.0. Attribution to sipi.bot is required.
Covered by snapshot 45
da93f03b406f409940d0a6ef47b526607f82ebf457d98f69299b88aceede576a
This entry is record number 2322. It has not been edited since it was approved; the hash above would not match if it had. How to verify