Show inline Agent pending dots

docs/api/rest.md

@@ -180,7 +180,7 @@ Behavior notes:
 
 Behavior notes:
 - With no `messageId`, the server copies the complete source transcript. With an assistant response `messageId`, it copies the transcript through that response, inclusive.
-- The source chat is unchanged. Copied messages receive new ids while retaining their role, content, name, creation time, order, and metadata except for the source request's transport-only `clientRequestId`. Attachments, tool-call metadata, and per-response `metadata.generation` are retained. For older replies with an exact call-log match, generation metadata is recovered before copying. LLM call logs, star/project memberships, and other child threads are not copied.
+- The source chat is unchanged. Copied messages receive new ids while retaining their role, content, name, creation time, order, and metadata except for the source request's transport-only `clientRequestId`. Attachments and tool-call metadata are retained. LLM call logs, star/project memberships, and other child threads are not copied.
 - The fork inherits the source chat's user, initiated/last-used provider and model, additional system prompt, and enabled tool settings.
 - A fork of a root or another fork always sets `parentChatId` to the single root chat id. Root chats keep `parentChatId: null`.
 - A whole-chat fork starts with `Fork of <source title>` (or `Fork of Untitled chat`). A message fork starts with `Fork of '<message snippet>'`.
@@ -233,9 +233,6 @@ Behavior notes:
 
 ### `GET /v1/chats/:chatId`
 - Response: `{ "chat": ChatDetail }`
-- Saved ordinary assistant responses can include `metadata.generation: { "provider": "openai", "model": "gpt-4.1-mini" }`. These are the provider/model identifiers used for that completion request, captured separately from the chat's mutable last-used selection. Model aliases remain the requested alias; this does not claim an underlying provider snapshot ID.
-- Newly generated responses store this metadata for both streaming and non-streaming completions. It survives reloads and forks. Inline Sybil Agent replies retain their separate `metadata.agentAside` identity.
-- For older assistant messages without generation metadata, this response recovers it only when `metadata.clientRequestId` matches exactly one completed, successful call in the same chat. This read does not rewrite stored history. Missing or ambiguous records, including some older forks/imports, remain unattributed; clients must not substitute the chat's current or last-used model. The web footer displays “Model not recorded” in that case.
 
 ### `GET /v1/chats/:chatId/messages`
 - Requires the same authenticated owner/admin credential as other chat routes. Responses use `Cache-Control: no-store`.
@@ -341,7 +338,6 @@ Behavior notes:
 - Before the Agent is invoked, the backend paginates and supplies the complete safe visible-thread projection as required initial context; the Agent does not have to choose `read_chat_history` for the current thread. User/assistant asides and full supported attachment representations are included, while system/tool rows and unrelated metadata are excluded. Historical content remains untrusted context, not new authority.
 - The initial context transfer is limited to 30 MiB. A stored text attachment marked truncated, incomplete history, or a transfer/provider context-limit failure returns an explicit error and no answer from partial history; providers may reject a complete thread that exceeds their model context window.
 - For `chatId` calls, server stores only *new* non-assistant messages from provided history to avoid duplicates.
-- Saved ordinary assistant responses also store the completion's provider/model in `metadata.generation`, exposed by `GET /v1/chats/:chatId`; changing the chat selection does not relabel previous responses.
 - `additionalSystemPrompt`, when present directly or loaded from stored chat settings, is prepended to the provider request as a `system` message and is not inserted into the persisted chat transcript by this endpoint.
 - `enabledTools` limits Sybil-managed tools for this request. When omitted for a saved chat, the stored chat setting is used; otherwise all available tools are enabled by default. An empty array disables Sybil-managed tools.
 - `maxTokens` is optional. For `anthropic`, when omitted the backend requests the selected model's maximum output token limit from Anthropic's Models API and uses that as `max_tokens`; if the model limit cannot be loaded, the fallback is 128000. For other providers, omitted `maxTokens` is not sent as an explicit cap.

docs/api/streaming-chat.md

@@ -146,8 +146,6 @@ Each tool invocation can emit multiple `tool_call` events with the same `toolCal
 
 For `persist: false` streams, `chatId` and `callId` are `null`.
