ios: add chat fork actions

ios/Packages/Sybil/Sources/Sybil/SybilAPIClient.swift

@@ -74,6 +74,16 @@ actor SybilAPIClient: SybilAPIClienting {
         return response.chat
     }
 
+    func forkChat(chatID: String, messageID: String? = nil) async throws -> ChatSummary {
+        let response = try await request(
+            "/v1/chats/\(chatID)/fork",
+            method: "POST",
+            body: AnyEncodable(ChatForkBody(messageId: messageID)),
+            responseType: ChatCreateResponse.self
+        )
+        return response.chat
+    }
+
     func updateChatTitle(chatID: String, title: String) async throws -> ChatSummary {
         let response = try await request(
             "/v1/chats/\(chatID)",
@@ -704,6 +714,10 @@ private struct ChatTitleUpdateBody: Encodable {
     var title: String
 }
 
+private struct ChatForkBody: Encodable {
+    var messageId: String?
+}
+
 private struct StarUpdateBody: Encodable {
     var starred: Bool
 }

ios/Packages/Sybil/Sources/Sybil/SybilAPIClienting.swift

@@ -11,6 +11,7 @@ protocol SybilAPIClienting: Sendable {
         messages: [CompletionRequestMessage]?
     ) async throws -> ChatSummary
     func getChat(chatID: String) async throws -> ChatDetail
+    func forkChat(chatID: String, messageID: String?) async throws -> ChatSummary
     func updateChatTitle(chatID: String, title: String) async throws -> ChatSummary
     func updateChatStar(chatID: String, starred: Bool) async throws -> ChatSummary
     func deleteChat(chatID: String) async throws

ios/Packages/Sybil/Sources/Sybil/SybilChatTranscriptView.swift

@@ -1,13 +1,17 @@
 import MarkdownUI
 import SwiftUI
+import UIKit
 
 struct SybilChatTranscriptView: View {
     var messages: [Message]
     var isLoading: Bool
     var isSending: Bool
+    var streamingAssistantPresentation: StreamingAssistantPresentation?
     var topContentInset: CGFloat = 0
     var bottomContentInset: CGFloat = 0
     var bottomPinRequestID: Int = 0
+    var isForking: Bool = false
+    var onForkResponse: ((String) -> Void)? = nil
 
     @State private var hasTrackedToolCallMessages = false
     @State private var knownToolCallMessageIDs: Set<String> = []
@@ -41,7 +45,15 @@ struct SybilChatTranscriptView: View {
                     ForEach(renderItems) { item in
                         switch item {
                         case let .message(message):
-                            MessageBubble(message: message, isSending: isSending)
+                            MessageBubble(
+                                message: message,
+                                isSending: isSending,
+                                streamingAssistantPresentation: streamingAssistantPresentation,
+                                isForking: isForking,
+                                onFork: {
+                                    onForkResponse?(message.id)
+                                }
+                            )
                                 .frame(maxWidth: .infinity)
                         case let .toolGroup(id, messages):
                             ToolCallStackView(
@@ -140,6 +152,9 @@ func buildTranscriptRenderItems(from messages: [Message]) -> [TranscriptRenderIt
 private struct MessageBubble: View {
     var message: Message
     var isSending: Bool
+    var streamingAssistantPresentation: StreamingAssistantPresentation?
+    var isForking: Bool
+    var onFork: (() -> Void)?
 
     private var toolCallMetadata: ToolCallMetadata? {
         message.toolCallMetadata
@@ -149,13 +164,46 @@ private struct MessageBubble: View {
         message.role == .user
     }
 
-    private var isPendingAssistant: Bool {
-        message.id.hasPrefix("temp-assistant-") &&
-            isSending &&
-            message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+    private var isStreamingAssistant: Bool {
+        message.role == .assistant && message.id.hasPrefix("temp-assistant-")
+    }
+
+    private var matchingStreamingAssistantPresentation: StreamingAssistantPresentation? {
+        guard streamingAssistantPresentation?.messageID == message.id else { return nil }
+        return streamingAssistantPresentation
+    }
+
+    private var canFork: Bool {
+        message.role == .assistant &&
+            !message.id.hasPrefix("temp-") &&
+            onFork != nil
     }
 
     var body: some View {
+        Group {
+            if canFork {
+                bubbleContent
+                    .contextMenu {
+                        Button {
+                            UIPasteboard.general.string = message.content
+                        } label: {
+                            Label("Copy", systemImage: "doc.on.doc")
+                        }
+
+                        Button {
+                            onFork?()
+                        } label: {
+                            Label("Fork", systemImage: "arrow.triangle.branch")
+                        }
+                        .disabled(isForking)
+                    }
+            } else {
+                bubbleContent
+            }
+        }
+    }
+
+    private var bubbleContent: some View {
         HStack(alignment: .top, spacing: 0) {
             leadingSpacer
 
@@ -174,16 +222,12 @@ private struct MessageBubble: View {
                         )
                     }
 
-                    if isPendingAssistant {
-                        HStack(spacing: 8) {
-                            ProgressView()
-                                .controlSize(.small)
-                                .tint(SybilTheme.primary)
-                            Text("Thinking…")
-                                .font(.sybil(.footnote))
-                                .foregroundStyle(SybilTheme.textMuted)
-                        }
-                        .padding(.vertical, 2)
+                    if isStreamingAssistant {
+                        StreamingAssistantContentView(
+                            content: message.content,
+                            isSending: isSending,
+                            presentation: matchingStreamingAssistantPresentation
+                        )
                     } else if !message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty {
                         Markdown(message.content)
                             .tint(SybilTheme.primary)
@@ -232,6 +276,123 @@ private struct MessageBubble: View {
     }
 }
 
+private struct StreamingTraceHeightPreferenceKey: PreferenceKey {
+    static let defaultValue: CGFloat = 0
+
+    static func reduce(value: inout CGFloat, nextValue: () -> CGFloat) {
+        value = max(value, nextValue())
+    }
+}
+
+struct StreamingAssistantContentView: View {
+    private enum Phase: Hashable {
+        case pending
+        case trace(Int)
+        case answer
+    }
+
+    var content: String
+    var isSending: Bool
+    var presentation: StreamingAssistantPresentation?
+
+    @Environment(\.accessibilityReduceMotion) private var reduceMotion
+    @State private var retainedTraceHeight: CGFloat = 0
+
+    private var traceText: String? {
+        guard let trace = presentation?.ephemeralTrace?.trimmingCharacters(in: .whitespacesAndNewlines),
+              !trace.isEmpty
+        else {
+            return nil
+        }
+        return trace
+    }
+
+    private var hasAnswer: Bool {
+        !content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+    }
+
+    private var phase: Phase {
+        if hasAnswer {
+            return .answer
+        }
+        if traceText != nil {
+            return .trace(presentation?.traceRevision ?? 0)
+        }
+        return .pending
+    }
+
+    private var traceTransition: AnyTransition {
+        guard !reduceMotion else { return .identity }
+        return .asymmetric(
+            insertion: .opacity.combined(with: .offset(y: 5)),
+            removal: .opacity.combined(with: .offset(y: -5))
+        )
+    }
+
+    private var answerTransition: AnyTransition {
+        guard !reduceMotion else { return .identity }
+        return .opacity.combined(with: .offset(y: 3))
+    }
+
+    var body: some View {
+        ZStack(alignment: .topLeading) {
+            if let traceText {
+                Text(traceText)
+                    .font(.sybil(size: 15))
+                    .italic()
+                    .foregroundStyle(SybilTheme.textMuted.opacity(0.88))
+                    .lineSpacing(5)
+                    .fixedSize(horizontal: false, vertical: true)
+                    .opacity(0.78)
+                    .textSelection(.disabled)
+                    .allowsHitTesting(false)
+                    .accessibilityLabel("Assistant is working")
+                    .background {
+                        GeometryReader { geometry in
+                            Color.clear.preference(
+                                key: StreamingTraceHeightPreferenceKey.self,
+                                value: geometry.size.height
+                            )
+                        }
+                    }
+                    .id("thinking-trace-\(presentation?.traceRevision ?? 0)")
+                    .transition(traceTransition)
+                    .zIndex(1)
+            }
+
+            if hasAnswer {
+                Markdown(content)
+                    .tint(SybilTheme.primary)
+                    .foregroundStyle(SybilTheme.text.opacity(0.95))
+                    .markdownTheme(.sybilReadable)
+                    .textSelection(.enabled)
+                    .id("streaming-assistant-answer")
+                    .transition(answerTransition)
+                    .zIndex(2)
+            }
+
+            if isSending && !hasAnswer && traceText == nil {
+                HStack(spacing: 8) {
+                    ProgressView()
+                        .controlSize(.small)
+                        .tint(SybilTheme.primary)
+                    Text("Thinking…")
+                        .font(.sybil(.footnote))
+                        .foregroundStyle(SybilTheme.textMuted)
+                }
+                .padding(.vertical, 2)
+                .transition(reduceMotion ? .identity : .opacity)
+            }
+        }
+        .frame(maxWidth: .infinity, minHeight: max(24, retainedTraceHeight), alignment: .topLeading)
+        .onPreferenceChange(StreamingTraceHeightPreferenceKey.self) { measuredHeight in
+            guard measuredHeight.isFinite, measuredHeight > retainedTraceHeight else { return }
+            retainedTraceHeight = measuredHeight
+        }
+        .animation(reduceMotion ? nil : .easeOut(duration: 0.20), value: phase)
+    }
+}
+
 private struct ToolCallStackView: View {
     private struct CardLayout {
         var x: CGFloat

ios/Packages/Sybil/Sources/Sybil/SybilPhoneShellView.swift

@@ -130,7 +130,10 @@ struct SybilPhoneShellView: View {
             route: route,
             onRequestBack: { _ in showSidebarOverlay() },
             onRequestNewChat: sidebarWorkspaceNewChatAction,
-            onShowSidebar: showSidebarOverlay
+            onShowSidebar: showSidebarOverlay,
+            onOpenForkedChat: { chatID in
+                showRoute(.chat(chatID))
+            }
         )
         .background(SybilTheme.background)
         .blur(radius: SidebarOverlaySwipeMetrics.workspaceBlurRadius(for: sidebarOverlayProgress))
@@ -511,6 +514,9 @@ private struct SybilPhoneSidebarRoot: View {
                 },
                 onSelect: { item in
                     onSelect(item.selection)
+                },
+                onOpenForkedChat: { chatID in
+                    onSelect(.chat(chatID))
                 }
             )
         }
@@ -585,6 +591,7 @@ private struct SybilPhoneDestinationView: View {
     let onRequestBack: (_ animateNavigation: Bool) -> Void
     let onRequestNewChat: (() -> Void)?
     let onShowSidebar: () -> Void
+    let onOpenForkedChat: (String) -> Void
 
