Claude Code AI agent update: - Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claud
- Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues - Fixed Claude seeing stale MEMORY.md and CLAUDE.md content right after automatic compaction when those files were edited earlier in the session - Fixed background agents in auto mode that wait on their own shells start
研究重點
- Fixed standard-context sessions stopping with "Usage credits required for 1M context" when a request ran over 200K tokens; Claude Code now compacts the conversation and continues - Fixed Claude seeing stale MEMORY.md and CLAUDE.md content right after automatic compaction when those files were edited earlier in the session - Fixed background agents in auto mode that wait on their own shells starting a new main conversation turn on every wake - Fixed ↑ in an agent's chat tab recalling a message that was still waiting to be delivered, so resending it sent a second copy
為什麼值得關注
這個議題涉及 Crew Pocket、Crew Deck 的實作方向。可先評估現有做法,再決定是否安排小型實驗。
可以進一步驗證什麼?
- 閱讀原文,確認它解決的問題、實驗方法及適用限制
- 檢查相關功能現有做法,找出可比較的差異
- 用小型 PoC 驗證成功率、品質、延遲和實際成本
參考資料
延伸探索
相關研究
- Claude Code AI agent update: - Fixed sessions on many third-party gateways and Foundry stopping with a context length error on every turn instead of compacting相同研究主題 · 2026-11-15
- Claude Code AI agent update: - Fixed running `/compact` again, or after a command such as `/context`, summarizing away a message that Claude had not answered y相同研究主題 · 2026-11-13
- Claude Code AI agent update: - Added Claude Fable 5.2 (`claude-fable-5-2`), now the default Fable model — 1M context, $8/$40 per Mtok with $0.20/Mtok cache rea相同研究主題 · 2026-11-10