test(app): add manual performance diagnostics (#32937)

This commit is contained in:
Luke Parker
2026-06-19 19:39:02 +02:00
committed by GitHub
parent 10ec856ff2
commit c6083a474c
26 changed files with 2656 additions and 3 deletions
@@ -0,0 +1,49 @@
import { benchmark, expect } from "../benchmark"
import { expectSessionTitle } from "../../utils/waits"
import { fixture } from "./session-timeline-stress.fixture"
import {
collectCachedRepaintTrace,
compressCachedRepaintTrace,
installCachedRepaintProbe,
waitForCachedRepaintWindow,
} from "./session-tab-repaint-probe"
import { waitForStableTimeline } from "./session-tab-switch-probe"
import {
installStressSessionTabs,
installTimelineSettings,
mockStressTimeline,
stressSessionHref,
} from "./timeline-test-helpers"
benchmark("samples cached session repaint after the click", async ({ page, report }) => {
benchmark.setTimeout(120_000)
await mockStressTimeline(page)
await installStressSessionTabs(page)
await installTimelineSettings(page)
await page.goto(stressSessionHref(fixture.targetID))
await expectSessionTitle(page, fixture.expected.targetTitle)
await waitForStableTimeline(page, fixture.expected.targetMessageIDs.at(-1)!)
await page
.locator(`[data-slot="titlebar-tabs"] a[href="${stressSessionHref(fixture.sourceID)}"]`)
.first()
.click()
await expectSessionTitle(page, fixture.expected.sourceTitle)
await waitForStableTimeline(page, fixture.expected.sourceMessageIDs.at(-1)!)
await installCachedRepaintProbe(page, {
targetHref: stressSessionHref(fixture.targetID),
destination: fixture.messages[fixture.targetID].map((message) => message.info.id),
source: fixture.messages[fixture.sourceID].map((message) => message.info.id),
last: fixture.expected.targetMessageIDs.at(-1)!,
windowMs: 1_000,
})
await page
.locator(`[data-slot="titlebar-tabs"] a[href="${stressSessionHref(fixture.targetID)}"]`)
.first()
.click()
await Promise.all([expectSessionTitle(page, fixture.expected.targetTitle), waitForCachedRepaintWindow(page, 1_000)])
const result = await collectCachedRepaintTrace(page)
report(compressCachedRepaintTrace(result))
expect(result.samples.length).toBeGreaterThan(0)
})
@@ -0,0 +1,251 @@
import type { Page } from "@playwright/test"
type CachedRepaintTrace = {
timeOriginEpochMs: number
startedAtPerformanceMs: number
samples: {
observedAtMs: number
root: number | undefined
scrollTop: number
scrollHeight: number
bottomErrorPx: number | undefined
last: boolean
rows: { key: string | undefined; node: number; top: number; bottom: number }[]
mounted: number
center: string | undefined
destination: string[]
source: string[]
}[]
mutations: { observedAtMs: number; changed: { type: string; node: number }[] }[]
shifts: { occurredAtMs: number; value: number }[]
windowMs: number
running: boolean
stop: () => void
}
export async function installCachedRepaintProbe(
page: Page,
input: { targetHref: string; destination: string[]; source: string[]; last: string; windowMs: number },
) {
await page.evaluate(({ targetHref, destination, source, last, windowMs }) => {
const destinationIDs = new Set(destination)
const sourceIDs = new Set(source)
const nodeIDs = new WeakMap<Node, number>()
let nextNodeID = 1
const id = (node: Node) => {
const current = nodeIDs.get(node)
if (current) return current
nodeIDs.set(node, nextNodeID)
return nextNodeID++
}
const state: CachedRepaintTrace = {
timeOriginEpochMs: performance.timeOrigin,
startedAtPerformanceMs: 0,
samples: [],
mutations: [],
shifts: [],
windowMs,
running: false,
stop: () => {},
}
const recordShifts = (entries: PerformanceEntry[]) => {
if (!state.running) return
state.shifts.push(
...entries
.map((entry) => {
if (
entry.startTime < state.startedAtPerformanceMs ||
entry.startTime > state.startedAtPerformanceMs + state.windowMs
)
return
return {
occurredAtMs: entry.startTime - state.startedAtPerformanceMs,
value: (entry as PerformanceEntry & { value: number }).value,
}
})
.filter((entry): entry is { occurredAtMs: number; value: number } => entry !== undefined),
)
}
const shiftObserver = new PerformanceObserver((entries) => recordShifts(entries.getEntries()))
shiftObserver.observe({ type: "layout-shift" })
const recordMutations = (entries: MutationRecord[]) => {
if (!state.running) return
const observedAtMs = performance.now() - state.startedAtPerformanceMs
if (observedAtMs > state.windowMs) return
const changed = entries.flatMap((entry) => [
...[...entry.addedNodes].map((node) => ({ type: "add", node: id(node) })),
...[...entry.removedNodes].map((node) => ({ type: "remove", node: id(node) })),
])
if (changed.length) state.mutations.push({ observedAtMs, changed })
}
const mutationObserver = new MutationObserver(recordMutations)
mutationObserver.observe(document.documentElement, { childList: true, subtree: true })
state.stop = () => {
recordShifts(shiftObserver.takeRecords())
recordMutations(mutationObserver.takeRecords())
state.running = false
shiftObserver.disconnect()
mutationObserver.disconnect()
}
const sample = () => {
if (!state.running) return
setTimeout(() => {
if (!state.running) return
const observedAtMs = performance.now() - state.startedAtPerformanceMs
if (observedAtMs > state.windowMs) return
const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
element.querySelector("[data-timeline-row]"),
)
if (root) {
const view = root.getBoundingClientRect()
const rows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")]
.map((element) => ({
key: element.dataset.timelineKey,
node: id(element),
rect: element.getBoundingClientRect(),
}))
.filter((item) => item.rect.bottom > view.top && item.rect.top < view.bottom)
.map((item) => ({
key: item.key,
node: item.node,
top: item.rect.top - view.top,
bottom: item.rect.bottom - view.top,
}))
const messages = [...root.querySelectorAll<HTMLElement>("[data-message-id]")]
.filter((element) => {
const rect = element.getBoundingClientRect()
return rect.bottom > view.top && rect.top < view.bottom
})
.map((element) => element.dataset.messageId!)
const spacer = root.querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')?.getBoundingClientRect()
state.samples.push({
observedAtMs,
root: id(root),
scrollTop: root.scrollTop,
scrollHeight: root.scrollHeight,
bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined,
last: messages.includes(last),
rows,
mounted: root.querySelectorAll("[data-timeline-key]").length,
center: document
.elementFromPoint(view.left + view.width / 2, view.top + view.height / 2)
?.textContent?.slice(0, 80),
destination: messages.filter((messageID) => destinationIDs.has(messageID)),
source: messages.filter((messageID) => sourceIDs.has(messageID)),
})
} else {
state.samples.push({
observedAtMs,
root: undefined,
scrollTop: 0,
scrollHeight: 0,
bottomErrorPx: undefined,
last: false,
rows: [],
mounted: 0,
center: document.elementFromPoint(innerWidth / 2, innerHeight / 2)?.textContent?.slice(0, 80),
destination: [],
source: [],
})
}
requestAnimationFrame(sample)
}, 0)
}
document.addEventListener(
"click",
(event) => {
const link = event.target instanceof Element ? event.target.closest("a") : undefined
if (link?.getAttribute("href") !== targetHref) return
state.startedAtPerformanceMs = performance.now()
state.running = true
requestAnimationFrame(sample)
},
{ capture: true, once: true },
)
;(window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash = state
}, input)
}
export function layoutShiftSample(entry: Pick<PerformanceEntry, "startTime"> & { value: number }, started: number) {
if (entry.startTime < started) return
return { occurredAtMs: entry.startTime - started, value: entry.value }
}
export async function waitForCachedRepaintWindow(page: Page, durationMs: number) {
await page.waitForFunction((durationMs) => {
const state = (window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash
return !!state?.running && performance.now() - state.startedAtPerformanceMs >= durationMs
}, durationMs)
}
export async function collectCachedRepaintTrace(page: Page) {
return page.evaluate(() => {
const state = (window as Window & { __cachedFlash?: CachedRepaintTrace }).__cachedFlash!