     var body: some View {
         SybilWorkspaceView(
@@ -593,7 +600,8 @@ private struct SybilPhoneDestinationView: View {
             navigationLeadingControl: .showSidebar,
             onShowSidebar: onShowSidebar,
             onRequestBack: onRequestBack,
-            onRequestNewChat: onRequestNewChat
+            onRequestNewChat: onRequestNewChat,
+            onOpenForkedChat: onOpenForkedChat
         )
         .frame(maxWidth: .infinity, maxHeight: .infinity, alignment: .topLeading)
         .task(id: route) {

ios/Packages/Sybil/Sources/Sybil/SybilQuickQuestionView.swift

@@ -62,7 +62,11 @@ struct SybilQuickQuestionView: View {
             VStack(alignment: .leading, spacing: 12) {
                 if hasAnswerContent {
                     ForEach(viewModel.quickQuestionMessages) { message in
-                        QuickQuestionMessageView(message: message, isSending: viewModel.isQuickQuestionSending)
+                        QuickQuestionMessageView(
+                            message: message,
+                            isSending: viewModel.isQuickQuestionSending,
+                            streamingAssistantPresentation: viewModel.quickQuestionStreamingAssistantPresentation
+                        )
                     }
 
                     if let error = viewModel.quickQuestionError {
@@ -98,13 +102,12 @@ struct SybilQuickQuestionView: View {
                         set: { viewModel.updateQuickQuestionPrompt($0) }
                     ),
                     selection: $promptSelection,
-                    axis: .vertical
+                    axis: .horizontal
                 )
                 .focused($promptFocused)
                 .font(.body)
                 .textInputAutocapitalization(.sentences)
                 .autocorrectionDisabled(false)
-                .lineLimit(1 ... 6)
                 .submitLabel(.send)
                 .onSubmit(submitQuestion)
                 .padding(.horizontal, 12)
@@ -263,11 +266,11 @@ private struct QuickQuestionPickerPill: View {
 private struct QuickQuestionMessageView: View {
     var message: Message
     var isSending: Bool
+    var streamingAssistantPresentation: StreamingAssistantPresentation?
 
-    private var isPendingAssistant: Bool {
-        message.id.hasPrefix("temp-assistant-quick-") &&
-            isSending &&
-            message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+    private var matchingStreamingAssistantPresentation: StreamingAssistantPresentation? {
+        guard streamingAssistantPresentation?.messageID == message.id else { return nil }
+        return streamingAssistantPresentation
     }
 
     var body: some View {
@@ -276,15 +279,12 @@ private struct QuickQuestionMessageView: View {
                 .font(.caption)
                 .foregroundStyle(SybilTheme.textMuted)
                 .fixedSize(horizontal: false, vertical: true)
-        } else if isPendingAssistant {
-            HStack(spacing: 8) {
-                ProgressView()
-                    .controlSize(.small)
-                    .tint(SybilTheme.primary)
-                Text("Thinking...")
-                    .font(.caption)
-                    .foregroundStyle(SybilTheme.textMuted)
-            }
+        } else if message.id.hasPrefix("temp-assistant-quick-") {
+            StreamingAssistantContentView(
+                content: message.content,
+                isSending: isSending,
+                presentation: matchingStreamingAssistantPresentation
+            )
         } else if !message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty {
             Markdown(message.content)
                 .font(.body)

ios/Packages/Sybil/Sources/Sybil/SybilSidebarView.swift

@@ -111,6 +111,7 @@ struct SybilSidebarItemList: View {
     @Bindable var viewModel: SybilViewModel
     var isSelected: (SidebarItem) -> Bool
     var onSelect: (SidebarItem) -> Void
+    var onOpenForkedChat: ((String) -> Void)? = nil
     @State private var renameTarget: SidebarItem?
     @State private var renameTitle = ""
 
@@ -169,6 +170,13 @@ struct SybilSidebarItemList: View {
                                 }
 
                                 if item.kind == .chat {
+                                    Button {
+                                        forkChat(item)
+                                    } label: {
+                                        Label("Fork", systemImage: "arrow.triangle.branch")
+                                    }
+                                    .disabled(viewModel.isForkingChat || item.isRunning)
+
                                     Button {
                                         renameTarget = item
                                         renameTitle = item.title
@@ -215,6 +223,28 @@ struct SybilSidebarItemList: View {
             .disabled(renameTitle.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty)
         }
     }
+
+    private func forkChat(_ item: SidebarItem) {
+        guard case let .chat(chatID) = item.selection else {
+            return
+        }
+
+        let selectionAtStart = viewModel.selectedItem
+        let draftKindAtStart = viewModel.draftKind
+        Task {
+            guard let forkedChat = await viewModel.forkChat(chatID: chatID),
+                  viewModel.selectedItem == selectionAtStart,
+                  viewModel.draftKind == draftKindAtStart else {
+                return
+            }
+
+            if let onOpenForkedChat {
+                onOpenForkedChat(forkedChat.id)
+            } else {
+                viewModel.select(.chat(forkedChat.id))
+            }
+        }
+    }
 }
 
 struct SybilSidebarRow: View {

ios/Packages/Sybil/Sources/Sybil/SybilViewModel.swift

@@ -40,9 +40,72 @@ struct SidebarItem: Identifiable, Hashable {
     var isRunning: Bool
 }
 
+enum StreamingAssistantContentUpdate: Equatable, Sendable {
+    case unchanged
+    case replace(String)
+}
+
+struct StreamingAssistantState: Equatable, Sendable {
+    private(set) var segmentText = ""
+    private(set) var initiatedToolCallIDs: Set<String> = []
+    private(set) var ephemeralTrace: String?
+    private(set) var traceRevision = 0
+
+    mutating func receiveDelta(_ text: String) -> StreamingAssistantContentUpdate {
+        guard !text.isEmpty else { return .unchanged }
+        segmentText += text
+        ephemeralTrace = nil
+        return .replace(segmentText)
+    }
+
+    mutating func receiveToolCall(id: String, status: String) -> StreamingAssistantContentUpdate {
+        guard status.lowercased() == "initiated", initiatedToolCallIDs.insert(id).inserted else {
+            return .unchanged
+        }
+
+        let trace = segmentText.trimmingCharacters(in: .whitespacesAndNewlines)
+        segmentText = ""
+        if !trace.isEmpty {
+            ephemeralTrace = trace
+            traceRevision += 1
+        }
+        return .replace("")
+    }
+
+    mutating func receiveDone(_ text: String) -> StreamingAssistantContentUpdate {
+        segmentText = ""
+        ephemeralTrace = nil
+        return .replace(text)
+    }
+
+    mutating func receiveError() -> StreamingAssistantContentUpdate {
+        segmentText = ""
+        ephemeralTrace = nil
+        return .unchanged
+    }
+}
+
+struct StreamingAssistantPresentation: Equatable, Sendable {
+    var messageID: String
+    var ephemeralTrace: String?
+    var traceRevision: Int
+}
+
 private struct PendingChatState {
     var chatID: String?
     var messages: [Message]
+    var streamingAssistantState = StreamingAssistantState()
+
+    var streamingAssistantPresentation: StreamingAssistantPresentation? {
+        guard let messageID = messages.last(where: { $0.id.hasPrefix("temp-assistant-") })?.id else {
+            return nil
+        }
+        return StreamingAssistantPresentation(
+            messageID: messageID,
+            ephemeralTrace: streamingAssistantState.ephemeralTrace,
+            traceRevision: streamingAssistantState.traceRevision
+        )
+    }
 }
 
 private enum ActiveSendContext: Hashable {
@@ -107,6 +170,7 @@ final class SybilViewModel {
     var isLoadingCollections = false
     var isLoadingSelection = false
     var isCreatingSearchChat = false
+    var isForkingChat = false
     var chatBottomPinRequestID = 0
     var errorMessage: String?
 
@@ -125,6 +189,7 @@ final class SybilViewModel {
     var quickQuestionSubmittedModel: String?
     var isQuickQuestionSending = false
     var isConvertingQuickQuestion = false
+    private var quickQuestionStreamingAssistantState = StreamingAssistantState()
 
     @ObservationIgnored
     private var hasBootstrapped = false
@@ -360,6 +425,30 @@ final class SybilViewModel {
         return canonical
     }
 
+    var displayedStreamingAssistantPresentation: StreamingAssistantPresentation? {
+        if case let .chat(chatID) = selectedItem,
+           let pending = pendingChatStates[chatID] {
+            return pending.streamingAssistantPresentation
+        }
+
+        if draftKind == .chat, let pending = pendingDraftChatState {
+            return pending.streamingAssistantPresentation
+        }
+
+        return nil
+    }
+
+    var quickQuestionStreamingAssistantPresentation: StreamingAssistantPresentation? {
+        guard let messageID = quickQuestionMessages.last(where: { $0.id.hasPrefix("temp-assistant-quick-") })?.id else {
+            return nil
+        }
+        return StreamingAssistantPresentation(
+            messageID: messageID,
+            ephemeralTrace: quickQuestionStreamingAssistantState.ephemeralTrace,
+            traceRevision: quickQuestionStreamingAssistantState.traceRevision
+        )
+    }
+
     var displayedSearch: SearchDetail? {
         if case let .search(searchID) = selectedItem,
            let activeSearch = activeSearchDetails[searchID] {
@@ -620,6 +709,7 @@ final class SybilViewModel {
         quickQuestionTask = nil
         quickQuestionRunID = nil
         isQuickQuestionSending = false
+        quickQuestionStreamingAssistantState = StreamingAssistantState()
     }
 
     @discardableResult
@@ -869,6 +959,36 @@ final class SybilViewModel {
         }
     }
 
+    @discardableResult
+    func forkChat(chatID: String, messageID: String? = nil) async -> ChatSummary? {
+        guard isAuthenticated, !isForkingChat else {
+            return nil
+        }
+
+        guard messageID != nil || !isChatRowRunning(chatID) else {
+            errorMessage = "Wait for the response to finish before forking this chat."
+            return nil
+        }
+
+        let forkDescription = messageID.map { "chat \(chatID) from response \($0)" } ?? "chat \(chatID)"
+        SybilLog.info(SybilLog.ui, "Forking \(forkDescription)")
+        errorMessage = nil
+        isForkingChat = true
+        defer {
+            isForkingChat = false
+        }
+
+        do {
+            let forkedChat = try await client().forkChat(chatID: chatID, messageID: messageID)
+            applyChatSummary(forkedChat, moveToFront: true)
+            return forkedChat
+        } catch {
+            errorMessage = normalizeAPIError(error)
+            SybilLog.error(SybilLog.ui, "Fork failed", error: error)
+            return nil
+        }
+    }
+
     func renameChat(chatID: String, title: String) async {
         guard isAuthenticated else {
             return
@@ -1140,6 +1260,7 @@ final class SybilViewModel {
         quickQuestionSubmittedPrompt = prompt
         quickQuestionSubmittedProvider = provider
         quickQuestionSubmittedModel = model
+        quickQuestionStreamingAssistantState = StreamingAssistantState()
         quickQuestionMessages = [
             Message(
                 id: "temp-assistant-quick-\(UUID().uuidString)",
@@ -1184,6 +1305,8 @@ final class SybilViewModel {
                 return
             }
 
