Make model download cancellation asynchronous
維護者通常 4 天內回覆
@ckelseynv 已經在處理了。
開始於 2026年9月23日。
評估
這個 Issue 還沒有評估資料。
描述
engine:cancel-pull and engine:remote-cancel-pull block until the download has stopped and its partial files are settled. That single decision is what forces every layer above them to carry a budget: the desktop picks 90s, the terminal interface picks 35s, the engine manager's peer client needs a separate long-header pool so a peer that takes minutes is not cut off, and each of those numbers has to be justified against the others.
It also sits awkwardly with state-and-auto-start.mdc, which says engine and model commands are fire-and-forget mutations whose outcome arrives on the push bus.
Proposal
Make cancellation fire-and-forget. The request acknowledges that the cancel was accepted; the terminal state arrives on the existing progress feed, the same way a pull's own completion does. Callers stop waiting, and most of the budgets in #114 stop being load-bearing.
Prerequisite
There is one non-obvious blocker. trackedPull routes a same-key retry to joinPull, so a retry issued while the previous download is still cleaning up would join the dying pull and receive its cancelled result rather than starting a new download. Today that is masked, because the caller is still blocked on the cancel and cannot retry yet. Removing the block exposes it.
So a retry arriving during cleanup has to start a new download rather than join the one being torn down. That ordering needs solving before, or alongside, the change — not after.
Worth preserving
Two behaviours from #111 should survive the redesign, because both were bugs that had to be fixed once already:
- A cancel must not overtake the pull it names. The remote path holds a cancel until the peer has accepted the matching pull; the local path claims the pull. A cancel that arrives first is answered as a cancel for nothing and leaves the transfer running.
- A cancel that stops being awaited must remain retryable, and the row must stay in Canceling rather than rolling back to Downloading. Asynchronous delivery makes the first half easier and the second half more important, since there is no longer a reply to distinguish "accepted" from "lost".
- 主要語言
- Go
- 星號
- 1.6k
- 分支
- 266
- 平均合併
- 3 天 18 小時
- 30 天內合併 PR
- 28
環境準備
- 沒有 Dockerfile 或 Docker Compose 檔案
- 有 Pull Request 範本
- 閱讀貢獻指南
從這裡開始
- 先讀完整個 Issue，再讀專案的貢獻指南。
- 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
- Fork 儲存庫，在一個分支上完成修改。
- 送出 Pull Request，並在描述裡引用這個 Issue 編號。
NVIDIA/Personal-AI-Router 的其他 Issue
-
難度 5/5 一週以上 新手友好度 20/100
NVIDIA/Personal-AI-Router#165 ·
維護者通常 4 天內回覆
-
bug
難度 4/5 3-5 天 新手友好度 46/100
NVIDIA/Personal-AI-Router#164 ·
維護者通常 4 天內回覆
-
enhancement
難度 4/5 一週以上 新手友好度 12/100
NVIDIA/Personal-AI-Router#162 ·
維護者通常 4 天內回覆
-
enhancement
難度 4/5 3-5 天 新手友好度 25/100
NVIDIA/Personal-AI-Router#154 · 1 則留言 ·
維護者通常 4 天內回覆
-
[Feature]: [Ollama] Alert the user about model pull failures可能已有人在做 @ckelseynv 於 5 天前認領。 未關閉enhancement
難度 3/5 1-2 天 新手友好度 56/100
NVIDIA/Personal-AI-Router#152 · 1 則留言 · 已指派 1 人 ·
維護者通常 4 天內回覆
查看 NVIDIA/Personal-AI-Router 的全部 Issue
相似的 Issue
-
mutation: parseInt64 accepts integers that overflow int64 and wrap to a non-negative value可能已有人在做 @ogulcanaydogan 今天認領。 未關閉
難度 2/5 1-3 小時 新手友好度 85/100
open-policy-agent/gatekeeper#4872 ·
維護者通常 1 天內回覆
-
needs-triage
難度 1/5 1 小時以內 新手友好度 88/100
維護者通常 1 天內回覆
-
難度 2/5 1-3 小時 新手友好度 68/100
containers/kubernetes-mcp-server#1496 · 1 則留言 ·
維護者通常 2 天內回覆
-
bug performance scalability
難度 2/5 1-3 小時 新手友好度 62/100
Davidjustice28/basildb#35 ·
-
難度 2/5 1-3 小時 新手友好度 78/100
rhysd/actionlint#761 ·