Files
ai-app/app/androidApp/src/main/kotlin/com/example/aiapp/TranscriptItems.kt
T
2026-09-10 01:24:16 -04:00

615 lines
30 KiB
Kotlin

package com.example.aiapp
import androidx.compose.runtime.Immutable
import kotlinx.coroutines.Dispatchers
import kotlinx.coroutines.withContext
/**
* What the transcript renders: the event stream folded into displayable rows (see [foldEvent]).
*
* Events are the only data source, and there is deliberately no second shape for history to drift
* from: a page fetched backwards, a live frame, and a line read out of this phone's own cache are
* all the same events through the same parser. [TranscriptCache] stores the server's lines rather
* than these rows for exactly that reason -- a row is a rendering, and its shape changes whenever
* this file does.
*/
@Immutable
sealed class TranscriptItem {
/**
* The transcript sequence number this row started at, and its identity on screen.
*
* The list is drawn newest-first, so every new message is an insertion at index 0 and every
* page of history is an insertion at the far end. Without an identity that survives both, the
* list is addressed by position: whatever somebody had scrolled to keeps its index while the
* content underneath it slides, which reads as the view scrolling on its own.
*
* A row built from several events keeps the seq of the first, so it holds still while the rest
* of it arrives.
*/
abstract val seq: Long
/**
* This item's identity on screen, which is its [seq] for everything that has one of its own.
*
* Here rather than in [TranscriptRow.Single] because the two items that need something else are
* the two that know why. Asking each item what it is called is also what stops the next such
* item being missed -- a `when` over concrete types would have to gain a case, silently.
*/
open val key: Any
get() = seq
data class UserMsg(
override val seq: Long,
val text: String,
/** Refs of what was attached, drawn inside the bubble. */
val attachments: List<String> = emptyList(),
) : TranscriptItem()
data class AssistantMsg(
override val seq: Long,
val text: String,
/**
* Whether this reply is finished: the session has stopped working since its last delta.
*
* What it buys is the split. [transcriptUnits] keeps the newest reply whole because a
* streaming reply's text changes per delta and splitting a changing text is a parse per
* delta -- but "newest" outlives the turn, so a session that ends on a long reply was
* drawing it as one item indefinitely. Measured on a Pixel 9 Pro XL: one 34,996px reply on
* screen put the frame's draw phase at 13.8ms, 79% of it framework bookkeeping.
*
* Folded from the status event that ended the turn rather than read off the screen's
* status, because rows only change through the held-events gate: the split changes the
* newest row's list identity, and doing that from a status flip while somebody is reading
* inside that reply would step the list under them.
*/
val settled: Boolean = false,
/** A final value that supersedes provisional deltas behind a page boundary. */
val replacesPrefix: Boolean = false,
) : TranscriptItem()
data class ToolRun(
override val seq: Long,
val id: String,
/**
* The run of adjacent calls this one belongs to, named once when the call is folded in and
* never recomputed.
*
* Carried rather than derived because a run can gain members at *either* end, so no
* function of its current members is stable. It is the first call's id at the moment the
* run started, which is a name rather than a description: [joinPages] hands it to older
* calls that turn out to belong to the same run.
*/
val runId: String,
val tool: String,
val input: String,
val output: String,
val done: Boolean,
/**
* The questions this call is waiting on, in the order they were asked.
*
* On the call's own row rather than beside it: an ask used to arrive as a second card
* repeating the input verbatim, so the reader saw the same command twice. The backend says
* which call a question is about, so this is a fact rather than a match on the input.
*
* A list because AskUserQuestion asks up to four at once, and a permission is the case of
* exactly one rather than a different shape.
*/
val asks: List<QuestionCard> = emptyList(),
/**
* Images this call's result carried, drawn under it. Beside it they had to be paired by
* position, and position is what a page boundary breaks.