+            let update = quickQuestionStreamingAssistantState.receiveError()
+            applyQuickQuestionAssistantContentUpdate(update)
             quickQuestionError = normalizeAPIError(error)
             SybilLog.error(SybilLog.ui, "Quick question failed", error: error)
         }
@@ -1198,17 +1321,16 @@ final class SybilViewModel {
             upsertQuickQuestionToolCallMessage(payload)
 
         case let .delta(payload):
-            guard !payload.text.isEmpty else { return }
-            mutateQuickQuestionAssistantMessage { existing in
-                existing + payload.text
-            }
+            let update = quickQuestionStreamingAssistantState.receiveDelta(payload.text)
+            applyQuickQuestionAssistantContentUpdate(update)
 
         case let .done(payload):
-            mutateQuickQuestionAssistantMessage { _ in
-                payload.text
-            }
+            let update = quickQuestionStreamingAssistantState.receiveDone(payload.text)
+            applyQuickQuestionAssistantContentUpdate(update)
 
         case let .error(payload):
+            let update = quickQuestionStreamingAssistantState.receiveError()
+            applyQuickQuestionAssistantContentUpdate(update)
             await streamStatus.setError(payload.message)
 
         case .ignored:
@@ -1607,21 +1729,28 @@ final class SybilViewModel {
             }
 
             serverActiveChatIDs.remove(chatID)
-            pendingChatStates[chatID] = nil
             await refreshCollections(preferredSelection: selectedItem, refreshSelection: false, attachVisibleActiveRun: false)
 
             if selectedItem == selection, draftKind == nil {
-                selectedChat = try await client.getChat(chatID: chatID)
-                selectedSearch = nil
+                let refreshedChat = try await client.getChat(chatID: chatID)
+                if selectedItem == selection, draftKind == nil {
+                    selectedChat = refreshedChat
+                    selectedSearch = nil
+                }
             }
+            pendingChatStates[chatID] = nil
         } catch {
             serverActiveChatIDs.remove(chatID)
-            pendingChatStates[chatID] = nil
+            defer {
+                pendingChatStates[chatID] = nil
+            }
 
             if isCancellation(error) {
                 return
             }
 
+            applyPendingAssistantError(chatID: chatID)
+
             if isActiveStreamNotFound(error) {
                 SybilLog.info(SybilLog.app, "Active chat stream \(chatID) no longer exists")
             } else if shouldSuppressInactiveTransportError(error) {
@@ -1635,8 +1764,11 @@ final class SybilViewModel {
 
             if selectedItem == selection, draftKind == nil {
                 do {
-                    selectedChat = try await client().getChat(chatID: chatID)
-                    selectedSearch = nil
+                    let refreshedChat = try await client().getChat(chatID: chatID)
+                    if selectedItem == selection, draftKind == nil {
+                        selectedChat = refreshedChat
+                        selectedSearch = nil
+                    }
                 } catch {
                     SybilLog.warning(SybilLog.app, "Chat refresh after attach failure failed: \(SybilLog.describe(error))")
                 }
@@ -1856,6 +1988,13 @@ final class SybilViewModel {
         } else {
             pendingDraftChatState = PendingChatState(chatID: nil, messages: optimisticMessages)
         }
+        defer {
+            if let resolvedChatID = chatID {
+                pendingChatStates[resolvedChatID] = nil
+            } else {
+                clearPendingChatState(for: sendContext)
+            }
+        }
         requestChatBottomPin()
 
         if chatID == nil {
@@ -2045,17 +2184,13 @@ final class SybilViewModel {
             upsertPendingToolCallMessage(payload, chatID: chatID)
 
         case let .delta(payload):
-            guard !payload.text.isEmpty else { return }
-            mutatePendingAssistantMessage(chatID: chatID) { existing in
-                existing + payload.text
-            }
+            applyPendingAssistantDelta(payload.text, chatID: chatID)
 
         case let .done(payload):
-            mutatePendingAssistantMessage(chatID: chatID) { _ in
-                payload.text
-            }
+            finalizePendingAssistant(payload.text, chatID: chatID)
 
         case let .error(payload):
+            applyPendingAssistantError(chatID: chatID)
             await streamStatus.setError(payload.message)
 
         case .ignored:
@@ -2233,29 +2368,68 @@ final class SybilViewModel {
         }
     }
 
-    private func mutatePendingAssistantMessage(chatID: String, _ transform: (String) -> String) {
+    private func applyPendingAssistantDelta(_ text: String, chatID: String) {
         guard var pending = pendingChatStates[chatID], !pending.messages.isEmpty else {
             return
         }
 
-        let index = pending.messages.indices.last { pending.messages[$0].id.hasPrefix("temp-assistant-") }
-        guard let index else {
-            return
-        }
-
-        var message = pending.messages[index]
-        message.content = transform(message.content)
-        pending.messages[index] = message
+        let update = pending.streamingAssistantState.receiveDelta(text)
+        applyStreamingAssistantContentUpdate(
+            update,
+            to: &pending.messages,
+            assistantMessagePrefix: "temp-assistant-"
+        )
         pendingChatStates[chatID] = pending
     }
 
-    private func mutateQuickQuestionAssistantMessage(_ transform: (String) -> String) {
-        let index = quickQuestionMessages.indices.last { quickQuestionMessages[$0].id.hasPrefix("temp-assistant-quick-") }
-        guard let index else {
+    private func finalizePendingAssistant(_ text: String, chatID: String) {
+        guard var pending = pendingChatStates[chatID], !pending.messages.isEmpty else {
             return
         }
 
-        quickQuestionMessages[index].content = transform(quickQuestionMessages[index].content)
+        let update = pending.streamingAssistantState.receiveDone(text)
+        applyStreamingAssistantContentUpdate(
+            update,
+            to: &pending.messages,
+            assistantMessagePrefix: "temp-assistant-"
+        )
+        pendingChatStates[chatID] = pending
+    }
+
+    private func applyPendingAssistantError(chatID: String) {
+        guard var pending = pendingChatStates[chatID] else {
+            return
+        }
+
+        let update = pending.streamingAssistantState.receiveError()
+        applyStreamingAssistantContentUpdate(
+            update,
+            to: &pending.messages,
+            assistantMessagePrefix: "temp-assistant-"
+        )
+        pendingChatStates[chatID] = pending
+    }
+
+    private func applyQuickQuestionAssistantContentUpdate(_ update: StreamingAssistantContentUpdate) {
+        applyStreamingAssistantContentUpdate(
+            update,
+            to: &quickQuestionMessages,
+            assistantMessagePrefix: "temp-assistant-quick-"
+        )
+    }
+
+    private func applyStreamingAssistantContentUpdate(
+        _ update: StreamingAssistantContentUpdate,
+        to messages: inout [Message],
+        assistantMessagePrefix: String
+    ) {
+        guard case let .replace(content) = update,
+              let index = messages.indices.last(where: { messages[$0].id.hasPrefix(assistantMessagePrefix) })
+        else {
+            return
+        }
+
+        messages[index].content = content
     }
 
     private func upsertPendingToolCallMessage(_ payload: CompletionStreamToolCall, chatID: String) {
@@ -2263,6 +2437,16 @@ final class SybilViewModel {
             return
         }
 
+        let update = pending.streamingAssistantState.receiveToolCall(
+            id: payload.toolCallId,
+            status: payload.status
+        )
+        applyStreamingAssistantContentUpdate(
+            update,
+            to: &pending.messages,
+            assistantMessagePrefix: "temp-assistant-"
+        )
+
         if let existingIndex = pending.messages.firstIndex(where: { $0.toolCallMetadata?.toolCallId == payload.toolCallId || $0.id == "temp-tool-\(payload.toolCallId)" }) {
             pending.messages[existingIndex] = toolCallMessage(for: payload, id: pending.messages[existingIndex].id)
             pendingChatStates[chatID] = pending
@@ -2281,6 +2465,12 @@ final class SybilViewModel {
     }
 
     private func upsertQuickQuestionToolCallMessage(_ payload: CompletionStreamToolCall) {
+        let update = quickQuestionStreamingAssistantState.receiveToolCall(
+            id: payload.toolCallId,
+            status: payload.status
+        )
+        applyQuickQuestionAssistantContentUpdate(update)
+
         if let existingIndex = quickQuestionMessages.firstIndex(where: { $0.toolCallMetadata?.toolCallId == payload.toolCallId || $0.id == "temp-tool-\(payload.toolCallId)" }) {
             quickQuestionMessages[existingIndex] = toolCallMessage(for: payload, id: quickQuestionMessages[existingIndex].id)
             return
@@ -2430,7 +2620,8 @@ final class SybilViewModel {
 
     private func clearPendingChatState(for context: ActiveSendContext) {
         switch context {
-        case .draftChat:
+        case let .draftChat(identity):
+            guard draftKind == .chat, draftIdentity == identity else { return }
             pendingDraftChatState = nil
         case let .chat(chatID):
             pendingChatStates[chatID] = nil

ios/Packages/Sybil/Sources/Sybil/SybilWorkspaceView.swift

@@ -19,6 +19,7 @@ struct SybilWorkspaceView: View {
     var onShowSidebar: (() -> Void)? = nil
     var onRequestBack: ((_ animateNavigation: Bool) -> Void)? = nil
     var onRequestNewChat: (() -> Void)? = nil
+    var onOpenForkedChat: ((String) -> Void)? = nil
     @FocusState private var composerFocused: Bool
     @Environment(\.dismiss) private var dismiss
     @State private var isShowingAttachmentOptions = false
@@ -193,9 +194,12 @@ struct SybilWorkspaceView: View {
                         messages: viewModel.displayedMessages,
                         isLoading: viewModel.isLoadingSelection,
                         isSending: viewModel.isSendingVisibleChat,
+                        streamingAssistantPresentation: viewModel.displayedStreamingAssistantPresentation,
                         topContentInset: showsCustomWorkspaceNavigation ? customWorkspaceNavigationContentInset : 0,
                         bottomContentInset: viewModel.showsComposer ? composerOverlayContentInset : 0,
-                        bottomPinRequestID: viewModel.chatBottomPinRequestID
+                        bottomPinRequestID: viewModel.chatBottomPinRequestID,
+                        isForking: viewModel.isForkingChat,
+                        onForkResponse: forkResponse
                     )
                     .id(transcriptScrollContextID)
                 }
@@ -229,6 +233,28 @@ struct SybilWorkspaceView: View {
         }
     }
 