state.stop()
return state
})
}
export function summarizeCachedRepaintTrace(trace: CachedRepaintTrace) {
const roots = trace.samples.map((sample) => sample.root)
const bottomErrors = trace.samples.flatMap((sample) =>
sample.bottomErrorPx === undefined ? [] : [Math.abs(sample.bottomErrorPx)],
)
const category = (sample: CachedRepaintTrace["samples"][number]) => {
if (sample.source.length) return "source"
if (sample.root === undefined || sample.rows.length === 0) return "blank"
if (!sample.destination.length) return "unknown"
if (sample.last && Math.abs(sample.bottomErrorPx ?? Infinity) <= 1) return "correct"
return "wrongDestination"
}
return {
samples: trace.samples.length,
durationMs: trace.samples.at(-1)?.observedAtMs ?? 0,
firstSampleObservedMs: trace.samples[0]?.observedAtMs,
firstSampleCorrect: trace.samples[0] ? category(trace.samples[0]) === "correct" : false,
blankSamples: trace.samples.filter((sample) => category(sample) === "blank").length,
sourceSamples: trace.samples.filter((sample) => category(sample) === "source").length,
wrongDestinationSamples: trace.samples.filter((sample) => category(sample) === "wrongDestination").length,
unknownSamples: trace.samples.filter((sample) => category(sample) === "unknown").length,
rootChanges: roots.slice(1).filter((root, index) => root !== roots[index]).length,
mountedMin: trace.samples.length ? Math.min(...trace.samples.map((sample) => sample.mounted)) : 0,
mountedMax: Math.max(...trace.samples.map((sample) => sample.mounted)),
maxBottomErrorPx: Math.max(0, ...bottomErrors),
mutationBatches: trace.mutations.length,
addedNodes: trace.mutations.reduce(
(sum, batch) => sum + batch.changed.filter((change) => change.type === "add").length,
0,
),
removedNodes: trace.mutations.reduce(
(sum, batch) => sum + batch.changed.filter((change) => change.type === "remove").length,
0,
),
layoutShiftValueSum: trace.shifts.reduce((sum, shift) => sum + shift.value, 0),
maxLayoutShiftValue: Math.max(0, ...trace.shifts.map((shift) => shift.value)),
}
}
export function compressCachedRepaintTrace(trace: CachedRepaintTrace) {
const samples: {
observedAtMs: number[]
state: Omit<CachedRepaintTrace["samples"][number], "observedAtMs">
}[] = []
for (const sample of trace.samples) {
const { observedAtMs, ...state } = sample
const previous = samples.at(-1)
if (previous && JSON.stringify(previous.state) === JSON.stringify(state)) {
previous.observedAtMs.push(observedAtMs)
continue
}
samples.push({ observedAtMs: [observedAtMs], state })
}
return {
timeOriginEpochMs: trace.timeOriginEpochMs,
startedAtPerformanceMs: trace.startedAtPerformanceMs,
windowMs: trace.windowMs,
summary: summarizeCachedRepaintTrace(trace),
samples,
mutations: trace.mutations,
shifts: trace.shifts,
}
}
@@ -0,0 +1,79 @@
import type { Page } from "@playwright/test"
import { expectSessionTitle } from "../../utils/waits"
import { benchmark, expect, withBenchmarkPage } from "../benchmark"
import { fixture } from "./session-timeline-stress.fixture"
import { installStressSessionTabs, mockStressTimeline, stressSessionHref } from "./timeline-test-helpers"
import { measureSessionSwitch, waitForStableTimeline } from "./session-tab-switch-probe"
type Result = Awaited<ReturnType<typeof measureSessionSwitch>>
benchmark("benchmarks cold and hot session tab switching", async ({ browser, report }, testInfo) => {
benchmark.setTimeout(180_000)
const results = { cold: [] as Result[], hot: [] as Result[] }
for (const mode of ["cold", "hot"] as const) {
for (let run = 0; run < 5; run++) {
results[mode].push(
await withBenchmarkPage(browser, `session-tab-switch-${mode}-${run}`, (page) => trial(page, mode), testInfo),
)
}
}
report({ results, summary: summarize(results) })
})
async function trial(page: Page, mode: "cold" | "hot") {
await mockStressTimeline(page)
await installStressSessionTabs(page)
if (mode === "hot") {
await page.goto(stressSessionHref(fixture.targetID))
await expectSessionTitle(page, fixture.expected.targetTitle)
await waitForStableTimeline(page, fixture.expected.targetMessageIDs.at(-1)!)
await switchSession(page, fixture.sourceID, fixture.expected.sourceTitle)
} else {
await page.goto(stressSessionHref(fixture.sourceID))
await expectSessionTitle(page, fixture.expected.sourceTitle)
}
await waitForStableTimeline(page, fixture.expected.sourceMessageIDs.at(-1)!)
const destinationIDs = fixture.messages[fixture.targetID].map((message) => message.info.id)
const sourceIDs = fixture.messages[fixture.sourceID].map((message) => message.info.id)
const lastID = fixture.expected.targetMessageIDs.at(-1)!
const href = stressSessionHref(fixture.targetID)
const result = await measureSessionSwitch(page, {
destinationIDs,
sourceIDs,
lastID,
href,
switch: () => switchSession(page, fixture.targetID, fixture.expected.targetTitle),
})
return result
}
function summarize(results: Record<"cold" | "hot", Result[]>) {
const stats = (values: (number | null)[]) => {
const sorted = values.filter((value): value is number => value !== null).sort((a, b) => a - b)
return {
min: sorted[0] ?? null,
median: sorted[Math.floor(sorted.length / 2)] ?? null,
max: sorted.at(-1) ?? null,
missing: values.length - sorted.length,
}
}
return Object.fromEntries(
Object.entries(results).map(([mode, values]) => [
mode,
{
firstDestinationObservedMs: stats(values.map((value) => value.firstDestinationObservedMs)),
firstCorrectObservedMs: stats(values.map((value) => value.firstCorrectObservedMs)),
stableObservedMs: stats(values.map((value) => value.stableObservedMs)),
},
]),
)
}
async function switchSession(page: Page, sessionID: string, title: string) {
const href = stressSessionHref(sessionID)
const tab = page.locator(`[data-slot="titlebar-tabs"] a[href="${href}"]`).first()
await expect(tab).toBeVisible()
await tab.click()
await expectSessionTitle(page, title)
}
@@ -0,0 +1,46 @@
export type SessionSwitchSample = {
observedAtMs: number
destination: string[]
source: string[]
hasVisibleRows: boolean
last: boolean
bottomErrorPx?: number
}
export function classifySessionSwitch(samples: SessionSwitchSample[]) {
const firstDestination = samples.findIndex((sample) => sample.destination.length > 0)
const firstCorrect = samples.findIndex(isCorrectDestination)
const stable = samples.findIndex((_, index) => isStableSessionSwitch(samples.slice(index, index + 3)))
return {
firstDestinationObservedMs: samples[firstDestination]?.observedAtMs ?? null,
firstCorrectObservedMs: samples[firstCorrect]?.observedAtMs ?? null,
stableObservedMs: samples[stable + 2]?.observedAtMs ?? null,
wrongDestinationSamples: samples
.slice(firstDestination)
.filter((sample) => sample.destination.length > 0 && !sample.last).length,
blankSamples: samples.filter((sample) => !sample.hasVisibleRows).length,
unknownSamples: samples.filter(
(sample) => sample.hasVisibleRows && sample.destination.length === 0 && sample.source.length === 0,
).length,
sourceSamples: samples.filter((sample) => sample.source.length > 0).length,
}
}
export function isCorrectDestination(sample: SessionSwitchSample) {
return (
sample.destination.length > 0 &&
sample.source.length === 0 &&
sample.last &&
Math.abs(sample.bottomErrorPx ?? Infinity) <= 1
)
}
export function isStableSessionSwitch(samples: SessionSwitchSample[]) {
return samples.length === 3 && samples.every(isCorrectDestination)
}
export function isStableDestination(samples: Pick<SessionSwitchSample, "last" | "bottomErrorPx">[]) {
return (
samples.length === 3 && samples.every((sample) => sample.last && Math.abs(sample.bottomErrorPx ?? Infinity) <= 1)
)
}
@@ -0,0 +1,152 @@
import { expect, type Page } from "@playwright/test"
import { classifySessionSwitch, isStableDestination, type SessionSwitchSample } from "./session-tab-switch-metrics"
type SessionSwitchProbe = {
samples: SessionSwitchSample[]
stop: () => void
}
async function installSessionSwitchProbe(
page: Page,
input: { destinationIDs: string[]; sourceIDs: string[]; lastID: string; href: string },
) {
await page.evaluate(({ destinationIDs, sourceIDs, lastID, href }) => {
const destination = new Set(destinationIDs)
const source = new Set(sourceIDs)
const samples: SessionSwitchSample[] = []
let started: number | undefined
let running = true
const sample = () => {
if (!running || started === undefined) return
setTimeout(() => {
if (!running || started === undefined) return
const observedAtMs = performance.now() - started
const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
element.querySelector("[data-timeline-row]"),
)
if (root) {
const view = root.getBoundingClientRect()
const visible = [...root.querySelectorAll<HTMLElement>("[data-message-id]")]
.filter((element) => {
const rect = element.getBoundingClientRect()
return rect.bottom > view.top && rect.top < view.bottom
})
.map((element) => element.dataset.messageId!)