*/
val images: List<String> = emptyList(),
) : TranscriptItem() {
/** A run, not a seq: see [TranscriptRow.key] for what that identity has to survive. */
override val key: Any
get() = runId
}
data class QuestionCard(
override val seq: Long,
val id: String,
val prompt: String,
/** A few words naming what this is about, when the asker offered one. */
val header: String?,
val options: List<QuestionOption>,
/** Whether several options may be chosen at once. */
val multiSelect: Boolean,
/** What was chosen, once something was; empty until then. */
val answers: List<String>,
) : TranscriptItem()
data class ErrorMsg(override val seq: Long, val message: String) : TranscriptItem()
/** An image by server-side ref, fetched from the session's files route. */
data class ImageItem(override val seq: Long, val ref: String) : TranscriptItem()
/**
* A message another agent sent this session. Its own row rather than a [UserMsg]: see
* [PeerMessageRow] for why the voice matters.
*/
data class PeerNote(
override val seq: Long,
val from: String,
val text: String,
/**
* The seq of the event this note came in on, which is what makes it itself.
*
* [seq] is where the note *sorts*, and [placePeerNote] sets it to the seq the turn began
* at. Two messages that arrive during one turn therefore share a seq -- and sharing an
* identity as well killed the app, because the list refuses two items with one key.
*/
val arrived: Long = seq,
) : TranscriptItem() {
override val key: Any
get() = arrived
}
/**
* Where one turn ended and the next began with nothing said in between.
*
* A rule and no words. Two replies meet like this whenever a turn starts without anybody typing
* -- a subagent reporting back, a session the CLI picked up by itself -- and drawn with only
* the ordinary gap between them they read as one answer with a paragraph break through the
* middle of it. What the reader needs is to see that these are two; what started the turn is
* somebody else's transcript's business, and a row per background task is a screenful of
* dividers about work nobody was asking after.
*
* Made by the fold rather than sent by the server, because it is not something that happened:
* it is the boundary between two things that did. See [foldEvent].
*/
data class TurnBreak(override val seq: Long) : TranscriptItem() {
/**
* Its own key, because it shares a [seq] with the reply it sits above -- that reply's first
* delta is the event this was made at, and a keyed list refuses two items with one key by
* taking the app down.
*/
override val key: Any
get() = "break$seq"
}
/**
* A command the session ran on itself -- `/compact`, `/rename`. Kept in the transcript rather
* than only shown while it waits, because it explains what follows: a conversation that
* suddenly has half the context, or a session with a new name.
*/
data class CommandRow(override val seq: Long, val text: String) : TranscriptItem()
/** Placeholder row for events this build can't render (newer kinds). */
data class Note(override val seq: Long, val text: String) : TranscriptItem()
/**
* A clear that happened: everything above it left the session's context and stayed on screen.
* Carries only its position, because that is all it means.
*/
data class ClearedNote(override val seq: Long) : TranscriptItem()
/**
* A compaction that happened, and what it recovered.
*
* In the transcript rather than only in the status line, because the status is gone the moment
* it finishes and this is the part worth keeping: the explanation for a gap in the
* conversation.
*
* The wire also says what triggered it, and this deliberately does not carry that -- the row
* says the two sizes and nothing else, so keeping the trigger would be a field nothing can
* read.
*/
data class CompactedNote(
override val seq: Long,
val preTokens: Long?,
val postTokens: Long?,
) : TranscriptItem()
/**
* The account ran out of quota, so the turn stopped here.
*
* A divider rather than an error: nothing failed, and what a reader scrolling back needs from
* it is the same thing a clear or a compaction gives them -- why the conversation stops at this
* line.
*
* [resetsAt] is epoch seconds and null where the session was told nothing, which is a state the
* row has words for rather than a time it invents.
*/
data class LimitNote(override val seq: Long, val resetsAt: Double?) : TranscriptItem()
}
/**
* The run a call joins: the one it lands next to, or a new one named after itself.
*
* Only ever consulted when the call is first folded in. That is what makes the name stable -- a run
* keeps whatever it was called when it started, however many calls arrive at either end afterwards.
*
* A question to the reader is in a run of its own, which is what puts it on the transcript as a row
* rather than inside a collapsed "Called 6 tools" card. Two things follow: it is always visible,
* since a run of one is drawn as itself; and the calls around it fall into a group before it and a
* group after it, so where the reader was asked something is legible in the shape of the transcript
* without opening anything.
