Briefing每日研發情報

選擇介面語言

僅變更 Koolo 的顯示語言,不影響老師教學與對話的語言。

Context & Memory2026年11月9日1 個來源

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

- 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 reads - Fixed context usage estimates overcounting tool definitions when exact token counts are unavailable - Fixed project skills, commands and agents staying missing after their folder was removed and came back mid-session, such as with `git stash`, including after enter

Crew PocketCrew Deck

研究重點

- 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 reads - Fixed context usage estimates overcounting tool definitions when exact token counts are unavailable - Fixed project skills, commands and agents staying missing after their folder was removed and came back mid-session, such as with `git stash`, including after entering a worktree - Fixed a large hook output pointing Claude to a file that held another hook's output from the same tool call

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?

  1. 閱讀原文,確認它解決的問題、實驗方法及適用限制
  2. 檢查相關功能現有做法,找出可比較的差異
  3. 用小型 PoC 驗證成功率、品質、延遲和實際成本

參考資料

研究報告會保留來源與發表日期;引用的論點及數據仍應以原文為準。

Claude Code v2.1.321 ↗2026-11-09T19:22:30Z · 官方產品更新

延伸探索