 
-When an ordinary persisted completion finishes, its assistant message stores the same request-time provider/model in `metadata.generation`, available in the canonical `GET /v1/chats/:chatId` refresh. Clients must use per-message generation metadata for historical response labels, not the current chat selection. Older messages can lack attribution; see [chat detail](rest.md#get-v1chatschatid). This adds no SSE events or fields, and does not change non-persistent Quick Questions or inline Agent identity.
-
 ### `delta`
 
 ```json

ios/Packages/Sybil/Sources/Sybil/SybilAgentView.swift

@@ -235,6 +235,53 @@ struct AgentAvatar: View {
     }
 }
 
+struct AgentTypingDots: View {
+    @Environment(\.accessibilityReduceMotion) private var reduceMotion
+
+    var body: some View {
+        TimelineView(.animation(minimumInterval: 1 / 30, paused: reduceMotion)) { timeline in
+            HStack(spacing: 3) {
+                ForEach(0..<3, id: \.self) { index in
+                    let pulse = pulse(at: timeline.date, index: index)
+                    Circle()
+                        .fill(Color(red: 0.80, green: 0.70, blue: 0.91))
+                        .frame(width: 3, height: 3)
+                        .opacity(reduceMotion ? 0.7 : pulse.opacity)
+                        .offset(y: reduceMotion ? 0 : pulse.rise)
+                }
+            }
+            .padding(.horizontal, 8)
+            .padding(.vertical, 6)
+            .background(
+                Color(red: 0.12, green: 0.075, blue: 0.21).opacity(0.42),
+                in: RoundedRectangle(cornerRadius: 9)
+            )
+        }
+        .accessibilityElement(children: .ignore)
+        .accessibilityLabel("Sybil is thinking")
+    }
+
+    private func pulse(at date: Date, index: Int) -> (opacity: Double, rise: CGFloat) {
+        let cycle = 1.4
+        let delay = Double(index) * 0.16 / cycle
+        let elapsed = date.timeIntervalSinceReferenceDate.truncatingRemainder(dividingBy: cycle) / cycle
+        let phase = (elapsed - delay + 1).truncatingRemainder(dividingBy: 1)
+        let intensity: Double
+        if phase <= 0.35 {
+            let progress = phase / 0.35
+            let eased = progress * progress * (3 - 2 * progress)
+            intensity = 0.35 + 0.65 * eased
+        } else if phase <= 0.70 {
+            let progress = (phase - 0.35) / 0.35
+            let eased = progress * progress * (3 - 2 * progress)
+            intensity = 1 - 0.65 * eased
+        } else {
+            intensity = 0.35
+        }
+        return (intensity, -2 * CGFloat((intensity - 0.35) / 0.65))
+    }
+}
+
 // Activity/read publications still update the transcript. Completed rows depend
 // only on message values and heading; scrolling needs no per-row geometry.
 private struct AgentTranscriptRow: View, Equatable {

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

@@ -234,7 +234,13 @@ struct MessageBubble: View {
                         )
                     }
 
-                    if isStreamingAssistant && !agentStyle {
+                    if agentStyle && shouldShowInlineAgentPendingDots(
+                        message: message,
+                        isSending: isSending,
+                        presentation: matchingStreamingAssistantPresentation
+                    ) {
+                        AgentTypingDots()
+                    } else if isStreamingAssistant && !agentStyle {
                         StreamingAssistantContentView(
                             content: message.content,
                             isSending: isSending,
@@ -289,6 +295,24 @@ struct MessageBubble: View {
     }
 }
 
+func shouldShowInlineAgentPendingDots(
+    message: Message,
+    isSending: Bool,
+    presentation: StreamingAssistantPresentation?
+) -> Bool {
+    guard message.isAgentAside,
+          message.role == .assistant,
+          message.id.hasPrefix("temp-assistant-"),
+          isSending,
+          let presentation,
+          presentation.messageID == message.id,
+          presentation.isAwaitingVisibleText
+    else {
+        return false
+    }
+    return message.content.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty
+}
+
 private struct StreamingTraceHeightPreferenceKey: PreferenceKey {
     static let defaultValue: CGFloat = 0
 

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

@@ -54,10 +54,14 @@ struct StreamingAssistantState: Equatable, Sendable {
     private(set) var initiatedToolCallIDs: Set<String> = []
     private(set) var ephemeralTrace: String?