*/
private fun runIdFor(items: List<TranscriptItem>, id: String, tool: String): String {
val previous = items.lastOrNull() as? TranscriptItem.ToolRun ?: return id
if (tool == ASK_USER_QUESTION || previous.tool == ASK_USER_QUESTION) return id
return previous.runId
}
/**
* Puts a page of older items in front of the ones already loaded, healing whatever the page
* boundary cut in two.
*
* Two things straddle a boundary: a tool call separated from its result, and a message separated
* from the rest of itself. Both were one thing before the transcript was cut into pages.
*
* A boundary lands wherever it lands, and roughly half the time that is between a call and its
* result. The newer page then holds a `ToolEnd` whose start it never saw, which [foldEvent] draws
* as a row of its own -- correctly, because a call that renders as nothing is indistinguishable
* from one that never happened. When the older page arrives it brings the real `ToolStart`, and
* concatenating the two lists left *both*: the same call twice.
*
* Merged by the call's own id rather than by position, because position is exactly what a page
* boundary destroys. The older row wins on what a start knows and the newer on what an end knows,
* which is the only way round that loses nothing.
*
* The third thing is the *run*, and it is the one that used to be missed. Every page ends up here,
* but [adoptRun] only ran on the path where a split call had been found -- so the boundary that
* falls cleanly between two finished calls, which is most of them, left the older page's calls
* under the run name they were folded with. On screen: one run of tool calls drawn as two groups,
* with the seam wherever the reader happened to have paged.
*/
fun joinPages(earlier: List<TranscriptItem>, later: List<TranscriptItem>): List<TranscriptItem> {
val (older, newer) = healSplitMessage(earlier, later)
val startedEarlier =
older.filterIsInstance<TranscriptItem.ToolRun>().mapTo(mutableSetOf()) { it.id }
val endedLater =
newer
.filterIsInstance<TranscriptItem.ToolRun>()
.associateBy { it.id }
.filterKeys { it in startedEarlier }
val healed = older.map { row ->
val half = (row as? TranscriptItem.ToolRun)?.let { endedLater[it.id] }
if (row is TranscriptItem.ToolRun && half != null) {
row.copy(
output = half.output,
done = half.done,
// Kept from both halves: a question or an image can be attached to either,
// depending on which side of the boundary its event fell.
asks = row.asks + half.asks,
images = row.images + half.images,
)
} else {
row
}
}
val kept = newer.filterNot { it is TranscriptItem.ToolRun && it.id in endedLater }
return adoptRun(healed, kept) + kept
}
/**
* Rejoins a message the page boundary cut, and hands back the two pages to concatenate.
*
* [foldEvent] never leaves an *unfinished* assistant message with another behind it inside one
* page, so an unsettled one at a join is always the far half of the reply the boundary cut, and
* leaving the two apart drew a single answer as two with a paragraph break through the middle of a
* sentence. Two settled replies meeting there are two turns and stay two.
*
* The newer half keeps its identity, for the reason [adoptRun] gives. It grows by what the older
* half brings, which is safe here and nowhere else -- the join is at the oldest end of what is
* loaded, so the growth extends off the top of the screen.
*/
private fun healSplitMessage(
earlier: List<TranscriptItem>,
later: List<TranscriptItem>,
): Pair<List<TranscriptItem>, List<TranscriptItem>> {
val head = earlier.lastOrNull()
val tail = later.firstOrNull()
if (head !is TranscriptItem.AssistantMsg || tail !is TranscriptItem.AssistantMsg) {
return earlier to later
}
// A settled reply is a whole turn, so the two are two answers that happen to meet at the
// boundary rather than one cut in half -- the same distinction the fold makes, and joining them
// here would put back exactly the run-together paragraph it stops.
// The rule between them is put in here too, since the fold that would have made it never saw
// these two side by side.
if (head.settled) return earlier to (listOf(TranscriptItem.TurnBreak(tail.seq)) + later)
if (tail.replacesPrefix) return earlier.dropLast(1) to later
return earlier.dropLast(1) to (listOf(tail.copy(text = head.text + tail.text)) + later.drop(1))
}
/**
* Hands the older calls at the join the name of the run they are joining.
*
* The two pages were folded separately, so a run split by the boundary came back as two runs with
* two names. Naming the joined run after the *older* half would be the obvious way round and is
* wrong: the newer half is the part already on screen, and renaming it is renaming the row the
* reader is looking at, which is how a list loses its anchor.
