test(web): expand long-chat regression and performance coverage
This commit is contained in:
kingwl
328
apps/web/tests/chat-continuous-conversation.e2e.ts
Normal file
328
apps/web/tests/chat-continuous-conversation.e2e.ts
Normal file
@@ -0,0 +1,328 @@
|
||||
// Web e2e contract for a conversation grown through the real composer rather
|
||||
// than pre-seeded history. Twelve deterministic replay turns exercise repeated
|
||||
// send/settle/render cycles, including two real bash executions and one long,
|
||||
// multi-chunk final turn. Assertions stay semantic: no host timing, heap, or
|
||||
// mounted-row cardinality is treated as a correctness contract.
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import { CallId, type StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import type { ReplayEntry, ReplayOverrideDoc } from '@deepseek-ai/dsh-llm-replay'
|
||||
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import {
|
||||
launchWebScaffold,
|
||||
watchConsole,
|
||||
webSnapshotMode,
|
||||
type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
|
||||
|
||||
const MODE = webSnapshotMode()
|
||||
const TURN_COUNT = 12
|
||||
const TOOL_TURNS = [4, 9] as const
|
||||
const STREAM_PACE_MS = 10
|
||||
|
||||
interface TurnSpec {
|
||||
readonly index: number
|
||||
readonly prompt: string
|
||||
readonly userMarker: string
|
||||
readonly firstMarker: string
|
||||
readonly doneMarker: string
|
||||
readonly deltas: readonly string[]
|
||||
readonly callId?: ReturnType<typeof CallId>
|
||||
readonly toolResultMarker?: string
|
||||
}
|
||||
|
||||
function suffix(index: number): string {
|
||||
return String(index).padStart(3, '0')
|
||||
}
|
||||
|
||||
function longFinalPrompt(userMarker: string): string {
|
||||
return [
|
||||
`${userMarker} Reconcile this accumulated conversation without losing earlier turn ownership.`,
|
||||
...Array.from(
|
||||
{ length: 36 },
|
||||
(_, index) => `Context ${String(index + 1).padStart(2, '0')}: preserve token-${String(index)} and verify ${'payload '.repeat(12).trimEnd()}.`,
|
||||
),
|
||||
'Return one continuous response and finish with the requested completion marker.',
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
function turnSpec(index: number): TurnSpec {
|
||||
const id = suffix(index)
|
||||
const userMarker = `CONTINUOUS_CHAT_USER_${id}`
|
||||
const firstMarker = `CONTINUOUS_CHAT_FIRST_${id}`
|
||||
const doneMarker = `CONTINUOUS_CHAT_DONE_${id}`
|
||||
const deltaCount = index === TURN_COUNT ? 36 : 8
|
||||
const deltas = Array.from({ length: deltaCount }, (_, chunkIndex) => {
|
||||
if (chunkIndex === 0) return `${firstMarker} `
|
||||
if (chunkIndex === deltaCount - 1) return `${doneMarker}.`
|
||||
return `turn-${id}-chunk-${String(chunkIndex).padStart(2, '0')} keeps semantic ownership stable. `
|
||||
})
|
||||
if (!TOOL_TURNS.includes(index as (typeof TOOL_TURNS)[number])) {
|
||||
return {
|
||||
index,
|
||||
prompt: index === TURN_COUNT
|
||||
? longFinalPrompt(userMarker)
|
||||
: `${userMarker} Continue this same conversation through turn ${String(index)}.`,
|
||||
userMarker,
|
||||
firstMarker,
|
||||
doneMarker,
|
||||
deltas,
|
||||
}
|
||||
}
|
||||
return {
|
||||
index,
|
||||
prompt: `${userMarker} Run the requested deterministic tool for turn ${String(index)}, then continue.`,
|
||||
userMarker,
|
||||
firstMarker,
|
||||
doneMarker,
|
||||
deltas,
|
||||
callId: CallId(`continuous-chat-tool-${id}`),
|
||||
toolResultMarker: `CONTINUOUS_CHAT_TOOL_RESULT_${id}`,
|
||||
}
|
||||
}
|
||||
|
||||
function textStream(spec: TurnSpec): StreamChunk[] {
|
||||
const response = spec.deltas.join('')
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'text' },
|
||||
...spec.deltas.map(text => ({ type: 'text-delta' as const, index: 0, text })),
|
||||
{ type: 'block-end', index: 0, block: { type: 'text', text: response } },
|
||||
{
|
||||
type: 'usage',
|
||||
usage: {
|
||||
inputTokens: Math.ceil(spec.prompt.length / 4),
|
||||
outputTokens: Math.ceil(response.length / 4),
|
||||
},
|
||||
},
|
||||
{ type: 'finish', reason: { kind: 'stop' } },
|
||||
]
|
||||
}
|
||||
|
||||
function toolStream(spec: TurnSpec): StreamChunk[] {
|
||||
if (spec.callId === undefined || spec.toolResultMarker === undefined) {
|
||||
throw new Error(`turn ${String(spec.index)} has no tool identity`)
|
||||
}
|
||||
const args = JSON.stringify({
|
||||
command: `printf '${spec.toolResultMarker}\\n'`,
|
||||
description: spec.toolResultMarker,
|
||||
})
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'tool-call' },
|
||||
{
|
||||
type: 'tool-call-delta',
|
||||
index: 0,
|
||||
id: spec.callId,
|
||||
name: 'bash',
|
||||
argumentsDelta: args,
|
||||
},
|
||||
{
|
||||
type: 'block-end',
|
||||
index: 0,
|
||||
block: { type: 'tool-call', id: spec.callId, name: 'bash', arguments: args },
|
||||
},
|
||||
{ type: 'usage', usage: { inputTokens: 256, outputTokens: 24 } },
|
||||
{ type: 'finish', reason: { kind: 'tool-calls' } },
|
||||
]
|
||||
}
|
||||
|
||||
function replayScript(specs: readonly TurnSpec[]): ReplayOverrideDoc {
|
||||
return specs.flatMap((spec): ReplayEntry[] => {
|
||||
const final: ReplayEntry = { kind: 'chunks', chunks: textStream(spec) }
|
||||
return spec.callId === undefined
|
||||
? [final]
|
||||
: [{ kind: 'chunks', chunks: toolStream(spec) }, final]
|
||||
})
|
||||
}
|
||||
|
||||
function userText(event: Extract<SessionEvent, { type: 'user/message' }>): string {
|
||||
return event.data.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
}
|
||||
|
||||
function assistantText(event: Extract<SessionEvent, { type: 'assistant/message' }>): string {
|
||||
return event.data.message.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
}
|
||||
|
||||
function toolResultText(event: Extract<SessionEvent, { type: 'tool/result' }>): string {
|
||||
return event.data.message.content[0].content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
}
|
||||
|
||||
describe('web e2e: continuous conversation grown through the composer', () => {
|
||||
let browser: Browser
|
||||
let page: Page
|
||||
let replayDir: string
|
||||
let scaffold: WebScaffold
|
||||
let tripwire: ReturnType<typeof watchConsole>
|
||||
const consoleWarnings: string[] = []
|
||||
const sessionEvents: SessionEvent[] = []
|
||||
const specs = Array.from({ length: TURN_COUNT }, (_, offset) => turnSpec(offset + 1))
|
||||
|
||||
beforeAll(async () => {
|
||||
replayDir = await mkdtemp(join(tmpdir(), 'dsh-continuous-chat-replay-'))
|
||||
const replayOverride = join(replayDir, 'replay.override.json')
|
||||
await writeFile(replayOverride, JSON.stringify(replayScript(specs)))
|
||||
scaffold = await launchWebScaffold({
|
||||
replayFixture: join(replayDir, 'override-only.jsonl'),
|
||||
replayOverride,
|
||||
replayContextWindow: 10_000_000,
|
||||
paceMs: STREAM_PACE_MS,
|
||||
})
|
||||
scaffold.ctx.on('session/event', (_session, event: SessionEvent) => {
|
||||
sessionEvents.push(event)
|
||||
})
|
||||
browser = await chromium.launch()
|
||||
page = await newEnglishPage(browser, 900)
|
||||
tripwire = watchConsole(page)
|
||||
page.on('console', (message) => {
|
||||
if (message.type() === 'warning') consoleWarnings.push(message.text())
|
||||
})
|
||||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
await connectFreshWorkspace(page, 'continuous-chat-e2e')
|
||||
}, 120_000)
|
||||
|
||||
afterAll(async () => {
|
||||
const failures: unknown[] = []
|
||||
await browser?.close().catch((error: unknown) => failures.push(error))
|
||||
await scaffold?.close().catch((error: unknown) => failures.push(error))
|
||||
if (replayDir !== undefined) {
|
||||
await rm(replayDir, { recursive: true, force: true })
|
||||
.catch((error: unknown) => failures.push(error))
|
||||
}
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'continuous Chat e2e cleanup failed')
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('keeps twelve generated turns and tool rows bound to one live session', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-chat-continuous-conversation'))
|
||||
const composer = page.locator('textarea:enabled').last()
|
||||
await composer.waitFor({ timeout: 15_000 })
|
||||
let sessionId: SessionId | undefined
|
||||
|
||||
for (const spec of specs) {
|
||||
const eventStart = sessionEvents.length
|
||||
expect(await composer.inputValue()).toBe('')
|
||||
expect(await composer.isEnabled()).toBe(true)
|
||||
await composer.fill(spec.prompt)
|
||||
expect(await composer.inputValue()).toBe(spec.prompt)
|
||||
|
||||
const settled = scaffold.whenTurnSettled(60_000)
|
||||
await page.getByRole('button', { name: 'Send message', exact: true }).click()
|
||||
await page.getByText(spec.userMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
const echoedUser = sessionEvents.slice(eventStart).find(
|
||||
(event): event is SessionEvent<'user/message'> => (
|
||||
event.type === 'user/message'
|
||||
&& event.data.source.kind === 'user'
|
||||
&& userText(event).includes(spec.userMarker)
|
||||
),
|
||||
)
|
||||
if (echoedUser === undefined) throw new Error(`turn ${String(spec.index)} has no user echo event`)
|
||||
const userRow = page.locator(`[data-chat-anchor-key="node:${String(echoedUser.seq)}"]`)
|
||||
await expect.poll(() => userRow.count(), { timeout: 10_000 }).toBe(1)
|
||||
expect(await userRow.getAttribute('data-chat-flow-kind')).toBe('user')
|
||||
expect(await userRow.textContent()).toContain(spec.userMarker)
|
||||
await page.getByText(spec.firstMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
const settledSessionId = await settled
|
||||
if (sessionId === undefined) {
|
||||
sessionId = settledSessionId
|
||||
} else {
|
||||
expect(settledSessionId).toBe(sessionId)
|
||||
}
|
||||
|
||||
await expect.poll(() => page.locator('[data-streaming="true"]').count(), { timeout: 15_000 }).toBe(0)
|
||||
await page.getByText(spec.doneMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
await expect.poll(() => composer.inputValue(), { timeout: 10_000 }).toBe('')
|
||||
await expect.poll(() => composer.isEnabled(), { timeout: 10_000 }).toBe(true)
|
||||
|
||||
const turnEvents = sessionEvents.slice(eventStart)
|
||||
const turnStarts = turnEvents.filter((event): event is SessionEvent<'turn/start'> => (
|
||||
event.type === 'turn/start'
|
||||
))
|
||||
const users = turnEvents.filter((event): event is SessionEvent<'user/message'> => (
|
||||
event.type === 'user/message' && event.data.source.kind === 'user'
|
||||
))
|
||||
const assistants = turnEvents.filter((event): event is SessionEvent<'assistant/message'> => (
|
||||
event.type === 'assistant/message'
|
||||
))
|
||||
const finalAssistants = assistants.filter(event => assistantText(event).includes(spec.doneMarker))
|
||||
const turnEnds = turnEvents.filter((event): event is SessionEvent<'turn/end'> => (
|
||||
event.type === 'turn/end'
|
||||
))
|
||||
const chunks = turnEvents.filter(event => event.type === 'assistant/chunk')
|
||||
|
||||
expect(turnStarts).toHaveLength(1)
|
||||
expect(turnStarts[0]?.data.turn).toBe(spec.index)
|
||||
expect(users).toHaveLength(1)
|
||||
expect(users[0]?.seq).toBe(echoedUser.seq)
|
||||
expect(userText(users[0]!)).toBe(spec.prompt)
|
||||
expect(finalAssistants).toHaveLength(1)
|
||||
expect(assistants).toHaveLength(spec.callId === undefined ? 1 : 2)
|
||||
expect(turnEnds).toHaveLength(1)
|
||||
expect(turnEnds[0]?.data).toEqual({ turn: spec.index, reason: { kind: 'completed' } })
|
||||
expect(chunks).toHaveLength(spec.deltas.length + (spec.callId === undefined ? 4 : 9))
|
||||
|
||||
const assistantRow = page.locator(`[data-chat-anchor-key="node:${String(finalAssistants[0]!.seq)}"]`)
|
||||
await expect.poll(() => assistantRow.count(), { timeout: 10_000 }).toBe(1)
|
||||
expect(await assistantRow.getAttribute('data-chat-flow-kind')).toBe('assistant')
|
||||
expect(await assistantRow.textContent()).toContain(spec.doneMarker)
|
||||
|
||||
const calls = turnEvents.filter((event): event is SessionEvent<'tool/call'> => event.type === 'tool/call')
|
||||
const results = turnEvents.filter((event): event is SessionEvent<'tool/result'> => event.type === 'tool/result')
|
||||
if (spec.callId === undefined || spec.toolResultMarker === undefined) {
|
||||
expect(calls).toHaveLength(0)
|
||||
expect(results).toHaveLength(0)
|
||||
continue
|
||||
}
|
||||
|
||||
expect(calls).toHaveLength(1)
|
||||
expect(results).toHaveLength(1)
|
||||
expect(calls[0]?.data).toMatchObject({
|
||||
turn: spec.index,
|
||||
callId: spec.callId,
|
||||
name: 'bash',
|
||||
})
|
||||
expect(results[0]?.data.turn).toBe(spec.index)
|
||||
expect(results[0]?.data.message.source.callId).toBe(spec.callId)
|
||||
expect(results[0]?.data.message.content[0].isError).toBe(false)
|
||||
expect(toolResultText(results[0]!)).toBe(`${spec.toolResultMarker}\n`)
|
||||
|
||||
const toolRow = page.locator(`[data-chat-call-id="${spec.callId}"]`)
|
||||
await expect.poll(() => toolRow.count(), { timeout: 10_000 }).toBe(1)
|
||||
expect(await toolRow.textContent()).toContain(spec.toolResultMarker)
|
||||
const disclosure = toolRow.locator('[data-sample="bash-global"]')
|
||||
expect(await disclosure.getAttribute('aria-expanded')).toBe('false')
|
||||
await disclosure.click()
|
||||
await expect.poll(() => disclosure.getAttribute('aria-expanded'), { timeout: 10_000 }).toBe('true')
|
||||
// The collapsed summary deliberately repeats the result marker; the
|
||||
// last exact match is the expanded terminal output owned by this call.
