You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 66a0e96
Browse filesBrowse the repository at this point in the historyBrowse files
- Model picker menu lives on the heap so a combo destroyed while it is
open no longer double-destroys a stack QMenu.
- PM2 banner buttons run a copy of their action: updateBanner() replaced
the stored std::function while it was executing.
- clang-tidy: no-automatic-move, enum-size, implicit-conversion-in-loop,
and move the pending entry out before erasing it.
- README: PM2 Processes dialog and Prewalk.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Copy file name to clipboardExpand all lines: README.md
+3-1Lines changed: 3 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -10,7 +10,7 @@ You shouldn't have to leave your editor to talk to an AI, run git, or open a she
10
10
11
11
NotepadAI speaks the Agent Client Protocol (ACP) over stdio. Claude Code and Codex ship as factory agents and can be edited or deleted in Settings. You can also add any other ACP-compatible agent, including Gemini, Auggie, or your own command. Agents read and write files, run terminal commands, and see your workspace context, so they work on the same code you do. Start a session from the AI menu or by right-clicking a folder in the file tree.
12
12
13
-
In a chat, a finished turn folds into a single "Worked for 2m14s" row; click it to bring back the tool calls and intermediate messages. Tool calls show how long they took. Claude Code background tasks and the wake-ups or cron jobs it schedules for itself appear under the transcript, with a Stop link for tasks that can be stopped. When the agent offers `/advisor`, an Advisor checkbox in the composer turns it on and off. When an agent needs a decision, its questions appear as a form in the chat with the suggested answer preselected, and a note box at the end takes anything else you want to add.
13
+
In a chat, a finished turn folds into a single "Worked for 2m14s" row; click it to bring back the tool calls and intermediate messages. Tool calls show how long they took. Claude Code background tasks and the wake-ups or cron jobs it schedules for itself appear under the transcript, with a Stop link for tasks that can be stopped. When the agent offers `/advisor`, an Advisor checkbox in the composer turns it on and off. For Claude Code, Prewalk (at the top of the model picker) switches to a cheaper model once the agent starts editing files and back when the turn ends. When an agent needs a decision, its questions appear as a form in the chat with the suggested answer preselected, and a note box at the end takes anything else you want to add.
14
14
15
15
There is also a Goal Agent: pick an ACP judge (Claude Code, Codex, Opencode) or a Custom API endpoint that speaks Anthropic's Messages API. You set success criteria and it drives the working agent until those criteria hold, or attach a goal to an existing conversation. Criteria presets can be saved globally, or into the current project's `.agents/.goals` folder so they travel with the repo; files already in that folder show up in the load list. A judge that needs a human action, or that hits the iteration cap with the criterion still unmet, stops and hands the criterion back instead of marking the goal done. With Prefix /goal checked, the first criterion is sent immediately when the agent supports `/goal`. If a reply is still running and the agent does not support `/goal`, that goal waits in the send queue so the current reply is not stopped. Later criteria wait until the previous is achieved. Send with Goal defaults to the agent's own `/goal` command instead: each criterion goes out on its own, with no separate judge. A `/goal` typed in the composer is sent while a turn is still running only when the agent supports that command; otherwise it waits in the queue. A goal is not judged, and auto compact does not run, while the agent still has background tasks running or a wake-up turn pending. When a goal is achieved, the session can compact automatically. Prompts sent while an agent is still working are queued and delivered when it finishes. AI chats group by project, with a session strip to switch conversations in the same dock. Open chats come back after a restart and resume their agent session on the first prompt. A local Claude Code chat can be moved to another agent from the agent button in the dock's title bar, keeping its transcript. The composer can ask the agent to work in a new git worktree. When you commit, AI can write the commit message from your staged diff. That generator (and other LLM calls) can talk to an OpenAI-compatible endpoint or Anthropic's Messages API. Leave the commit box empty (when not amending) and Commit lets you pick an ACP agent to do the commit. Protocol details and how to wire up a custom ACP agent are in [doc/AcpAgents.md](doc/AcpAgents.md).
A PTY terminal built on libvterm and libptyqt, with mouse reporting and a scrollback buffer. New terminals open as a bottom tab under the editor. When a workspace opens with no terminal, that area shows a placeholder with a New terminal button and the workspace's configured tasks; close it to hide it for that workspace, or turn it off under Preferences → Terminal. The tab strip follows the raised workspace: only terminals whose working directory belongs to that folder (or a nested workspace, longest match) are shown. If any open terminal sits outside every workspace, the filter turns off and every tab stays visible. Closing a workspace closes its terminals. Programs launched from a local terminal share a memory ceiling (16 GB by default, changeable under Preferences → Terminal) so a runaway process is stopped instead of exhausting the machine. A local terminal's title bar shows that process tree's CPU and RAM; hover the CPU figure for each logical core's load. Remote terminals omit those figures. It reads Justfile, Makefile, package.json, and deno.json, finds which tasks you can run, and draws clickable run icons in the editor margin. Open a terminal at the active workspace or at the current file's folder.
24
24
25
+
Terminal → PM2 Processes lists every process of your local pm2 with live status, uptime, CPU and memory. You can start, stop, restart, or delete them, follow their logs in a terminal tab, and run a new command under pm2 with its own directory, shell, and environment variables. pm2 is fetched through npx if it is not installed.
0 commit comments