*/
private fun adoptRun(
earlier: List<TranscriptItem>,
later: List<TranscriptItem>,
): List<TranscriptItem> {
val first = later.firstOrNull() as? TranscriptItem.ToolRun ?: return earlier
// A question is in a run of its own on both sides of the join, the same as it would be had the
// two pages been folded as one. Without this the heal would merge a group straight through the
// row the reader was asked something on.
if (first.tool == ASK_USER_QUESTION) return earlier
val joining = first.runId
val tail = earlier.takeLastWhile {
it is TranscriptItem.ToolRun && it.tool != ASK_USER_QUESTION
}
if (tail.isEmpty()) return earlier
return earlier.dropLast(tail.size) +
tail.map { (it as TranscriptItem.ToolRun).copy(runId = joining) }
}
/**
* A peer message goes above the turn it started, not where it happened to arrive.
*
* The live Claude Code path cannot record it in place: the CLI says nothing about a peer message
* until the turn's `result`, so the event lands below the whole reply it caused. The server stamps
* it with where that turn began and the note takes that seq.
*
* Taking the turn's opening seq as its own is also what keeps the list sorted, which anchors and
* paging both depend on. It is only a *position*, though, and the note keeps its own arrival seq as
* its identity ([TranscriptItem.PeerNote.arrived]). The argument for sharing was that the turn's
* seq belongs to a status change and a status draws no row -- true, and it answered the wrong
* question: what two notes stamped with the same turn collide with is each other.
*
* Without a stamp -- a message replayed out of a session file -- it stays where it arrived.
*/
private fun placePeerNote(
items: List<TranscriptItem>,
seq: Long,
event: SessionEvent.PeerMessage,
): List<TranscriptItem> {
val at = event.turnStart ?: return items + TranscriptItem.PeerNote(seq, event.from, event.text)
val note = TranscriptItem.PeerNote(at, event.from, event.text, arrived = seq)
val index = items.indexOfFirst { it.seq > at }
if (index < 0) return items + note
val behind = (items.getOrNull(index - 1) as? TranscriptItem.ToolRun)?.runId
return items.subList(0, index) + note + splitRun(items.subList(index, items.size), behind)
}
/**
* The calls the note now sits in front of, renamed if they were sharing a run with the calls behind
* it.
*
* A run is named from what a call landed next to, and nothing there knows about turns -- so a turn
* opening with a tool call, straight after one that ended with one, folds them into a single run.
* Left alone, [groupToolRuns] would flush at the note and hand both halves the same name: two rows
* with one key, which a keyed list cannot draw at all.
*
* The later half is the one renamed, which is the opposite of a page join ([adoptRun]) and right
* for the opposite reason: there the two halves were always one run, here they were never one
* turn's work.
*/
private fun splitRun(tail: List<TranscriptItem>, behind: String?): List<TranscriptItem> {
val first = tail.firstOrNull() as? TranscriptItem.ToolRun ?: return tail
if (behind == null || first.runId != behind) return tail
val run = tail.takeWhile { it is TranscriptItem.ToolRun && it.runId == behind }
return run.map { (it as TranscriptItem.ToolRun).copy(runId = first.id) } + tail.drop(run.size)
}
fun foldEvent(items: List<TranscriptItem>, entry: SeqEvent): List<TranscriptItem> =
when (val event = entry.event) {
is SessionEvent.UserMessage ->
items + TranscriptItem.UserMsg(entry.seq, event.text, event.attachments)
is SessionEvent.AssistantText -> {
// Deltas accumulate into the message they're streaming, which keeps the seq of the
// first of them: a row whose identity changed with every delta would be a new row on
// every frame, and the list would jump for the whole of a streamed answer.
val last = items.lastOrNull()
// Only into a reply that is still arriving. A settled one is a turn that ended, and
// text after it belongs to the next turn -- a separate message, drawn as its own row.