const hasVisibleRows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")].some((element) => {
const rect = element.getBoundingClientRect()
return rect.bottom > view.top && rect.top < view.bottom
})
const spacer = root.querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')?.getBoundingClientRect()
samples.push({
observedAtMs,
destination: visible.filter((id) => destination.has(id)),
source: visible.filter((id) => source.has(id)),
hasVisibleRows,
last: visible.includes(lastID),
bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined,
})
} else {
samples.push({ observedAtMs, destination: [], source: [], hasVisibleRows: false, last: false })
}
requestAnimationFrame(sample)
}, 0)
}
document.addEventListener(
"click",
(event) => {
const link = event.target instanceof Element ? event.target.closest("a") : undefined
if (link?.getAttribute("href") !== href) return
started = performance.now()
requestAnimationFrame(sample)
},
{ capture: true, once: true },
)
;(window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe = {
samples,
stop: () => {
running = false
},
}
}, input)
}
async function waitForStableSessionSwitch(page: Page) {
await page.waitForFunction(() => {
const samples = (window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe?.samples
if (!samples) return false
return samples.some((_, index) => {
const stable = samples.slice(index, index + 3)
return (
stable.length === 3 &&
stable.every(
(sample) =>
sample.destination.length > 0 &&
sample.source.length === 0 &&
sample.last &&
Math.abs(sample.bottomErrorPx ?? Infinity) <= 1,
)
)
})
})
}
async function collectSessionSwitchResult(page: Page) {
const samples = await page.evaluate(() => {
const probe = (window as Window & { __sessionSwitchProbe?: SessionSwitchProbe }).__sessionSwitchProbe!
probe.stop()
return probe.samples
})
return classifySessionSwitch(samples)
}
export async function measureSessionSwitch(
page: Page,
input: { destinationIDs: string[]; sourceIDs: string[]; lastID: string; href: string; switch: () => Promise<void> },
) {
const { switch: run, ...probe } = input
await installSessionSwitchProbe(page, probe)
await run()
await waitForStableSessionSwitch(page)
return collectSessionSwitchResult(page)
}
export async function waitForStableTimeline(page: Page, lastID: string) {
const samples: Pick<SessionSwitchSample, "last" | "bottomErrorPx">[] = []
await expect
.poll(
async () => {
samples.push(
await page.evaluate(
(lastID) =>
new Promise<Pick<SessionSwitchSample, "last" | "bottomErrorPx">>((resolve) => {
requestAnimationFrame(() =>
setTimeout(() => {
const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
element.querySelector("[data-timeline-row]"),
)
if (!root) {
resolve({ last: false })
return
}
const view = root.getBoundingClientRect()
const last = [...root.querySelectorAll<HTMLElement>("[data-message-id]")].some((element) => {
if (element.dataset.messageId !== lastID) return false
const rect = element.getBoundingClientRect()
return rect.bottom > view.top && rect.top < view.bottom
})
const spacer = root
.querySelector<HTMLElement>('[data-timeline-row="bottom-spacer"]')
?.getBoundingClientRect()
resolve({ last, bottomErrorPx: spacer ? spacer.bottom - view.bottom : undefined })
}, 0),
)
}),
lastID,
),
)
return isStableDestination(samples.slice(-3))
},
{ timeout: 30_000, intervals: [0] },
)
.toBe(true)
}
@@ -0,0 +1,488 @@
import { base64Encode } from "@opencode-ai/core/util/encode"
import type { Page } from "@playwright/test"
import { mockOpenCodeServer } from "../../utils/mock-server"
import { expectAppVisible, expectSessionTitle } from "../../utils/waits"
import { expect } from "../benchmark"
const directory = "C:/OpenCode/TimelineStateRegression"
const projectID = "proj_timeline_state_regression"
const sessionID = "ses_timeline_state_regression"
const userMessageID = "msg_user_regression"
const assistantMessageID = "msg_assistant_regression"
const editPartID = "prt_0001_edit"
export const textPartID = "prt_9999_text"
const title = "Timeline collapse state regression"
const model = { providerID: "opencode", modelID: "claude-opus-4-6", variant: "max" }
type EventPayload = {
directory: string
payload: Record<string, unknown>
}
const userMessage = {
info: {
id: userMessageID,
sessionID,
role: "user",
time: { created: 1700000000000 },
summary: { diffs: [] },
agent: "build",
model,
},
parts: [
{
id: "prt_user_text",
sessionID,
messageID: userMessageID,
type: "text",
text: "Please edit the file.",
},
],
}
const editPart = {
id: editPartID,
sessionID,
messageID: assistantMessageID,
type: "tool",
callID: "call_edit_regression",
tool: "edit",
state: {
status: "completed",
input: { filePath: "src/regression.ts" },
output: "Edited src/regression.ts",
title: "src/regression.ts",
metadata: {
filediff: {
file: "src/regression.ts",
additions: 1,
deletions: 1,
before: "export const value = 'before'\n",
after: "export const value = 'after'\n",
},
diff: "diff --git a/src/regression.ts b/src/regression.ts\n-export const value = 'before'\n+export const value = 'after'\n",
},
time: { start: 1700000001000, end: 1700000002000 },
},
}
const streamedTextPart = {
id: textPartID,
sessionID,
messageID: assistantMessageID,
type: "text",
text: "Streaming added a later assistant text part.",
}
const assistantMessage = {
info: {
id: assistantMessageID,
sessionID,
role: "assistant",
time: { created: 1700000001000 },
parentID: userMessageID,
modelID: model.modelID,
providerID: model.providerID,
mode: "build",
agent: "build",
path: { cwd: directory, root: directory },
cost: 0.01,
tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
variant: "max",
},
parts: [editPart],
}
export async function setupTimelineBenchmark(page: Page, options: { historyTurns: number; eventBatch: number }) {
const events: EventPayload[] = []
let eventBatch = options.eventBatch
await mockOpenCodeServer(page, {
directory,
project: project(),
provider: provider(),
sessions: [session()],
pageMessages: () => ({
items: [
...Array.from({ length: options.historyTurns }, (_, index) => performanceTurn(index)).flat(),
userMessage,
assistantMessage,
],
}),
events: () => events.splice(0, eventBatch),
eventRetry: 16,
})
await page.addInitScript(() => {
localStorage.setItem(
"settings.v3",
JSON.stringify({
general: {
editToolPartsExpanded: true,
shellToolPartsExpanded: true,
showReasoningSummaries: true,
showSessionProgressBar: true,
},
}),
)
})
await page.setViewportSize({ width: 1366, height: 768 })
const scroller = page.locator(".scroll-view__viewport", { has: page.locator("[data-timeline-row]") })
const text = page.locator(`[data-timeline-part-id="${textPartID}"]`).first()
await page.goto(`/${base64Encode(directory)}/session/${sessionID}`)
await expectSessionTitle(page, title)
await expectAppVisible(scroller)
return {
scroller,
text,
transport: {
enqueue(payload: EventPayload | EventPayload[]) {
events.push(...(Array.isArray(payload) ? payload : [payload]))
},
pendingCount() {
return events.length
},
releaseAll() {
eventBatch = events.length
},
},
async scrollToBottom() {
await scroller.evaluate((element) => {
element.scrollTop = element.scrollHeight
})
},
async waitForStableGeometry() {
await expect
.poll(() => scroller.evaluate((element) => element.scrollHeight - element.clientHeight - element.scrollTop))
.toBeLessThanOrEqual(1)
await page.waitForFunction((partID) => {
const root = [...document.querySelectorAll<HTMLElement>(".scroll-view__viewport")].find((element) =>
element.querySelector(`[data-timeline-part-id="${partID}"]`),
)
if (!root) return false
return new Promise<boolean>((resolve) => {
const height = root.scrollHeight
requestAnimationFrame(() =>
requestAnimationFrame(() =>
resolve(root.scrollHeight === height && root.scrollHeight - root.clientHeight - root.scrollTop <= 1),