     private(set) var traceRevision = 0
+    private(set) var isAwaitingVisibleText = true
 
     mutating func receiveDelta(_ text: String) -> StreamingAssistantContentUpdate {
         guard !text.isEmpty else { return .unchanged }
         segmentText += text
+        if !segmentText.trimmingCharacters(in: .whitespacesAndNewlines).isEmpty {
+            isAwaitingVisibleText = false
+        }
         ephemeralTrace = nil
         return .replace(segmentText)
     }
@@ -79,20 +83,27 @@ struct StreamingAssistantState: Equatable, Sendable {
     mutating func receiveDone(_ text: String) -> StreamingAssistantContentUpdate {
         segmentText = ""
         ephemeralTrace = nil
+        isAwaitingVisibleText = false
         return .replace(text)
     }
 
     mutating func receiveError() -> StreamingAssistantContentUpdate {
         segmentText = ""
         ephemeralTrace = nil
+        isAwaitingVisibleText = false
         return .unchanged
     }
+
+    mutating func receiveCancel() {
+        isAwaitingVisibleText = false
+    }
 }
 
 struct StreamingAssistantPresentation: Equatable, Sendable {
     var messageID: String
     var ephemeralTrace: String?
     var traceRevision: Int
+    var isAwaitingVisibleText: Bool
 }
 
 private struct PendingChatState {
@@ -107,7 +118,8 @@ private struct PendingChatState {
         return StreamingAssistantPresentation(
             messageID: messageID,
             ephemeralTrace: streamingAssistantState.ephemeralTrace,
-            traceRevision: streamingAssistantState.traceRevision
+            traceRevision: streamingAssistantState.traceRevision,
+            isAwaitingVisibleText: streamingAssistantState.isAwaitingVisibleText
         )
     }
 }
@@ -467,7 +479,8 @@ final class SybilViewModel {
         return StreamingAssistantPresentation(
             messageID: messageID,
             ephemeralTrace: quickQuestionStreamingAssistantState.ephemeralTrace,
-            traceRevision: quickQuestionStreamingAssistantState.traceRevision
+            traceRevision: quickQuestionStreamingAssistantState.traceRevision,
+            isAwaitingVisibleText: quickQuestionStreamingAssistantState.isAwaitingVisibleText
         )
     }
 
@@ -2151,6 +2164,13 @@ final class SybilViewModel {
             pendingDraftChatState = PendingChatState(chatID: nil, messages: optimisticMessages)
         }
         defer {
+            if Task.isCancelled {
+                if let resolvedChatID = chatID {
+                    pendingChatStates[resolvedChatID]?.streamingAssistantState.receiveCancel()
+                } else {
+                    pendingDraftChatState?.streamingAssistantState.receiveCancel()
+                }
+            }
             if let resolvedChatID = chatID {
                 pendingChatStates[resolvedChatID] = nil
             } else {

ios/Tests/SybilPresentationTests/AgentInlineThinkingDotsTests.swift

@@ -0,0 +1,141 @@
+import SwiftUI
+import UIKit
+import XCTest
+@testable import Sybil
+
+@MainActor
+final class AgentInlineThinkingDotsTests: XCTestCase {
+    func testPendingDotsReplaceWithTextAndHideOnDoneFailureOrCancel() async throws {
+        let messageID = "temp-assistant-inline-dots-fixture"
+        let date = Date(timeIntervalSince1970: 1_750_000_000)
+        let user = Message(id: "temp-user-inline-dots-fixture", createdAt: date, role: .user, content: "@Sybil, summarize this.", name: nil)
+        var reply = Message(
+            id: messageID,
+            createdAt: date,
+            role: .assistant,
+            content: "",
+            name: nil,
+            metadata: .object(["agentAside": .bool(true)])
+        )
+        var state = StreamingAssistantState()
+        var presentation = Self.presentation(messageID: messageID, state: state)
+
+        XCTAssertTrue(shouldShowInlineAgentPendingDots(message: reply, isSending: true, presentation: presentation))
+        await capture(messages: [user, reply], presentation: presentation, sending: true, name: "inline-agent-pending-dancing-dots")
+
+        XCTAssertEqual(state.receiveDelta(" \n"), .replace(" \n"))
+        reply.content = state.segmentText
+        presentation = Self.presentation(messageID: messageID, state: state)
+        XCTAssertTrue(shouldShowInlineAgentPendingDots(message: reply, isSending: true, presentation: presentation))
+
+        XCTAssertEqual(state.receiveDelta("Here is the Agent reply."), .replace(" \nHere is the Agent reply."))
