Submit root events through the local socket

[onechat] / view_layout.go

diff --git a/view_layout.go b/view_layout.go
index 560abb21042ad854cb2e61fcbff4d0703b8ce624..a88c8fdb1bdf0c2f7f3accce0de78948936e6fd0 100644 (file)
--- a/view_layout.go
+++ b/view_layout.go
@@ -18,9 +18,9 @@ const viewLayoutFileName = "layout.json"
 // grow between batches. The view goes out as the same messages as in the
 // request before, while their lines give the same text, and the new lines
 // follow as one new message. So the end of the view of each earlier turn stays
 // grow between batches. The view goes out as the same messages as in the
 // request before, while their lines give the same text, and the new lines
 // follow as one new message. So the end of the view of each earlier turn stays

-// a message end. On the ChatGPT backend, the first request of a turn with this
-// layout read the view of the turn before from the prompt cache in each of 10
-// turns, and with the view in one message it missed once in 5.
+// a message end. Stable message boundaries let the model reuse the unchanged
+// view prefix from its prompt cache instead of invalidating it when new lines
+// arrive.

 //
 // The first message starts with "<chat>\n". The closing tag goes into the state
 // message after the view, so that no view message changes when lines come. The
 //
 // The first message starts with "<chat>\n". The closing tag goes into the state
 // message after the view, so that no view message changes when lines come. The