// Growing it instead ran two answers together with not even a space between them,
// which is what happens whenever a turn starts with nothing recorded in front of it:
// a subagent reporting back, or a peer message the CLI only owns up to at the end.
if (last is TranscriptItem.AssistantMsg && !last.settled) {
items.dropLast(1) + last.copy(text = last.text + event.delta)
} else {
// A rule between the two, and only where they actually meet: anything that draws a
// row of its own -- a message, a command, a peer note -- is already the boundary.
val between =
if (last is TranscriptItem.AssistantMsg)
listOf(TranscriptItem.TurnBreak(entry.seq))
else emptyList()
items + between + TranscriptItem.AssistantMsg(entry.seq, event.delta)
}
}
is SessionEvent.AssistantTextFinal -> {
val last = items.lastOrNull()
if (last is TranscriptItem.AssistantMsg && !last.settled) {
items.dropLast(1) + last.copy(text = event.text, replacesPrefix = true)
} else {
val between =
if (last is TranscriptItem.AssistantMsg)
listOf(TranscriptItem.TurnBreak(entry.seq))
else emptyList()
items +
between +
TranscriptItem.AssistantMsg(
entry.seq,
event.text,
replacesPrefix = true,
)
}
}
is SessionEvent.ToolStart ->
items +
TranscriptItem.ToolRun(
entry.seq,
event.id,
runIdFor(items, event.id, event.tool),
event.tool,
event.input,
"",
done = false,
)
is SessionEvent.ToolUpdate -> updateTool(items, event.id) { it.copy(output = event.output) }
is SessionEvent.ToolEnd ->
// Created when its start is not here, rather than dropped. A fold that only ever
// *updates* loses the whole call when the start fell outside the loaded window, and a
// tool call that renders as nothing is indistinguishable from one that never happened.
// Loading the page before this one replaces the row with the real thing.
if (items.any { it is TranscriptItem.ToolRun && it.id == event.id }) {
updateTool(items, event.id) { it.copy(output = event.output, done = true) }
} else {
items +
TranscriptItem.ToolRun(
entry.seq,
event.id,
// The name is not known from an end alone, so a call that was an ask cannot
// be recognised as one here; the page before this replaces the row.
runIdFor(items, event.id, "tool"),
"tool",
"",
event.output,
done = true,
)
}
is SessionEvent.Question -> {
val card =
TranscriptItem.QuestionCard(
entry.seq,
event.id,
event.prompt,
event.header,
event.options,
event.multiSelect,
emptyList(),
)
// A question with no tool behind it -- AskUserQuestion, or an ask whose call fell
// outside the loaded window -- is a card of its own.
if (
event.about != null &&
items.any { it is TranscriptItem.ToolRun && it.id == event.about }
) {
updateTool(items, event.about) { it.copy(asks = it.asks + card) }
} else {
items + card
}
}
is SessionEvent.Answered ->
// Resolved wherever it is drawn: a card of its own, or a tool row's ask. Missing the
// second left an Allow/Deny pair live on a question already answered from another
// device.
items.map {
when {
it is TranscriptItem.QuestionCard && it.id == event.id ->
it.copy(answers = event.answers)
it is TranscriptItem.ToolRun && it.asks.any { ask -> ask.id == event.id } ->
it.copy(
asks =
it.asks.map { ask ->
if (ask.id == event.id) ask.copy(answers = event.answers)
else ask
}
)
else -> it
}
}
is SessionEvent.PeerMessage -> placePeerNote(items, entry.seq, event)
is SessionEvent.CommandSent -> items + TranscriptItem.CommandRow(entry.seq, event.text)
// Screen-level state, not transcript rows -- see SessionScreen.
is SessionEvent.CommandQueued -> items
// No row of its own: a message that is still waiting is drawn as a pending bubble below the
// transcript, and becomes an ordinary one where the session read it.
is SessionEvent.MessageQueued -> items
// The bubble goes away and nothing takes its place: the message was never read, so there is
// nothing it belongs above.
is SessionEvent.MessageDropped -> items
is SessionEvent.Settings -> items
is SessionEvent.Status -> settleReply(items, event.state)
is SessionEvent.Error -> items + TranscriptItem.ErrorMsg(entry.seq, event.message)
is SessionEvent.Image ->
// Under the call that produced it when there is one, and a row of its own when there is
// not -- a person's own attachment belongs to no call, and neither does one whose call
// fell outside the loaded window.