+        reply.content = state.segmentText
+        presentation = Self.presentation(messageID: messageID, state: state)
+        XCTAssertFalse(shouldShowInlineAgentPendingDots(message: reply, isSending: true, presentation: presentation))
+        await capture(messages: [user, reply], presentation: presentation, sending: true, name: "inline-agent-first-visible-text-same-bubble")
+
+        XCTAssertEqual(state.receiveDone("Completed Agent reply."), .replace("Completed Agent reply."))
+        reply.content = "Completed Agent reply."
+        presentation = Self.presentation(messageID: messageID, state: state)
+        XCTAssertFalse(shouldShowInlineAgentPendingDots(message: reply, isSending: true, presentation: presentation))
+        XCTAssertEqual(reply.id, messageID)
+
+        var failed = StreamingAssistantState()
+        let failurePresentation = Self.presentation(messageID: messageID, state: failed)
+        XCTAssertTrue(shouldShowInlineAgentPendingDots(message: reply.withContent(""), isSending: true, presentation: failurePresentation))
+        XCTAssertEqual(failed.receiveError(), .unchanged)
+        XCTAssertFalse(shouldShowInlineAgentPendingDots(
+            message: reply.withContent(""), isSending: true, presentation: Self.presentation(messageID: messageID, state: failed)
+        ))
+
+        var cancelled = StreamingAssistantState()
+        let cancelPresentation = Self.presentation(messageID: messageID, state: cancelled)
+        XCTAssertTrue(shouldShowInlineAgentPendingDots(message: reply.withContent(""), isSending: true, presentation: cancelPresentation))
+        cancelled.receiveCancel()
+        XCTAssertFalse(shouldShowInlineAgentPendingDots(
+            message: reply.withContent(""), isSending: true, presentation: Self.presentation(messageID: messageID, state: cancelled)
+        ))
+    }
+
+    private static func presentation(messageID: String, state: StreamingAssistantState) -> StreamingAssistantPresentation {
+        StreamingAssistantPresentation(
+            messageID: messageID,
+            ephemeralTrace: state.ephemeralTrace,
+            traceRevision: state.traceRevision,
+            isAwaitingVisibleText: state.isAwaitingVisibleText
+        )
+    }
+
+    private func capture(
+        messages: [Message],
+        presentation: StreamingAssistantPresentation,
+        sending: Bool,
+        name: String
+    ) async {
+        let host = UIHostingController(rootView: InlineAgentReplySnapshot(
+            messages: messages,
+            presentation: presentation,
+            sending: sending
+        ))
+        let window = UIWindow(frame: CGRect(x: 0, y: 0, width: 390, height: 170))
+        window.rootViewController = host
+        window.makeKeyAndVisible()
+        host.view.frame = window.bounds
+        host.view.setNeedsLayout()
+        host.view.layoutIfNeeded()
+        try? await Task.sleep(for: .milliseconds(80))
+        let image = UIGraphicsImageRenderer(bounds: host.view.bounds).image { _ in
+            XCTAssertTrue(host.view.drawHierarchy(in: host.view.bounds, afterScreenUpdates: true))
+        }
+        if let data = image.pngData() {
+            let attachment = XCTAttachment(data: data, uniformTypeIdentifier: "public.png")
+            attachment.name = name
+            attachment.lifetime = .keepAlways
+            add(attachment)
+        } else {
+            XCTFail("Could not encode (name) screenshot")
+        }
+        window.isHidden = true
+        window.rootViewController = nil
+    }
+}
+
+private struct InlineAgentReplySnapshot: View {
+    var messages: [Message]
+    var presentation: StreamingAssistantPresentation
+    var sending: Bool
+
+    var body: some View {
+        ZStack(alignment: .topLeading) {
+            SybilTheme.background.ignoresSafeArea()
+            VStack(alignment: .leading, spacing: 8) {
+                Text("Inline @Sybil reply")
+                    .font(.sybil(.caption))
+                    .foregroundStyle(SybilTheme.textMuted)
+                ForEach(messages) { message in
+                    if message.isAgentAside {
+                        AgentMessageRow(
+                            message: message,
+                            isSending: sending,
+                            streamingAssistantPresentation: presentation
+                        )
