ios: isolate Agent scrolling and activity rendering

ios/Tests/AgentPerformance.md

@@ -0,0 +1,68 @@
+# Agent scrolling benchmark
+
+Run the production Agent view in an app-hosted XCTest on the iPhone 16e simulator:
+
+```sh
+just generate
+xcodebuild test -scheme SybilPresentation \
+  -destination 'platform=iOS Simulator,name=iPhone 16e,OS=latest' \
+  -derivedDataPath build/DerivedData -parallel-testing-enabled NO \
+  -only-testing:SybilPresentationTests/AgentPerformanceTests \
+  -resultBundlePath build/agent-performance.xcresult
+```
+
+`AgentPerformanceTests` seeds a room through its normal event reducer with 160
+local messages (100 initially displayed). User text is literal; assistant text
+contains paragraphs, lists, links, emphasis and code. The real Agent view,
+composer, avatar, entrance layout and thinking spinner remain enabled. No server,
+production credentials, notification delivery or network images are needed.
+
+Three approximately 12-second phases run in order: idle scrolling, thinking at
+the bottom, and thinking while scrolling. The test explicitly resets the offset
+to the bottom before the stationary thinking phase (including in the baseline).
+Thinking activity changes queue depth, worker count and tool progress every
+500 ms through the normal 100 ms publication
+batch. The display link sweeps a 2400-point range at 600 points/second, reversing
+every four seconds. Use the **same test source, simulator, build configuration
+and host load** for before/after runs. Don't run other builds or profilers during
+a measured run. Warm builds and repeat runs help distinguish stable effects from
+host noise.
+
+The geometry assertions use iPhone 16e, iOS 26.5, and the default text size. They
+retain the unoptimized transcript heights (39181.333 points idle, 39223.333 while
+thinking), so an isolation wrapper cannot silently change row spacing. Rebaseline
+these explicitly when changing simulator/font configuration or the fixture.
+
+The log prints `AGENT_PERFORMANCE_JSON`; the result bundle retains the JSON as an
+attachment. Delivery-gap p50/p95/p99/max and counts over 25/50 ms measure actual
+main-run-loop responsiveness. `missedBudgetIntervals` estimates gaps relative to
+the reported display-link budget. These are **not compositor FPS, GPU hitches,
+touch latency or physical-device results**. Scrolling is programmatic; native
+swipe/anchor/read behavior needs the local-fixture UI regression tests as well.
+The hosted view excludes the surrounding app shell. Physical iPhone scrolling,
+streaming and thinking animation remain a required follow-up.
+
+Opt-in `AgentRenderDiagnostics` counters are compiled only in Debug and are off
+outside this test. They explain work (Agent body evaluations, message projection,
+message text construction, isolated row evaluations, geometry callbacks and
+snapshot publications). A drop in these counts alone does not establish improved
+frame responsiveness.
+
+## Reference result
+
+On monsoon, Xcode 26.5, Debug, iPhone 16e / iOS 26.5, clean repeat runs against
+`f534f76` plus counters and against the geometry/row isolation fix gave:
+
+| Phase | Before p95 / p99 (ms) | After p95 / p99 (ms) | Gaps >50 ms, before / after |
+| --- | ---: | ---: | ---: |
+| Idle scroll | 50.01 / 50.02 | 16.68 / 16.71 | 128 / 0 |
+| Thinking stationary | 33.33 / 81.92 | 28.91 / 38.35 | 22 / 2 |
+| Thinking scroll | 88.78 / 90.89 | 19.41 / 30.42 | 123 / 1 |
+
+Each phase lasted approximately 12 seconds. Content heights matched exactly.
+Busy-scroll Agent body/projection evaluations fell from 261 to 27; unchanged
+text constructions were zero in both versions. Geometry isolation alone removed
+the idle-scroll stalls; individual row isolation reduced activity-related gaps.
+These results support those two boundaries, without a Markdown cache or lazy
+layout change. Occasional simulator gaps remain; this does not replace device
+validation.

ios/Tests/Fixtures/agent_server.py

@@ -138,6 +138,18 @@ async def route(request):
         elif action == 'busy':
             busy = body.get('value', True)
             await broadcast(dict(type='activity', conversationId='fixture-root', activity=activity()))
+        elif action == 'progress':
+            busy = True
+            progress = dict(activity(), queued=body['queued'], backgroundWorkers=body['workers'],
+                            tools=[dict(id='local-review', name='review_transcript', status='running',
+                                        output=f"Checked {body['step']} local entries")])
+            await broadcast(dict(type='activity', conversationId='fixture-root', activity=progress))
+        elif action == 'edit-last':
+            cursor += 1
+            row = dict(messages[-1], content=body['content'],
+                       metadata=dict(messages[-1]['metadata'], entryId=cursor))
+            messages[-1] = row
+            await broadcast(dict(type='messages', **page([row])))
         elif action == 'read':
             read_cursor = cursor
             await broadcast(dict(type='read_state', sourceId=PUSH_SOURCE, cursor=str(read_cursor), updatedAt=stamp()))