|
||||
await toolRow.getByText(spec.toolResultMarker, { exact: true }).last().waitFor({ timeout: 10_000 })
|
||||
await disclosure.click()
|
||||
await expect.poll(() => disclosure.getAttribute('aria-expanded'), { timeout: 10_000 }).toBe('false')
|
||||
}
|
||||
|
||||
if (sessionId === undefined) throw new Error('continuous conversation completed no turn')
|
||||
expect(scaffold.ctx.agents.get(sessionId)?.session.events.filter(event => (
|
||||
event.type === 'turn/end' && event.data.reason.kind === 'completed'
|
||||
))).toHaveLength(TURN_COUNT)
|
||||
expect(specs.at(-1)?.prompt.length).toBeGreaterThan(4_000)
|
||||
expect(sessionEvents.filter(event => (
|
||||
event.type === 'assistant/chunk' && event.data.turn === TURN_COUNT
|
||||
)).length).toBeGreaterThan(30)
|
||||
expect(consoleWarnings).toEqual([])
|
||||
expect(tripwire.pageErrors).toEqual([])
|
||||
expect(tripwire.warnings).toEqual([])
|
||||
}, 180_000)
|
||||
})
|
||||
268
apps/web/tests/chat-long-interactions.e2e.ts
Normal file
268
apps/web/tests/chat-long-interactions.e2e.ts
Normal file
@@ -0,0 +1,268 @@
|
||||
// Long-history Chat behavior contract for a future virtualized renderer. Wheel
|
||||
// input only navigates to the semantic target; assertions pin content identity
|
||||
// and interaction routing rather than scroll geometry or mounted row counts.
|
||||
import { mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import type { StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import type { ReplayEntry, ReplayOverrideDoc } from '@deepseek-ai/dsh-llm-replay'
|
||||
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import { createChatScrollFixture } from './chat-scroll-fixture.ts'
|
||||
import {
|
||||
launchWebScaffold,
|
||||
seedSession,
|
||||
watchConsole,
|
||||
webSnapshotMode,
|
||||
type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { newEnglishPage, saveFailureShot } from './support.ts'
|
||||
|
||||
const MODE = webSnapshotMode()
|
||||
const SESSION_ID = 'chat-long-interactions-e2e'
|
||||
const FIXTURE_TURNS = 88
|
||||
const TOOL_TURN = FIXTURE_TURNS
|
||||
const BRANCH_TURN = 80
|
||||
const TARGET_CALL_1 = 'chat-scroll-088-1'
|
||||
const TARGET_CALL_2 = 'chat-scroll-088-2'
|
||||
const CONTINUE_PROMPT = 'CHAT_INTERACTION_CONTINUE Continue from this exact branch point.'
|
||||
const CONTINUE_FIRST = 'CHAT_INTERACTION_CONTINUE_FIRST'
|
||||
const CONTINUE_DONE = 'CHAT_INTERACTION_CONTINUE_DONE'
|
||||
const FIXTURE = createChatScrollFixture({
|
||||
markerPrefix: 'INTERACTION',
|
||||
title: 'CHAT_INTERACTION long semantic identity session',
|
||||
turns: FIXTURE_TURNS,
|
||||
})
|
||||
|
||||
function continuationChunks(): StreamChunk[] {
|
||||
const response = `${CONTINUE_FIRST} The fork retained the intended prefix. ${CONTINUE_DONE}.`
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'text' },
|
||||
{ type: 'text-delta', index: 0, text: `${CONTINUE_FIRST} ` },
|
||||
{ type: 'text-delta', index: 0, text: `The fork retained the intended prefix. ${CONTINUE_DONE}.` },
|
||||
{ type: 'block-end', index: 0, block: { type: 'text', text: response } },
|
||||
{ type: 'usage', usage: { inputTokens: 512, outputTokens: 32 } },
|
||||
{ type: 'finish', reason: { kind: 'stop' } },
|
||||
]
|
||||
}
|
||||
|
||||
function replayEntry(chunks: StreamChunk[]): ReplayEntry {
|
||||
return { kind: 'chunks', chunks }
|
||||
}
|
||||
|
||||
function carries(event: SessionEvent, marker: string): boolean {
|
||||
return JSON.stringify(event).includes(marker)
|
||||
}
|
||||
|
||||
function textContent(content: readonly unknown[]): string {
|
||||
return content.flatMap((block) => {
|
||||
if (typeof block !== 'object' || block === null) return []
|
||||
const candidate = block as { type?: unknown; text?: unknown }
|
||||
return candidate.type === 'text' && typeof candidate.text === 'string'
|
||||
? [candidate.text]
|
||||
: []
|
||||
}).join('')
|
||||
}
|
||||
|
||||
async function nextPaint(page: Page): Promise<void> {
|
||||
await page.evaluate(async () => {
|
||||
await document.fonts.ready
|
||||
await new Promise<void>(resolve => requestAnimationFrame(() => {
|
||||
requestAnimationFrame(() => { resolve() })
|
||||
}))
|
||||
})
|
||||
}
|
||||
|
||||
async function openSeed(page: Page): Promise<void> {
|
||||
await page.getByText(/^\d+ sessions?$/, { exact: true }).waitFor({ timeout: 30_000 })
|
||||
const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
|
||||
await search.fill(FIXTURE.markers.user(1))
|
||||
const results = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
|
||||
await results.first().waitFor({ timeout: 60_000 })
|
||||
const resultCount = await results.count()
|
||||
if (resultCount !== 1) throw new Error(`expected one seeded search result, received ${String(resultCount)}`)
|
||||
await results.click()
|
||||
await results.click()
|
||||
await page.getByText(FIXTURE.markers.assistant(FIXTURE.turns), { exact: false })
|
||||
.last().waitFor({ timeout: 30_000 })
|
||||
await nextPaint(page)
|
||||
}
|
||||
|
||||
async function wheelUntilMounted(page: Page, selector: string, deltaY: number): Promise<void> {
|
||||
const scrollport = page.locator('[data-conversation-scroll]')
|
||||
const box = await scrollport.boundingBox()
|
||||
if (box === null) throw new Error('conversation scrollport has no layout box')
|
||||
await page.mouse.move(box.x + box.width / 2, box.y + Math.min(140, box.height / 3))
|
||||
for (let attempt = 0; attempt < 20; attempt += 1) {
|
||||
if (await page.locator(selector).count() > 0) return
|
||||
await page.mouse.wheel(0, deltaY)
|
||||
await nextPaint(page)
|
||||
}
|
||||
throw new Error(`semantic Chat target did not mount: ${selector}`)
|
||||
}
|
||||
|
||||
function requiredEvent<T extends SessionEvent['type']>(
|
||||
events: readonly SessionEvent[],
|
||||
type: T,
|
||||
marker: string,
|
||||
): Extract<SessionEvent, { type: T }> {
|
||||
const event = events.find((candidate): candidate is Extract<SessionEvent, { type: T }> => (
|
||||
candidate.type === type && carries(candidate, marker)
|
||||
))
|
||||
if (event === undefined) throw new Error(`${type} carrying ${marker} is absent`)
|
||||
return event
|
||||
}
|
||||
|
||||
describe('web e2e: long Chat interaction contract', () => {
|
||||
let browser: Browser
|
||||
let page: Page
|
||||
let replayDir: string
|
||||
let scaffold: WebScaffold
|
||||
let tripwire: ReturnType<typeof watchConsole>
|
||||
|
||||
beforeAll(async () => {
|
||||
replayDir = await mkdtemp(join(tmpdir(), 'dsh-chat-interaction-replay-'))
|
||||
const replayOverride = join(replayDir, 'replay.override.json')
|
||||
const replay: ReplayOverrideDoc = [replayEntry(continuationChunks())]
|
||||
await writeFile(replayOverride, JSON.stringify(replay))
|
||||
scaffold = await launchWebScaffold({
|
||||
replayFixture: join(replayDir, 'override-only.jsonl'),
|
||||
replayOverride,
|
||||
replayContextWindow: 10_000_000,
|
||||
paceMs: 18,
|
||||
})
|
||||
await seedSession(scaffold, FIXTURE.log, SESSION_ID)
|
||||
browser = await chromium.launch()
|
||||
page = await newEnglishPage(browser, 900)
|
||||
tripwire = watchConsole(page)
|
||||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
await openSeed(page)
|
||||
}, 120_000)
|
||||
|
||||
afterAll(async () => {
|
||||
const failures: unknown[] = []
|
||||
await browser?.close().catch((error: unknown) => failures.push(error))
|
||||
await scaffold?.close().catch((error: unknown) => failures.push(error))
|
||||
if (replayDir !== undefined) {
|
||||
await rm(replayDir, { recursive: true, force: true })
|
||||
.catch((error: unknown) => failures.push(error))
|
||||
}
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'long Chat interaction cleanup failed')
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('keeps heterogeneous rows and their actions bound to exact semantic identities', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-chat-long-interactions'))
|
||||
const source = scaffold.ctx.agents.get(SessionId(SESSION_ID))
|
||||
if (source === undefined) throw new Error('seeded long-history agent is not attached')
|
||||
|
||||
const toolUserMarker = FIXTURE.markers.user(TOOL_TURN)
|
||||
const toolAssistantMarker = FIXTURE.markers.assistant(TOOL_TURN)
|
||||
const toolMarker1 = FIXTURE.markers.tool(TOOL_TURN, 1)
|
||||
const toolMarker2 = FIXTURE.markers.tool(TOOL_TURN, 2)
|
||||
const toolUserEvent = requiredEvent(source.session.events, 'user/message', toolUserMarker)
|
||||
const toolAssistantEvent = requiredEvent(source.session.events, 'assistant/message', toolAssistantMarker)
|
||||
const branchUserMarker = FIXTURE.markers.user(BRANCH_TURN)
|
||||
const branchAssistantMarker = FIXTURE.markers.assistant(BRANCH_TURN)
|
||||
const branchUserEvent = requiredEvent(source.session.events, 'user/message', branchUserMarker)
|
||||
const boundary = source.session.events.find((event): event is SessionEvent<'turn/end'> => (
|
||||
event.type === 'turn/end' && event.data.turn === BRANCH_TURN
|
||||
))
|
||||
if (boundary === undefined) throw new Error(`turn ${String(BRANCH_TURN)} has no completed boundary`)
|
||||
const expectedUserText = textContent(branchUserEvent.data.content)
|
||||
|
||||
await wheelUntilMounted(page, `[data-chat-call-id="${TARGET_CALL_2}"]`, -1_100)
|
||||
const toolUserRow = page.locator(`[data-chat-anchor-key="node:${String(toolUserEvent.seq)}"]`)
|
||||
const toolAssistantRow = page.locator(`[data-chat-anchor-key="node:${String(toolAssistantEvent.seq)}"]`)
|
||||
const call1 = page.locator(`[data-chat-call-id="${TARGET_CALL_1}"]`)
|
||||
const call2 = page.locator(`[data-chat-call-id="${TARGET_CALL_2}"]`)
|
||||
|
||||
await expect.poll(() => toolUserRow.count(), { timeout: 10_000 }).toBe(1)
|
||||
await expect.poll(() => toolAssistantRow.count(), { timeout: 10_000 }).toBe(1)
|
||||
expect(await call1.count()).toBe(1)
|
||||
expect(await call2.count()).toBe(1)
|
||||
expect(await toolUserRow.getAttribute('data-chat-flow-kind')).toBe('user')
|
||||
expect(await toolAssistantRow.getAttribute('data-chat-flow-kind')).toBe('assistant')
|
||||
expect(await toolUserRow.textContent()).toContain(toolUserMarker)
|
||||
expect(await toolAssistantRow.textContent()).toContain(toolAssistantMarker)
|
||||
expect(await call1.textContent()).toContain(toolMarker1)
|
||||
expect(await call2.textContent()).toContain(toolMarker2)
|
||||
|
||||
const expectedOrder = [
|
||||
`node:${String(toolUserEvent.seq)}`,
|
||||
`call:${TARGET_CALL_1}`,
|
||||
`call:${TARGET_CALL_2}`,
|
||||
`node:${String(toolAssistantEvent.seq)}`,
|
||||
]
|
||||
const actualOrder = await page.locator('[data-chat-anchor-key]').evaluateAll((rows, keys) => (
|
||||
rows.map(row => (row as HTMLElement).dataset.chatAnchorKey)
|
||||
.filter((key): key is string => key !== undefined && keys.includes(key))
|
||||
), expectedOrder)
|
||||
expect(actualOrder).toEqual(expectedOrder)