+                    } else {
+                        Text(message.content).foregroundStyle(SybilTheme.text)
+                    }
+                }
+                Spacer(minLength: 0)
+            }
+            .padding(16)
+        }
+        .frame(width: 390, height: 170)
+        .environment(\.colorScheme, .dark)
+    }
+}
+
+private extension Message {
+    func withContent(_ content: String) -> Message {
+        var copy = self
+        copy.content = content
+        return copy
+    }
+}

server/src/llm/multiplexer.ts

@@ -85,7 +85,6 @@ export async function runMultiplex(req: MultiplexRequest): Promise<MultiplexResp
           chatId: call.chatId,
           role: "assistant" as any,
           content: outText,
-          metadata: { generation: { provider: req.provider, model: req.model } },
         },
       });
       await tx.llmCall.update({

server/src/llm/streaming.ts

@@ -123,10 +123,7 @@ export async function* runMultiplexStream(req: MultiplexRequest): AsyncGenerator
             chatId,
             role: "assistant" as any,
             content: text,
-            metadata: {
-              ...(req.clientRequestId ? { clientRequestId: req.clientRequestId } : {}),
-              generation: { provider: req.provider, model: req.model },
-            },
+            metadata: req.clientRequestId ? ({ clientRequestId: req.clientRequestId } as any) : undefined,
           },
         });
         await tx.llmCall.update({

server/src/message-generation.ts

@@ -1,31 +0,0 @@
-import { fromPrismaProvider } from "./llm/provider-ids.js";
-
-function record(value: unknown): Record<string, unknown> {
-  return value && typeof value === "object" && !Array.isArray(value) ? value as Record<string, unknown> : {};
-}
-
-type RecordedCall = {
-  provider: unknown;
-  model: string;
-  request: unknown;
-  error: string | null;
-  latencyMs: number | null;
-};
-
-/** Recover older streaming replies only through an unambiguous, completed request ID. */
-export function withMessageGenerations<T extends { role: string; metadata: unknown }>(messages: T[], calls: RecordedCall[]): T[] {
-  const byRequest = new Map<string, { provider: string; model: string } | null>();
-  for (const call of calls) {
-    const requestId = record(call.request).clientRequestId;
-    if (typeof requestId !== "string" || !requestId || call.error !== null || call.latencyMs === null) continue;
-    const provider = fromPrismaProvider(call.provider);
-    if (!provider || !call.model.trim()) continue;
-    byRequest.set(requestId, byRequest.has(requestId) ? null : { provider, model: call.model });
-  }
-  return messages.map(message => {
-    const metadata = record(message.metadata);
-    if (message.role !== "assistant" || metadata.agentAside === true || metadata.generation !== undefined) return message;
-    const generation = typeof metadata.clientRequestId === "string" ? byRequest.get(metadata.clientRequestId) : null;
-    return generation ? { ...message, metadata: { ...metadata, generation } } : message;
-  });
-}

server/src/routes.ts

@@ -7,7 +7,6 @@ import { invokeAgentInline, type AgentInlineInvoker } from "./agent-inline.js";
 import { buildInlineAgentThreadContext, decodeChatHistoryCursor, decodeChatListCursor, encodeChatListCursor, loadCompleteChatHistory, readChatHistoryPage } from "./chat-history.js";
 import { containsSybilMention, filterAgentAsideMessages } from "./agent-mention.js";
 import { prisma } from "./db.js";
-import { withMessageGenerations } from "./message-generation.js";
 import { requireAdmin } from "./auth.js";
 import { env } from "./env.js";
 import { buildComparableAttachments } from "./llm/message-content.js";
@@ -1174,12 +1173,11 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
           enabledTools: true,
           userId: true,
           messages: { orderBy: [{ createdAt: "asc" }, { id: "asc" }] },
-          calls: { select: { provider: true, model: true, request: true, error: true, latencyMs: true } },
         },
       });
       if (!source) return { status: "chat-not-found" as const };
 
-      let messages = withMessageGenerations(source.messages, source.calls);
+      let messages = source.messages;
       let selectedMessage: (typeof source.messages)[number] | undefined;
       if (parsed.data.messageId) {