),
)
})
}, textPartID)
},
}
}
export function buildInitialStreamEvent(deltaCount: number): EventPayload {
return {
directory,
payload: {
type: "message.part.updated",
properties: {
part: {
...streamedTextPart,
text: `Streaming${streamChunk(0, deltaCount + 1)}\n\n\`\`\`ts\nconst initial = true\n\`\`\``,
},
},
},
}
}
export function buildStreamDeltaEvents(deltaCount: number): EventPayload[] {
return Array.from({ length: deltaCount }, (_, index) => ({
directory,
payload: {
type: "message.part.delta",
properties: {
messageID: assistantMessageID,
partID: textPartID,
field: "text",
delta: streamChunk(index + 1, deltaCount + 1),
},
},
}))
}
function performanceTurn(index: number) {
const suffix = String(index).padStart(4, "0")
const userID = `msg_0000_${suffix}_a_user`
const assistantID = `msg_0000_${suffix}_b_assistant`
const before = historicalSource(index, false)
const after = historicalSource(index, true)
const parts = [
...(index % 5 === 0
? [
{
id: `prt_0000_${suffix}_reasoning`,
sessionID,
messageID: assistantID,
type: "reasoning",
text: `Reviewing the existing implementation. ${"constraint analysis ".repeat(20)}`,
time: { start: 1690000001000 + index * 2_000, end: 1690000001200 + index * 2_000 },
},
]
: []),
{
id: `prt_0000_${suffix}_assistant`,
sessionID,
messageID: assistantID,
type: "text",
text: historicalMarkdown(index),
},
...(index % 8 === 0
? [
{
id: `prt_0000_${suffix}_edit`,
sessionID,
messageID: assistantID,
type: "tool",
callID: `call_0000_${suffix}_edit`,
tool: "edit",
state: {
status: "completed",
input: { filePath: `src/history-${index}.ts` },
output: `Edited src/history-${index}.ts`,
title: `src/history-${index}.ts`,
metadata: {
filediff: { file: `src/history-${index}.ts`, additions: 48, deletions: 48, before, after },
},
time: { start: 1690000001200 + index * 2_000, end: 1690000001400 + index * 2_000 },
},
},
]
: []),
...(index % 12 === 0
? [
{
id: `prt_0000_${suffix}_write`,
sessionID,
messageID: assistantID,
type: "tool",
callID: `call_0000_${suffix}_write`,
tool: "write",
state: {
status: "completed",
input: { filePath: `src/generated-${index}.tsx`, content: after },
output: `Wrote src/generated-${index}.tsx`,
title: `src/generated-${index}.tsx`,
metadata: {
filediff: { file: `src/generated-${index}.tsx`, additions: 32, deletions: 0, before: "", after },
},
time: { start: 1690000001400 + index * 2_000, end: 1690000001500 + index * 2_000 },
},
},
]
: []),
...(index % 16 === 0
? [
{
id: `prt_0000_${suffix}_patch`,
sessionID,
messageID: assistantID,
type: "tool",
callID: `call_0000_${suffix}_patch`,
tool: "apply_patch",
state: {
status: "completed",
input: { patchText: realisticPatch(index) },
output: "Success. Updated src/components/SessionCard.tsx",
title: "src/components/SessionCard.tsx",
metadata: {
files: [
{
filePath: "src/components/SessionCard.tsx",
relativePath: "src/components/SessionCard.tsx",
type: "update",
additions: 8,
deletions: 3,
patch: realisticPatch(index),
before,
after,
},
],
},
time: { start: 1690000001500 + index * 2_000, end: 1690000001700 + index * 2_000 },
},
},
]
: []),
]
return [
{
info: {
id: userID,
sessionID,
role: "user",
time: { created: 1690000000000 + index * 2_000 },
summary: { diffs: [] },
agent: "build",
model,
},
parts: [
{
id: `prt_0000_${suffix}_user`,
sessionID,
messageID: userID,
type: "text",
text: `Historical prompt ${index}`,
},
],
},
{
info: {
id: assistantID,
sessionID,
role: "assistant",
time: { created: 1690000001000 + index * 2_000, completed: 1690000001500 + index * 2_000 },
parentID: userID,
modelID: model.modelID,
providerID: model.providerID,
mode: "build",
agent: "build",
path: { cwd: directory, root: directory },
cost: 0.01,
tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
variant: "max",
finish: "stop",
},
parts,
},
]
}
function historicalMarkdown(index: number) {
const code = `import { For, Show, createSignal } from "solid-js"
type SessionRow = { id: string; title: string; active: boolean }
export function SessionList(props: { rows: SessionRow[] }) {
const [selected, setSelected] = createSignal<string>()
return (
<section aria-label="Sessions">
<For each={props.rows}>{(row) => (
<button classList={{ active: row.active }} onClick={() => setSelected(row.id)}>
<Show when={selected() === row.id} fallback={row.title}>{row.title.toUpperCase()}</Show>
</button>
)}</For>
</section>
)
}`
return `## Session renderer review ${index}
The active session keeps **semantic row identity** while reconciling measured content. See [Solid documentation](https://docs.solidjs.com/) and the inline \`measureElement(node)\` call.
| Concern | Current behavior | Verification |
| --- | --- | --- |
| streaming | appends Markdown blocks | painted frames |
| geometry | anchors visible rows | DOM coordinates |
| tools | preserves expanded state | keyed remount probe |
> Long sessions combine Markdown, syntax highlighting, tool output, and asynchronously rendered diffs.
${index % 4 === 0 ? `\`\`\`tsx\n${code}\n\`\`\`\n\n\`\`\`bash\nbun typecheck\nbun test --preload ./happydom.ts ./src/pages/session\ngit diff --check\n\`\`\`` : "- preserve the viewport anchor\n- avoid replacing stable Markdown nodes\n- process provider deltas without blocking input"}`
}
function historicalSource(index: number, updated: boolean) {
const method = updated ? "toLocaleUpperCase(props.locale)" : "toUpperCase()"
const limit = updated ? 24 : 20
return `import { createMemo, For } from "solid-js"
type Message = {
id: string
role: "user" | "assistant"
text: string
tokens: { input: number; output: number }
}
export function MessageSummary(props: { messages: Message[]; locale: string }) {
const visible = createMemo(() => props.messages.filter((message) => message.text.trim()).slice(-${limit}))
const total = createMemo(() => visible().reduce((sum, message) => sum + message.tokens.output, 0))
return (
<article data-session-index="${index}">
<header>{total().toLocaleString(props.locale)} output tokens</header>
<For each={visible()}>{(message) => <p data-role={message.role}>{message.text.${method}}</p>}</For>
</article>
)
}
`
}
function realisticPatch(index: number) {
return `*** Begin Patch
*** Update File: src/components/SessionCard.tsx
@@
-const title = props.session.title.toUpperCase()
-const messages = props.messages.slice(-20)
+const title = props.session.title.toLocaleUpperCase(props.locale)
+const messages = props.messages.filter((message) => message.text.trim()).slice(-24)
+const outputTokens = messages.reduce((sum, message) => sum + message.tokens.output, 0)
@@
- <h2>{title}</h2>
+ <h2 data-session-index="${index}">{title}</h2>
+ <span>{outputTokens.toLocaleString(props.locale)} output tokens</span>
*** End Patch`
}
export function streamChunk(index: number, count: number) {
if (index === 0) return `\n\n## Implementation plan\n\nStreaming **bold analysis`
if (index === count - 1)
return `\n\`\`\`\n\n## Verification\n\n- **Typecheck:** passed\n- **Timeline geometry:** stable\n- **Streaming output:** benchmark-complete <!-- stream-${index} -->`
const section = Math.floor(index / 18) + 1
const fragments = [
` continues across three`,
` or four word`,
` provider deltas and`,
` closes in this fragment**. <!-- stream-${index} -->\n\n`,
`| Concern | State`,
` | Verification |\n|`,
` --- | ---`,
` | --- |\n|`,
` markdown | incremental |`,
` painted frames | <!-- stream-${index} -->\n\n`,
`\`\`\`tsx\nconst row: SessionRow`,
` = rows[index] ??`,
` fallback\nconst title =`,
` row.title.toLocaleUpperCase(locale)\n`,
`const selected = createMemo(()`,
` => row.id ===`,
` activeID()) // stream-${index}\n`,
`// stream-${index}\n\`\`\`\n\n### Iteration ${section}\n\nStreaming **bold analysis`,
]
return fragments[(index - 1) % fragments.length]!