|
||||
const groupKeys = await Promise.all([call1, call2].map(row => row.evaluate(element => (
|
||||
element.closest<HTMLElement>('[data-chat-flow-kind="tool-group"]')?.dataset.chatFlowKey ?? null
|
||||
))))
|
||||
expect(groupKeys[0]).not.toBeNull()
|
||||
expect(groupKeys[1]).toBe(groupKeys[0])
|
||||
|
||||
const summary1 = call1.locator('[data-sample="bash-global"]')
|
||||
const summary2 = call2.locator('[data-sample="bash-global"]')
|
||||
expect(await summary1.getAttribute('aria-expanded')).toBe('false')
|
||||
expect(await summary2.getAttribute('aria-expanded')).toBe('false')
|
||||
await summary2.focus()
|
||||
await summary2.press('Enter')
|
||||
await expect.poll(() => summary2.getAttribute('aria-expanded'), { timeout: 10_000 }).toBe('true')
|
||||
expect(await summary1.getAttribute('aria-expanded')).toBe('false')
|
||||
await call2.getByText(`${toolMarker2} output line 12`, { exact: true }).waitFor({ timeout: 10_000 })
|
||||
|
||||
await wheelUntilMounted(page, `[data-chat-anchor-key="node:${String(branchUserEvent.seq)}"]`, -1_100)
|
||||
const userRow = page.locator(`[data-chat-anchor-key="node:${String(branchUserEvent.seq)}"]`)
|
||||
expect(await userRow.textContent()).toContain(branchUserMarker)
|
||||
await page.context().grantPermissions(['clipboard-read', 'clipboard-write'])
|
||||
await userRow.hover()
|
||||
await userRow.getByRole('button', { name: 'Copy', exact: true }).click()
|
||||
await expect.poll(() => page.evaluate(() => navigator.clipboard.readText()), { timeout: 5_000 })
|
||||
.toBe(expectedUserText)
|
||||
|
||||
await userRow.hover()
|
||||
await userRow.getByRole('button', { name: 'Branch into a new conversation', exact: true }).click()
|
||||
await expect.poll(
|
||||
() => scaffold.ctx.agents.list().find(agent => agent.session.header.parentSession === SessionId(SESSION_ID)),
|
||||
{ timeout: 15_000 },
|
||||
).toBeDefined()
|
||||
const child = scaffold.ctx.agents.list()
|
||||
.find(agent => agent.session.header.parentSession === SessionId(SESSION_ID))
|
||||
if (child === undefined) throw new Error('message branch did not create a child session')
|
||||
expect(child.session.header.seedLength).toBe(boundary.seq + 1)
|
||||
expect(child.session.events.some(event => carries(event, branchAssistantMarker))).toBe(true)
|
||||
expect(child.session.events.some(event => carries(event, FIXTURE.markers.user(BRANCH_TURN + 1)))).toBe(false)
|
||||
expect(child.session.events.some(event => carries(event, FIXTURE.markers.user(FIXTURE.turns)))).toBe(false)
|
||||
|
||||
const currentCrumb = page.getByRole('navigation', { name: 'Session hierarchy' })
|
||||
.getByRole('button').last()
|
||||
await expect.poll(() => currentCrumb.textContent(), { timeout: 15_000 })
|
||||
.toBe(`${FIXTURE.title} (1)`)
|
||||
await page.getByText(branchAssistantMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
const settled = scaffold.whenTurnSettled(60_000)
|
||||
const composer = page.locator('textarea:enabled').last()
|
||||
await composer.fill(CONTINUE_PROMPT)
|
||||
await page.getByRole('button', { name: 'Send message', exact: true }).click()
|
||||
await expect.poll(() => page.getByText(CONTINUE_PROMPT, { exact: true }).count(), { timeout: 15_000 }).toBe(1)
|
||||
expect(await settled).toBe(child.session.id)
|
||||
await page.getByText(CONTINUE_DONE, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
await expect.poll(() => page.locator('[data-streaming="true"]').count(), { timeout: 15_000 }).toBe(0)
|
||||
expect(await composer.inputValue()).toBe('')
|
||||
expect(await composer.isEnabled()).toBe(true)
|
||||
expect(source.session.events.some(event => carries(event, CONTINUE_PROMPT))).toBe(false)
|
||||
expect(child.session.events.filter(event => carries(event, CONTINUE_PROMPT))).toHaveLength(1)
|
||||
const lastTurnEnd = child.session.events.findLast((event): event is SessionEvent<'turn/end'> => (
|
||||
event.type === 'turn/end'
|
||||
))
|
||||
expect(lastTurnEnd?.data.reason).toEqual({ kind: 'completed' })
|
||||
expect(tripwire.pageErrors).toEqual([])
|
||||
expect(tripwire.warnings).toEqual([])
|
||||
}, 180_000)
|
||||
})
|
||||
667
apps/web/tests/chat-scroll-contract.e2e.ts
Normal file
667
apps/web/tests/chat-scroll-contract.e2e.ts
Normal file
@@ -0,0 +1,667 @@
|
||||
// Browser geometry contracts for a long Chat transcript. These scenarios are
|
||||
// deliberately virtualizer-neutral: they assert semantic-row position,
|
||||
// bottom ownership, interaction state, and the real outer scroll host rather
|
||||
// than DOM cardinality or implementation-specific spacer markup.
|
||||
import { access, mkdtemp, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it } from 'vitest'
|
||||
import type { StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import type { ReplayEntry, ReplayOverrideDoc } from '@deepseek-ai/dsh-llm-replay'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import { createChatScrollFixture, type ChatScrollFixture } from './chat-scroll-fixture.ts'
|
||||
import {
|
||||
launchWebScaffold,
|
||||
seedSession,
|
||||
watchConsole,
|
||||
webSnapshotMode,
|
||||
type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { newEnglishPage, saveFailureShot } from './support.ts'
|
||||
|
||||
const MODE = webSnapshotMode()
|
||||
const HISTORY_SESSION_ID = 'chat-scroll-history-e2e'
|
||||
const TOOL_SESSION_ID = 'chat-scroll-tool-e2e'
|
||||
const RESTORE_SESSION_A_ID = 'chat-scroll-restore-a-e2e'
|
||||
const RESTORE_SESSION_B_ID = 'chat-scroll-restore-b-e2e'
|
||||
const REPLAY_CONTEXT_WINDOW = 10_000_000
|
||||
const STREAM_PACE_MS = 24
|
||||
const GEOMETRY_TOLERANCE = 2
|
||||
const LIVE_TEXT_PROMPT = 'CHAT_SCROLL_LIVE_USER Continue this long conversation while I inspect older history.'
|
||||
const LIVE_TEXT_FIRST = 'CHAT_SCROLL_LIVE_FIRST'
|
||||
const LIVE_TEXT_DONE = 'CHAT_SCROLL_LIVE_DONE'
|
||||
const LIVE_TOOL_PROMPT = 'CHAT_SCROLL_TOOL_USER Run the requested diagnostic and then summarize it.'
|
||||
const LIVE_TOOL_CALL_ID = CallId('chat-scroll-live-tool-call')
|
||||
const LIVE_TOOL_RESULT = 'CHAT_SCROLL_LIVE_TOOL_RESULT'
|
||||
const LIVE_TOOL_FIRST = 'CHAT_SCROLL_TOOL_STREAM_FIRST'
|
||||
const LIVE_TOOL_DONE = 'CHAT_SCROLL_TOOL_STREAM_DONE'
|
||||
const TOOL_READY_FILE = '.chat-scroll-tool-ready'
|
||||
const TOOL_RELEASE_FILE = '.chat-scroll-tool-release'
|
||||
|
||||
const HISTORY_FIXTURE = createChatScrollFixture({
|
||||
markerPrefix: 'HISTORY',
|
||||
title: 'CHAT_SCROLL_HISTORY long paging session',
|
||||
})
|
||||
const TOOL_FIXTURE = createChatScrollFixture({
|
||||
markerPrefix: 'TOOL',
|
||||
title: 'CHAT_SCROLL_TOOL live tool session',
|
||||
})
|
||||
const RESTORE_FIXTURE_A = createChatScrollFixture({
|
||||
markerPrefix: 'RESTORE_A',
|
||||
title: 'CHAT_SCROLL_RESTORE_A long session',
|
||||
})
|
||||
const RESTORE_FIXTURE_B = createChatScrollFixture({
|
||||
markerPrefix: 'RESTORE_B',
|
||||
title: 'CHAT_SCROLL_RESTORE_B comparison session',
|
||||
turns: 32,
|
||||
})
|
||||
|
||||
interface ScrollGeometry {
|
||||
readonly distanceFromBottom: number
|
||||
readonly scrollTop: number
|
||||
}
|
||||
|
||||
interface FlowAnchor {
|
||||
readonly key: string
|
||||
readonly top: number
|
||||
}
|
||||
|
||||
interface ScrollWorld {
|
||||
readonly events: SessionEvent[]
|
||||
readonly page: Page
|
||||
readonly replayDir?: string
|
||||
readonly scaffold: WebScaffold
|
||||
readonly tripwire: ReturnType<typeof watchConsole>
|
||||
}
|
||||
|
||||
interface ScrollWorldOptions {
|
||||
readonly failureShot: string
|
||||
readonly replay?: ReplayOverrideDoc
|
||||
readonly seeds: readonly { fixture: ChatScrollFixture; id: string }[]
|
||||
}
|
||||
|
||||
function textStream(first: string, done: string, deltaCount: number): StreamChunk[] {
|
||||
const deltas = Array.from({ length: deltaCount }, (_, index) => {
|
||||
if (index === 0) return `${first} `
|
||||
if (index === deltaCount - 1) return `${done}.`
|
||||
return `stream-chunk-${String(index).padStart(3, '0')} ${'incremental response '.repeat(3)}`
|
||||
})
|
||||
const response = deltas.join('')
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'text' },
|
||||
...deltas.map(text => ({ type: 'text-delta' as const, index: 0, text })),
|
||||
{ type: 'block-end', index: 0, block: { type: 'text', text: response } },
|
||||
{
|
||||
type: 'usage',
|
||||
usage: { inputTokens: 512, outputTokens: Math.ceil(response.length / 4) },
|
||||
},
|
||||
{ type: 'finish', reason: { kind: 'stop' } },
|
||||
]
|
||||
}
|
||||
|
||||
function toolStream(): StreamChunk[] {
|
||||
const command = [
|
||||
`: > ${TOOL_READY_FILE}`,
|
||||
`while [ ! -f ${TOOL_RELEASE_FILE} ]; do sleep 0.02; done`,
|
||||
'line=1',
|
||||
`while [ "$line" -le 64 ]; do printf '${LIVE_TOOL_RESULT} line %02d\\n' "$line"; line=$((line + 1)); done`,
|
||||
].join('; ')
|
||||
const args = JSON.stringify({ command, description: LIVE_TOOL_RESULT })
|
||||
return [
|
||||
{ type: 'block-start', index: 0, blockType: 'tool-call' },
|
||||
{
|
||||
type: 'tool-call-delta',
|
||||
index: 0,
|
||||
id: LIVE_TOOL_CALL_ID,
|
||||
name: 'bash',
|
||||
argumentsDelta: args,
|
||||
},
|
||||
{
|
||||
type: 'block-end',
|
||||
index: 0,
|
||||
block: { type: 'tool-call', id: LIVE_TOOL_CALL_ID, name: 'bash', arguments: args },
|
||||
},
|
||||
{ type: 'usage', usage: { inputTokens: 256, outputTokens: 48 } },
|
||||
{ type: 'finish', reason: { kind: 'tool-calls' } },
|
||||
]
|
||||
}
|
||||
|
||||
function replayEntry(chunks: StreamChunk[]): ReplayEntry {
|
||||
return { kind: 'chunks', chunks }
|
||||
}
|
||||
|
||||
async function launchScrollWorld(options: ScrollWorldOptions): Promise<ScrollWorld> {
|
||||
let replayDir: string | undefined
|
||||
let scaffold: WebScaffold | undefined
|
||||
let page: Page | undefined
|
||||
try {
|
||||
if (options.replay !== undefined) {
|
||||
replayDir = await mkdtemp(join(tmpdir(), 'dsh-chat-scroll-replay-'))
|
||||
const replayOverride = join(replayDir, 'replay.override.json')
|
||||
await writeFile(replayOverride, JSON.stringify(options.replay))
|
||||
scaffold = await launchWebScaffold({
|
||||
replayFixture: join(replayDir, 'override-only.jsonl'),
|
||||
replayOverride,
|
||||
paceMs: STREAM_PACE_MS,
|
||||
replayContextWindow: REPLAY_CONTEXT_WINDOW,
|
||||
})
|
||||
} else {
|
||||
scaffold = await launchWebScaffold({})
|
||||
}
|
||||
for (const seed of options.seeds) await seedSession(scaffold, seed.fixture.log, seed.id)
|
||||
const events: SessionEvent[] = []
|
||||
scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { events.push(event) })
|
||||
page = await newEnglishPage(browser, 900)
|
||||
const tripwire = watchConsole(page)
|
||||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
// Session-list bootstrap can replace the controlled search state. Wait
|
||||
// for the seeded baseline before openSeed starts the lazy content query.