         const selectedIndex = messages.findIndex((message) => message.id === parsed.data.messageId);
@@ -1682,7 +1680,7 @@ export async function registerRoutes(app: FastifyInstance, options: { agentInlin
       },
     });
     if (!chat) return app.httpErrors.notFound("chat not found");
-    return { chat: serializeChatLike({ ...chat, messages: withMessageGenerations(chat.messages, chat.calls) }) };
+    return { chat: serializeChatLike(chat) };
   });
 
   app.post("/v1/chats/:chatId/messages", async (req) => {

server/tests/message-generation.test.ts

@@ -1,85 +0,0 @@
-import assert from "node:assert/strict";
-import { execFileSync } from "node:child_process";
-import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
-import { tmpdir } from "node:os";
-import { dirname, join, resolve } from "node:path";
-import test from "node:test";
-import { fileURLToPath } from "node:url";
-import Fastify from "fastify";
-import sensible from "@fastify/sensible";
-import { withMessageGenerations } from "../src/message-generation.js";
-
-const serverRoot = resolve(dirname(fileURLToPath(import.meta.url)), "..");
-const databaseDir = mkdtempSync(join(tmpdir(), "sybil-message-generation-"));
-process.env.DATABASE_URL = `file:${join(databaseDir, "test.db")}`;
-process.env.ADMIN_TOKEN = "message-generation-test-token";
-process.env.OPENAI_API_KEY = "synthetic-openai-key";
-process.env.XAI_API_KEY = "synthetic-xai-key";
-writeFileSync(join(databaseDir, "test.db"), "");
-execFileSync(process.execPath, [join(serverRoot, "node_modules/prisma/build/index.js"), "migrate", "deploy"], {
-  cwd: serverRoot, env: { ...process.env, PRISMA_HIDE_UPDATE_MESSAGE: "1" }, stdio: "pipe",
-});
-const [{ registerRoutes }, { prisma }, { runMultiplex }, { runMultiplexStream }] = await Promise.all([
-  import("../src/routes.js"), import("../src/db.js"), import("../src/llm/multiplexer.js"), import("../src/llm/streaming.js"),
-]);
-const app = Fastify({ logger: false });
-await app.register(sensible);
-await registerRoutes(app);
-await app.ready();
-const auth = { authorization: "Bearer message-generation-test-token" };
-test.after(async () => { await app.close(); await prisma.$disconnect(); rmSync(databaseDir, { recursive: true, force: true }); });
-
-test("streaming and non-streaming replies retain their own model across selection changes and forks", async t => {
-  t.mock.method(globalThis, "fetch", async (input: RequestInfo | URL, init?: RequestInit) => {
-    const url = input instanceof Request ? input.url : String(input);
-    assert.ok(["https://api.openai.com/v1/chat/completions", "https://api.x.ai/v1/chat/completions"].includes(url), url);
-    const body = JSON.parse(input instanceof Request ? await input.text() : String(init?.body));
-    const content = `Reply from ${body.model}`;
-    return body.stream
-      ? new Response(`data: ${JSON.stringify({ choices: [{ index: 0, delta: { content }, finish_reason: null }] })}\n\ndata: [DONE]\n\n`, { headers: { "content-type": "text/event-stream" } })
-      : Response.json({ choices: [{ message: { role: "assistant", content } }] });
-  });
-  const chat = await prisma.chat.create({ data: { title: "Mixed models" } });
-  const messages = [{ role: "user" as const, content: "Answer" }];
-  const events = [];
-  for await (const event of runMultiplexStream({ chatId: chat.id, provider: "openai", model: "model-one", clientRequestId: "first-turn", messages, enabledTools: [] })) events.push(event);
-  assert.equal(events.at(-1)?.type, "done");
-  await runMultiplex({ chatId: chat.id, provider: "xai", model: "model-two", messages, enabledTools: [] });
-  await prisma.chat.update({ where: { id: chat.id }, data: { lastUsedProvider: "gemini", lastUsedModel: "model-next" } });
-  const detail = await app.inject({ method: "GET", url: `/v1/chats/${chat.id}`, headers: auth });
-  assert.equal(detail.statusCode, 200);
-  const saved = detail.json().chat.messages;
-  assert.deepEqual(saved.map((m: any) => m.metadata.generation), [{ provider: "openai", model: "model-one" }, { provider: "xai", model: "model-two" }]);
-  assert.equal(saved[0].metadata.clientRequestId, "first-turn");
-  const fork = await app.inject({ method: "POST", url: `/v1/chats/${chat.id}/fork`, headers: auth, payload: { messageId: saved[1].id } });
-  assert.equal(fork.statusCode, 200);