}
function project() {
return {
id: projectID,
worktree: directory,
vcs: "git",
name: "timeline-state-regression",
time: { created: 1700000000000, updated: 1700000000000 },
sandboxes: [],
}
}
function session() {
return {
id: sessionID,
slug: "timeline-state-regression",
projectID,
directory,
title,
version: "dev",
time: { created: 1700000000000, updated: 1700000000000 },
}
}
function provider() {
return {
all: [
{
id: "opencode",
name: "OpenCode",
models: { "claude-opus-4-6": { id: "claude-opus-4-6", name: "Claude Opus 4.6", limit: { context: 200_000 } } },
},
],
connected: ["opencode"],
default: { providerID: "opencode", modelID: "claude-opus-4-6" },
}
}
@@ -0,0 +1,85 @@
import { benchmark, benchmarkDiagnostics, expect } from "../benchmark"
import {
buildInitialStreamEvent,
buildStreamDeltaEvents,
setupTimelineBenchmark,
textPartID,
} from "./session-timeline-benchmark.fixture"
import { startTimelineProfile } from "./session-timeline-profile"
import {
collectTimelineStreamMetrics,
installTimelineStreamProbe,
startTimelineStreamProbe,
} from "./session-timeline-stream-probe"
benchmark.describe("performance: session timeline streaming", () => {
benchmark("streams assistant text without remounting or oscillating", async ({ page, report }) => {
benchmark.setTimeout(480_000)
const cpuThrottle = Number(process.env.TIMELINE_CPU_THROTTLE ?? 30)
const deltaCount = Number(process.env.TIMELINE_DELTA_COUNT ?? 160)
const historyTurns = Number(process.env.TIMELINE_HISTORY_TURNS ?? 320)
const eventBatch = Number(process.env.TIMELINE_EVENT_BATCH ?? 1)
const minimal = process.env.TIMELINE_MINIMAL === "1"
const profileCPU = process.env.TIMELINE_CPU_PROFILE === "1"
const profileVisual = !minimal && profileCPU && process.env.TIMELINE_VISUAL_PROFILE !== "0"
const fixture = await setupTimelineBenchmark(page, {
historyTurns,
eventBatch,
})
fixture.transport.enqueue(buildInitialStreamEvent(deltaCount))
const contentStart = performance.now()
await expect(fixture.text).toBeVisible()
await expect(fixture.text).toContainText("Implementation plan")
const initialContentObservedMs = performance.now() - contentStart
await fixture.scrollToBottom()
await fixture.waitForStableGeometry()
const profile = await startTimelineProfile(page, { cpuThrottle, profileCPU })
await installTimelineStreamProbe(page, { textPartID, finalIndex: deltaCount, profileVisual, minimal })
const deltas = buildStreamDeltaEvents(deltaCount)
await startTimelineStreamProbe(page)
fixture.transport.enqueue(deltas)
await page.waitForFunction(
(finalIndex) =>
(
window as Window & {
__timelineStreamBenchmark?: { applied: { index: number }[] }
}
).__timelineStreamBenchmark?.applied.some((value) => value.index === finalIndex),
deltaCount,
{ timeout: 420_000 },
)
await expect(fixture.text).toContainText("benchmark-complete")
await expect(fixture.text).toContainText("Streaming")
await fixture.waitForStableGeometry()
const metrics = await collectTimelineStreamMetrics(page, {
textPartID,
finalIndex: deltaCount,
navigations: benchmarkDiagnostics(page).navigations,
})
const delivered = deltas.length - fixture.transport.pendingCount()
await profile.stop()
report(
{
endToEndInitialContentObservedMs: initialContentObservedMs,
...metrics,
deliveredDeltas: delivered,
pendingDeltas: fixture.transport.pendingCount(),
},
{
cpuThrottle,
profileCPU,
profileVisual,
minimal,
queuedDeltas: deltas.length,
historyTurns,
eventBatch,
},
)
await profile.reset()
})
})
@@ -0,0 +1,40 @@
import type { CDPSession, Page } from "@playwright/test"
export async function startTimelineProfile(page: Page, options: { cpuThrottle: number; profileCPU: boolean }) {
const cdp = await page.context().newCDPSession(page)
if (options.cpuThrottle > 1) await cdp.send("Emulation.setCPUThrottlingRate", { rate: options.cpuThrottle })
if (options.profileCPU) {
await cdp.send("Profiler.enable")
await cdp.send("Profiler.setSamplingInterval", { interval: 100 })
await cdp.send("Profiler.start")
}
return {
async stop() {
if (!options.profileCPU) return
const result = await cdp.send("Profiler.stop")
const self = new Map<number, number>()
result.profile.samples?.forEach((id, index) => {
const duration = (result.profile.timeDeltas?.[index] ?? 0) / 1_000
self.set(id, (self.get(id) ?? 0) + duration)
})
console.log(
"timeline cpu profile",
JSON.stringify(
result.profile.nodes
.map((node) => ({
function: node.callFrame.functionName || "(anonymous)",
url: node.callFrame.url,
line: node.callFrame.lineNumber + 1,
selfMs: self.get(node.id) ?? 0,
}))
.filter((node) => node.selfMs > 1)
.sort((a, b) => b.selfMs - a.selfMs)
.slice(0, 40),
),
)
},
async reset() {
if (options.cpuThrottle > 1) await cdp.send("Emulation.setCPUThrottlingRate", { rate: 1 })
},
}
}
@@ -0,0 +1,547 @@
import type { Page } from "@playwright/test"
const STREAM_MARKER_PATTERN = "stream-(\\d+)"
const STREAM_FRAGMENT_COUNT = 18
type TimelineProbeState = {
started: number
ended: number
profileVisual: boolean
minimal: boolean
frames: number[]
frameAt: number[]
applied: { at: number; index: number }[]
geometry: {
scrollTop: number
scrollHeight: number
clientHeight: number
distance: number
virtualHeight: number
headerHeight: number
}[]
blanks: number
longTasks: number[]
layoutShifts: number[]
visibleMounts: number
visibleUnmounts: number
visibleRows: Set<Element>
visibleSubtreeMounts: string[]
visibleSubtreeUnmounts: string[]
visibleSubtreeReplacements: number
visibleSubtreeDropouts: string[]
visibleSubtrees: Map<string, Element>
subtreeKeys: WeakMap<Element, string>
maxOverlap: number
maxGap: number
maxPartTopMovement: number
previousPartTop: number
slowFrames: {
duration: number
index: number
phase: "stream" | "boundary" | "complete" | "unknown"
tokenSpans: number
blocks: number
codeBlocks: number
height: number
distance: number
}[]
scroll: {
calls: number
callNoops: number
sameFrameCalls: number
assignments: number
assignmentNoops: number
lastCallFrame: number
frame: number
}
row: HTMLElement
markdown: HTMLElement
running: boolean
previous: number
cleanup: () => void
start: () => void
}
export async function installTimelineStreamProbe(
page: Page,
options: { textPartID: string; finalIndex: number; profileVisual: boolean; minimal: boolean },
) {
await page.evaluate(
({ textPartID, finalIndex, profileVisual, minimal, markerPattern, fragmentCount }) => {
const part = document.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
const row = part?.closest<HTMLElement>("[data-timeline-row]")
const markdown = part?.querySelector<HTMLElement>('[data-component="markdown"]')
const root = part?.closest<HTMLElement>(".scroll-view__viewport")
if (!part || !row || !markdown || !root) throw new Error("missing streaming benchmark nodes")
const viewport = root.getBoundingClientRect()
const state: TimelineProbeState = {
started: 0,
ended: Infinity,
profileVisual,
minimal,
frames: [],
frameAt: [],
applied: [],
geometry: [],
blanks: 0,
longTasks: [],
layoutShifts: [],
visibleMounts: 0,
visibleUnmounts: 0,
visibleRows: new Set(
[...root.querySelectorAll("[data-timeline-key]")].filter((element) => {
const rect = element.getBoundingClientRect()
return rect.bottom > viewport.top && rect.top < viewport.bottom
}),
),
visibleSubtreeMounts: [],
visibleSubtreeUnmounts: [],
visibleSubtreeReplacements: 0,
visibleSubtreeDropouts: [],
visibleSubtrees: new Map<string, Element>(),
subtreeKeys: new WeakMap<Element, string>(),
maxOverlap: 0,
maxGap: 0,
maxPartTopMovement: 0,
previousPartTop: part.getBoundingClientRect().top,
slowFrames: [],
scroll: {
calls: 0,
callNoops: 0,
sameFrameCalls: 0,
assignments: 0,
assignmentNoops: 0,
lastCallFrame: -1,
frame: 0,
},
row,
markdown,
running: false,
previous: 0,
cleanup: () => {},
start: () => {},
}
;(window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark = state
const scrollTo = Element.prototype.scrollTo
const scrollTop = Object.getOwnPropertyDescriptor(Element.prototype, "scrollTop")!
if (profileVisual) {
Element.prototype.scrollTo = function (...args) {
state.scroll.calls += 1
const top = typeof args[0] === "object" ? args[0]?.top : args[1]
if (typeof top === "number") {
const target = Math.min(top, this.scrollHeight - this.clientHeight)
if (Math.abs(this.scrollTop - target) < 1) state.scroll.callNoops += 1
}
if (state.scroll.lastCallFrame === state.scroll.frame) state.scroll.sameFrameCalls += 1
state.scroll.lastCallFrame = state.scroll.frame
return scrollTo.apply(this, args)
}
Object.defineProperty(Element.prototype, "scrollTop", {
configurable: true,
get: scrollTop.get,
set(value) {
state.scroll.assignments += 1
if (Math.abs(this.scrollTop - value) < 1) state.scroll.assignmentNoops += 1
scrollTop.set!.call(this, value)
},
})
}
const recordLongTasks = (entries: PerformanceEntry[]) => {
if (!state.running) return
state.longTasks.push(
...entries
.filter((entry) => entry.startTime >= state.started && entry.startTime <= state.ended)