|
||||
await page.getByText(/^\d+ sessions?$/, { exact: true }).waitFor({ timeout: 30_000 })
|
||||
return {
|
||||
events,
|
||||
page,
|
||||
scaffold,
|
||||
tripwire,
|
||||
...(replayDir === undefined ? {} : { replayDir }),
|
||||
}
|
||||
} catch (error) {
|
||||
const failures: unknown[] = [error]
|
||||
if (page !== undefined) await page.context().close().catch((cleanupError: unknown) => failures.push(cleanupError))
|
||||
if (scaffold !== undefined) await scaffold.close().catch((cleanupError: unknown) => failures.push(cleanupError))
|
||||
if (replayDir !== undefined) {
|
||||
await rm(replayDir, { recursive: true, force: true }).catch((cleanupError: unknown) => failures.push(cleanupError))
|
||||
}
|
||||
if (failures.length === 1) throw error
|
||||
throw new AggregateError(failures, 'chat-scroll browser world setup failed and cleanup was incomplete')
|
||||
}
|
||||
}
|
||||
|
||||
async function closeScrollWorld(world: ScrollWorld): Promise<void> {
|
||||
const failures: unknown[] = []
|
||||
// newEnglishPage/browser.newPage owns an isolated context. Close the whole
|
||||
// context so its SSE connection and cache cannot leak into the next world
|
||||
// in this file's shared Chromium process.
|
||||
await world.page.context().close().catch((error: unknown) => failures.push(error))
|
||||
await world.scaffold.close().catch((error: unknown) => failures.push(error))
|
||||
if (world.replayDir !== undefined) {
|
||||
await rm(world.replayDir, { recursive: true, force: true }).catch((error: unknown) => failures.push(error))
|
||||
}
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'chat-scroll browser world cleanup failed')
|
||||
}
|
||||
|
||||
async function withScrollWorld(
|
||||
options: ScrollWorldOptions,
|
||||
run: (world: ScrollWorld) => Promise<void>,
|
||||
): Promise<void> {
|
||||
const world = await launchScrollWorld(options)
|
||||
let runFailure: unknown
|
||||
try {
|
||||
await run(world)
|
||||
} catch (error) {
|
||||
runFailure = error
|
||||
try {
|
||||
await saveFailureShot(world.page, options.failureShot)
|
||||
} catch {
|
||||
// Best-effort evidence must never prevent cleanup of the owned world.
|
||||
}
|
||||
}
|
||||
let cleanupFailure: unknown
|
||||
try {
|
||||
await closeScrollWorld(world)
|
||||
} catch (error) {
|
||||
cleanupFailure = error
|
||||
}
|
||||
if (runFailure !== undefined && cleanupFailure !== undefined) {
|
||||
throw new AggregateError([runFailure, cleanupFailure], 'chat-scroll scenario and cleanup both failed')
|
||||
}
|
||||
if (runFailure !== undefined) throw runFailure
|
||||
if (cleanupFailure !== undefined) throw cleanupFailure
|
||||
}
|
||||
|
||||
async function nextPaint(page: Page): Promise<void> {
|
||||
await page.evaluate(async () => {
|
||||
await document.fonts.ready
|
||||
await new Promise<void>(resolve => requestAnimationFrame(() => {
|
||||
requestAnimationFrame(() => { resolve() })
|
||||
}))
|
||||
})
|
||||
}
|
||||
|
||||
function scrollGeometry(page: Page): Promise<ScrollGeometry> {
|
||||
return page.locator('[data-conversation-scroll]').evaluate(host => ({
|
||||
distanceFromBottom: host.scrollHeight - host.clientHeight - host.scrollTop,
|
||||
scrollTop: host.scrollTop,
|
||||
}))
|
||||
}
|
||||
|
||||
async function conversationTurns(page: Page): Promise<number> {
|
||||
const stats = page.getByText(/\d+ turns · \d+ steps/, { exact: true }).last()
|
||||
await stats.waitFor({ timeout: 15_000 })
|
||||
const value = await stats.textContent()
|
||||
const match = value?.match(/^(\d+) turns · \d+ steps$/)
|
||||
if (match?.[1] === undefined) throw new Error(`unexpected conversation stats ${JSON.stringify(value)}`)
|
||||
return Number(match[1])
|
||||
}
|
||||
|
||||
async function openSeed(page: Page, fixture: ChatScrollFixture, tailMarker?: string): Promise<void> {
|
||||
const search = page.getByRole('textbox', { name: 'Search name, keywords...', exact: true })
|
||||
// Cold summaries initially show the temporary workspace basename, so the
|
||||
// persisted first-message marker is the stable user-facing identity. The
|
||||
// query itself triggers lazy content-index reconciliation; no transient
|
||||
// empty-state paint is used as a barrier.
|
||||
await search.fill(fixture.markers.user(1))
|
||||
const results = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
|
||||
await expect.poll(() => results.count(), { timeout: 60_000 }).toBe(1)
|
||||
await results.click()
|
||||
await page.getByRole('tab', { name: 'Chat', exact: true }).waitFor({ timeout: 30_000 })
|
||||
if (tailMarker !== undefined) {
|
||||
await page.getByText(tailMarker, { exact: false }).last().waitFor({ timeout: 30_000 })
|
||||
}
|
||||
await nextPaint(page)
|
||||
}
|
||||
|
||||
async function wheelTranscript(page: Page, deltaY: number): Promise<void> {
|
||||
const box = await page.locator('[data-conversation-scroll]').boundingBox()
|
||||
if (box === null) throw new Error('conversation scrollport has no layout box')
|
||||
await page.mouse.move(box.x + box.width / 2, box.y + Math.min(140, box.height / 3))
|
||||
await page.mouse.wheel(0, deltaY)
|
||||
await nextPaint(page)
|
||||
}
|
||||
|
||||
async function wheelToHistoryStart(page: Page): Promise<void> {
|
||||
for (let attempt = 0; attempt < 12; attempt += 1) {
|
||||
if ((await scrollGeometry(page)).scrollTop <= 1) break
|
||||
await wheelTranscript(page, -2_400)
|
||||
}
|
||||
await expect.poll(async () => (await scrollGeometry(page)).scrollTop, { timeout: 10_000 })
|
||||
.toBeLessThanOrEqual(1)
|
||||
}
|
||||
|
||||
async function wheelUntilMounted(page: Page, selector: string, deltaY: number): Promise<void> {
|
||||
for (let attempt = 0; attempt < 16; attempt += 1) {
|
||||
if (await page.locator(selector).count() > 0) return
|
||||
await wheelTranscript(page, deltaY)
|
||||
}
|
||||
throw new Error(`selector did not mount during transcript wheel: ${selector}`)
|
||||
}
|
||||
|
||||
function visibleFlowAnchor(page: Page): Promise<FlowAnchor> {
|
||||
return page.locator('[data-conversation-scroll]').evaluate((host) => {
|
||||
const rows = [...host.querySelectorAll<HTMLElement>('[data-chat-anchor-key]')]
|
||||
const viewport = host.getBoundingClientRect()
|
||||
const composer = host.querySelector<HTMLElement>('[data-composer-seat]')
|
||||
const visibleBottom = composer?.getBoundingClientRect().top ?? viewport.bottom
|
||||
const visible = rows.filter((candidate) => {
|
||||
const rect = candidate.getBoundingClientRect()
|
||||
return rect.bottom > viewport.top && rect.top < visibleBottom
|
||||
})
|
||||
const row = visible[0]
|
||||
if (row?.dataset.chatAnchorKey === undefined) {
|
||||
throw new Error(`no visible settled Chat row: ${JSON.stringify({
|
||||
composerTop: visibleBottom,
|
||||
host: { bottom: viewport.bottom, top: viewport.top },
|
||||
rows: rows.slice(0, 4).map(candidate => ({
|
||||
callId: candidate.dataset.chatCallId,
|
||||
key: candidate.dataset.chatAnchorKey,
|
||||
rect: {
|
||||
bottom: candidate.getBoundingClientRect().bottom,
|
||||
top: candidate.getBoundingClientRect().top,
|
||||
},
|
||||
})),
|
||||
totalRows: rows.length,
|
||||
})}`)
|
||||
}
|
||||
return {
|
||||
key: row.dataset.chatAnchorKey,
|
||||
top: row.getBoundingClientRect().top - viewport.top,
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
function flowTop(page: Page, key: string): Promise<number> {
|
||||
return page.locator('[data-chat-anchor-key]').evaluateAll((rows, anchorKey) => {
|
||||
const row = rows.find(candidate => (candidate as HTMLElement).dataset.chatAnchorKey === anchorKey)
|
||||
if (!(row instanceof HTMLElement)) throw new Error(`stable Chat anchor ${anchorKey} is not mounted`)
|
||||
const host = row.closest('[data-conversation-scroll]')
|
||||
if (!(host instanceof HTMLElement)) throw new Error('flow row has no conversation scrollport')
|
||||
return row.getBoundingClientRect().top - host.getBoundingClientRect().top
|
||||
}, key)
|
||||
}
|
||||
|
||||
async function expectSameFlowTop(page: Page, anchor: FlowAnchor): Promise<void> {
|
||||
await expect.poll(async () => Math.abs((await flowTop(page, anchor.key)) - anchor.top), {
|
||||
timeout: 10_000,
|
||||
message: `flow row ${anchor.key} moved relative to the transcript viewport`,
|
||||
}).toBeLessThanOrEqual(GEOMETRY_TOLERANCE)
|
||||
}
|
||||
|
||||
async function expectBottom(page: Page): Promise<void> {
|
||||
await expect.poll(async () => Math.abs((await scrollGeometry(page)).distanceFromBottom), {
|
||||
timeout: 10_000,
|
||||
}).toBeLessThanOrEqual(1)
|
||||
}
|
||||
|
||||
async function expectMarkerAboveComposer(page: Page, marker: string): Promise<void> {
|
||||
const geometry = await page.getByText(marker, { exact: false }).last().evaluate((node) => {
|
||||
const row = node.closest('[data-chat-flow-key], [data-streaming]')
|
||||
const composer = node.closest('[data-conversation-scroll]')?.querySelector('[data-composer-seat]')
|
||||
if (!(row instanceof HTMLElement) || !(composer instanceof HTMLElement)) {
|
||||
throw new Error('latest marker or composer geometry is unavailable')
|
||||
}
|
||||
return {
|
||||
composerTop: composer.getBoundingClientRect().top,
|
||||
rowBottom: row.getBoundingClientRect().bottom,
|
||||
}
|
||||
})
|
||||
expect(geometry.rowBottom).toBeLessThanOrEqual(geometry.composerTop + GEOMETRY_TOLERANCE)
|
||||
}
|
||||
|
||||
async function loadEarlierWithAnchor(page: Page): Promise<void> {
|
||||
await wheelToHistoryStart(page)
|
||||
const older = page.getByRole('button', { name: 'Load earlier', exact: true })
|
||||
await older.waitFor({ timeout: 10_000 })
|
||||
const anchor = await visibleFlowAnchor(page)
|
||||
const before = await conversationTurns(page)
|
||||
await older.click()
|
||||
await expect.poll(() => conversationTurns(page), { timeout: 30_000 }).toBeGreaterThan(before)