+    private func forkResponse(messageID: String) {
+        guard viewModel.draftKind == nil,
+              case let .chat(chatID) = viewModel.selectedItem else {
+            return
+        }
+
+        let selectionAtStart = viewModel.selectedItem
+        Task {
+            guard let forkedChat = await viewModel.forkChat(chatID: chatID, messageID: messageID),
+                  viewModel.selectedItem == selectionAtStart,
+                  viewModel.draftKind == nil else {
+                return
+            }
+
+            if let onOpenForkedChat {
+                onOpenForkedChat(forkedChat.id)
+            } else {
+                viewModel.select(.chat(forkedChat.id))
+            }
+        }
+    }
+
     private var customWorkspaceNavigationBar: some View {
         HStack(spacing: 14) {
             workspaceNavigationLeadingControl

ios/Packages/Sybil/Tests/SybilTests/SybilTests.swift

@@ -13,6 +13,9 @@ private struct MockClientCallSnapshot: Sendable {
     var listSearches = 0
     var createChat = 0
     var getChat = 0
+    var forkChat = 0
+    var lastForkChatID: String?
+    var lastForkMessageID: String?
     var updateChatTitle = 0
     var suggestChatTitle = 0
     var updateChatStar = 0
@@ -43,6 +46,7 @@ private actor MockSybilClient: SybilAPIClienting {
     private let chatDetails: [String: ChatDetail]
     private let searchDetails: [String: SearchDetail]
     private let createChatResponse: ChatSummary?
+    private let forkChatResponse: ChatSummary?
     private let updateChatTitleResponses: [String: ChatSummary]
     private let suggestChatTitleResponses: [String: ChatSummary]
     private let updateChatStarResponses: [String: ChatSummary]
@@ -53,6 +57,7 @@ private actor MockSybilClient: SybilAPIClienting {
     private var lastCreateChatCall: ChatCreateCallSnapshot?
     private var lastQuickQuestionStreamBody: QuickQuestionStreamRequest?
     private var completionStreamEvents: [CompletionStreamEvent]?
+    private var completionStreamPostEventNetworkErrorMessage: String?
     private var listChatsDelayNanoseconds: UInt64 = 0
     private var listSearchesDelayNanoseconds: UInt64 = 0
     private var getChatDelayNanoseconds: UInt64 = 0
@@ -61,6 +66,7 @@ private actor MockSybilClient: SybilAPIClienting {
     private var completionStreamDelayNanoseconds: UInt64 = 0
     private var completionAttachEvents: [String: [CompletionStreamEvent]] = [:]
     private var completionAttachDelayNanoseconds: UInt64 = 0
+    private var chatDetailResponseSequences: [String: [ChatDetail]] = [:]
     private var searchStreamNetworkErrorMessage: String?
     private var searchStreamDelayNanoseconds: UInt64 = 0
     private var searchAttachEvents: [String: [SearchStreamEvent]] = [:]
@@ -72,6 +78,7 @@ private actor MockSybilClient: SybilAPIClienting {
         chatDetails: [String: ChatDetail] = [:],
         searchDetails: [String: SearchDetail] = [:],
         createChatResponse: ChatSummary? = nil,
+        forkChatResponse: ChatSummary? = nil,
         updateChatTitleResponses: [String: ChatSummary] = [:],
         suggestChatTitleResponses: [String: ChatSummary] = [:],
         updateChatStarResponses: [String: ChatSummary] = [:],
@@ -85,6 +92,7 @@ private actor MockSybilClient: SybilAPIClienting {
         self.chatDetails = chatDetails
         self.searchDetails = searchDetails
         self.createChatResponse = createChatResponse
+        self.forkChatResponse = forkChatResponse
         self.updateChatTitleResponses = updateChatTitleResponses
         self.suggestChatTitleResponses = suggestChatTitleResponses
         self.updateChatStarResponses = updateChatStarResponses
@@ -113,6 +121,10 @@ private actor MockSybilClient: SybilAPIClienting {
         completionStreamDelayNanoseconds = delayNanoseconds
     }
 
+    func setCompletionStreamPostEventNetworkError(_ message: String) {
+        completionStreamPostEventNetworkErrorMessage = message
+    }
+
     func setCompletionStreamNetworkError(_ message: String, delayNanoseconds: UInt64 = 0) {
         completionStreamNetworkErrorMessage = message
         completionStreamDelayNanoseconds = delayNanoseconds
@@ -127,6 +139,10 @@ private actor MockSybilClient: SybilAPIClienting {
         getChatDelayNanoseconds = delayNanoseconds
     }
 
+    func setChatDetailResponses(chatID: String, responses: [ChatDetail]) {
+        chatDetailResponseSequences[chatID] = responses
+    }
+
     func setGetSearchDelay(_ delayNanoseconds: UInt64) {
         getSearchDelayNanoseconds = delayNanoseconds
     }
@@ -199,12 +215,27 @@ private actor MockSybilClient: SybilAPIClienting {
         if getChatDelayNanoseconds > 0 {
             try await Task.sleep(nanoseconds: getChatDelayNanoseconds)
         }
+        if var responses = chatDetailResponseSequences[chatID], !responses.isEmpty {
+            let response = responses.removeFirst()
+            chatDetailResponseSequences[chatID] = responses
+            return response
+        }
         guard let detail = chatDetails[chatID] else {
             throw UnexpectedClientCall()
         }
         return detail
     }
 
+    func forkChat(chatID: String, messageID: String?) async throws -> ChatSummary {
+        snapshot.forkChat += 1
+        snapshot.lastForkChatID = chatID
+        snapshot.lastForkMessageID = messageID
+        guard let forkChatResponse else {
+            throw UnexpectedClientCall()
+        }
+        return forkChatResponse
+    }
+
     func updateChatTitle(chatID: String, title: String) async throws -> ChatSummary {
         snapshot.updateChatTitle += 1
         guard let summary = updateChatTitleResponses[chatID] else {
@@ -319,6 +350,9 @@ private actor MockSybilClient: SybilAPIClienting {
             for event in completionStreamEvents {
                 await onEvent(event)
             }
+            if let completionStreamPostEventNetworkErrorMessage {
+                throw APIError.networkError(message: completionStreamPostEventNetworkErrorMessage)
+            }
             return
         }
         throw UnexpectedClientCall()
@@ -457,6 +491,25 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     )
 }
 
+private func makeCompletionToolCall(
+    id: String,
+    status: String,
+    summary: String = "Searched the web"
+) -> CompletionStreamToolCall {
+    CompletionStreamToolCall(
+        toolCallId: id,
+        name: "web_search",
+        status: status,
+        summary: summary,
+        args: ["query": .string("Sybil streaming traces")],
+        startedAt: "2026-08-30T12:00:00.000Z",
+        completedAt: status == "initiated" ? nil : "2026-08-30T12:00:00.120Z",
+        durationMs: status == "initiated" ? nil : 120,
+        error: nil,
+        resultPreview: status == "initiated" ? nil : "{\"ok\":true}"
+    )
+}
+
 @Test func chatForkMetadataDecodesBackwardCompatiblyAndSurvivesWorkspaceConversions() throws {
     let decoder = JSONDecoder()
     let legacySummary = try decoder.decode(
@@ -543,6 +596,63 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     #expect(toolMessage.id == "tool-a")
 }
 
+@Test func streamingAssistantStatePromotesAndReplacesEphemeralTraces() {
+    var state = StreamingAssistantState()
+
+    #expect(state.receiveDelta("  I'll search ") == .replace("  I'll search "))
+    #expect(state.receiveDelta("for that.  ") == .replace("  I'll search for that.  "))
+    #expect(state.receiveToolCall(id: "call-1", status: "INITIATED") == .replace(""))
+    #expect(state.segmentText == "")
+    #expect(state.ephemeralTrace == "I'll search for that.")
+    #expect(state.traceRevision == 1)
+
+    #expect(state.receiveToolCall(id: "call-1", status: "completed") == .unchanged)
+    #expect(state.receiveToolCall(id: "call-1", status: "initiated") == .unchanged)
+    #expect(state.ephemeralTrace == "I'll search for that.")
+    #expect(state.traceRevision == 1)
+
+    #expect(state.receiveToolCall(id: "parallel-call", status: "initiated") == .replace(""))
+    #expect(state.ephemeralTrace == "I'll search for that.")
+    #expect(state.traceRevision == 1)
+
+    #expect(state.receiveDelta("I need one more source.") == .replace("I need one more source."))
+    #expect(state.ephemeralTrace == nil)
+    #expect(state.receiveToolCall(id: "call-2", status: "initiated") == .replace(""))
+    #expect(state.ephemeralTrace == "I need one more source.")
+    #expect(state.traceRevision == 2)
+
+    #expect(state.receiveDelta("Final answer") == .replace("Final answer"))
+    #expect(state.ephemeralTrace == nil)
+    #expect(state.receiveDone("Canonical final answer.") == .replace("Canonical final answer."))
+    #expect(state.segmentText == "")
+    #expect(state.ephemeralTrace == nil)
+}
+
+@Test func streamingAssistantErrorClearsTraceWithoutReplacingPartialContent() {
+    var traceState = StreamingAssistantState()
+    #expect(traceState.receiveDelta("I'll inspect that.") == .replace("I'll inspect that."))
+    #expect(traceState.receiveToolCall(id: "inspect", status: "initiated") == .replace(""))
+    #expect(traceState.ephemeralTrace == "I'll inspect that.")
+    #expect(traceState.receiveError() == .unchanged)
+    #expect(traceState.segmentText.isEmpty)
+    #expect(traceState.ephemeralTrace == nil)
+
+    var partialState = StreamingAssistantState()
+    var renderedContent = ""
+    if case let .replace(content) = partialState.receiveDelta("Partial answer") {
+        renderedContent = content
+    }
+    let errorUpdate = partialState.receiveError()
+    if case let .replace(content) = errorUpdate {
+        renderedContent = content
+    }
+
+    #expect(errorUpdate == .unchanged)
+    #expect(renderedContent == "Partial answer")
+    #expect(partialState.segmentText.isEmpty)
+    #expect(partialState.ephemeralTrace == nil)
+}
+
 @MainActor
 @Test func normalizedAPIBaseURLPreservesExplicitAPIPath() async throws {
     let defaults = UserDefaults(suiteName: #function)!
@@ -681,6 +791,63 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     #expect(viewModel.errorMessage == nil)
 }
 
