X-Git-Url: http://git.giacomolli.uk/onechat/blobdiff_plain/e0ab6220b6fd35f7e92a04e4bf149940185713ab..6d1d9d9a7cf90b25a2e10af1c5bc56faee7e494c:/layout.go

diff --git a/layout.go b/layout.go
index a3f9de0..c5e9ac3 100644
--- a/layout.go
+++ b/layout.go
@@ -14,12 +14,12 @@ import (
 const layoutFileName = "layout.json"
 
 // viewLayout splits the view of a turn request into user messages that only
-// grow between batches. The ChatGPT backend writes a cache entry only at the
-// end of the latest message of a request, and a later request reads it only at
-// one of its own message ends. So 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. Then the end of each earlier view stays a message
-// end, and a warm-up entry there stays readable when the view grows.
+// 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.
 //
 // 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