.map((entry) => entry.duration),
)
}
const longTaskObserver = new PerformanceObserver((list) => recordLongTasks(list.getEntries()))
longTaskObserver.observe({ type: "longtask" })
const recordLayoutShifts = (entries: PerformanceEntry[]) => {
if (!state.running) return
state.layoutShifts.push(
...entries
.map((entry) => {
const shift = entry as LayoutShiftEntry
if (shift.startTime < state.started || shift.hadRecentInput) return
return shift.value
})
.filter((value): value is number => value !== undefined),
)
}
const layoutShiftObserver = profileVisual
? new PerformanceObserver((list) => recordLayoutShifts(list.getEntries()))
: undefined
layoutShiftObserver?.observe({ type: "layout-shift", buffered: true })
const visible = (element: Element) => {
const rect = element.getBoundingClientRect()
const viewport = root.getBoundingClientRect()
const style = getComputedStyle(element)
return (
element.isConnected &&
rect.width > 0 &&
rect.height > 0 &&
rect.bottom > viewport.top &&
rect.top < viewport.bottom &&
style.display !== "none" &&
style.visibility !== "hidden" &&
Number(style.opacity) > 0
)
}
const critical = [
"[data-timeline-part-id]",
'[data-component="edit-content"]',
'[data-component="apply-patch-file-diff"]',
'[data-component="file"]',
'[data-component="markdown-code"]',
"[data-markdown-block]",
].join(",")
const describe = (element: Element) => {
const cached = state.subtreeKeys.get(element)
if (!element.isConnected && cached) return cached
const part = element.closest<HTMLElement>("[data-timeline-part-id]")?.dataset.timelinePartId ?? "unknown"
const block = element
.closest<HTMLElement>("[data-markdown-key]")
?.dataset.markdownKey?.replace(/:(?:code|full|live)$/, "")
const component =
element.getAttribute("data-component") ?? element.getAttribute("data-markdown-block") ?? element.tagName
const key = `${part}:${block ?? "root"}:${component}`
state.subtreeKeys.set(element, key)
return key
}
const recordMutations = (records: MutationRecord[]) => {
if (!state.running) return
records.forEach((record) => {
record.addedNodes.forEach((node) => {
if (node instanceof HTMLElement && node.matches("[data-timeline-key]") && visible(node)) {
state.visibleMounts += 1
state.visibleRows.add(node)
}
if (!(node instanceof Element)) return
const added = [node, ...node.querySelectorAll(critical)].filter((element) => element.matches(critical))
added.forEach((element) => {
if (visible(element)) state.visibleSubtreeMounts.push(describe(element))
})
})
record.removedNodes.forEach((node) => {
if (node instanceof HTMLElement && node.matches("[data-timeline-key]") && state.visibleRows.delete(node))
state.visibleUnmounts += 1
if (!(node instanceof Element)) return
const removed = [node, ...node.querySelectorAll(critical)].filter((element) => element.matches(critical))
removed.forEach((element) => {
const key = describe(element)
if (state.visibleSubtrees.get(key) === element) state.visibleSubtreeUnmounts.push(key)
})
})
})
}
const mutationObserver = profileVisual ? new MutationObserver(recordMutations) : undefined
mutationObserver?.observe(root, { childList: true, subtree: true })
const currentPart = () => root.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
const observeProgress = (at: number) => {
if (!state.running) return
const content = currentPart()?.textContent ?? ""
const index = content.includes("benchmark-complete")
? finalIndex
: Number(content.match(new RegExp(markerPattern, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
if (index >= 0 && index !== state.applied.at(-1)?.index) state.applied.push({ at, index })
}
const progressObserver = new MutationObserver(() => observeProgress(performance.now()))
progressObserver.observe(root, { characterData: true, childList: true, subtree: true })
state.cleanup = () => {
recordLongTasks(longTaskObserver.takeRecords())
recordLayoutShifts(layoutShiftObserver?.takeRecords() ?? [])
recordMutations(mutationObserver?.takeRecords() ?? [])
if (progressObserver.takeRecords().length) observeProgress(performance.now())
longTaskObserver.disconnect()
layoutShiftObserver?.disconnect()
mutationObserver?.disconnect()
progressObserver.disconnect()
if (!profileVisual) return
Element.prototype.scrollTo = scrollTo
Object.defineProperty(Element.prototype, "scrollTop", scrollTop)
}
const sample = (now: number) => {
if (!state.running) return
state.frameAt.push(now)
observeProgress(now)
if (minimal) {
state.frames.push(now - state.previous)
state.previous = now
requestAnimationFrame(sample)
return
}
setTimeout(() => {
if (!state.running) return
state.scroll.frame += 1
const duration = now - state.previous
state.frames.push(duration)
state.previous = now
const virtualRoot = root.querySelector<HTMLElement>("[data-timeline-virtual-content]")
const header = root.querySelector<HTMLElement>("[data-session-title]")
state.geometry.push({
scrollTop: root.scrollTop,
scrollHeight: root.scrollHeight,
clientHeight: root.clientHeight,
distance: root.scrollHeight - root.clientHeight - root.scrollTop,
virtualHeight: virtualRoot?.getBoundingClientRect().height ?? 0,
headerHeight: header?.getBoundingClientRect().height ?? 0,
})
const viewport = root.getBoundingClientRect()
if (profileVisual) {
const visibleRows = [...root.querySelectorAll<HTMLElement>("[data-timeline-key]")]
.map((element) => ({ element, rect: element.getBoundingClientRect() }))
.filter((item) => item.rect.bottom > viewport.top && item.rect.top < viewport.bottom)
.sort((a, b) => a.rect.top - b.rect.top)
state.visibleRows = new Set(visibleRows.map((item) => item.element))
const rows = visibleRows.map((item) => item.rect)
rows.slice(1).forEach((rect, index) => {
const previous = rows[index]!
state.maxOverlap = Math.max(state.maxOverlap, previous.bottom - rect.top)
state.maxGap = Math.max(state.maxGap, rect.top - previous.bottom)
})
const partTop = part.getBoundingClientRect().top
state.maxPartTopMovement = Math.max(state.maxPartTopMovement, Math.abs(partTop - state.previousPartTop))
state.previousPartTop = partTop
}
const visibleRow = [...root.querySelectorAll<HTMLElement>("[data-timeline-row]")].some((element) => {
const rect = element.getBoundingClientRect()
return rect.bottom > viewport.top && rect.top < viewport.bottom
})
if (!visibleRow) state.blanks += 1
if (profileVisual) {
const subtrees = new Map<string, { element: Element; rendered: boolean }>()
const visibleSubtrees = new Map<string, Element>()
root.querySelectorAll(critical).forEach((element) => {
const key = describe(element)
const rect = element.getBoundingClientRect()
const style = getComputedStyle(element)
const rendered =
element.isConnected &&
rect.width > 0 &&
rect.height > 0 &&
style.display !== "none" &&
style.visibility !== "hidden" &&
Number(style.opacity) > 0
subtrees.set(key, { element, rendered })
if (rendered && rect.bottom > viewport.top && rect.top < viewport.bottom) {
const previous = state.visibleSubtrees.get(key)
if (previous && previous !== element && key.startsWith(`${textPartID}:`))
state.visibleSubtreeReplacements += 1
visibleSubtrees.set(key, element)
}
})
state.visibleSubtrees.forEach((element, key) => {
const current = subtrees.get(key)
if (key.startsWith(`${textPartID}:`) && !current?.rendered) {
const markdown = part.querySelector<HTMLElement>('[data-component="markdown"]')
state.visibleSubtreeDropouts.push(
`${key}:projection=${markdown?.dataset.markdownProjectionLength}/${markdown?.dataset.markdownProjectionBlocks}:result=${markdown?.dataset.markdownResultLength}/${markdown?.dataset.markdownResultBlocks}:applied=${markdown?.dataset.markdownAppliedBlocks}:dom=${markdown?.children.length}`,
)
}
if (element.matches('[data-component="file"]')) {
const hadLines = element.hasAttribute("data-profiler-had-lines")
const hasLines = element.shadowRoot?.querySelector("[data-line]") != null
if (hasLines) element.setAttribute("data-profiler-had-lines", "")
if (hadLines && !hasLines) state.visibleSubtreeDropouts.push(`${key}:shadow-lines`)
}
})
state.visibleSubtrees = visibleSubtrees
}
if (profileVisual && duration > 33.34) {
const livePart = currentPart()
const content = livePart?.textContent ?? ""
const complete = content.includes("benchmark-complete")
const index = complete
? finalIndex
: Number(content.match(new RegExp(markerPattern, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
state.slowFrames.push({
duration,
index,
phase: complete
? "complete"
: index >= 0 && index % fragmentCount === 0
? "boundary"
: index >= 0
? "stream"
: "unknown",
tokenSpans: livePart?.querySelectorAll(".shiki span").length ?? 0,
blocks: livePart?.querySelectorAll("[data-markdown-block]").length ?? 0,
codeBlocks: livePart?.querySelectorAll('[data-component="markdown-code"]').length ?? 0,
height: livePart?.getBoundingClientRect().height ?? 0,
distance: root.scrollHeight - root.clientHeight - root.scrollTop,
})
}