+@MainActor
+@Test func wholeChatForkAddsReturnedChatToWorkspace() async throws {
+    let date = Date(timeIntervalSince1970: 1_700_000_160)
+    let source = makeChatSummary(id: "chat-source", date: date)
+    var forked = makeChatSummary(id: "chat-fork", date: date.addingTimeInterval(10))
+    forked.title = "Fork of Chat chat-source"
+    forked.parentChatId = source.id
+    forked.titleGenerationPending = true
+    let client = MockSybilClient(forkChatResponse: forked)
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+    viewModel.isAuthenticated = true
+    viewModel.isCheckingSession = false
+    viewModel.chats = [source]
+    viewModel.workspaceItems = [WorkspaceItem(chat: source)]
+    viewModel.selectedItem = .chat(source.id)
+
+    let result = await viewModel.forkChat(chatID: source.id)
+
+    let snapshot = await client.currentSnapshot()
+    #expect(snapshot.forkChat == 1)
+    #expect(snapshot.lastForkChatID == source.id)
+    #expect(snapshot.lastForkMessageID == nil)
+    #expect(result == forked)
+    #expect(viewModel.chats.first == forked)
+    #expect(viewModel.workspaceItems.first == WorkspaceItem(chat: forked))
+    #expect(viewModel.selectedItem == .chat(source.id))
+    #expect(!viewModel.isForkingChat)
+    #expect(viewModel.errorMessage == nil)
+}
+
+@MainActor
+@Test func responseForkPassesAssistantMessageID() async throws {
+    let date = Date(timeIntervalSince1970: 1_700_000_165)
+    let source = makeChatSummary(id: "chat-source", date: date)
+    var forked = makeChatSummary(id: "response-fork", date: date.addingTimeInterval(10))
+    forked.title = "Fork of 'A useful response'"
+    forked.parentChatId = source.id
+    forked.titleGenerationPending = true
+    let client = MockSybilClient(forkChatResponse: forked)
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+    viewModel.isAuthenticated = true
+    viewModel.isCheckingSession = false
+    viewModel.chats = [source]
+    viewModel.workspaceItems = [WorkspaceItem(chat: source)]
+
+    let result = await viewModel.forkChat(chatID: source.id, messageID: "assistant-message")
+
+    let snapshot = await client.currentSnapshot()
+    #expect(snapshot.forkChat == 1)
+    #expect(snapshot.lastForkChatID == source.id)
+    #expect(snapshot.lastForkMessageID == "assistant-message")
+    #expect(result == forked)
+    #expect(viewModel.sidebarItems.contains(where: { $0.selection == .chat(forked.id) }))
+    #expect(!viewModel.isForkingChat)
+    #expect(viewModel.errorMessage == nil)
+}
+
 @MainActor
 @Test func starringItemsUpdatesSidebarState() async throws {
     let date = Date(timeIntervalSince1970: 1_700_000_175)
@@ -848,6 +1015,29 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     #expect(!viewModel.isLoadingSelection)
 }
 
+@MainActor
+@Test func failedFirstSendClearsPendingStateMigratedToCreatedChat() async throws {
+    let date = Date(timeIntervalSince1970: 1_700_000_235)
+    let createdChat = makeChatSummary(id: "chat-created-before-failure", date: date)
+    let client = MockSybilClient(createChatResponse: createdChat)
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+    viewModel.isAuthenticated = true
+    viewModel.isCheckingSession = false
+    viewModel.startNewChat()
+    viewModel.model = ""
+    viewModel.composer = "This send should fail after chat creation"
+
+    await viewModel.sendComposer()
+
+    let snapshot = await client.currentSnapshot()
+    #expect(snapshot.createChat == 1)
+    #expect(snapshot.runCompletionStream == 0)
+    #expect(viewModel.selectedItem == .chat(createdChat.id))
+    #expect(viewModel.selectedChat?.id == createdChat.id)
+    #expect(viewModel.displayedMessages.isEmpty)
+    #expect(viewModel.displayedStreamingAssistantPresentation == nil)
+}
+
 @MainActor
 @Test func newDraftChatDoesNotShowTypingStateFromPreviousSend() async throws {
     let date = Date(timeIntervalSince1970: 1_700_000_240)
@@ -1072,6 +1262,60 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     #expect(!viewModel.isQuickQuestionSending)
 }
 
+@MainActor
+@Test func quickQuestionKeepsToolNarrationEphemeralAndFinalizesCanonicalAnswer() async throws {
+    let client = MockSybilClient()
+    await client.setCompletionStreamEvents([
+        .delta(CompletionStreamDelta(text: "I'll search for that.")),
+        .toolCall(makeCompletionToolCall(id: "quick-search", status: "initiated")),
+        .toolCall(makeCompletionToolCall(id: "quick-search", status: "completed")),
+        .delta(CompletionStreamDelta(text: "The streamed answer")),
+        .done(CompletionStreamDone(text: "The canonical answer."))
+    ])
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+    viewModel.isAuthenticated = true
+    viewModel.isCheckingSession = false
+    viewModel.quickQuestionPrompt = "What changed?"
+
+    let task = viewModel.sendQuickQuestion()
+    await task?.value
+
+    let toolMessages = viewModel.quickQuestionMessages.filter { $0.toolCallMetadata != nil }
+    let assistantMessage = try #require(viewModel.quickQuestionMessages.last(where: { $0.role == .assistant }))
+    #expect(toolMessages.count == 1)
+    #expect(toolMessages.first?.toolCallMetadata?.status == "completed")
+    #expect(assistantMessage.content == "The canonical answer.")
+    #expect(!assistantMessage.content.contains("I'll search"))
+    #expect(viewModel.quickQuestionAnswerText == "The canonical answer.")
+    #expect(viewModel.quickQuestionStreamingAssistantPresentation?.ephemeralTrace == nil)
+    #expect(!viewModel.isQuickQuestionSending)
+}
+
+@MainActor
+@Test func quickQuestionTransportErrorClearsTraceAndPreservesPartialAnswer() async throws {
+    let client = MockSybilClient()
+    await client.setCompletionStreamEvents([
+        .delta(CompletionStreamDelta(text: "I'll inspect that.")),
+        .toolCall(makeCompletionToolCall(id: "quick-inspect", status: "initiated")),
+        .delta(CompletionStreamDelta(text: "Partial answer"))
+    ])
+    await client.setCompletionStreamPostEventNetworkError("connection lost")
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+    viewModel.isAuthenticated = true
+    viewModel.isCheckingSession = false
+    viewModel.quickQuestionPrompt = "What changed?"
+
+    let task = viewModel.sendQuickQuestion()
+    await task?.value
+
+    let assistantMessage = try #require(viewModel.quickQuestionMessages.last(where: { $0.role == .assistant }))
+    #expect(assistantMessage.content == "Partial answer")
+    #expect(viewModel.quickQuestionAnswerText == "Partial answer")
+    #expect(viewModel.quickQuestionStreamingAssistantPresentation?.ephemeralTrace == nil)
+    #expect(viewModel.quickQuestionError != nil)
+    #expect(!viewModel.isQuickQuestionSending)
+}
+
 @MainActor
 @Test func quickQuestionConvertCreatesSeededChat() async throws {
     let date = Date(timeIntervalSince1970: 1_700_000_250)
@@ -1184,6 +1428,44 @@ private func makeToolCallMessage(id: String, date: Date, summary: String = "Ran
     #expect(viewModel.displayedMessages.last?.content == "streaming")
 }
 
+@MainActor
+@Test func completedAttachKeepsFinalContentVisibleUntilCanonicalChatLoads() async throws {
+    let date = Date(timeIntervalSince1970: 1_700_000_265)
+    let chat = makeChatSummary(id: "chat-active-complete", date: date)
+    let baseDetail = makeChatDetail(id: chat.id, date: date, body: "base transcript")
+    let canonicalDetail = makeChatDetail(id: chat.id, date: date, body: "canonical attached response")
+    let client = MockSybilClient(
+        chatsResponse: [chat],
+        chatDetails: [chat.id: canonicalDetail],
+        activeRunsResponse: ActiveRunsResponse(chats: [chat.id])
+    )
+    await client.setChatDetailResponses(chatID: chat.id, responses: [baseDetail, canonicalDetail])
+    await client.setGetChatDelay(80_000_000)
+    await client.setCompletionAttachEvents(
+        chatID: chat.id,
+        events: [.done(CompletionStreamDone(text: "attached response"))]
+    )
+    let viewModel = SybilViewModel(settings: testSettings(named: #function)) { _ in client }
+
+    await viewModel.reconnect()
+
+    var snapshot = await client.currentSnapshot()
+    for _ in 0..<80 {
+        guard snapshot.getChat < 2 else { break }
+        try await Task.sleep(nanoseconds: 5_000_000)
+        snapshot = await client.currentSnapshot()
+    }
+
+    #expect(snapshot.getChat >= 2)
+    #expect(viewModel.displayedMessages.last?.content == "attached response")
+
+    for _ in 0..<80 {
+        guard viewModel.displayedMessages.last?.content != "canonical attached response" else { break }
+        try await Task.sleep(nanoseconds: 5_000_000)
+    }
+    #expect(viewModel.displayedMessages.last?.content == "canonical attached response")
+}
+
 @MainActor
 @Test func activeRunOnDifferentChatDoesNotDisableComposer() async throws {
     let date = Date(timeIntervalSince1970: 1_700_000_270)

ios/README.md

@@ -17,7 +17,9 @@ Hiding the panel preserves the draft and answer and lets an in-flight answer fin
 **Open in Chat** saves the question and answer in the regular workspace.
 
 The regular Mac chat/search composer uses the same Return/Shift+Return rules.
-Holding Return does not repeatedly submit. The iOS software keyboard is unchanged.
+Holding Return does not repeatedly submit. On iOS, Return submits from Quick
+Question, while the normal chat/search composer continues to use Return for a
+new line.
 