-  const forkDetail = await app.inject({ method: "GET", url: `/v1/chats/${fork.json().chat.id}`, headers: auth });
-  assert.deepEqual(forkDetail.json().chat.messages.map((m: any) => m.metadata.generation), saved.map((m: any) => m.metadata.generation));
-  assert.equal(forkDetail.json().chat.messages[0].metadata.clientRequestId, undefined);
-});
-
-test("legacy call matches are projected without rewriting history and survive a new fork", async () => {
-  const chat = await prisma.chat.create({ data: {
-    title: "Older reply", lastUsedProvider: "gemini", lastUsedModel: "different-current-model",
-    messages: { create: { role: "assistant", content: "Older reply", metadata: { clientRequestId: "legacy-request", citations: ["https://example.test"] } } },
-    calls: { create: { provider: "anthropic", model: "original-model", request: { clientRequestId: "legacy-request" }, latencyMs: 10 } },
-  }, include: { messages: true } });
-  const detail = await app.inject({ method: "GET", url: `/v1/chats/${chat.id}`, headers: auth });
-  assert.deepEqual(detail.json().chat.messages[0].metadata.generation, { provider: "anthropic", model: "original-model" });
-  assert.deepEqual((await prisma.message.findUniqueOrThrow({ where: { id: chat.messages[0]!.id } })).metadata, chat.messages[0]!.metadata);
-  const fork = await app.inject({ method: "POST", url: `/v1/chats/${chat.id}/fork`, headers: auth, payload: {} });
-  const forkDetail = await app.inject({ method: "GET", url: `/v1/chats/${fork.json().chat.id}`, headers: auth });
-  assert.deepEqual(forkDetail.json().chat.messages[0].metadata, { citations: ["https://example.test"], generation: { provider: "anthropic", model: "original-model" } });
-});
-
-test("missing, ambiguous, failed and unfinished calls never guess a reply's model", () => {
-  const call = { provider: "openai", model: "model-one", request: { clientRequestId: "request" }, error: null, latencyMs: 10 };
-  const message = { role: "assistant", metadata: { clientRequestId: "request" } };
-  for (const calls of [[], [call, { ...call, provider: "xai" }], [{ ...call, error: "failed" }], [{ ...call, latencyMs: null }]]) {
-    assert.deepEqual(withMessageGenerations([message], calls), [message]);
-  }
-  const existing = { ...message, metadata: { ...message.metadata, generation: { provider: "gemini", model: "original" } } };
-  const aside = { ...message, metadata: { ...message.metadata, agentAside: true } };
-  const user = { ...message, role: "user" };
-  assert.deepEqual(withMessageGenerations([existing, aside, user], [call]), [existing, aside, user]);
-});

web/src/components/agent/agent-conversation.tsx

@@ -50,19 +50,23 @@ function toolName(value: unknown) {
   return typeof value === "string" ? value.replace(/_/g, " ") : "Tool";
 }
 
-export const AgentBubble = memo(function AgentBubble({ message, animate, onRetry, download, showThinkingIndicator = false }: { message: Message; animate: boolean; onRetry: (id: string) => void; download: AgentRoomHookResult["downloadAttachment"]; showThinkingIndicator?: boolean }) {
+export function AgentThinkingDots({ label = "Sybil is thinking" }: { label?: string }) {
+  return <span className="agent-room__typing-dots" aria-label={label} role="status"><i /><i /><i /></span>;
+}
+
+export const AgentBubble = memo(function AgentBubble({ message, animate, onRetry, download, showThinkingIndicator = false, isPending = false }: { message: Message; animate: boolean; onRetry: (id: string) => void; download: AgentRoomHookResult["downloadAttachment"]; showThinkingIndicator?: boolean; isPending?: boolean }) {
   const own = message.role === "user";
   const info = metadata(message);
   const status = typeof info.status === "string" ? info.status : "complete";
   const failed = status === "failed" || status === "unconfirmed";
-  const thinking = showThinkingIndicator && !own && status === "sending" && !message.content.trim();
+  const thinking = showThinkingIndicator && !own && (isPending ?? status === "sending") && !message.content.trim();
   const date = dateOf(message.createdAt);
   return (
     <article className={`agent-room__message ${own ? "is-own" : "is-agent"}`} data-agent-message-id={message.id} data-message-status={status} data-animation={animate ? "enter" : undefined} aria-label={own ? "Your message" : "Sybil's message"}>
