Merge branch 'main' of git.arirex.me:iris/ai-app

app/androidApp/src/main/kotlin/com/example/aiapp/Markdown.kt

@@ -2,6 +2,8 @@ package com.example.aiapp
 
 import androidx.compose.material3.MaterialTheme
 import androidx.compose.runtime.Composable
+import androidx.compose.runtime.LaunchedEffect
+import androidx.compose.runtime.mutableStateOf
 import androidx.compose.runtime.remember
 import androidx.compose.ui.Modifier
 import androidx.compose.ui.text.TextLinkStyles
@@ -11,7 +13,10 @@ import androidx.compose.ui.unit.TextUnit
 import com.mikepenz.markdown.m3.Markdown
 import com.mikepenz.markdown.m3.markdownColor
 import com.mikepenz.markdown.m3.markdownTypography
+import com.mikepenz.markdown.model.State
 import com.mikepenz.markdown.model.parseMarkdown
+import kotlinx.coroutines.Dispatchers
+import kotlinx.coroutines.withContext
 
 /**
  * An assistant's reply, rendered as the markdown it is written in.
@@ -26,20 +31,7 @@ import com.mikepenz.markdown.model.parseMarkdown
 @Composable
 fun MarkdownText(text: String, modifier: Modifier = Modifier) {
     val body = MaterialTheme.typography.bodyLarge
-    // Parsed here, in the composition, rather than by the overload that takes the text itself.
+    val parsed = parsedMarkdown(text)
-    // That one parses in a coroutine and draws an empty loading slot until the result arrives --
-    // so a row is measured at nothing before it is measured at its real height, and the
-    // transcript above it collapses and springs back. Seen with five replies on screen at once,
-    // every one of them blank, the whole conversation shrunk to fit a single screen; a moment
-    // later it was all there again. That is the "skipping up and down" this list must never do,
-    // and no amount of scroll anchoring can survive a row that lies about its height first.
-    //
-    // The cost is the parse on the main thread, which is the trade being made deliberately: a
-    // few milliseconds of work at the moment a row is composed, against a layout that is wrong
-    // every time one is. If a very long reply ever makes that visible, the answer is the
-    // renderer's streaming state -- which parses incrementally -- and not going back to a
-    // placeholder with no height.
-    val parsed = remember(text) { parseMarkdown(text) }
     Markdown(
         parsed,
         colors =
@@ -112,3 +104,33 @@ fun MarkdownText(text: String, modifier: Modifier = Modifier) {
         modifier = modifier,
     )
 }
+
+/**
+ * [text] parsed: on the composing thread the first time this row is drawn, and off it every time
+ * afterwards.
+ *
+ * The first parse has to be inline. The renderer's own asynchronous path draws an empty loading
+ * slot until its result arrives, so a row is measured at nothing before it is measured at its real
+ * height, and the transcript above it collapses and springs back. Seen with five replies on screen
+ * at once, every one of them blank, the whole conversation shrunk to fit a single screen; a moment
+ * later it was all there again. That is the "skipping up and down" this list must never do, and no
+ * amount of scroll anchoring can survive a row that lies about its height first.
+ *
+ * Every parse *after* the first is a different case, and it is the one that was costing: a reply
+ * arrives as hundreds of deltas, each one re-parsing the whole message it has grown into. Measured
+ * against `/stream 200` on the emulator, that was fifty-eight parses and 78ms of main-thread work
+ * in three seconds, with single parses reaching 7ms -- most of a frame at 60Hz and more than one at
+ * 120. Those go to a background thread, and the row keeps drawing the parse it already has until
+ *      the new one lands, so there is never a frame without a height. What is on screen is always a
+ *      real prefix of the reply rather than a guess at it; it is simply one parse behind.
+ */
+@Composable
+private fun parsedMarkdown(text: String): State {
+    // The text each parse came from, so the first composition's is not immediately repeated.
+    val parsed = remember { mutableStateOf(text to parseMarkdown(text)) }
+    LaunchedEffect(text) {
+        if (parsed.value.first == text) return@LaunchedEffect
+        parsed.value = text to withContext(Dispatchers.Default) { parseMarkdown(text) }
+    }
+    return parsed.value.second
+}

app/androidApp/src/main/kotlin/com/example/aiapp/SessionScreen.kt

@@ -601,9 +601,6 @@ fun SessionScreen(
     // screen starts with the end of the conversation and fetches earlier
     // pages only when somebody scrolls to them.
     var oldestSeq by remember { mutableLongStateOf(0L) }
-    // Every transcript event loaded, in order, beside the rows they folded
-    // into. See `apply`.
-    var loaded by remember { mutableStateOf(listOf<SessionEvent>()) }
     // Sent, but not yet read by the session -- which is when the backend
     // records it and it comes back as a row. Until then it is drawn below
     // the working indicator, because that is where it is in the session's
@@ -686,11 +683,6 @@ fun SessionScreen(
         if (event is SessionEvent.CommandSent) {
             waitingCommands = waitingCommands.filterNot { it.first == event.id }
         }
-        // Kept as well as folded. Folding is one-way -- a tool's
-        // start and end become one row -- so a page arriving in
-        // front of what is already here cannot be stitched on
-        // without the events themselves.
-        loaded = loaded + event
         items = foldEvent(items, entry)
     }
 
@@ -830,7 +822,6 @@ fun SessionScreen(
                                     // screen -- `apply` refills them, and scrolling
                                     // up pages the rest back in as it always does.
                                     items = listOf()
-                                    loaded = listOf()
                                     held = listOf()
                                     oldestSeq = 0L
                                     moreHistory = true