A saved AI! or AI? comment starts a quick or answer branch of the watching session, in its checkout, never a turn of its own agent; the branch asks before every write unless watch_auto_approve is on; watch state is on the protocol¶
Decision 844 · accepted · 2026-10-10 · issue #502
Where a trigger goes¶
- A branch, never the root. Each debounced scan that finds
AI!orAI?comments starts one session whoseparentis the watching session (Troupe.Watch.Branch), onquickwhen any comment is a change and onanswerwhen all are questions: the agents TUI Decision 67 sent them to. - In the checkout. The branch works in the watching session's workspace, not a fresh worktree: the comment, and usually the code it is about, are in files there that need not be committed, and a small local change is wanted where the person is looking, not on a branch to merge.
- Under the plan permission set for
AI?. The trigger is the branch's first input, as awatchinput, so an all-question trigger runs its turn withturn_mode: :question. That mode now keeps the agent's own definition — model, prompt, turns — and narrows it to the toolsplanalso has, withplan'sdenyentries over its own. - No
watch.change_command/watch.question_command. Decision 67 had them because "quick and cheap" is a judgement about the repository. That judgement is now made by redefiningquickoranswerin.troupe/agents/(or the person's ownagents/), which the definitions ladder already gives (Decisions 822, 826). Two settings naming another agent would be a second way to say the same thing, and would make anAI!and/quicktwo paths again, which #502 asks to be one.
What a trigger may do unasked¶
Anything that writes a file can write an AI! comment: a pull, a generator, a formatter,
another tool, a dependency's post-install step. With watch on, that is a change turn the
person did not ask for. So the branch a trigger starts asks before every write, edit,
shell command and MCP server's tool, whatever auto_approve says and whatever the agent's
own permissions and a server's permission: auto say. It runs with auto_approve:
false and is started with hold_auto: every definition it runs under has its auto
entries taken out (Branch.hold_auto/1, in Session.build_opts/1), and every MCP server
it starts has its permission: auto set back to ask (Troupe.Session.MCP), the way
Decisions 825 and 830 hold back a workspace's until it is trusted.
watch_auto_approve (boolean, default false, trusted scope, so a project's file sets it
only in a trusted workspace, as auto_approve) turns that off: the branch then runs
auto_approve: true, and its agents' and servers' auto entries apply.
watch itself has trusted scope too: a repository's own .troupe/config.yaml turns watch
on only in a workspace the person trusts, so a clone cannot make every comment in it start
work. The person's own file, --watch, a client's session.create config and watch.set
are not affected.
Where watch runs¶
A pod's session never watches, whatever its config says: watching is for files on the person's own machine, and a branch it started there would be a session no plane placed.
Governs: apps/troupe_core/lib/troupe/watch.ex, apps/troupe_core/lib/troupe/watch/branch.ex, apps/troupe_core/lib/troupe/session/watcher.ex