|
||||
await nextPaint(page)
|
||||
await expectSameFlowTop(page, anchor)
|
||||
}
|
||||
|
||||
async function fileExists(path: string): Promise<boolean> {
|
||||
try {
|
||||
await access(path)
|
||||
return true
|
||||
} catch {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
function eventCarries(event: SessionEvent, marker: string): boolean {
|
||||
return JSON.stringify(event).includes(marker)
|
||||
}
|
||||
|
||||
function assertClean(world: ScrollWorld): void {
|
||||
expect(world.tripwire.pageErrors).toEqual([])
|
||||
expect(world.tripwire.warnings).toEqual([])
|
||||
}
|
||||
|
||||
let browser: Browser
|
||||
|
||||
describe('web e2e: long Chat scroll contract', () => {
|
||||
beforeAll(async () => {
|
||||
browser = await chromium.launch()
|
||||
})
|
||||
|
||||
afterAll(async () => {
|
||||
await browser?.close()
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('preserves the reader anchor when history and streaming arrive concurrently', async () => {
|
||||
await withScrollWorld({
|
||||
failureShot: 'web-e2e-chat-scroll-history-stream',
|
||||
replay: [replayEntry(textStream(LIVE_TEXT_FIRST, LIVE_TEXT_DONE, 120))],
|
||||
seeds: [{ fixture: HISTORY_FIXTURE, id: HISTORY_SESSION_ID }],
|
||||
}, async (world) => {
|
||||
await openSeed(
|
||||
world.page,
|
||||
HISTORY_FIXTURE,
|
||||
HISTORY_FIXTURE.markers.assistant(HISTORY_FIXTURE.turns),
|
||||
)
|
||||
await expectBottom(world.page)
|
||||
|
||||
let releaseHistory = (): void => {}
|
||||
let held = false
|
||||
let releaseGate: (() => void) | undefined
|
||||
const gate = new Promise<void>((resolve) => { releaseGate = resolve })
|
||||
releaseHistory = () => { releaseGate?.() }
|
||||
await world.page.route('**/api/session.history', async (route) => {
|
||||
const request = route.request().postDataJSON() as {
|
||||
method?: string
|
||||
payload?: { beforeSeq?: number }
|
||||
}
|
||||
if (!held && request.method === 'session.history' && request.payload?.beforeSeq !== undefined) {
|
||||
held = true
|
||||
await gate
|
||||
}
|
||||
await route.continue()
|
||||
})
|
||||
|
||||
const settled = world.scaffold.whenTurnSettled(60_000)
|
||||
try {
|
||||
const composer = world.page.locator('textarea:enabled').last()
|
||||
await composer.fill(LIVE_TEXT_PROMPT)
|
||||
await world.page.getByRole('button', { name: 'Send message', exact: true }).click()
|
||||
await world.page.getByText(LIVE_TEXT_FIRST, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
await wheelToHistoryStart(world.page)
|
||||
const beforeTurns = await conversationTurns(world.page)
|
||||
await world.page.getByRole('button', { name: 'Load earlier', exact: true }).click()
|
||||
await expect.poll(() => held, { timeout: 10_000 }).toBe(true)
|
||||
|
||||
await wheelTranscript(world.page, 420)
|
||||
const readerAnchor = await visibleFlowAnchor(world.page)
|
||||
const chunksAfterAnchor = world.events.filter(event => event.type === 'assistant/chunk').length
|
||||
await expect.poll(
|
||||
() => world.events.filter(event => event.type === 'assistant/chunk').length,
|
||||
{ timeout: 10_000 },
|
||||
).toBeGreaterThan(chunksAfterAnchor + 5)
|
||||
|
||||
releaseHistory()
|
||||
await expect.poll(() => conversationTurns(world.page), { timeout: 30_000 }).toBeGreaterThan(beforeTurns)
|
||||
await nextPaint(world.page)
|
||||
await expectSameFlowTop(world.page, readerAnchor)
|
||||
} finally {
|
||||
releaseHistory()
|
||||
}
|
||||
|
||||
await settled
|
||||
await expect.poll(() => world.page.locator('[data-streaming="true"]').count(), { timeout: 15_000 }).toBe(0)
|
||||
await world.page.getByText(LIVE_TEXT_DONE, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
await world.page.unroute('**/api/session.history')
|
||||
|
||||
let additionalPages = 0
|
||||
while (additionalPages < 8) {
|
||||
await wheelToHistoryStart(world.page)
|
||||
if (await world.page.getByRole('button', { name: 'Load earlier', exact: true }).count() === 0) break
|
||||
await loadEarlierWithAnchor(world.page)
|
||||
additionalPages += 1
|
||||
}
|
||||
expect(additionalPages).toBeGreaterThan(0)
|
||||
expect(await conversationTurns(world.page)).toBe(HISTORY_FIXTURE.turns + 1)
|
||||
expect(await world.page.getByRole('button', { name: 'Load earlier', exact: true }).count()).toBe(0)
|
||||
assertClean(world)
|
||||
})
|
||||
}, 180_000)
|
||||
|
||||
it.skipIf(MODE === 'record')('keeps streaming ownership and tool disclosure state across a long scroll-away cycle', async () => {
|
||||
await withScrollWorld({
|
||||
failureShot: 'web-e2e-chat-scroll-live-tool',
|
||||
replay: [
|
||||
replayEntry(toolStream()),
|
||||
replayEntry(textStream(LIVE_TOOL_FIRST, LIVE_TOOL_DONE, 84)),
|
||||
],
|
||||
seeds: [{ fixture: TOOL_FIXTURE, id: TOOL_SESSION_ID }],
|
||||
}, async (world) => {
|
||||
const readyPath = join(world.scaffold.workspaceCwd, TOOL_READY_FILE)
|
||||
const releasePath = join(world.scaffold.workspaceCwd, TOOL_RELEASE_FILE)
|
||||
await openSeed(world.page, TOOL_FIXTURE, TOOL_FIXTURE.markers.assistant(TOOL_FIXTURE.turns))
|
||||
const settled = world.scaffold.whenTurnSettled(60_000)
|
||||
let released = false
|
||||
try {
|
||||
const composer = world.page.locator('textarea:enabled').last()
|
||||
await composer.fill(LIVE_TOOL_PROMPT)
|
||||
await world.page.getByRole('button', { name: 'Send message', exact: true }).click()
|
||||
await expect.poll(() => fileExists(readyPath), { timeout: 15_000 }).toBe(true)
|
||||
const liveRow = world.page.locator(`[data-chat-call-id="${LIVE_TOOL_CALL_ID}"] [data-sample="bash-global"]`)
|
||||
await liveRow.waitFor({ timeout: 15_000 })
|
||||
expect(await liveRow.getAttribute('data-state')).toBe('running')
|
||||
await expectBottom(world.page)
|
||||
|
||||
await wheelTranscript(world.page, -1_200)
|
||||
await world.page.getByRole('button', { name: 'Back to bottom', exact: true }).waitFor({ timeout: 10_000 })
|
||||
const awayAnchor = await visibleFlowAnchor(world.page)
|
||||
const chunksBeforeRelease = world.events.filter(event => event.type === 'assistant/chunk').length
|
||||
await writeFile(releasePath, 'release\n')
|
||||
released = true
|
||||
await expect.poll(
|
||||
() => world.events.some(event => event.type === 'tool/result'),
|
||||
{ timeout: 15_000 },
|
||||
).toBe(true)
|
||||
await expect.poll(
|
||||
() => world.events.some(event => eventCarries(event, LIVE_TOOL_FIRST)),
|
||||
{ timeout: 15_000 },
|
||||
).toBe(true)
|
||||
await expect.poll(
|
||||
() => world.events.filter(event => event.type === 'assistant/chunk').length,
|
||||
{ timeout: 15_000 },
|
||||
).toBeGreaterThan(chunksBeforeRelease + 5)
|
||||
await expectSameFlowTop(world.page, awayAnchor)
|
||||
|
||||
const chunksAtRepin = world.events.filter(event => event.type === 'assistant/chunk').length
|
||||
await world.page.getByRole('button', { name: 'Back to bottom', exact: true }).click()
|
||||
await expectBottom(world.page)
|
||||
await expect.poll(
|
||||
() => world.events.filter(event => event.type === 'assistant/chunk').length,
|
||||
{ timeout: 15_000 },
|
||||
).toBeGreaterThan(chunksAtRepin + 5)
|
||||
await expectBottom(world.page)
|
||||
} finally {
|
||||
if (!released) await writeFile(releasePath, 'release\n').catch(() => {})
|
||||
}
|
||||
|
||||
await settled
|
||||
await expect.poll(() => world.page.locator('[data-streaming="true"]').count(), { timeout: 15_000 }).toBe(0)
|
||||
await world.page.getByText(LIVE_TOOL_DONE, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
await expectBottom(world.page)
|
||||
await expectMarkerAboveComposer(world.page, LIVE_TOOL_DONE)
|
||||
|
||||
const liveRowSelector = `[data-chat-call-id="${LIVE_TOOL_CALL_ID}"] [data-sample="bash-global"]`
|
||||
const liveRow = world.page.locator(liveRowSelector)
|
||||
await liveRow.scrollIntoViewIfNeeded()
|
||||
await nextPaint(world.page)
|
||||
const toolAnchor = await liveRow.evaluate((row) => {
|
||||
const flow = row.closest<HTMLElement>('[data-chat-anchor-key]')
|
||||
const host = row.closest<HTMLElement>('[data-conversation-scroll]')
|
||||
if (flow?.dataset.chatAnchorKey === undefined || host === null) {
|
||||
throw new Error('live tool row has no settled flow identity')
|
||||
}
|
||||
return {
|
||||
key: flow.dataset.chatAnchorKey,
|
||||
top: flow.getBoundingClientRect().top - host.getBoundingClientRect().top,
|
||||
}
|
||||
})
|
||||
await liveRow.click()
|
||||
await expect.poll(() => liveRow.getAttribute('aria-expanded'), { timeout: 10_000 }).toBe('true')
|
||||
await expectSameFlowTop(world.page, toolAnchor)
|
||||
await wheelToHistoryStart(world.page)
|
||||
await world.page.getByRole('button', { name: 'Back to bottom', exact: true }).click()
|
||||
await expectBottom(world.page)
|
||||
await wheelUntilMounted(world.page, liveRowSelector, -1_100)
|
||||
const restoredRow = world.page.locator(liveRowSelector)
|
||||
await restoredRow.waitFor({ timeout: 10_000 })
|
||||
expect(await restoredRow.getAttribute('aria-expanded')).toBe('true')
|
||||
expect(await world.page.getByText(LIVE_TOOL_RESULT, { exact: false }).count()).toBeGreaterThan(0)
|
||||
assertClean(world)
|
||||
})
|
||||
}, 180_000)
|
||||
|
||||
it.skipIf(MODE === 'record')('restores tab/session position and keeps composer resizing on the correct scroll owner', async () => {
|
||||
await withScrollWorld({
|
||||
failureShot: 'web-e2e-chat-scroll-restore-composer',
|
||||
seeds: [
|
||||
{ fixture: RESTORE_FIXTURE_A, id: RESTORE_SESSION_A_ID },
|
||||
{ fixture: RESTORE_FIXTURE_B, id: RESTORE_SESSION_B_ID },
|
||||
],
|
||||
}, async (world) => {
|
||||
await openSeed(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_A,
|
||||
RESTORE_FIXTURE_A.markers.assistant(RESTORE_FIXTURE_A.turns),
|
||||
)
|
||||
await loadEarlierWithAnchor(world.page)
|
||||