ios/Tests/SybilPresentationTests/AgentPerformanceTests.swift

@@ -0,0 +1,142 @@
+import XCTest
+import SwiftUI
+@testable import Sybil
+
+/// Run on an iPhone simulator, with the real Agent view and deterministic local
+/// messages. Display-link delivery gaps measure main-run-loop responsiveness,
+/// not GPU presentation, touch latency, or physical-device frame rate.
+@MainActor
+final class AgentPerformanceTests: XCTestCase {
+    func testThinkingScrollResponsiveness() async throws {
+        let room = SybilAgentRoom()
+        var rows: [Message] = []
+        for index in 1...160 { rows.append(Self.message(index)) }
+        try room.receive(.messages(AgentPage(conversationId: "performance", messages: rows, cursor: "160", beforeCursor: nil, hasMore: false)), replay: true)
+        room.flush()
+        let host = UIHostingController(rootView: SybilAgentView(room: room, topInset: 64)
+            .background(SybilTheme.background).environment(\.colorScheme, .dark))
+        let scene = try XCTUnwrap(UIApplication.shared.connectedScenes.compactMap { $0 as? UIWindowScene }.first)
+        let window = UIWindow(windowScene: scene)
+        window.rootViewController = host
+        window.makeKeyAndVisible()
+        defer {
+            AgentRenderDiagnostics.enabled = false
+            window.isHidden = true
+            window.rootViewController = nil
+            room.stop()
+        }
+        host.view.frame = window.bounds
+        host.view.layoutIfNeeded()
+        try await Task.sleep(for: .seconds(2))
+        let scroll = try XCTUnwrap(findScroll(host.view))
+        XCTAssertGreaterThan(scroll.contentSize.height, 10_000)
+        // Move away from the pinned bottom before the controlled sweeps.
+        scroll.setContentOffset(CGPoint(x: 0, y: max(0, scroll.contentSize.height - scroll.bounds.height - 1200)), animated: false)
+        try await Task.sleep(for: .seconds(1))
+        AgentRenderDiagnostics.enabled = true
+        var reports: [[String: Any]] = []
+        for phase in ["idle-scroll", "thinking-stationary", "thinking-scroll"] {
+            if phase == "thinking-stationary" {
+                try room.receive(.activity("performance", busyActivity(step: 0)))
+                room.flush()
+                scroll.setContentOffset(CGPoint(x: 0, y: scroll.contentSize.height - scroll.bounds.height + scroll.adjustedContentInset.bottom), animated: false)
+                try await Task.sleep(for: .seconds(1))
+                XCTAssertTrue(room.snapshot.isTyping)
+            }
+            AgentRenderDiagnostics.counts = [:]
+            let sampler = AgentFrameSampler(scroll: phase == "thinking-stationary" ? nil : scroll)
+            sampler.start()
+            // Changing queue/worker/tool progress every 500 ms exercises real
+            // activity observation while the typing spinner remains active. No IO.
+            for step in 1...24 {
+                try await Task.sleep(for: .milliseconds(500))
+                if phase != "idle-scroll" {
+                    try room.receive(.activity("performance", busyActivity(step: step)))
+                }
+            }
+            var report = sampler.stop()
+            report["phase"] = phase
+            report["procedure"] = "mixed160-changing-activity-v1"
+            report["operations"] = AgentRenderDiagnostics.counts
+            report["contentHeight"] = scroll.contentSize.height
+            // iPhone 16e / iOS 26.5 / default text size reference geometry from
+            // the unoptimized view. A faster result must not shrink the content.
+            XCTAssertEqual(scroll.contentSize.height,
+                           phase == "idle-scroll" ? 39_181.333333 : 39_223.333333,
+                           accuracy: 1)
+            reports.append(report)
+        }
+        let data = try JSONSerialization.data(withJSONObject: reports, options: [.sortedKeys])
+        print("AGENT_PERFORMANCE_JSON " + String(decoding: data, as: UTF8.self))
+        let attachment = XCTAttachment(data: data, uniformTypeIdentifier: "public.json")
+        attachment.name = "agent-performance"; attachment.lifetime = .keepAlways; add(attachment)
+    }
+
+    private static func message(_ index: Int) -> Message {
+        let own = index % 3 == 0
+        let content = own
+            ? "Can you review step \(index)? Keep the scroll position and the **literal input** intact.\n\nInclude the next checks."
+            : "### Investigation \(index)\n\nThe worker checked the local transcript and found a repeatable result. This paragraph contains **emphasis**, `inline code`, and a [reference](https://example.com).\n\n- Preserve the reading position while new messages arrive.\n- Keep attachments, queued messages, and status updates visible.\n- Verify the result on the simulator before publishing.\n\n```swift\nlet item = messages[\(index)]\nrender(item)\n```\n\nThe next step is to compare the measurements and report any remaining limitations."
+        return Message(id: "perf-\(index)", createdAt: Date(timeIntervalSince1970: 1_700_000_000 + Double(index * 60)),
+                       role: own ? .user : .assistant, content: content,
+                       metadata: .object(["kind": .string("message"), "entryId": .string(String(index))]))
+    }
+
+    private func busyActivity(step: Int) -> AgentActivity {
+        AgentActivity(state: "thinking", isThinking: true, queued: 1 + step % 3,
+                      backgroundWorkers: 1 + step % 2,
+                      tools: [.init(id: "local-review", name: "review_transcript", status: "running",
+                                    output: "Checked \(step * 7) of 200 local entries; preparing batch \(step + 1).")])
+    }
+
+    private func findScroll(_ view: UIView) -> UIScrollView? {
+        if let scroll = view as? UIScrollView, scroll.contentSize.height > 10_000 { return scroll }
+        return view.subviews.lazy.compactMap { self.findScroll($0) }.first
+    }
+}
+
+@MainActor
+private final class AgentFrameSampler: NSObject {
+    private weak var scroll: UIScrollView?
+    private var link: CADisplayLink?
+    private var previous: CFTimeInterval?
+    private var started: CFTimeInterval = 0
+    private var gaps: [Double] = []
+    private var budgets: [Double] = []
+    private var origin: CGFloat = 0
+    private var scrollDistance: CGFloat = 0
+    init(scroll: UIScrollView?) { self.scroll = scroll }
+    func start() {
+        origin = scroll?.contentOffset.y ?? 0
+        started = CACurrentMediaTime()
+        let link = CADisplayLink(target: self, selector: #selector(frame(_:)))
+        link.preferredFrameRateRange = CAFrameRateRange(minimum: 60, maximum: 60, preferred: 60)
+        link.add(to: .main, forMode: .common)
+        self.link = link
+    }
+    @objc private func frame(_ link: CADisplayLink) {
+        let now = CACurrentMediaTime()
+        if let previous { gaps.append((now - previous) * 1000); budgets.append((link.targetTimestamp - link.timestamp) * 1000) }
+        previous = now
+        if let scroll {
+            // Constant-speed triangular sweep over 2400 points, one cycle / 8 s.
+            let phase = (now - started).truncatingRemainder(dividingBy: 8) / 4
+            let delta = CGFloat(phase <= 1 ? phase : 2 - phase) * 2400
+            let target = max(-scroll.adjustedContentInset.top, origin - delta)
+            scrollDistance += abs(target - scroll.contentOffset.y)
+            scroll.setContentOffset(CGPoint(x: 0, y: target), animated: false)
+        }
+    }
+    func stop() -> [String: Any] {
+        link?.invalidate(); link = nil
+        let sorted = gaps.sorted()
+        let budget = budgets.sorted()[budgets.count / 2]
+        func percentile(_ value: Double) -> Double { sorted[min(sorted.count - 1, Int(Double(sorted.count - 1) * value))] }
+        return ["seconds": CACurrentMediaTime() - started, "callbacks": gaps.count,
+                "medianBudgetMS": budget, "p50MS": percentile(0.5), "p95MS": percentile(0.95),
+                "p99MS": percentile(0.99), "maxMS": sorted.last ?? 0,
+                "over25MS": gaps.filter { $0 > 25 }.count, "over50MS": gaps.filter { $0 > 50 }.count,
+                "missedBudgetIntervals": gaps.reduce(0) { $0 + max(0, Int(($1 / budget).rounded()) - 1) },
+                "scrollDistance": scrollDistance]
+    }
+}