if (
event.about != null &&
items.any { it is TranscriptItem.ToolRun && it.id == event.about }
) {
updateTool(items, event.about) { it.copy(images = it.images + event.ref) }
} else {
items + TranscriptItem.ImageItem(entry.seq, event.ref)
}
is SessionEvent.LimitReached -> items + TranscriptItem.LimitNote(entry.seq, event.resetsAt)
is SessionEvent.Cleared -> items + TranscriptItem.ClearedNote(entry.seq)
is SessionEvent.Compacted ->
items + TranscriptItem.CompactedNote(entry.seq, event.preTokens, event.postTokens)
is SessionEvent.Unknown -> items + TranscriptItem.Note(entry.seq, "[${event.type}]")
// Said rather than skipped: a line the server could not read is a hole in the conversation,
// and one that draws nothing is a hole nothing on screen ever mentions.
is SessionEvent.Unreadable ->
items + TranscriptItem.Note(entry.seq, "[unreadable: ${event.kind}]")
// No row: see [SessionEvent.RetiredTaskNote].
is SessionEvent.RetiredTaskNote -> items
// Screen-level state, not transcript rows -- see SessionScreen.
is SessionEvent.UsageDelta -> items
}
/**
* A status saying the session stopped working is the moment its newest reply is finished.
*
* See [TranscriptItem.AssistantMsg.settled]. Status changes are transcript events with seqs of
* their own, so a replayed session settles its replies the same way a live one does.
*/
private fun settleReply(items: List<TranscriptItem>, state: String): List<TranscriptItem> {
if (sessionWorking(state)) return items
val last = items.lastOrNull() as? TranscriptItem.AssistantMsg ?: return items
if (last.settled) return items
return items.dropLast(1) + last.copy(settled = true)
}
private fun updateTool(
items: List<TranscriptItem>,
id: String,
change: (TranscriptItem.ToolRun) -> TranscriptItem.ToolRun,
): List<TranscriptItem> = items.map {
if (it is TranscriptItem.ToolRun && it.id == id) change(it) else it
}
/**
* Where markdown is parsed ahead of being drawn: two threads, never all of them.
*
* The default dispatcher sizes itself to the machine, which is right for work somebody is waiting
* on and wrong for work nobody is. A page of history is hundreds of parses arriving at once, and
* taking every core for them leaves the thread that draws the frame queueing behind one -- measured
* on a Pixel 9 Pro XL as 21ms of `waited` at the 90th percentile.
*/
@OptIn(kotlinx.coroutines.ExperimentalCoroutinesApi::class)
private val parsingThreads = Dispatchers.Default.limitedParallelism(2)
/**
* Parses the markdown among [rows], off whatever thread is drawing.
*
* Called where a page of transcript is folded rather than where a row is composed, which is the
* whole point: the work happens seconds before the reader reaches the rows it was done for.
*
* What is warmed mirrors what the rows draw -- each prose part of a reply, a memory note, a peer
* message -- because a string warmed under a key no row ever looks up is a miss that nothing
* reports; see [transcriptUnits], which is the flatten this has to agree with. It reads the same
* [ParsedReplies.partsOf] cache the flatten does, so a message is scanned once however many pages
* hand it back through here.
*
* Every kind of row that draws markdown belongs in the `when` below. That is the rule the peer
* message was missing: this used to filter for assistant replies alone, so the one row type nobody
* had thought about paid its whole parse in the frame it appeared in.
*/
suspend fun warm(replies: ParsedReplies, rows: List<TranscriptItem>) {
withContext(parsingThreads) {
val texts = rows.flatMap { row ->
when (row) {
is TranscriptItem.AssistantMsg -> replies.partsOf(row.text).map { it.text }
// A message from another agent is markdown too, and it is the longest thing in a
// transcript often enough that leaving it out was the whole of why one cost a fifth
// of a second to open.
is TranscriptItem.PeerNote -> listOf(row.text)
else -> emptyList()
}
}
if (texts.isNotEmpty()) replies.warm(texts)
// After the parses exist, not before: [ParsedReplies.splitReady] is the flatten's licence
// to draw these as blocks on the composing thread.
rows.forEach { if (it is TranscriptItem.AssistantMsg) replies.markSplitReady(it.text) }
}
}