 Closing the last Mac window leaves Sybil running, so Option+Space still works.
 Use **Sybil → Quit Sybil** or **Command+Q** to quit the application. The Catalyst
@@ -66,7 +68,9 @@ action, and does not build or embed the macOS helper.
   answer remain available. Reopen the workspace from the panel, then explicitly
   quit with Command+Q. Rebuild and relaunch after changing lifecycle plist keys.
 - In both Mac and iOS Quick Question, reopen an existing prompt and type to replace
-  it. In the Mac workspace, verify Return submits and Shift+Return adds a newline.
+  it. On iOS, verify Return submits Quick Question while Return in the normal
+  prompt adds a newline. In the Mac workspace, verify Return submits and
+  Shift+Return adds a newline.
 - Check Command+N both with a workspace open and after closing every workspace.
   Command+Shift+N must open another window even when one already exists, and
   Command+Option+N must start a search without opening a window.

web/src/App.tsx

@@ -81,6 +81,16 @@ import {
   type SidebarSelection,
 } from "@/lib/sidebar-selection";
 import { buildQuickQuestionRequest } from "@/lib/quick-question";
+import {
+  appendStreamingDelta,
+  clearStreamingAssistantTrace,
+  createStreamingAssistantMetadata,
+  createStreamingAttemptState,
+  finalizeStreamingAssistant,
+  promoteStreamingAssistantTrace,
+  setStreamingAssistantSegment,
+  transitionStreamingToolCall,
+} from "@/lib/chat-stream-presentation";
 import { cn } from "@/lib/utils";
 
 type DraftSelectionKind = "chat" | "search";
@@ -2486,7 +2496,7 @@ export default function App() {
       role: "assistant",
       content: "",
       name: null,
-      metadata: null,
+      metadata: createStreamingAssistantMetadata(),
     };
 
     let chatId = draftKind === "chat" ? null : selectedItem?.kind === "chat" ? selectedItem.id : null;
@@ -2591,7 +2601,7 @@ export default function App() {
 
     while (true) {
       let streamErrorMessage: string | null = null;
-      let replayedAssistantText = "";
+      let streamingAttempt = createStreamingAttemptState();
       const abortController = new AbortController();
       chatStreamAbortRefs.current.set(chatId, abortController);
 
@@ -2609,45 +2619,39 @@ export default function App() {
               if (payload.chatId !== chatId) return;
             },
             onToolCall: (payload) => {
+              const transition = transitionStreamingToolCall(streamingAttempt, payload);
+              streamingAttempt = transition.attempt;
               setPendingChatStates((current) => {
                 const pendingState = current[chatId];
                 if (!pendingState) return current;
+                const messages = transition.startedNewToolCall
+                  ? promoteStreamingAssistantTrace(pendingState.messages, "temp-assistant-", transition.traceText ?? "")
+                  : pendingState.messages;
                 return {
                   ...current,
                   [chatId]: {
-                    messages: upsertOptimisticToolMessage(pendingState.messages, payload, "temp-assistant-"),
+                    messages: upsertOptimisticToolMessage(messages, payload, "temp-assistant-"),
                   },
                 };
               });
             },
             onDelta: (payload) => {
               if (!payload.text) return;
-              replayedAssistantText += payload.text;
+              streamingAttempt = appendStreamingDelta(streamingAttempt, payload.text);
+              const segmentText = streamingAttempt.segmentText;
               setPendingChatStates((current) => {
                 const pendingState = current[chatId];
                 if (!pendingState) return current;
-                let updated = false;
-                const nextMessages = pendingState.messages.map((message, index, all) => {
-                  const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-");
-                  if (!isTarget) return message;
-                  updated = true;
-                  return { ...message, content: replayedAssistantText };
-                });
-                return updated ? { ...current, [chatId]: { messages: nextMessages } } : current;
+                const nextMessages = setStreamingAssistantSegment(pendingState.messages, "temp-assistant-", segmentText);
+                return nextMessages === pendingState.messages ? current : { ...current, [chatId]: { messages: nextMessages } };
               });
             },
             onDone: (payload) => {
               setPendingChatStates((current) => {
                 const pendingState = current[chatId];
                 if (!pendingState) return current;
-                let updated = false;
-                const nextMessages = pendingState.messages.map((message, index, all) => {
-                  const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-");
-                  if (!isTarget) return message;
-                  updated = true;
-                  return { ...message, content: payload.text };
-                });
-                return updated ? { ...current, [chatId]: { messages: nextMessages } } : current;
+                const nextMessages = finalizeStreamingAssistant(pendingState.messages, "temp-assistant-", payload.text);
+                return nextMessages === pendingState.messages ? current : { ...current, [chatId]: { messages: nextMessages } };
               });
             },
             onError: (payload) => {
@@ -2896,6 +2900,7 @@ export default function App() {
         const abortController = new AbortController();
         chatStreamAbortRefs.current.set(chatId, abortController);
         let streamErrorMessage: string | null = null;
+        let streamingAttempt = createStreamingAttemptState();
 
         try {
           const baseChat = await getChat(chatId);
@@ -2912,7 +2917,7 @@ export default function App() {
                   role: "assistant",
                   content: "",
                   name: null,
-                  metadata: null,
+                  metadata: createStreamingAssistantMetadata(),
                 }),
               },
             };
@@ -2922,44 +2927,39 @@ export default function App() {
             chatId,
             {
               onToolCall: (payload) => {
+                const transition = transitionStreamingToolCall(streamingAttempt, payload);
+                streamingAttempt = transition.attempt;
                 setPendingChatStates((current) => {
                   const pendingState = current[chatId];
                   if (!pendingState) return current;
+                  const messages = transition.startedNewToolCall
+                    ? promoteStreamingAssistantTrace(pendingState.messages, "temp-assistant-", transition.traceText ?? "")
+                    : pendingState.messages;
                   return {
                     ...current,
                     [chatId]: {
-                      messages: upsertOptimisticToolMessage(pendingState.messages, payload, "temp-assistant-"),
+                      messages: upsertOptimisticToolMessage(messages, payload, "temp-assistant-"),
                     },
                   };
                 });
               },
               onDelta: (payload) => {
                 if (!payload.text) return;
+                streamingAttempt = appendStreamingDelta(streamingAttempt, payload.text);
+                const segmentText = streamingAttempt.segmentText;
                 setPendingChatStates((current) => {
                   const pendingState = current[chatId];
                   if (!pendingState) return current;
-                  let updated = false;
-                  const nextMessages = pendingState.messages.map((message, index, all) => {
-                    const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-");
-                    if (!isTarget) return message;
-                    updated = true;
-                    return { ...message, content: message.content + payload.text };
-                  });
-                  return updated ? { ...current, [chatId]: { messages: nextMessages } } : current;
+                  const nextMessages = setStreamingAssistantSegment(pendingState.messages, "temp-assistant-", segmentText);
+                  return nextMessages === pendingState.messages ? current : { ...current, [chatId]: { messages: nextMessages } };
                 });
               },
               onDone: (payload) => {
                 setPendingChatStates((current) => {
                   const pendingState = current[chatId];
                   if (!pendingState) return current;
-                  let updated = false;
-                  const nextMessages = pendingState.messages.map((message, index, all) => {
-                    const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-");
-                    if (!isTarget) return message;
-                    updated = true;
-                    return { ...message, content: payload.text };
-                  });
-                  return updated ? { ...current, [chatId]: { messages: nextMessages } } : current;
+                  const nextMessages = finalizeStreamingAssistant(pendingState.messages, "temp-assistant-", payload.text);
+                  return nextMessages === pendingState.messages ? current : { ...current, [chatId]: { messages: nextMessages } };
                 });
               },
               onError: (payload) => {
@@ -3211,7 +3211,7 @@ export default function App() {
       role: "assistant",
       content: "",
       name: null,
-      metadata: null,
+      metadata: createStreamingAssistantMetadata(),
     };
 
     quickQuestionAbortRef.current?.abort();
@@ -3225,6 +3225,7 @@ export default function App() {
     setIsQuickQuestionSending(true);
 
     let streamErrorMessage: string | null = null;
+    let streamingAttempt = createStreamingAttemptState();
 
     try {
       await runQuickQuestionStream(
@@ -3235,33 +3236,26 @@ export default function App() {
         }),
         {
           onToolCall: (payload) => {
+            const transition = transitionStreamingToolCall(streamingAttempt, payload);
+            streamingAttempt = transition.attempt;
             setQuickQuestionMessages((current) => {
-              return upsertOptimisticToolMessage(current, payload, "temp-assistant-quick-");
+              const messages = transition.startedNewToolCall
+                ? promoteStreamingAssistantTrace(current, "temp-assistant-quick-", transition.traceText ?? "")
+                : current;
+              return upsertOptimisticToolMessage(messages, payload, "temp-assistant-quick-");
             });
           },
           onDelta: (payload) => {
             if (!payload.text) return;
+            streamingAttempt = appendStreamingDelta(streamingAttempt, payload.text);
+            const segmentText = streamingAttempt.segmentText;
             setQuickQuestionMessages((current) => {
-              let updated = false;
-              const nextMessages = current.map((message, index, all) => {
-                const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-quick-");
-                if (!isTarget) return message;
-                updated = true;
-                return { ...message, content: message.content + payload.text };
-              });
-              return updated ? nextMessages : current;
+              return setStreamingAssistantSegment(current, "temp-assistant-quick-", segmentText);
             });
           },
           onDone: (payload) => {
             setQuickQuestionMessages((current) => {
-              let updated = false;
-              const nextMessages = current.map((message, index, all) => {
-                const isTarget = index === all.length - 1 && message.id.startsWith("temp-assistant-quick-");
-                if (!isTarget) return message;
-                updated = true;
-                return { ...message, content: payload.text };
-              });
-              return updated ? nextMessages : current;
+              return finalizeStreamingAssistant(current, "temp-assistant-quick-", payload.text);
             });
           },
           onError: (payload) => {
@@ -3276,6 +3270,7 @@ export default function App() {
       }
     } catch (err) {
       if (abortController.signal.aborted) return;
+      setQuickQuestionMessages((current) => clearStreamingAssistantTrace(current, "temp-assistant-quick-"));
       const message = err instanceof Error ? err.message : String(err);
       if (message.includes("bearer token")) {
         handleAuthFailure(message);

web/src/components/chat/chat-messages-panel.tsx

@@ -1,8 +1,9 @@
-import { useEffect, useMemo, useRef, useState } from "preact/hooks";
+import { useEffect, useLayoutEffect, useMemo, useRef, useState } from "preact/hooks";
 import type { ComponentChildren, JSX } from "preact";
 import { cn } from "@/lib/utils";
 import { ChatAttachmentList } from "@/components/chat/chat-attachment-list";
 import { getMessageAttachments, type Message } from "@/lib/api";
+import { asStreamingAssistantMetadata } from "@/lib/chat-stream-presentation";
 import { MarkdownContent } from "@/components/markdown/markdown-content";
 import { ChevronDown, ChevronUp, Globe2, Link2, Wrench } from "lucide-preact";
 