requestAnimationFrame(sample)
}, 0)
}
state.start = () => {
state.started = performance.now()
state.previous = state.started
state.running = true
requestAnimationFrame(sample)
}
},
{ ...options, markerPattern: STREAM_MARKER_PATTERN, fragmentCount: STREAM_FRAGMENT_COUNT },
)
}
export function startTimelineStreamProbe(page: Page) {
return page.evaluate(() => {
const state = (window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark
if (!state) throw new Error("missing streaming benchmark state")
state.start()
})
}
type LayoutShiftEntry = PerformanceEntry & { value: number; hadRecentInput?: boolean }
export function layoutShiftValue(
entry: Pick<LayoutShiftEntry, "startTime" | "value" | "hadRecentInput">,
start: number,
) {
if (entry.startTime < start || entry.hadRecentInput) return
return entry.value
}
export function removeVisibleRow<T>(visible: Set<T>, row: T) {
return visible.delete(row)
}
export function streamProgress(content: string) {
const index = Number(content.match(new RegExp(STREAM_MARKER_PATTERN, "g"))?.at(-1)?.match(/\d+/)?.[0] ?? -1)
return {
index,
phase: content.includes("benchmark-complete")
? ("complete" as const)
: index >= 0 && index % STREAM_FRAGMENT_COUNT === 0
? ("boundary" as const)
: index >= 0
? ("stream" as const)
: ("unknown" as const),
}
}
export async function collectTimelineStreamMetrics(
page: Page,
options: { textPartID: string; finalIndex: number; navigations: string[] },
) {
return page.evaluate(({ textPartID, finalIndex, navigations }) => {
const state = (window as Window & { __timelineStreamBenchmark?: TimelineProbeState }).__timelineStreamBenchmark
if (!state) throw new Error(`missing streaming benchmark state after navigation: ${JSON.stringify(navigations)}`)
state.ended = performance.now()
state.cleanup()
state.running = false
const part = document.querySelector<HTMLElement>(`[data-timeline-part-id="${textPartID}"]`)
const row = part?.closest<HTMLElement>("[data-timeline-row]")
const markdown = part?.querySelector<HTMLElement>('[data-component="markdown"]')
const sorted = state.frames.slice().sort((a, b) => a - b)
const duration = state.frames.reduce((sum, value) => sum + value, 0)
const longestSlowStreak = state.frames.reduce(
(result, value) => {
const current = value > 33.34 ? result.current + 1 : 0
return { current, longest: Math.max(result.longest, current) }
},
{ current: 0, longest: 0 },
).longest
const busyStart = state.applied.at(0)?.at
const completion = state.applied.find((value) => value.index === finalIndex)
const busyEnd = completion?.at
const busyFrames =
busyStart === undefined || busyEnd === undefined
? []
: state.frames.filter((_, index) => state.frameAt[index]! >= busyStart && state.frameAt[index]! <= busyEnd)
const busySorted = busyFrames.slice().sort((a, b) => a - b)
const busyDuration = busyFrames.reduce((sum, value) => sum + value, 0)
const completionObservedMs = (completion?.at ?? NaN) - state.started
const visual = state.profileVisual
? {
layoutShiftValueSum: state.layoutShifts.reduce((sum, value) => sum + value, 0),
maxLayoutShiftValue: Math.max(0, ...state.layoutShifts),
visibleMounts: state.visibleMounts,
visibleUnmounts: state.visibleUnmounts,
visibleSubtreeMounts: state.visibleSubtreeMounts,
visibleSubtreeUnmounts: [...new Set(state.visibleSubtreeUnmounts)],
visibleSubtreeReplacements: state.visibleSubtreeReplacements,
visibleSubtreeDropouts: [...new Set(state.visibleSubtreeDropouts)],
maxOverlapPx: state.maxOverlap,
maxGapPx: state.maxGap,
maxPartTopMovementPx: state.maxPartTopMovement,
slowestRafGaps: state.slowFrames
.sort((a, b) => b.duration - a.duration)
.slice(0, 20)
.map((frame) => ({
durationMs: frame.duration,
index: frame.index,
phase: frame.phase,
tokenSpans: frame.tokenSpans,
blocks: frame.blocks,
codeBlocks: frame.codeBlocks,
heightPx: frame.height,
distancePx: frame.distance,
})),
slowRafGapPhases: Object.fromEntries(
["stream", "boundary", "complete", "unknown"].map((phase) => {
const frames = state.slowFrames.filter((frame) => frame.phase === phase)
return [
phase,
{
count: frames.length,
totalMs: frames.reduce((sum, frame) => sum + frame.duration, 0),
maxMs: Math.max(0, ...frames.map((frame) => frame.duration)),
},
]
}),
),
scroll: state.scroll,
}
: null
const geometry = state.minimal
? null
: {
maxDistancePx: Math.max(0, ...state.geometry.map((sample) => sample.distance)),
finalDistancePx: state.geometry.at(-1)?.distance ?? 0,
final: state.geometry.at(-1),
distanceTransitionsPx: state.geometry
.map((sample) => Math.round(sample.distance))
.filter((value, index, values) => index === 0 || value !== values[index - 1]),
bottomDriftTransitions: state.geometry.slice(1).filter((value, index) => {
const previous = state.geometry[index]?.distance ?? 0
return previous <= 1 && value.distance > 1
}).length,
blankSamples: state.blanks,
}
return {
capabilities: { visual: state.profileVisual, geometry: !state.minimal },
completionObservedMs,
deltasPerSecond: Number.isFinite(completionObservedMs) ? finalIndex / (completionObservedMs / 1_000) : null,
rafGapSamples: state.frames.length,
rafCallbackRate: duration ? (state.frames.length * 1000) / duration : 0,
observedProgressWindowRafCallbackRate: busyDuration ? (busyFrames.length * 1000) / busyDuration : null,
observedProgressWindowRafGapP95Ms: busySorted[Math.floor(busySorted.length * 0.95)] ?? null,
observedProgressWindowRafGaps: busyFrames.length,
maxObservedProgressIndex: Math.max(-1, ...state.applied.map((value) => value.index)),
observedProgressTransitions: state.applied.length,
rafGapP50Ms: sorted[Math.floor(sorted.length * 0.5)] ?? 0,
rafGapP95Ms: sorted[Math.floor(sorted.length * 0.95)] ?? 0,
rafGapP99Ms: sorted[Math.floor(sorted.length * 0.99)] ?? 0,
maxRafGapMs: sorted.at(-1) ?? 0,
rafGapsOver33Ms: state.frames.filter((value) => value > 33.34).length,
rafGapsOver50Ms: state.frames.filter((value) => value > 50).length,
missedFrameBudgetEquivalents: state.frames.reduce(
(sum, value) => sum + Math.max(0, Math.round(value / 16.67) - 1),
0,
),
longestRafGapOver33MsStreak: longestSlowStreak,
longTaskCount: state.longTasks.length,
longTaskTimeMs: state.longTasks.reduce((sum, value) => sum + value, 0),
visual,
geometry,
rowReplaced: row !== state.row,
markdownReplaced: markdown !== state.markdown,
domTextCharacters: part?.textContent?.length ?? 0,
}
}, options)
}
@@ -0,0 +1,335 @@
const words = [
"alpha",
"bravo",
"charlie",
"delta",
"echo",
"foxtrot",
"golf",
"hotel",
"india",
"juliet",
"kilo",
"lima",
"metro",
"nova",
"orbit",
"pixel",
"quartz",
"river",
"signal",
"vector",
]
const sourceID = "ses_smoke_source"
const targetID = "ses_smoke_target"
const directory = "C:/OpenCode/SmokeProject"
const projectID = "proj_smoke_timeline"
const model = { providerID: "opencode", modelID: "claude-opus-4-6", variant: "max" }
type MessageInfo = Record<string, unknown> & { id: string; role: "user" | "assistant" }
type MessagePart = Record<string, unknown> & { id: string; type: string; text?: string; tool?: string }
type Message = { info: MessageInfo; parts: MessagePart[] }
function lorem(seed: number, length: number) {
let out = ""
let i = seed
while (out.length < length) {
const word = words[i % words.length]
out += (out ? " " : "") + word
if (i % 17 === 0) out += ".\n\n"
i += 7
}
return out.slice(0, length)
}
function id(prefix: string, value: number) {
return `${prefix}_smoke_${String(value).padStart(4, "0")}`
}
function userMessage(sessionID: string, index: number, textLength: number, diffs: unknown[] = []): Message {
const messageID = id("msg_user", index)
return {
info: {
id: messageID,
sessionID,
role: "user",
time: { created: 1700000000000 + index * 10_000 },
summary: { diffs },
agent: "build",
model,
},
parts: [
{
id: id("prt_user_text", index),
sessionID,
messageID,
type: "text",
text: lorem(index, textLength),
},
],
}
}
function assistantMessage(sessionID: string, index: number, parentID: string, parts: MessagePart[]): Message {
const messageID = id("msg_assistant", index)
return {
info: {
id: messageID,
sessionID,
role: "assistant",
time: { created: 1700000000000 + index * 10_000 + 1_000, completed: 1700000000000 + index * 10_000 + 8_000 },
parentID,
modelID: model.modelID,
providerID: model.providerID,
mode: "build",
agent: "build",
path: { cwd: directory, root: directory },
cost: 0.01,
tokens: { input: 100, output: 200, reasoning: 0, cache: { read: 0, write: 0 } },
variant: "max",
finish: "stop",
},
parts: parts.map((part) => ({
...part,
sessionID,
messageID,
})),
}
}
function textPart(index: number, partIndex: number, length: number): MessagePart {
const prose = lorem(index * 13 + partIndex, length)
const text =
index % 12 === 0
? `${prose}\n\n\`\`\`ts\n${code(index, 80)}\n\`\`\``
: index % 5 === 0
? `${prose}\n\n\`\`\`ts\nexport const value = "${lorem(index, 220)}"\n\`\`\``
: index % 7 === 0
? `${prose}\n\nThe wrapped inline value is \`${lorem(index, 180)}\`.`
