Claude Code bug: prompt cache TTL drops from 1h to 5min in v2.1.301
DavideDelbiancoZucchetti · ghdev · 2026-10-16
A user reports a regression in Claude Code v2.1.301: on a Team premium seat, sessions running version 2.1.196 get a 1-hour prompt cache TTL, while every new chat on v2.1.301 drops to 5 minutes. Shorter TTL means fewer cache hits and more re-billed tokens, raising effective usage costs. The issue is labeled duplicate (Windows terminal environment); no fix noted yet. Heavy subscribers may want to check their current version's cache behavior.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23