@@ -396,8 +397,144 @@ function ToolCallStack({
   );
 }
 
+type RenderedThinkingTrace = {
+  text: string;
+  revision: number;
+};
+
+const THINKING_TRACE_EXIT_MS = 220;
+
+export function StreamingAssistantPresentation({ message, isSending }: { message: Message; isSending: boolean }) {
+  const metadata = asStreamingAssistantMetadata(message.metadata);
+  const traceText = metadata?.ephemeralTrace?.trim() || null;
+  const traceRevision = metadata?.traceRevision ?? 0;
+  const [activeTrace, setActiveTrace] = useState<RenderedThinkingTrace | null>(() =>
+    traceText ? { text: traceText, revision: traceRevision } : null
+  );
+  const [outgoingTrace, setOutgoingTrace] = useState<RenderedThinkingTrace | null>(null);
+  const [reservedTraceHeight, setReservedTraceHeight] = useState(0);
+  const activeTraceRef = useRef<HTMLDivElement | null>(null);
+  const outgoingTraceRef = useRef<HTMLDivElement | null>(null);
+  const exitTimerRef = useRef<number | null>(null);
+
+  useLayoutEffect(() => {
+    const isSameTrace =
+      (!activeTrace && !traceText) ||
+      (activeTrace?.text === traceText && activeTrace?.revision === traceRevision && Boolean(activeTrace) === Boolean(traceText));
+    if (isSameTrace) return;
+
+    if (exitTimerRef.current !== null) {
+      window.clearTimeout(exitTimerRef.current);
+      exitTimerRef.current = null;
+    }
+
+    if (activeTrace) {
+      setOutgoingTrace(activeTrace);
+      exitTimerRef.current = window.setTimeout(() => {
+        setOutgoingTrace(null);
+        exitTimerRef.current = null;
+      }, THINKING_TRACE_EXIT_MS);
+    } else {
+      setOutgoingTrace(null);
+    }
+
+    setActiveTrace(traceText ? { text: traceText, revision: traceRevision } : null);
+  }, [traceRevision, traceText]);
+
+  useEffect(() => {
+    return () => {
+      if (exitTimerRef.current !== null) window.clearTimeout(exitTimerRef.current);
+    };
+  }, []);
+
+  useLayoutEffect(() => {
+    const traceElements = [activeTraceRef.current, outgoingTraceRef.current].filter(
+      (element): element is HTMLDivElement => element !== null
+    );
+    if (!traceElements.length) return;
+
+    const reserveMeasuredHeight = () => {
+      const measuredHeight = Math.max(...traceElements.map((element) => element.getBoundingClientRect().height));
+      if (measuredHeight > 0) {
+        setReservedTraceHeight((current) => Math.max(current, Math.ceil(measuredHeight)));
+      }
+    };
+
+    reserveMeasuredHeight();
+    if (typeof ResizeObserver === "undefined") return;
+
+    const observer = new ResizeObserver(reserveMeasuredHeight);
+    for (const element of traceElements) observer.observe(element);
+    return () => observer.disconnect();
+  }, [activeTrace, outgoingTrace]);
+
+  const hasAnswer = message.content.trim().length > 0;
+  const showTyping = isSending && !hasAnswer && !traceText && !activeTrace && !outgoingTrace;
+  const phase = hasAnswer ? "answer" : traceText || activeTrace || outgoingTrace ? "trace" : "pending";
+
+  return (
+    <div
+      className="streaming-assistant-slot"
+      data-streaming-assistant="true"
+      data-streaming-phase={phase}
+      style={reservedTraceHeight ? { minHeight: `${reservedTraceHeight}px` } : undefined}
+    >
+      {outgoingTrace ? (
+        <div
+          ref={outgoingTraceRef}
+          key={`outgoing-trace-${outgoingTrace.revision}`}
+          className="streaming-assistant-layer ephemeral-thinking-trace ephemeral-thinking-trace-exit"
+          data-thinking-trace="true"
+          data-thinking-trace-state="outgoing"
+          aria-hidden="true"
+        >
+          <p className="whitespace-pre-wrap">{outgoingTrace.text}</p>
+        </div>
+      ) : null}
+      {activeTrace ? (
+        <div
+          ref={activeTraceRef}
+          key={`active-trace-${activeTrace.revision}`}
+          className="streaming-assistant-layer ephemeral-thinking-trace ephemeral-thinking-trace-enter"
+          data-thinking-trace="true"
+          data-thinking-trace-state="active"
+          aria-hidden="true"
+        >
+          <p className="whitespace-pre-wrap">{activeTrace.text}</p>
+        </div>
+      ) : null}
+      {activeTrace && !hasAnswer ? (
+        <span className="sr-only" role="status" aria-live="polite">
+          Assistant is working
+        </span>
+      ) : null}
+      {hasAnswer ? (
+        <div className="streaming-assistant-layer streaming-assistant-answer" data-streaming-answer="true">
+          <MarkdownContent
+            markdown={message.content}
+            openLinksInNewTab
+            className="leading-[1.82] text-violet-50 [&_a]:text-inherit [&_a]:underline"
+          />
+        </div>
+      ) : null}
+      {showTyping ? (
+        <span
+          className="streaming-assistant-layer inline-flex items-center gap-1"
+          data-streaming-pending="true"
+          aria-label="Assistant is typing"
+          role="status"
+        >
+          <span className="inline-block h-1.5 w-1.5 animate-bounce rounded-full bg-muted-foreground [animation-delay:0ms]" />
+          <span className="inline-block h-1.5 w-1.5 animate-bounce rounded-full bg-muted-foreground [animation-delay:140ms]" />
+          <span className="inline-block h-1.5 w-1.5 animate-bounce rounded-full bg-muted-foreground [animation-delay:280ms]" />
+        </span>
+      ) : null}
+    </div>
+  );
+}
+
 export function ChatMessagesPanel({ messages, isLoading, isSending, onMessageContextMenu }: Props) {
-  const hasPendingAssistant = messages.some((message) => message.id.startsWith("temp-assistant-") && message.content.trim().length === 0);
+  const hasPendingAssistant = messages.some((message) => message.id.startsWith("temp-assistant-"));
   const renderItems = useMemo(() => buildMessageRenderItems(messages), [messages]);
   const toolCallMessageIDs = useMemo(() => getToolCallMessageIDs(messages), [messages]);
   const seenToolCallMessageIDsRef = useRef<Set<string> | null>(null);
@@ -457,6 +594,7 @@ export function ChatMessagesPanel({ messages, isLoading, isSending, onMessageCon
           }
 
           const isUser = message.role === "user";
+          const streamingAssistantMetadata = asStreamingAssistantMetadata(message.metadata);
           const isPendingAssistant = message.id.startsWith("temp-assistant-") && isSending && message.content.trim().length === 0;
           const attachments = getMessageAttachments(message.metadata);
           return (
@@ -475,7 +613,9 @@ export function ChatMessagesPanel({ messages, isLoading, isSending, onMessageCon
                 }
               >
                 {attachments.length ? <ChatAttachmentList attachments={attachments} tone={isUser ? "user" : "assistant"} /> : null}
-                {isPendingAssistant ? (
+                {streamingAssistantMetadata ? (
+                  <StreamingAssistantPresentation message={message} isSending={isSending} />
+                ) : isPendingAssistant ? (
                   <span className="inline-flex items-center gap-1" aria-label="Assistant is typing" role="status">
                     <span className="inline-block h-1.5 w-1.5 animate-bounce rounded-full bg-muted-foreground [animation-delay:0ms]" />
                     <span className="inline-block h-1.5 w-1.5 animate-bounce rounded-full bg-muted-foreground [animation-delay:140ms]" />

web/src/index.css

@@ -321,6 +321,97 @@ textarea {
   }
 }
 
+.streaming-assistant-slot {
+  display: grid;
+  min-width: 0;
+  min-height: 1.82em;
+  align-items: start;
+}
+
+.streaming-assistant-layer {
+  grid-area: 1 / 1;
+  min-width: 0;
+  transform-origin: top left;
+}
+
+.ephemeral-thinking-trace {
+  position: relative;
+  z-index: 1;
+  color: hsl(252 35% 88% / 0.8);
+  font-style: italic;
+  opacity: 0.78;
+  filter: saturate(0.72);
+  will-change: opacity, transform, filter;
+}
+
+.ephemeral-thinking-trace-enter {
+  animation: ephemeral-thinking-trace-enter 200ms cubic-bezier(0.2, 0.78, 0.24, 1) both;
+}
+
+.ephemeral-thinking-trace-exit {
+  pointer-events: none;
+  animation: ephemeral-thinking-trace-exit 220ms cubic-bezier(0.4, 0, 0.8, 0.28) both;
+}
+
+.streaming-assistant-answer {
+  position: relative;
+  z-index: 2;
+  animation: streaming-assistant-answer-enter 180ms cubic-bezier(0.2, 0.78, 0.24, 1) both;
+}
+
+@keyframes ephemeral-thinking-trace-enter {
+  from {
+    opacity: 0;
+    filter: saturate(0.72) blur(1px);
+    transform: translate3d(0, 0.32rem, 0);
+  }
+
+  to {
+    opacity: 0.78;
+    filter: saturate(0.72) blur(0);
+    transform: translate3d(0, 0, 0);
+  }
+}
+
+@keyframes ephemeral-thinking-trace-exit {
+  from {
+    opacity: 0.78;
+    filter: saturate(0.72) blur(0);
+    transform: translate3d(0, 0, 0);
+  }
+
+  to {
+    opacity: 0;
+    filter: saturate(0.72) blur(1px);
+    transform: translate3d(0, -0.32rem, 0);
+  }
+}
+
+@keyframes streaming-assistant-answer-enter {
+  from {
+    opacity: 0;
+    transform: translate3d(0, 0.18rem, 0);
+  }
+
+  to {
+    opacity: 1;
+    transform: translate3d(0, 0, 0);
+  }
+}
+
+@media (prefers-reduced-motion: reduce) {
+  .ephemeral-thinking-trace-enter,
+  .ephemeral-thinking-trace-exit,
+  .streaming-assistant-answer {
+    animation: none;
+    transform: none;
+  }
+
+  .ephemeral-thinking-trace-exit {
+    opacity: 0;
+  }
+}
+
 .md-content {
   word-break: break-word;
 }

