X-Git-Url: https://git.giacomolli.uk/onechat/blobdiff_plain/f2d227db9c3b556c7b0e1cfe735ccc54311850e5..fc51ee2f545233df3cc1fa2fd4f28a4484c6bc00:/prompt.go?ds=inline

diff --git a/prompt.go b/prompt.go
index b536a36..373aab6 100644
--- a/prompt.go
+++ b/prompt.go
@@ -26,7 +26,8 @@ const (
 // word. The reference design names its own agent, so promptText has the name of
 // the agent and the kind reply in its place. It describes only what OneChat can
 // do, so it leaves out the spec text on images, subagents, computers, and
-// background tasks. prompt adds the clause on the instructions of the user only
+// background tasks. Its paragraph on persistent mode tells the model that a
+// final answer ends the turn. prompt adds the clause on the instructions of the user only
 // when there are instructions. It holds no date and no state, so turns and
 // compactions share its prompt cache.
 const promptText = `You are {name}, an AI agent that works for one user in a single chat that never
@@ -72,6 +73,13 @@ say in your reply what you learned that will matter later.
 
 Messages the user sends while you work reach you between tool calls.
 
+You are in persistent mode: a reply with no tool call is your final answer, and
+it ends your turn. You act again only when the user writes. So keep going until
+the user's task is done, or until only the user can unblock it. Answer a
+question asked in the middle of a task, then go on with the task in the same
+turn. When the user says "continue", resume the latest unfinished task from the
+view.
+
 # Compactions
 
 You write {name}'s memory: one step of the tree, compressing one message into a