       {!own ? <span className="agent-room__message-avatar" aria-hidden="true"><img src="/character-still.png" alt="" draggable={false} /></span> : null}
       <div className="agent-room__message-content">
         <div className={`message-bubble${own ? " message-bubble--user" : ""}`}>
-          {own ? <p className="agent-room__plain-message">{message.content}</p> : thinking ? <span className="inline-flex items-center gap-1" aria-label="Sybil is thinking" 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> : <MarkdownContent markdown={message.content} openLinksInNewTab allowImages={false} />}
+          {own ? <p className="agent-room__plain-message">{message.content}</p> : thinking ? <AgentThinkingDots /> : <MarkdownContent markdown={message.content} openLinksInNewTab allowImages={false} />}
           {agentAttachments(message.metadata, message.role).map(file => <AgentAttachmentCard key={file.id} file={file} download={download} inline={message.role === "assistant"} />)}
         </div>
         {own && failed && typeof info.error === "string" ? <div className="agent-attachment__error" role="alert">{info.error}</div> : null}

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

@@ -3,7 +3,7 @@ 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 { asStreamingAssistantMetadata, isInlineAgentReplyPending } from "@/lib/chat-stream-presentation";
 import { AgentBubble } from "@/components/agent/agent-conversation";
 import { MarkdownContent } from "@/components/markdown/markdown-content";
 import { ChevronDown, ChevronUp, Globe2, Link2, Wrench } from "lucide-preact";
@@ -604,7 +604,7 @@ export function ChatMessagesPanel({ messages, isLoading, isSending, onMessageCon
           if (message.role === "assistant" && metadata.agentAside === true) {
             return (
               <div key={message.id} className="flex justify-start" data-agent-aside="true">
-                <AgentBubble message={message} animate={message.id.startsWith("temp-assistant-")} onRetry={() => {}} download={noAgentAttachmentDownload} showThinkingIndicator />
+                <AgentBubble message={message} animate={message.id.startsWith("temp-assistant-")} onRetry={() => {}} download={noAgentAttachmentDownload} showThinkingIndicator isPending={isInlineAgentReplyPending(message, isSending)} />
               </div>
             );
           }

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

@@ -2,6 +2,13 @@ import type { Message, ToolCallEvent } from "@/lib/api";
 
 export const STREAMING_ASSISTANT_METADATA_KIND = "streaming_assistant";
 
+export function isInlineAgentReplyPending(message: Message, isSending: boolean): boolean {
+  const metadata = message.metadata && typeof message.metadata === "object" && !Array.isArray(message.metadata)
+    ? message.metadata as Record<string, unknown> : {};
+  return isSending && message.role === "assistant" && message.id.startsWith("temp-assistant-")
+    && metadata.agentAside === true && !message.content.trim();
+}
+
 export type StreamingAssistantMetadata = {
   kind: typeof STREAMING_ASSISTANT_METADATA_KIND;
   ephemeralTrace: string | null;

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

@@ -7,6 +7,7 @@ import {
   createStreamingAssistantMetadata,
   createStreamingAttemptState,
   finalizeStreamingAssistant,
+  isInlineAgentReplyPending,
   markStreamingAssistantAsAgentAside,
   promoteStreamingAssistantTrace,
   setStreamingAssistantSegment,
@@ -126,6 +127,15 @@ test("Agent aside stream keeps identity through loading, markdown deltas, and co
   assert.equal(messages.at(-1).content, "**Inline** reply");
 });
 
+test("inline Agent pending dots stop on first text, completion, failure, and cancellation", () => {
+  let message = markStreamingAssistantAsAgentAside([assistantMessage()], "temp-assistant-").at(-1);
+  assert.equal(isInlineAgentReplyPending(message, true), true);
+  message = setStreamingAssistantSegment([message], "temp-assistant-", "First visible text").at(-1);
+  assert.equal(isInlineAgentReplyPending(message, true), false);
+  assert.equal(isInlineAgentReplyPending(assistantMessage(), false), false, "failed or cancelled pending state is hidden");
+  assert.equal(isInlineAgentReplyPending({ ...message, id: "saved-agent-reply", content: "" }, true), false);
+});
+
 test("message helpers preserve identity when no matching temporary assistant exists", () => {
   const messages = [
     {