ios/Tests/SybilUITests/AgentUITests.swift

@@ -241,6 +241,24 @@ final class AgentUITests: XCTestCase {
         let state = try await control(["action": "state"])
         XCTAssertEqual((state["requests"] as? [String: Any])?.count, 4)
     }
+    func testBusyProgressAndSameIDMessageUpdate() async throws {
+        try await control(["action": "progress", "queued": 2, "workers": 1, "step": 7])
+        XCTAssertTrue(app.staticTexts["Sybil is thinking…"].waitForExistence(timeout: 5))
+        XCTAssertTrue(app.staticTexts["2 queued"].waitForExistence(timeout: 5))
+        try await control(["action": "progress", "queued": 3, "workers": 2, "step": 14])
+        XCTAssertTrue(app.staticTexts["3 queued"].waitForExistence(timeout: 5))
+        XCTAssertTrue(app.staticTexts["2 working"].exists)
+        // Same stable ID, changed content: the transcript boundary must update.
+        try await control(["action": "edit-last", "content": "**Revised response**\n\n[Updated reference](http://127.0.0.1:8799)"])
+        XCTAssertTrue(app.staticTexts["Revised response"].waitForExistence(timeout: 5))
+        XCTAssertTrue(app.links["Updated reference"].exists)
+        XCTAssertFalse(app.staticTexts["History message 3: local simulator fixture."].exists)
+        XCTAssertTrue(app.staticTexts["Sybil is thinking…"].exists)
+        try await control(["action": "busy", "value": false])
+        let stopped = XCTNSPredicateExpectation(predicate: NSPredicate(format: "exists == false"), object: app.staticTexts["Sybil is thinking…"])
+        await fulfillment(of: [stopped], timeout: 5)
+    }
+
     func testReduceMotionSend() async throws {
         try XCTSkipUnless(UIAccessibility.isReduceMotionEnabled, "Run with Simulator Reduce Motion enabled")
         send("reduce motion fixture")