ClaudeMods
☰
ZH-TW
● 0 人在線上 · 瀏覽 0 次
贊助提交作品
GitHub 儲存庫 · 發布者 ildunari

cache-timer

一個 Claude Code mod(function-hook 外掛),用來追蹤主要對話的提示快取視窗。

ildunari@ildunari

ildunari/kosta-plugins/tree/main/plugins/cache-timer

已翻譯

關於這個 mod

cache-timer

一個 Claude Code mod(function-hook 外掛),用來追蹤主要對話的提示快取視窗。

  • 狀態列:🟢 ▰▰▰▰▰▰▰▰▱▱ 47:12,顯示在模型名稱旁。視窗使用量超過一半時顯示 🟢,降到 15% 時變為 🟡,低於該值時變為 🔴,過期後顯示 ⚪ cold。視窗會從主要執行緒送出要求的時間開始重新計時,並在模型完成回應後結束(被中斷的回應也算);子代理程式和壓縮要求使用各自的快取前綴,會被忽略。
  • **警告:**剩下 12 分鐘時,提示訊息會說如果不傳送內容,2 分鐘後將進行自動壓縮。如果上下文太小而無法壓縮,或時鐘在休眠後已經跳過 10 分鐘的位置,就不會顯示警告。
  • **自動壓縮,只執行一次:**剩下 10 分鐘時,只要快取仍然是暖的,就會執行與 /compact 相同的壓縮。每一代快取(以要求時間命名)只有一次機會:呼叫前就會消耗機會,跳過呼叫或在工作階段中途拒絕也會消耗機會;只有抵達模型的新要求,才會以新的機會啟動新一代。上下文少於 40k 權杖時會跳過;如果要求在準備期間重新預熱快取,也會關閉這次壓縮呼叫。📦 表示某一代確實執行過壓縮。

這裡假設視窗使用 1 小時 TTL(TTL_MS)。使用 5 分鐘 TTL 的工作階段(超額用量、某些 API key 設定)會看到錯誤的倒數。門檻是 hooks/register.tsx 頂端的常數。

安裝:claude plugin install cache-timer@kosta-plugins。檢查:claude plugin validate plugins/cache-timer。

安裝

請先查看作者 README,確認 marketplace 與外掛名稱;指令可能隨儲存庫結構而變動。

claude plugin marketplace add ildunari/kosta-plugins
claude plugin install cache-timer
原文 / README

cache-timer

A Claude Code mod (function-hook plugin) that tracks the prompt-cache window of the main conversation.

  • Status line: 🟢 ▰▰▰▰▰▰▰▰▱▱ 47:12 beside the model name. The dot goes 🟢 above half the window, 🟡 down to 15%, 🔴 below, ⚪ cold once it has expired. The window restarts from when a main-thread request is sent, once the model has answered it (an interrupted answer counts); subagent and compaction requests run on their own cache prefix and are ignored.
  • Warning: at 12 minutes left, a toast says an auto-compact is coming in 2 minutes unless you send something. It's skipped when the context is too small to compact, or when the clock has already jumped past the 10-minute mark (after a sleep).
  • Auto-compact, once: at 10 minutes left, while the cache is still warm, it runs the same compaction as /compact. Each cache generation (named by its request time) gets one shot: it's spent before the call, a skip or a mid-turn refusal leaves it spent, and only a new request that reaches the model starts a generation with a fresh shot. It skips contexts under 40k tokens and calls the compaction off if a request re-warmed the cache while it was getting ready. 📦 marks a generation where a compaction actually stood.

The window is assumed to be the 1-hour TTL (TTL_MS). Sessions on the 5-minute TTL (usage overage, some API-key setups) will see the wrong countdown. The thresholds are constants at the top of hooks/register.tsx.

Install: claude plugin install cache-timer@kosta-plugins. Check: claude plugin validate plugins/cache-timer.

其他同名作品

更多類似作品