await loadEarlierWithAnchor(world.page)
|
||||
await wheelToHistoryStart(world.page)
|
||||
await wheelTranscript(world.page, 1_300)
|
||||
const sessionAnchor = await visibleFlowAnchor(world.page)
|
||||
|
||||
await world.page.getByRole('tab', { name: 'Trajectory', exact: true }).click()
|
||||
await world.page.getByLabel('Trajectory timeline').waitFor({ timeout: 30_000 })
|
||||
await world.page.setViewportSize({ width: 700, height: 900 })
|
||||
await world.page.getByRole('tab', { name: 'Chat', exact: true }).click()
|
||||
await nextPaint(world.page)
|
||||
await expectSameFlowTop(world.page, sessionAnchor)
|
||||
|
||||
await openSeed(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_B,
|
||||
RESTORE_FIXTURE_B.markers.assistant(RESTORE_FIXTURE_B.turns),
|
||||
)
|
||||
await openSeed(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_A,
|
||||
)
|
||||
await expectSameFlowTop(world.page, sessionAnchor)
|
||||
|
||||
const backToBottom = world.page.getByRole('button', { name: 'Back to bottom', exact: true })
|
||||
await backToBottom.evaluate((button) => {
|
||||
if (!(button instanceof HTMLElement)) throw new Error('Back-to-bottom control is not an HTML element')
|
||||
button.click()
|
||||
const trajectory = [...document.querySelectorAll<HTMLElement>('[role="tab"]')]
|
||||
.find(tab => tab.textContent?.trim() === 'Trajectory')
|
||||
if (!(trajectory instanceof HTMLElement)) {
|
||||
throw new Error('Trajectory tab is unavailable during pinned remount')
|
||||
}
|
||||
trajectory.click()
|
||||
})
|
||||
await world.page.getByLabel('Trajectory timeline').waitFor({ timeout: 30_000 })
|
||||
await world.page.getByRole('tab', { name: 'Chat', exact: true }).click()
|
||||
await expectBottom(world.page)
|
||||
await openSeed(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_B,
|
||||
RESTORE_FIXTURE_B.markers.assistant(RESTORE_FIXTURE_B.turns),
|
||||
)
|
||||
await openSeed(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_A,
|
||||
RESTORE_FIXTURE_A.markers.assistant(RESTORE_FIXTURE_A.turns),
|
||||
)
|
||||
await expectBottom(world.page)
|
||||
const composer = world.page.locator('textarea:enabled').last()
|
||||
const longDraft = Array.from(
|
||||
{ length: 18 },
|
||||
(_, index) => `composer resize line ${String(index + 1).padStart(2, '0')}`,
|
||||
).join('\n')
|
||||
await composer.fill(longDraft)
|
||||
await nextPaint(world.page)
|
||||
await expectBottom(world.page)
|
||||
await expectMarkerAboveComposer(
|
||||
world.page,
|
||||
RESTORE_FIXTURE_A.markers.assistant(RESTORE_FIXTURE_A.turns),
|
||||
)
|
||||
|
||||
await composer.fill('short draft')
|
||||
await nextPaint(world.page)
|
||||
await wheelTranscript(world.page, -900)
|
||||
const resizeAnchor = await visibleFlowAnchor(world.page)
|
||||
await composer.fill(longDraft)
|
||||
await nextPaint(world.page)
|
||||
await expectSameFlowTop(world.page, resizeAnchor)
|
||||
await composer.fill('short draft')
|
||||
await nextPaint(world.page)
|
||||
await expectSameFlowTop(world.page, resizeAnchor)
|
||||
|
||||
const beforeChain = await scrollGeometry(world.page)
|
||||
await composer.hover()
|
||||
await world.page.mouse.wheel(0, -320)
|
||||
await expect.poll(async () => (await scrollGeometry(world.page)).scrollTop, { timeout: 10_000 })
|
||||
.toBeLessThan(beforeChain.scrollTop)
|
||||
assertClean(world)
|
||||
})
|
||||
}, 180_000)
|
||||
})
|
||||
235
apps/web/tests/chat-scroll-fixture.ts
Normal file
235
apps/web/tests/chat-scroll-fixture.ts
Normal file
@@ -0,0 +1,235 @@
|
||||
// Synthetic long-chat history for browser behavior contracts. The fixture is
|
||||
// generated through Session so pagination exercises the same event shapes as
|
||||
// persisted conversations, while unique markers let tests identify semantic
|
||||
// rows without depending on CSS-module names or the eventual virtualizer DOM.
|
||||
import {
|
||||
CallId,
|
||||
createAssistantMessage,
|
||||
createToolResultMessage,
|
||||
createUserMessage,
|
||||
} from '@deepseek-ai/dsh-llm'
|
||||
import {
|
||||
SESSION_FORMAT_VERSION,
|
||||
Session,
|
||||
SessionId,
|
||||
} from '@deepseek-ai/dsh-session'
|
||||
// Carries the session/title event declaration into this fixture builder.
|
||||
import type {} from '@deepseek-ai/dsh-session-title'
|
||||
|
||||
/** Options for one deterministic long-chat fixture. */
|
||||
export interface ChatScrollFixtureOptions {
|
||||
/** Marker namespace, used when two sessions share one browser world. */
|
||||
readonly markerPrefix: string
|
||||
/** Searchable title projected into the sidebar. */
|
||||
readonly title: string
|
||||
/** Number of closed turns to generate. */
|
||||
readonly turns?: number
|
||||
}
|
||||
|
||||
/** Semantic marker helpers returned with a generated fixture. */
|
||||
export interface ChatScrollMarkers {
|
||||
/** Marker painted in the human message for a turn. */
|
||||
user(turn: number): string
|
||||
/** Marker painted in the final assistant message for a turn. */
|
||||
assistant(turn: number): string
|
||||
/** Marker painted in one seeded bash call and result. */
|
||||
tool(turn: number, index: number): string
|
||||
}
|
||||
|
||||
/** Generated JSONL plus the stable facts browser scenarios assert. */
|
||||
export interface ChatScrollFixture {
|
||||
readonly log: string
|
||||
readonly markers: ChatScrollMarkers
|
||||
readonly title: string
|
||||
readonly turns: number
|
||||
}
|
||||
|
||||
const DEFAULT_TURNS = 88
|
||||
const TOOL_INTERVAL = 8
|
||||
const CODE_INTERVAL = 11
|
||||
|
||||
function text(value: string): { type: 'text'; text: string }[] {
|
||||
return [{ type: 'text', text: value }]
|
||||
}
|
||||
|
||||
function suffix(turn: number): string {
|
||||
return String(turn).padStart(3, '0')
|
||||
}
|
||||
|
||||
function markerHelpers(prefix: string): ChatScrollMarkers {
|
||||
return {
|
||||
user: turn => `CHAT_SCROLL_${prefix}_USER_${suffix(turn)}`,
|
||||
assistant: turn => `CHAT_SCROLL_${prefix}_ASSISTANT_${suffix(turn)}`,
|
||||
tool: (turn, index) => `CHAT_SCROLL_${prefix}_TOOL_${suffix(turn)}_${String(index)}`,
|
||||
}
|
||||
}
|
||||
|
||||
function appendRequestHeader(session: Session, turn: number, step: number): void {
|
||||
session.append('request/header', {
|
||||
header: {
|
||||
config: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
system: `Synthetic chat-scroll request for turn ${String(turn)}, step ${String(step)}.`,
|
||||
},
|
||||
reason: turn === 1 && step === 1 ? 'initial' : 'change',
|
||||
})
|
||||
}
|
||||
|
||||
function appendAssistant(session: Session, turn: number, step: number, body: string): void {
|
||||
session.append('assistant/message', {
|
||||
turn,
|
||||
step,
|
||||
message: createAssistantMessage({
|
||||
content: text(body),
|
||||
source: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
}),
|
||||
usage: {
|
||||
inputTokens: 2_000 + turn * 7,
|
||||
outputTokens: 180 + step * 20,
|
||||
},
|
||||
}, { surfaceOp: 'append' })
|
||||
}
|
||||
|
||||
function codeBlock(turn: number): string {
|
||||
if (turn % CODE_INTERVAL !== 0) return ''
|
||||
const lines = Array.from(
|
||||
{ length: 30 },
|
||||
(_, index) => `const scroll_case_${suffix(turn)}_${String(index).padStart(2, '0')} = ${String(turn + index)}`,
|
||||
)
|
||||
return `\n\n\`\`\`ts\n${lines.join('\n')}\n\`\`\``
|
||||
}
|
||||
|
||||
function appendToolStep(
|
||||
session: Session,
|
||||
markers: ChatScrollMarkers,
|
||||
turn: number,
|
||||
): void {
|
||||
const calls = [1, 2].map((index) => {
|
||||
const marker = markers.tool(turn, index)
|
||||
const callId = CallId(`chat-scroll-${suffix(turn)}-${String(index)}`)
|
||||
const args = JSON.stringify({
|
||||
command: `printf '${marker}\\n'`,
|
||||
description: marker,
|
||||
})
|
||||
return { args, callId, marker }
|
||||
})
|
||||
|
||||
session.append('assistant/message', {
|
||||
turn,
|
||||
step: 1,
|
||||
message: createAssistantMessage({
|
||||
content: [
|
||||
{ type: 'reasoning', text: `Inspecting two scroll fixtures for turn ${String(turn)}.` },
|
||||
...calls.map(call => ({
|
||||
type: 'tool-call' as const,
|
||||
id: call.callId,
|
||||
name: 'bash',
|
||||
arguments: call.args,
|
||||
})),
|
||||
],
|
||||
source: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
}),
|
||||
usage: { inputTokens: 2_000 + turn * 7, outputTokens: 240, reasoningTokens: 30 },
|
||||
}, { surfaceOp: 'append' })
|
||||
|
||||
for (const call of calls) {
|
||||
const source = session.append('tool/call', {
|
||||
turn,
|
||||
step: 1,
|
||||
callId: call.callId,
|
||||
name: 'bash',
|
||||
arguments: call.args,
|
||||
})
|
||||
session.append('tool/result', {
|
||||
turn,
|
||||
step: 1,
|
||||
message: createToolResultMessage({
|
||||
callId: call.callId,
|
||||
content: text(Array.from(
|
||||
{ length: 12 },
|
||||
(_, line) => `${call.marker} output line ${String(line + 1).padStart(2, '0')}`,
|
||||
).join('\n')),
|
||||
isError: false,
|
||||
}),
|
||||
}, { surfaceOp: 'append', sourceEventSeqs: [source.seq] })
|
||||
}
|
||||
}
|
||||
|
||||
function fixtureLog(session: Session): string {
|
||||
return [
|
||||
JSON.stringify({
|
||||
type: 'session',
|
||||
version: SESSION_FORMAT_VERSION,
|
||||
id: '{{sessionId}}',
|
||||
createdAt: Date.now() - 60_000,
|
||||
cwd: '{{cwd}}',
|
||||
delegationDepth: 0,
|
||||
}),
|
||||
...session.events.map(event => JSON.stringify(event)),
|
||||
'',
|
||||
].join('\n')
|
||||
}
|
||||
|
||||
/**
|
||||
* Build a multi-page conversation with prose, fenced code, and paired bash
|
||||
* calls/results. Every turn is closed, so cold resume cannot repair or mutate
|
||||
* the seed before the browser observes it.
|
||||
* @param options - Fixture identity and optional turn count.
|
||||
* @returns Canonical JSONL and semantic marker helpers.