: prose
return { id: id(`prt_text_${partIndex}`, index), type: "text", text }
}
function reasoningPart(index: number, partIndex: number, length: number): MessagePart {
return {
id: id(`prt_reasoning_${partIndex}`, index),
type: "reasoning",
text: lorem(index * 19 + partIndex, length),
time: { start: 1700000000000 + index * 10_000, end: 1700000000000 + index * 10_000 + 500 },
}
}
function toolPart(
index: number,
partIndex: number,
tool: string,
input: Record<string, unknown>,
outputLength = 160,
): MessagePart {
const metadata =
tool === "apply_patch"
? { files: [patchFile(index, "update"), patchFile(index + 1, index % 2 === 0 ? "add" : "delete")] }
: tool === "edit" || tool === "write"
? {
filediff: fileDiff(String(input.filePath ?? `src/generated/file-${index}.ts`), index),
diff: patch(index, outputLength),
preview: patch(index + 1, 420),
}
: tool === "question"
? { answers: [["Proceed"], ["Keep sample output"]] }
: {}
return {
id: id(`prt_tool_${tool}_${partIndex}`, index),
type: "tool",
callID: id("call", index * 10 + partIndex),
tool,
state: {
status: "completed",
input,
output: lorem(index * 23 + partIndex, outputLength),
title: tool === "bash" ? "Verify generated output" : input.filePath || input.path || input.pattern || "completed",
metadata,
time: { start: 1700000000000 + index * 10_000, end: 1700000000000 + index * 10_000 + 400 },
},
}
}
function patchFile(seed: number, type: "add" | "update" | "delete") {
return {
filePath: `src/generated/patch-${seed}.ts`,
relativePath: `src/generated/patch-${seed}.ts`,
type,
additions: (seed % 7) + 1,
deletions: type === "add" ? 0 : seed % 4,
patch: patch(seed, 520),
before: type === "add" ? undefined : code(seed, 18),
after: type === "delete" ? undefined : code(seed + 1, 24),
}
}
function fileDiff(file: string, seed: number) {
const lines = seed % 12 === 0 ? 300 : seed % 8 === 0 ? 2 : 38
const before = code(seed, lines, seed % 10 === 0 ? 280 : 32)
const after =
lines === 2
? before.replace("value1", "updatedValue1")
: lines === 300
? code(seed + 1, lines, seed % 10 === 0 ? 280 : 32)
: before.replace("value4", "updatedValue4").replace("value20", "updatedValue20")
return {
file,
additions: lines === 300 ? 300 : lines === 2 ? 1 : 2,
deletions: lines === 300 ? 300 : lines === 2 ? 1 : 2,
before,
after,
}
}
function patch(seed: number, length: number) {
return `diff --git a/src/generated/file-${seed}.ts b/src/generated/file-${seed}.ts\n+${lorem(seed, length).replace(/\n/g, "\n+")}`
}
function code(seed: number, lines: number, width = 32) {
return Array.from(
{ length: lines },
(_, index) => `export const value${index} = "${lorem(seed + index, width)}"`,
).join("\n")
}
function turn(index: number): Message[] {
const diff = index % 9 === 0 ? [fileDiff(`src/generated/summary-${index}.ts`, index)] : []
const user = userMessage(targetID, index, 100 + (index % 4) * 80, diff)
const parts = [
...(index % 5 === 0 ? [reasoningPart(index, 0, 420)] : []),
...(index % 3 === 0
? [
toolPart(index, 0, "read", { filePath: `src/generated/file-${index}.ts`, offset: 0, limit: 80 }, 220),
toolPart(index, 5, "glob", { path: directory, pattern: `**/*sample-${index}*.ts` }, 140),
toolPart(index, 1, "grep", { path: directory, pattern: `sample-${index}`, include: "*.ts" }, 180),
toolPart(index, 6, "list", { path: `src/generated/${index}` }, 120),
]
: []),
textPart(index, 2, 160 + (index % 6) * 90),
...(index % 4 === 0 ? [toolPart(index, 3, "edit", { filePath: `src/generated/file-${index}.ts` }, 700)] : []),
...(index % 6 === 0
? [toolPart(index, 7, "write", { filePath: `src/generated/write-${index}.ts`, content: code(index, 28) }, 560)]
: []),
...(index % 8 === 0
? [toolPart(index, 8, "apply_patch", { files: [`src/generated/patch-${index}.ts`] }, 620)]
: []),
...(index % 7 === 0
? [toolPart(index, 4, "bash", { command: "bun typecheck", description: "Verify generated output" }, 620)]
: []),
...(index % 10 === 0 ? [toolPart(index, 9, "webfetch", { url: "https://example.com/docs/sample" }, 120)] : []),
...(index % 11 === 0 ? [toolPart(index, 10, "websearch", { query: "sample movement notes" }, 240)] : []),
...(index % 13 === 0
? [
toolPart(
index,
11,
"question",
{ questions: [{ question: "Use generated fixture?" }, { question: "Keep same row shape?" }] },
120,
),
]
: []),
...(index % 17 === 0
? [toolPart(index, 12, "task", { description: "Inspect generated fixture", subagent_type: "explore" }, 160)]
: []),
]
return [user, assistantMessage(targetID, index, user.info.id, parts)]
}
const targetMessages = Array.from({ length: 72 }, (_, index) => turn(index)).flat()
const sourceMessages = Array.from({ length: 12 }, (_, index) => [
userMessage(sourceID, index + 1000, 120),
assistantMessage(sourceID, index + 1000, id("msg_user", index + 1000), [textPart(index + 1000, 0, 240)]),
]).flat()
function renderable(part: MessagePart) {
if (part.type === "tool" && part.tool === "todowrite") return false
if (part.type === "text") return !!part.text.trim()
if (part.type === "reasoning") return !!part.text.trim()
return part.type !== "step-start" && part.type !== "step-finish" && part.type !== "patch"
}
function orderedParts(message: Message) {
return message.parts.slice().sort((a, b) => a.id.localeCompare(b.id))
}
export const fixture = {
directory,
project: {
id: projectID,
worktree: directory,
vcs: "git",
name: "smoke-project",
time: { created: 1700000000000, updated: 1700000000000 },
sandboxes: [],
},
provider: {
all: [
{
id: "opencode",
name: "OpenCode",
models: { "claude-opus-4-6": { id: "claude-opus-4-6", name: "Claude Opus 4.6", limit: { context: 200_000 } } },
},
],
connected: ["opencode"],
default: { providerID: "opencode", modelID: "claude-opus-4-6" },
},
sessions: [
{
id: sourceID,
slug: "source",
projectID,
directory,
title: "Uncommitted changes inquiry",
version: "dev",
time: { created: 1700000000000, updated: 1700000000000 },
},
{
id: targetID,
slug: "target",
projectID,
directory,
title: "Example Game: sample jump movement & sample physics analysis",
version: "dev",
time: { created: 1700000001000, updated: 1700000001000 },
},
],
sourceID,
targetID,
messages: { [sourceID]: sourceMessages, [targetID]: targetMessages },
expected: {
sourceTitle: "Uncommitted changes inquiry",
targetTitle: "Example Game: sample jump movement & sample physics analysis",
sourceMessageIDs: sourceMessages
.filter((message) => message.info.role === "user")
.map((message) => message.info.id),
targetMessageIDs: targetMessages
.filter((message) => message.info.role === "user")
.map((message) => message.info.id),
targetPartIDs: targetMessages.flatMap((message) =>
orderedParts(message)
.filter(renderable)
.map((part) => part.id),
),
},
}
export function pageMessages(sessionID: string, limit: number, before?: string) {
const messages = fixture.messages[sessionID as keyof typeof fixture.messages] ?? []
const end = before
? Math.max(
0,
messages.findIndex((message) => message.info.id === before),
)
: messages.length
const start = Math.max(0, end - limit)
return {
items: messages.slice(start, end),
cursor: start > 0 ? messages[start]!.info.id : undefined,
}
}
@@ -0,0 +1,67 @@
import type { Page } from "@playwright/test"
import { base64Encode } from "@opencode-ai/core/util/encode"
import { mockOpenCodeServer } from "../../utils/mock-server"
import { fixture } from "./session-timeline-stress.fixture"
export async function installTimelineSettings(page: Page) {
await page.addInitScript(() => {
localStorage.setItem(
"settings.v3",
JSON.stringify({
general: {
editToolPartsExpanded: true,
shellToolPartsExpanded: true,
showReasoningSummaries: true,
showSessionProgressBar: true,
},
}),
)
})
}
export function mockStressTimeline(page: Page) {
return mockOpenCodeServer(page, {
sessions: fixture.sessions,
provider: fixture.provider,
directory: fixture.directory,
project: fixture.project,
pageMessages: (sessionID) => ({ items: fixture.messages[sessionID as keyof typeof fixture.messages] ?? [] }),
})
}
export async function installStressSessionTabs(page: Page) {
const server = `http://${process.env.PLAYWRIGHT_SERVER_HOST ?? "127.0.0.1"}:${process.env.PLAYWRIGHT_SERVER_PORT ?? "4096"}`
await page.addInitScript(
({ directory, sourceID, targetID, dirBase64, server }) => {
localStorage.setItem(
"opencode.global.dat:server",
JSON.stringify({
projects: { local: [{ worktree: directory, expanded: true }] },
lastProject: { local: directory },
}),
)
localStorage.setItem(
"opencode.global.dat:tabs",
JSON.stringify(
[sourceID, targetID].map((sessionId) => ({
type: "session",
server,
dirBase64,
sessionId,
})),
),
)
},
{
directory: fixture.directory,
sourceID: fixture.sourceID,
targetID: fixture.targetID,
dirBase64: base64Encode(fixture.directory),
server,
},
)
}
export function stressSessionHref(sessionID: string) {
return `/${base64Encode(fixture.directory)}/session/${sessionID}`
}