Auto mode using a safety classifier for tool calls
還沒有人認領這個 Issue。
評估
研究方向
沒有指定檔案、測試或具體進入點。首先定位現有的 edit 和 plan 模式，以及允許已核准命令自動執行的功能。完成這項工作需要定義一個 Auto Mode，使用使用者可設定的安全分類器評估工具呼叫，並避免不必要的手動核准。
由索引模型根據 Issue 內容生成。
描述
Feature Description
Instead of just having edit and plan modes, introduce a new mode called "Auto Mode". This would use an automatic safety classifier for things like bash commands and such, similar to what Claude Code has, so that users don't have to constantly babysit the harness when it's running commands. It would likely be powered by a cheap open source model, like DeepSeek V4 Flash or Qwen 3.8 Flash to keep costs low, but the classifier model should be able to be changed by the user at any point.
Use Case
Allows for users who are working to step back while the agent does its own thing, instead of having to manually accept bash commands and the like. There is already functionality for allowing the agent to run specific commands on its own, after it's been allowed, but I find that often doesn't work very well for one reason or another. In workflows where the user may be doing multiple things at once, it can get annoying to have to go back and allow things in order to stop the agent from hanging on a single bash command request for potentially minutes on end while the user isn't aware it's even there.
Additional Context
No response
How important is this to you?
Important for my workflow
- 主要語言
- 沒有語言資料
- 星號
- 4k
- 分支
- 350
- PR 合併指標
- 30 天內沒有已合併 PR
貢獻指南
這個儲存庫沒有索引到貢獻指南
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。
CommandCodeAI/command-code 的其他 Issue
-
難度 2/5 1-3 小時 新手友好度 68/100
CommandCodeAI/command-code#855 ·
-
難度 2/5 1-3 小時 新手友好度 78/100
CommandCodeAI/command-code#841 · 1 則留言 ·
-
難度 2/5 1-3 小時 新手友好度 68/100
CommandCodeAI/command-code#655 · 1 則留言 ·
-
難度 2/5 1-3 小時 新手友好度 68/100
CommandCodeAI/command-code#608 ·
-
難度 3/5 1-2 天 新手友好度 70/100
CommandCodeAI/command-code#893 ·
查看 CommandCodeAI/command-code 的全部 Issue
相似的 Issue
-
難度 2/5 1-3 小時 新手友好度 78/100
use-agent-os/agent-os#3263 ·
-
[Bug]: context-limit error parsing has no pattern for llama.cpp's "context size (N tokens)" phrasing 未關閉area/compression area/local-models area/sessions comp/agent duplicate P2 sweeper:risk-session-state type/bug
難度 2/5 1-3 小時 新手友好度 82/100
NousResearch/hermes-agent#117793 · 1 則留言 ·
-
難度 2/5 1-3 小時 新手友好度 82/100
-
難度 2/5 1-3 小時 新手友好度 84/100
-
難度 2/5 1-3 小時 新手友好度 75/100
BasedHardware/omi#15236 · 1 則留言 ·