|
||||
*/
|
||||
export function createChatScrollFixture(options: ChatScrollFixtureOptions): ChatScrollFixture {
|
||||
const turns = options.turns ?? DEFAULT_TURNS
|
||||
const markers = markerHelpers(options.markerPrefix)
|
||||
const session = new Session(SessionId(`chat-scroll-${options.markerPrefix.toLowerCase()}-template`))
|
||||
|
||||
for (let turn = 1; turn <= turns; turn += 1) {
|
||||
session.append('turn/start', {
|
||||
turn,
|
||||
trigger: { kind: 'message', source: { kind: 'user' } },
|
||||
})
|
||||
const user = session.append('user/message', createUserMessage({
|
||||
content: text(
|
||||
`${markers.user(turn)} Review the long-running conversation state for turn ${String(turn)}. `
|
||||
+ 'Keep the visible message stable while history, tools, and new output change around it.',
|
||||
),
|
||||
source: { kind: 'user' },
|
||||
}), { surfaceOp: 'append' })
|
||||
if (turn === 1) {
|
||||
session.append('session/title', {
|
||||
title: options.title,
|
||||
messageSeqs: [user.seq],
|
||||
source: { kind: 'fallback' },
|
||||
})
|
||||
}
|
||||
|
||||
session.append('step/start', { turn, step: 1 })
|
||||
appendRequestHeader(session, turn, 1)
|
||||
if (turn % TOOL_INTERVAL === 0) {
|
||||
appendToolStep(session, markers, turn)
|
||||
session.append('step/end', { turn, step: 1 })
|
||||
session.append('step/start', { turn, step: 2 })
|
||||
appendRequestHeader(session, turn, 2)
|
||||
appendAssistant(
|
||||
session,
|
||||
turn,
|
||||
2,
|
||||
`${markers.assistant(turn)} Both tool results are accounted for. `
|
||||
+ `This settled response keeps turn ${String(turn)} identifiable after paging.${codeBlock(turn)}`,
|
||||
)
|
||||
session.append('step/end', { turn, step: 2 })
|
||||
} else {
|
||||
appendAssistant(
|
||||
session,
|
||||
turn,
|
||||
1,
|
||||
`${markers.assistant(turn)} The conversation remains readable after several paragraphs.\n\n`
|
||||
+ `Turn ${String(turn)} deliberately carries enough prose to wrap at narrower viewport widths. `
|
||||
+ 'The semantic marker stays near the start so geometry probes can find the same rendered row.\n\n'
|
||||
+ `The closing paragraph makes this a realistic assistant response rather than a one-line list item.${codeBlock(turn)}`,
|
||||
)
|
||||
session.append('step/end', { turn, step: 1 })
|
||||
}
|
||||
session.append('turn/end', { turn, reason: { kind: 'completed' } })
|
||||
}
|
||||
|
||||
return { log: fixtureLog(session), markers, title: options.title, turns }
|
||||
}
|
||||
@@ -50,6 +50,7 @@ const COMPARISON_TURNS = 8
|
||||
const COMPARISON_DELTA_COUNT = 24
|
||||
const COMPARISON_TOOL_INTERVAL = 3
|
||||
const SOAK_TURNS = 100
|
||||
const POST_SOAK_RENDER_TURN = SOAK_TURNS + 1
|
||||
const SOAK_DELTA_COUNT = 8
|
||||
const SOAK_TOOL_INTERVAL = 10
|
||||
const SOAK_CHECKPOINT_INTERVAL = 10
|
||||
@@ -107,6 +108,15 @@ interface MutationProbeResult {
|
||||
readonly records: number
|
||||
}
|
||||
|
||||
interface UserRenderProbeResult {
|
||||
readonly trustedClick: boolean
|
||||
readonly sendToDomMs: number
|
||||
readonly sendToPaintMs: number
|
||||
readonly domToPaintMs: number
|
||||
readonly mutationBatches: number
|
||||
readonly mutationRecords: number
|
||||
}
|
||||
|
||||
interface RetainedBrowserState {
|
||||
readonly domElements: number
|
||||
readonly nodes: number
|
||||
@@ -608,6 +618,168 @@ async function stopMutationProbe(page: Page): Promise<MutationProbeResult> {
|
||||
})
|
||||
}
|
||||
|
||||
async function startUserRenderProbe(
|
||||
page: Page,
|
||||
marker: string,
|
||||
): Promise<void> {
|
||||
const send = page.getByRole('button', { name: 'Send message', exact: true })
|
||||
await send.waitFor({ timeout: 15_000 })
|
||||
await expect.poll(() => send.isEnabled(), { timeout: 15_000 }).toBe(true)
|
||||
await page.evaluate((expectedMarker) => {
|
||||
const target = document.querySelector('[data-conversation-scroll]')
|
||||
if (target === null) throw new Error('user render probe target is unavailable')
|
||||
const probe: {
|
||||
sendAt?: number
|
||||
domAt?: number
|
||||
paintAt?: number
|
||||
trustedClick?: boolean
|
||||
batches: number
|
||||
records: number
|
||||
observer?: MutationObserver
|
||||
pollForMarker?: () => void
|
||||
} = { batches: 0, records: 0 }
|
||||
const transcriptContainsMarker = (): boolean => {
|
||||
// The composer projects the draft into a backdrop and hidden sizing
|
||||
// mirror; only a matching text node outside that card proves delivery.
|
||||
const walker = document.createTreeWalker(target, NodeFilter.SHOW_TEXT)
|
||||
for (let node = walker.nextNode(); node !== null; node = walker.nextNode()) {
|
||||
if (!node.textContent?.includes(expectedMarker)) continue
|
||||
const parent = node.parentElement
|
||||
if (parent !== null && parent.closest('[data-composer-card]') === null) return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
const markDomVisible = (): void => {
|
||||
if (
|
||||
probe.sendAt === undefined
|
||||
|| probe.domAt !== undefined
|
||||
|| !transcriptContainsMarker()
|
||||
) return
|
||||
probe.domAt = globalThis.performance.now()
|
||||
// The second callback runs only after a render opportunity for the DOM
|
||||
// insertion observed before the first callback.
|
||||
requestAnimationFrame(() => {
|
||||
requestAnimationFrame(() => {
|
||||
probe.paintAt = globalThis.performance.now()
|
||||
observer.disconnect()
|
||||
})
|
||||
})
|
||||
}
|
||||
const pollForMarker = (): void => {
|
||||
markDomVisible()
|
||||
if (probe.domAt === undefined) requestAnimationFrame(pollForMarker)
|
||||
}
|
||||
const observer = new MutationObserver((records) => {
|
||||
if (probe.sendAt === undefined) return
|
||||
probe.batches += 1
|
||||
probe.records += records.length
|
||||
markDomVisible()
|
||||
})
|
||||
probe.observer = observer
|
||||
probe.pollForMarker = pollForMarker
|
||||
observer.observe(target, {
|
||||
attributes: true,
|
||||
attributeFilter: ['data-streaming'],
|
||||
characterData: true,
|
||||
childList: true,
|
||||
subtree: true,
|
||||
})
|
||||
Reflect.set(globalThis, '__dshPerfUserRenderProbe', probe)
|
||||
}, marker)
|
||||
await send.evaluate((button) => {
|
||||
button.addEventListener('click', (event) => {
|
||||
const probe = Reflect.get(globalThis, '__dshPerfUserRenderProbe') as
|
||||
| { sendAt?: number; trustedClick?: boolean; pollForMarker?: () => void }
|
||||
| undefined
|
||||
if (probe?.pollForMarker === undefined) throw new Error('user render probe was not started')
|
||||
probe.trustedClick = event.isTrusted
|
||||
probe.sendAt = globalThis.performance.now()
|
||||
requestAnimationFrame(probe.pollForMarker)
|
||||
}, { capture: true, once: true })
|
||||
})
|
||||
}
|
||||
|
||||
async function triggerUserRenderProbe(page: Page): Promise<void> {
|
||||
const send = page.getByRole('button', { name: 'Send message', exact: true })
|
||||
await send.click()
|
||||
}
|
||||
|
||||
async function stopUserRenderProbe(
|
||||
page: Page,
|
||||
marker: string,
|
||||
): Promise<UserRenderProbeResult> {
|
||||
try {
|
||||
await page.waitForFunction(() => {
|
||||
const probe = Reflect.get(globalThis, '__dshPerfUserRenderProbe') as
|
||||
| { paintAt?: number }
|
||||
| undefined
|
||||
return probe?.paintAt !== undefined
|
||||
}, undefined, { timeout: 15_000 })
|
||||
} catch (error) {
|
||||
const diagnostic = await page.evaluate((expectedMarker) => {
|
||||
const probe = Reflect.get(globalThis, '__dshPerfUserRenderProbe') as
|
||||
| {
|
||||
sendAt?: number
|
||||
domAt?: number
|
||||
paintAt?: number
|
||||
trustedClick?: boolean
|
||||
batches: number
|
||||
records: number
|
||||
}
|
||||
| undefined
|
||||
const target = document.querySelector('[data-conversation-scroll]')
|
||||
let markerOutsideComposer = false
|
||||
if (target !== null) {
|
||||
const walker = document.createTreeWalker(target, NodeFilter.SHOW_TEXT)
|
||||
for (let node = walker.nextNode(); node !== null; node = walker.nextNode()) {
|
||||
if (!node.textContent?.includes(expectedMarker)) continue
|
||||
const parent = node.parentElement
|
||||
if (parent !== null && parent.closest('[data-composer-card]') === null) {
|
||||
markerOutsideComposer = true
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
return {
|
||||
probe,
|
||||
markerOutsideComposer,
|
||||
markerInComposer: document.querySelector('[data-composer-card]')
|
||||
?.textContent?.includes(expectedMarker) ?? false,
|
||||
}
|
||||
}, marker)
|
||||
throw new Error(`user render probe timed out: ${JSON.stringify(diagnostic)}`, { cause: error })
|
||||
}
|
||||
return page.evaluate(() => {
|
||||
const probe = Reflect.get(globalThis, '__dshPerfUserRenderProbe') as
|
||||
| {
|
||||
sendAt?: number
|
||||
domAt?: number
|
||||
paintAt?: number
|
||||
trustedClick?: boolean
|
||||
batches: number
|
||||
records: number
|
||||
}
|
||||
| undefined
|
||||
Reflect.deleteProperty(globalThis, '__dshPerfUserRenderProbe')
|
||||
if (
|
||||
probe?.trustedClick !== true
|
||||
|| probe.sendAt === undefined
|
||||
|| probe.domAt === undefined
|
||||
|| probe.paintAt === undefined
|
||||
) {
|
||||
throw new Error('user render probe did not observe a trusted click, DOM insertion, and paint')
|
||||
}
|
||||
return {
|
||||
trustedClick: probe.trustedClick,
|
||||
sendToDomMs: probe.domAt - probe.sendAt,
|
||||
sendToPaintMs: probe.paintAt - probe.sendAt,
|
||||
domToPaintMs: probe.paintAt - probe.domAt,
|
||||
mutationBatches: probe.batches,
|
||||
mutationRecords: probe.records,
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
async function stableCount(
|
||||
locator: Locator,
|
||||
accepts: (count: number) => boolean,
|
||||
@@ -887,6 +1059,77 @@ async function continueConversation(
|
||||
}
|
||||
}
|
||||
|
||||
async function measurePostSoakUserRender(
|
||||
world: PerformanceWorld,
|
||||
cdp: CDPSession,
|
||||
): Promise<object> {
|
||||
const spec = soakTurn(POST_SOAK_RENDER_TURN)
|
||||
if (spec.toolResultMarker !== undefined) {
|
||||
throw new Error('post-soak render probe must remain a text-only turn')
|
||||
}
|
||||
const composer = world.page.locator('textarea:enabled').last()
|
||||
const composerFill = await measure(cdp, async () => {
|
||||
await composer.fill(spec.prompt)
|
||||
await expect.poll(() => composer.inputValue()).toBe(spec.prompt)
|
||||
return (await composer.inputValue()).length
|
||||
})
|
||||
expect(composerFill.value).toBe(spec.prompt.length)
|
||||
|
||||
const eventStart = world.sessionEvents.length
|
||||
await startUserRenderProbe(world.page, spec.userMarker)
|
||||
const browserBefore = await chromiumMetrics(cdp)
|
||||
const fullTurnStarted = performance.now()
|
||||
const settled = world.scaffold.whenTurnSettled(60_000)
|
||||
await triggerUserRenderProbe(world.page)
|
||||
const browserTiming = await stopUserRenderProbe(world.page, spec.userMarker)
|
||||
const browserAfter = await chromiumMetrics(cdp)
|
||||
const browserAfterPaintSample = metricDelta(
|
||||
browserBefore,
|
||||
browserAfter,
|
||||
performance.now() - fullTurnStarted,
|
||||
)
|
||||
await world.page.getByText(spec.firstMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
const settledSessionId = await settled
|
||||
await expect.poll(
|
||||
() => world.page.locator('[data-streaming="true"]').count(),
|
||||
{ timeout: 15_000 },
|
||||
).toBe(0)
|
||||
await world.page.getByText(spec.doneMarker, { exact: false }).last().waitFor({ timeout: 15_000 })
|
||||
const fullTurnMs = performance.now() - fullTurnStarted
|
||||
|
||||
const turnEvents = world.sessionEvents.slice(eventStart)
|
||||
const chunks = turnEvents.filter(event => event.type === 'assistant/chunk')
|
||||
const user = turnEvents.find(
|
||||
event => event.type === 'user/message' && event.data.source.kind === 'user',
|
||||
)
|
||||
if (user?.type !== 'user/message') throw new Error('post-soak render probe did not log its user message')
|
||||
expect(user.data.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')).toBe(spec.prompt)
|
||||
expect(chunks).toHaveLength(spec.deltas.length + 4)
|
||||
expect(turnEvents.filter(event => event.type === 'tool/call')).toHaveLength(0)
|
||||
expect(turnEvents.filter(event => event.type === 'tool/result')).toHaveLength(0)
|
||||
expect(world.scaffold.ctx.agents.get(settledSessionId)).toBeDefined()