web/src/lib/chat-stream-presentation.ts

@@ -0,0 +1,139 @@
+import type { Message, ToolCallEvent } from "@/lib/api";
+
+export const STREAMING_ASSISTANT_METADATA_KIND = "streaming_assistant";
+
+export type StreamingAssistantMetadata = {
+  kind: typeof STREAMING_ASSISTANT_METADATA_KIND;
+  ephemeralTrace: string | null;
+  traceRevision: number;
+};
+
+export type StreamingAttemptState = {
+  segmentText: string;
+  initiatedToolCallIds: string[];
+};
+
+export type StreamingToolCallTransition = {
+  attempt: StreamingAttemptState;
+  startedNewToolCall: boolean;
+  traceText: string | null;
+};
+
+export function createStreamingAssistantMetadata(): StreamingAssistantMetadata {
+  return {
+    kind: STREAMING_ASSISTANT_METADATA_KIND,
+    ephemeralTrace: null,
+    traceRevision: 0,
+  };
+}
+
+export function asStreamingAssistantMetadata(value: unknown): StreamingAssistantMetadata | null {
+  if (!value || typeof value !== "object" || Array.isArray(value)) return null;
+  const record = value as Record<string, unknown>;
+  if (record.kind !== STREAMING_ASSISTANT_METADATA_KIND) return null;
+
+  return {
+    kind: STREAMING_ASSISTANT_METADATA_KIND,
+    ephemeralTrace: typeof record.ephemeralTrace === "string" ? record.ephemeralTrace : null,
+    traceRevision:
+      typeof record.traceRevision === "number" && Number.isFinite(record.traceRevision)
+        ? Math.max(0, Math.floor(record.traceRevision))
+        : 0,
+  };
+}
+
+export function createStreamingAttemptState(): StreamingAttemptState {
+  return {
+    segmentText: "",
+    initiatedToolCallIds: [],
+  };
+}
+
+export function appendStreamingDelta(attempt: StreamingAttemptState, delta: string): StreamingAttemptState {
+  if (!delta) return attempt;
+  return {
+    ...attempt,
+    segmentText: attempt.segmentText + delta,
+  };
+}
+
+export function transitionStreamingToolCall(
+  attempt: StreamingAttemptState,
+  event: Pick<ToolCallEvent, "toolCallId" | "status">
+): StreamingToolCallTransition {
+  if (event.status !== "initiated" || attempt.initiatedToolCallIds.includes(event.toolCallId)) {
+    return { attempt, startedNewToolCall: false, traceText: null };
+  }
+
+  const traceText = attempt.segmentText.trim();
+  return {
+    attempt: {
+      segmentText: "",
+      initiatedToolCallIds: attempt.initiatedToolCallIds.concat(event.toolCallId),
+    },
+    startedNewToolCall: true,
+    traceText: traceText || null,
+  };
+}
+
+function updateStreamingAssistant(
+  messages: Message[],
+  assistantMessagePrefix: string,
+  update: (message: Message, metadata: StreamingAssistantMetadata) => Message
+) {
+  let didUpdate = false;
+  const nextMessages = messages.map((message, index, all) => {
+    const isTarget = index === all.length - 1 && message.id.startsWith(assistantMessagePrefix);
+    if (!isTarget) return message;
+    didUpdate = true;
+    return update(message, asStreamingAssistantMetadata(message.metadata) ?? createStreamingAssistantMetadata());
+  });
+  return didUpdate ? nextMessages : messages;
+}
+
+export function setStreamingAssistantSegment(messages: Message[], assistantMessagePrefix: string, segmentText: string) {
+  return updateStreamingAssistant(messages, assistantMessagePrefix, (message, metadata) => ({
+    ...message,
+    content: segmentText,
+    metadata: {
+      ...metadata,
+      ephemeralTrace: null,
+    } satisfies StreamingAssistantMetadata,
+  }));
+}
+
+export function promoteStreamingAssistantTrace(messages: Message[], assistantMessagePrefix: string, traceText: string) {
+  const normalizedTrace = traceText.trim();
+  return updateStreamingAssistant(messages, assistantMessagePrefix, (message, metadata) => ({
+    ...message,
+    content: "",
+    metadata: normalizedTrace
+      ? ({
+          ...metadata,
+          ephemeralTrace: normalizedTrace,
+          traceRevision: metadata.traceRevision + 1,
+        } satisfies StreamingAssistantMetadata)
+      : metadata,
+  }));
+}
+
+export function finalizeStreamingAssistant(messages: Message[], assistantMessagePrefix: string, finalText: string) {
+  return updateStreamingAssistant(messages, assistantMessagePrefix, (message, metadata) => ({
+    ...message,
+    content: finalText,
+    metadata: {
+      ...metadata,
+      ephemeralTrace: null,
+    } satisfies StreamingAssistantMetadata,
+  }));
+}
+
+export function clearStreamingAssistantTrace(messages: Message[], assistantMessagePrefix: string) {
+  return updateStreamingAssistant(messages, assistantMessagePrefix, (message, metadata) => ({
+    ...message,
+    metadata: {
+      ...metadata,
+      ephemeralTrace: null,
+    } satisfies StreamingAssistantMetadata,
+  }));
+}

web/tests/chat-stream-presentation.test.mjs

@@ -0,0 +1,148 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import {
+  appendStreamingDelta,
+  asStreamingAssistantMetadata,
+  clearStreamingAssistantTrace,
+  createStreamingAssistantMetadata,
+  createStreamingAttemptState,
+  finalizeStreamingAssistant,
+  promoteStreamingAssistantTrace,
+  setStreamingAssistantSegment,
+  transitionStreamingToolCall,
+} from "../src/lib/chat-stream-presentation.ts";
+
+function assistantMessage(content = "") {
+  return {
+    id: "temp-assistant-test",
+    createdAt: "2026-08-30T00:00:00.000Z",
+    role: "assistant",
+    content,
+    name: null,
+    metadata: createStreamingAssistantMetadata(),
+  };
+}
+
+function metadata(messages) {
+  return asStreamingAssistantMetadata(messages.at(-1)?.metadata);
+}
+
+test("a tool boundary promotes the current segment and the next delta starts the answer in its place", () => {
+  let messages = [assistantMessage()];
+  let attempt = appendStreamingDelta(createStreamingAttemptState(), "I'll search for that.");
+  messages = setStreamingAssistantSegment(messages, "temp-assistant-", attempt.segmentText);
+
+  const toolTransition = transitionStreamingToolCall(attempt, {
+    toolCallId: "search-1",
+    status: "initiated",
+  });
+  attempt = toolTransition.attempt;
+  messages = promoteStreamingAssistantTrace(messages, "temp-assistant-", toolTransition.traceText ?? "");
+
+  assert.equal(messages.at(-1).content, "");
+  assert.deepEqual(metadata(messages), {
+    kind: "streaming_assistant",
+    ephemeralTrace: "I'll search for that.",
+    traceRevision: 1,
+  });
+
+  attempt = appendStreamingDelta(attempt, "Here is the answer");
+  messages = setStreamingAssistantSegment(messages, "temp-assistant-", attempt.segmentText);
+
+  assert.equal(messages.at(-1).content, "Here is the answer");
+  assert.equal(metadata(messages)?.ephemeralTrace, null);
+
+  messages = finalizeStreamingAssistant(messages, "temp-assistant-", "Here is the answer.");
+  assert.equal(messages.at(-1).content, "Here is the answer.");
+  assert.equal(metadata(messages)?.ephemeralTrace, null);
+});
+
+test("a later tool round replaces the previous trace and parallel initiated calls do not erase it", () => {
+  let messages = [assistantMessage("First trace")];
+  let attempt = appendStreamingDelta(createStreamingAttemptState(), "First trace");
+  let transition = transitionStreamingToolCall(attempt, { toolCallId: "tool-1", status: "initiated" });
+  attempt = transition.attempt;
+  messages = promoteStreamingAssistantTrace(messages, "temp-assistant-", transition.traceText ?? "");
+
+  attempt = appendStreamingDelta(attempt, "I need one more lookup.");
+  messages = setStreamingAssistantSegment(messages, "temp-assistant-", attempt.segmentText);
+  transition = transitionStreamingToolCall(attempt, { toolCallId: "tool-2", status: "initiated" });
+  attempt = transition.attempt;
+  messages = promoteStreamingAssistantTrace(messages, "temp-assistant-", transition.traceText ?? "");
+
+  assert.equal(metadata(messages)?.ephemeralTrace, "I need one more lookup.");
+  assert.equal(metadata(messages)?.traceRevision, 2);
+
+  transition = transitionStreamingToolCall(attempt, { toolCallId: "tool-3", status: "initiated" });
+  assert.equal(transition.startedNewToolCall, true);
+  assert.equal(transition.traceText, null);
+  messages = promoteStreamingAssistantTrace(messages, "temp-assistant-", transition.traceText ?? "");
+
+  assert.equal(metadata(messages)?.ephemeralTrace, "I need one more lookup.");
+  assert.equal(metadata(messages)?.traceRevision, 2);
+});
+
+test("terminal and duplicate tool events never promote or reset the in-progress segment", () => {
+  const initial = appendStreamingDelta(createStreamingAttemptState(), "candidate");
+  const completed = transitionStreamingToolCall(initial, { toolCallId: "tool-1", status: "completed" });
+
+  assert.equal(completed.startedNewToolCall, false);
+  assert.strictEqual(completed.attempt, initial);
+
+  const initiated = transitionStreamingToolCall(initial, { toolCallId: "tool-1", status: "initiated" });
+  const withNextSegment = appendStreamingDelta(initiated.attempt, "next segment");
+  const duplicate = transitionStreamingToolCall(withNextSegment, { toolCallId: "tool-1", status: "initiated" });
+
+  assert.equal(duplicate.startedNewToolCall, false);
+  assert.strictEqual(duplicate.attempt, withNextSegment);
+  assert.equal(duplicate.attempt.segmentText, "next segment");
+});
+
+test("a fresh per-attempt accumulator can replay and reclassify an already-seen tool round", () => {
+  let messages = [assistantMessage("stale partial answer")];
+  let replayAttempt = appendStreamingDelta(createStreamingAttemptState(), "Replayed trace");
+  messages = setStreamingAssistantSegment(messages, "temp-assistant-", replayAttempt.segmentText);
+
+  const replayedTool = transitionStreamingToolCall(replayAttempt, { toolCallId: "same-tool-id", status: "initiated" });
+  messages = promoteStreamingAssistantTrace(messages, "temp-assistant-", replayedTool.traceText ?? "");
+
+  assert.equal(replayedTool.startedNewToolCall, true);
+  assert.equal(messages.at(-1).content, "");
+  assert.equal(metadata(messages)?.ephemeralTrace, "Replayed trace");
+});
+
+test("message helpers preserve identity when no matching temporary assistant exists", () => {
+  const messages = [
+    {
+      id: "persisted-assistant",
+      createdAt: "2026-08-30T00:00:00.000Z",
+      role: "assistant",
+      content: "Persisted",
+      name: null,
+      metadata: null,
+    },
+  ];
+
+  assert.strictEqual(setStreamingAssistantSegment(messages, "temp-assistant-", "new"), messages);
+  assert.strictEqual(promoteStreamingAssistantTrace(messages, "temp-assistant-", "trace"), messages);
+  assert.strictEqual(finalizeStreamingAssistant(messages, "temp-assistant-", "done"), messages);
+  assert.strictEqual(clearStreamingAssistantTrace(messages, "temp-assistant-"), messages);
+});
+
+test("a terminal error clears the ephemeral trace without discarding a partial answer", () => {
+  let messages = [
+    {
+      ...assistantMessage("Partial answer"),
+      metadata: {
+        ...createStreamingAssistantMetadata(),
+        ephemeralTrace: "Still checking one source.",
+        traceRevision: 1,
+      },
+    },
+  ];
+
+  messages = clearStreamingAssistantTrace(messages, "temp-assistant-");
+
+  assert.equal(messages.at(-1).content, "Partial answer");
+  assert.equal(metadata(messages)?.ephemeralTrace, null);
+});