|
||||
expect(await conversationTurns(world.page)).toBe(POST_SOAK_RENDER_TURN)
|
||||
|
||||
return {
|
||||
ordinal: POST_SOAK_RENDER_TURN,
|
||||
resultingTurns: POST_SOAK_RENDER_TURN,
|
||||
promptChars: spec.prompt.length,
|
||||
composerFill: composerFill.measurement,
|
||||
trustedClick: browserTiming.trustedClick,
|
||||
sendToDomMs: rounded(browserTiming.sendToDomMs),
|
||||
sendToPaintMs: rounded(browserTiming.sendToPaintMs),
|
||||
domToPaintMs: rounded(browserTiming.domToPaintMs),
|
||||
mutationBatchesThroughPaint: browserTiming.mutationBatches,
|
||||
mutationRecordsThroughPaint: browserTiming.mutationRecords,
|
||||
browserAfterPaintSample,
|
||||
fullTurnMs: rounded(fullTurnMs),
|
||||
persistedChunks: chunks.length,
|
||||
}
|
||||
}
|
||||
|
||||
function average(values: readonly number[]): number {
|
||||
return rounded(values.reduce((sum, value) => sum + value, 0) / values.length)
|
||||
}
|
||||
@@ -1142,11 +1385,12 @@ describe('manual web performance: complex workspace and history', () => {
|
||||
}
|
||||
})
|
||||
|
||||
it('reports one hundred continuously generated turns with retained checkpoints', async () => {
|
||||
it('reports one hundred generated turns and the next user-message paint', async () => {
|
||||
const world = await launchPerformanceWorld({
|
||||
browser,
|
||||
replay: performanceReplayOverride(SOAK_TURNS, soakTurn),
|
||||
replay: performanceReplayOverride(POST_SOAK_RENDER_TURN, soakTurn),
|
||||
})
|
||||
let testFailure: unknown
|
||||
try {
|
||||
await world.page.goto(world.scaffold.baseUrl, { waitUntil: 'load' })
|
||||
await world.page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
@@ -1160,6 +1404,7 @@ describe('manual web performance: complex workspace and history', () => {
|
||||
checkpointInterval: SOAK_CHECKPOINT_INTERVAL,
|
||||
})
|
||||
expect(conversation.toolTurns).toBe(SOAK_TURNS / SOAK_TOOL_INTERVAL)
|
||||
const postSoakUserRender = await measurePostSoakUserRender(world, cdp)
|
||||
const { turns, ...retained } = conversation
|
||||
console.info(`WEB_PERF_RESULT ${JSON.stringify({
|
||||
scenario: 'continuous-100-turn-soak',
|
||||
@@ -1167,11 +1412,23 @@ describe('manual web performance: complex workspace and history', () => {
|
||||
replayContextWindow: PERF_REPLAY_CONTEXT_WINDOW,
|
||||
...retained,
|
||||
windows: summarizeTurnWindows(turns, SOAK_CHECKPOINT_INTERVAL),
|
||||
postSoakUserRender,
|
||||
}, null, 2)}`)
|
||||
expect(world.tripwire.warnings).toEqual([])
|
||||
expect(world.tripwire.pageErrors).toEqual([])
|
||||
} catch (error) {
|
||||
testFailure = error
|
||||
throw error
|
||||
} finally {
|
||||
await closePerformanceWorld(world)
|
||||
try {
|
||||
await closePerformanceWorld(world)
|
||||
} catch (cleanupError) {
|
||||
if (testFailure === undefined) throw cleanupError
|
||||
throw new AggregateError(
|
||||
[testFailure, cleanupError],
|
||||
'continuous conversation performance test and teardown failed',
|
||||
)
|
||||
}
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
@@ -9,9 +9,9 @@
|
||||
import { mkdir, readFile, writeFile } from 'node:fs/promises'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { join } from 'node:path'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
import type { Browser, Page, Response } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import { parseSessionLog } from '@deepseek-ai/dsh-llm-replay'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import {
|
||||
@@ -34,12 +34,46 @@ const SEED_ID = 'navigation-panes-web-e2e'
|
||||
const PROMPT_TURN1 = 'NavScenario: first run bash to print exactly NAVIGATION_OK, then read nav-a.md and nav-b.md using two read calls in ONE assistant message, then reply with the single word FIRST_DONE and stop.'
|
||||
const PROMPT_TURN2 = 'Reply in markdown with: a level-2 heading "Navigation Summary", a bulleted list of exactly two items, and a fenced code block containing echo WATERFALL. Then stop.'
|
||||
|
||||
async function baselineResponse(
|
||||
page: Page,
|
||||
method: 'session.list' | 'workspace.list',
|
||||
): Promise<Response> {
|
||||
return page.waitForResponse(response => (
|
||||
response.request().method() === 'POST'
|
||||
&& new URL(response.url()).pathname === `/api/${method}`
|
||||
), { timeout: 30_000 })
|
||||
}
|
||||
|
||||
async function assertBaselineSucceeded(response: Response, method: string): Promise<void> {
|
||||
expect(response.ok(), `${method} baseline HTTP response`).toBe(true)
|
||||
const body = await response.json() as { result?: { ok?: unknown } }
|
||||
expect(body.result?.ok, `${method} baseline RPC result`).toBe(true)
|
||||
}
|
||||
|
||||
async function ensureSeedOpen(page: Page): Promise<void> {
|
||||
const chat = page.getByRole('tab', { name: 'Chat', exact: true })
|
||||
const search = page.getByPlaceholder('Search name, keywords', { exact: false })
|
||||
if (await chat.count() === 0) {
|
||||
await search.fill('WATERFALL')
|
||||
const result = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
|
||||
await expect.poll(() => result.count(), { timeout: 15_000 }).toBe(1)
|
||||
await result.click()
|
||||
await chat.waitFor({ timeout: 15_000 })
|
||||
}
|
||||
await chat.click()
|
||||
await page.getByText('FIRST_DONE', { exact: true }).waitFor({ timeout: 15_000 })
|
||||
if (await search.inputValue() !== '') {
|
||||
await search.fill('')
|
||||
await expect.poll(() => search.inputValue(), { timeout: 5_000 }).toBe('')
|
||||
}
|
||||
}
|
||||
|
||||
describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
let scaffold: WebScaffold
|
||||
let browser: Browser
|
||||
let page: Page
|
||||
let tripwire: ReturnType<typeof watchConsole>
|
||||
let slotErrors: string[]
|
||||
let tripwire: ReturnType<typeof watchConsole> = { warnings: [], pageErrors: [] }
|
||||
let slotErrors: string[] = []
|
||||
|
||||
beforeAll(async () => {
|
||||
scaffold = await launchWebScaffold({})
|
||||
@@ -57,6 +91,9 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
await seedSession(scaffold, raw, SEED_ID)
|
||||
}
|
||||
browser = await chromium.launch()
|
||||
}, 120_000)
|
||||
|
||||
beforeEach(async () => {
|
||||
page = await newEnglishPage(browser)
|
||||
tripwire = watchConsole(page)
|
||||
slotErrors = []
|
||||
@@ -65,7 +102,19 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
slotErrors.push(message.text())
|
||||
}
|
||||
})
|
||||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||||
// Initial navigation and list ownership settle only after both independent
|
||||
// RPC baselines succeed; arm before navigation so neither response is missed.
|
||||
const sessionBaseline = baselineResponse(page, 'session.list')
|
||||
const workspaceBaseline = baselineResponse(page, 'workspace.list')
|
||||
const [, sessionResponse, workspaceResponse] = await Promise.all([
|
||||
page.goto(scaffold.baseUrl, { waitUntil: 'load' }),
|
||||
sessionBaseline,
|
||||
workspaceBaseline,
|
||||
])
|
||||
await Promise.all([
|
||||
assertBaselineSucceeded(sessionResponse, 'session.list'),
|
||||
assertBaselineSucceeded(workspaceResponse, 'workspace.list'),
|
||||
])
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
// The frame mounts before the asynchronous session-list baseline lands.
|
||||
// Search must target the settled seeded row, not the startup input that
|
||||
@@ -73,9 +122,32 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
|
||||
}, 120_000)
|
||||
|
||||
afterEach(async () => {
|
||||
const failures: unknown[] = []
|
||||
try {
|
||||
expect({
|
||||
pageErrors: tripwire.pageErrors,
|
||||
slotErrors,
|
||||
warnings: tripwire.warnings,
|
||||
}).toEqual({
|
||||
pageErrors: [],
|
||||
slotErrors: [],
|
||||
warnings: [],
|
||||
})
|
||||
} catch (error) {
|
||||
failures.push(error)
|
||||
}
|
||||
await page?.close().catch((error: unknown) => failures.push(error))
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'navigation case cleanup failed')
|
||||
})
|
||||
|
||||
afterAll(async () => {
|
||||
await browser?.close()
|
||||
await scaffold?.close()
|
||||
const failures: unknown[] = []
|
||||
await browser?.close().catch((error: unknown) => failures.push(error))
|
||||
await scaffold?.close().catch((error: unknown) => failures.push(error))
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'navigation e2e cleanup failed')
|
||||
})
|
||||
|
||||
it.skipIf(MODE !== 'record')('records the two-turn seed live through the composer', async () => {
|
||||
@@ -102,6 +174,9 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('finds an unopened seeded session by message content and opens it', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-search'))
|
||||
// The API baselines can settle before React commits their projection. The
|
||||
// seeded count is the final user-visible barrier before editing search.
|
||||
await page.getByText('1 session', { exact: true }).waitFor({ timeout: 30_000 })
|
||||
const search = page.getByPlaceholder('Search name, keywords', { exact: false })
|
||||
// The cold row has not been opened, so only the persisted log can satisfy
|
||||
// this query. First search lazily reconciles the SQLite content index.
|
||||
@@ -136,6 +211,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('renders the trajectory ledger and opens its local record inspector', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-trajectory'))
|
||||
await ensureSeedOpen(page)
|
||||
await page.getByRole('tab', { name: 'Trajectory' }).click()
|
||||
await page.waitForTimeout(100)
|
||||
const overlayLayout = await page.getByRole('table').evaluate((table) => {
|
||||
@@ -200,7 +276,10 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('focuses the ledger by dragging an overview interval', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-timeline'))
|
||||
await ensureSeedOpen(page)
|
||||
await page.getByRole('tab', { name: 'Trajectory' }).click()
|
||||
const plot = page.getByLabel('Timeline overview; drag horizontally to focus events')
|
||||
await plot.waitFor({ timeout: 15_000 })
|
||||
const before = await page.locator('tr[data-kind]').count()
|
||||
const box = await plot.boundingBox()
|
||||
if (box === null) throw new Error('trajectory timeline plot has no layout box')
|
||||
@@ -217,7 +296,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('bash and file-path rows leave the default details column closed', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-details'))
|
||||
await page.getByRole('tab', { name: 'Chat' }).click()
|
||||
await ensureSeedOpen(page)
|
||||
const bashRow = page.locator('[data-sample="bash"]').first()
|
||||
await bashRow.waitFor({ timeout: 15_000 })
|
||||
const frame = page.locator('[style*="grid-template-columns"]').first()
|
||||
@@ -239,9 +318,9 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
|
||||
it.skipIf(MODE === 'record')('renders the bash row as a terminal card in the real browser', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-navigation-terminal'))
|
||||
await page.getByRole('tab', { name: 'Chat' }).click()
|
||||
await ensureSeedOpen(page)
|
||||
// The card is expand-gated behind the whole-row toggle (the unified
|
||||
// tool-row interaction): open it if a previous case left it collapsed.
|
||||
// tool-row interaction): open it if this fresh view leaves it collapsed.
|
||||
// Expanded, the recorded command's own output sits in the message flow,
|
||||
// derived from the logged call/result presentations alone.
|
||||
const bashRow = page.locator('[data-sample="bash"]').first()
|
||||
@@ -322,10 +401,7 @@ describe('web e2e: navigation & panes over a rich seeded session', () => {
|
||||
expect(await page.evaluate(() => navigator.clipboard.readText())).toContain('NAVIGATION_OK')
|
||||
}, 60_000)
|
||||
|
||||
it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
|
||||
expect(tripwire.pageErrors).toEqual([])
|
||||
expect(slotErrors).toEqual([])
|
||||
expect(tripwire.warnings).toEqual([])
|
||||
it.skipIf(MODE === 'record')('keeps the recorded fixture inventory exact', async () => {
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, [
|
||||
'seed.jsonl', 'search-results.expected.md', 'trajectory.expected.md',
|
||||
'terminal-card.expected.md',
|
||||
|
||||
Reference in New Issue
Block a user