test(web): cover the settings surface and workspace management

Two new keyless scenarios for the functionality master gained since this
lane's base (#644 websettings, #643 workspace browser rework), both zero
model calls:

- settings-chrome: the modal shell (sidebar-foot trigger aria states,
  role=dialog, aria-current section switch to the deliberately empty
  Models, Escape + close-button paths, dialog aria golden); the Appearance
  row as the REAL theme gesture — retiring lifecycle-chrome's
  TODO(web-theme-gesture): clicking 深色 runs aria-pressed -> persisted
  dsh.theme -> body[data-ds-dark-theme] -> alias-token flip, survives
  reload, and 'system' follows the emulated OS scheme both ways; the
  Language row switches the settings-scoped copy to English (dsh.locale
  persisted, survives reload) and restores zh. Intentional reloads tear
  the SSE stream, so the spec drains exactly its own reconnect warnings —
  the tripwire still fails on unexpected connection loss.
- workspace-management: create-by-name twice through the region-header
  dialog (host-durable via ctx.workspace.list()); rename end to end —
  hover-revealed row menu (the button is display:none until the row
  hovers), duplicate-name pre-check (inline role=alert + disabled primary
  before any wire call), then workspace.rename through the real RPC,
  row update, host durability, reload survival; the flat 'In one list'
  view (section label flips, group headers drop, dsh.workspace.view
  persists across reload, grouped restored); the session hover card
  (dwell to open, closes on pointer leave). The one session row reuses
  seeded-history's committed seed — no new recording. Deliberately not
  driven: the inert menu rows and drag reorder (deferred in the note
  with re-entry triggers).

Agent Note gains scenarios 8-9 and the drag-reorder deferred item in both
languages; llm-replay README's zh side catches up with the { patches }
paragraph; pairings re-recorded.
This commit is contained in:
Tianyi Cui
2026-07-26 20:38:36 +08:00
parent 43ff7795ec
commit f8342b0a8e
12 changed files with 400 additions and 11 deletions

View File

@@ -124,10 +124,11 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
it.skipIf(MODE === 'record')('cascades the dark theme from the body attribute to painted surfaces', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-lifecycle-dark'))
// No product control flips the theme yet — the ThemeService's whole DOM
// contract is the body[data-ds-dark-theme] attribute, so the scenario
// drives exactly that seam and pins the shipped stylesheet's cascade.
// TODO(web-theme-gesture): drive a real settings control once one exists.
// This scenario pins the ThemeService's DOM contract seam directly (the
// body[data-ds-dark-theme] attribute -> stylesheet cascade); the REAL
// user gesture above it (Settings -> Appearance cubes) is owned by
// settings-chrome.e2e.ts. Driving the attribute here keeps the cascade
// pinned independently of the settings surface's own lifecycle.
const sample = async (): Promise<{ token: string; sidebarBg: string; bodyBg: string }> =>
await page.evaluate(() => {
const sidebar = document.querySelector('[class*="sidebar"], [class*="rail"]') ?? document.body

View File

@@ -0,0 +1,179 @@
// Web e2e scenarios: the settings surface — the modal shell (trigger, nav,
// section switching, both close paths), the Appearance preference row (the
// real theme gesture — click 深色 and the whole cascade runs: ThemeService preference -> localStorage dsh.theme
// -> theme/change -> ui-layout's presenter -> body attribute -> alias token)
// and the Language row (settings-scoped localization + persisted dsh.locale).
// Zero model calls: everything is pure client + persistence state on a blank
// frame, so there is no fixture and a stray stream would fail loud on the
// open llm seam.
import { fileURLToPath } from 'node:url'
import type { Browser, Page } from 'playwright'
import { chromium } from 'playwright'
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
import { join } from 'node:path'
import {
assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { saveFailureShot } from './support.ts'
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/settings-chrome', import.meta.url))
const DIALOG_EXPECTED = join(SNAPSHOT_DIR, 'dialog.expected.md')
const MODE = webSnapshotMode()
describe('web e2e: settings modal, appearance gesture, language switch', () => {
let scaffold: WebScaffold
let browser: Browser
let page: Page
let tripwire: ReturnType<typeof watchConsole>
beforeAll(async () => {
scaffold = await launchWebScaffold({})
browser = await chromium.launch()
page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
tripwire = watchConsole(page)
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
}, 120_000)
/**
* An INTENTIONAL reload tears the SSE stream mid-flight, so the dying
* page's reconnect note is expected — drain exactly those entries so the
* tripwire still fails the spec on any UNEXPECTED connection loss.
*/
const drainReloadWarnings = (): void => {
const kept = tripwire.warnings.filter(text => !/connection lost/i.test(text))
tripwire.warnings.length = 0
tripwire.warnings.push(...kept)
}
afterAll(async () => {
await browser?.close()
await scaffold?.close()
})
it('opens the settings dialog, switches sections, and closes by every path', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-settings-shell'))
const trigger = page.getByRole('button', { name: '设置', exact: true })
expect(await trigger.getAttribute('aria-haspopup')).toBe('dialog')
expect(await trigger.getAttribute('aria-expanded')).toBe('false')
await trigger.click()
const dialog = page.getByRole('dialog', { name: '设置' })
await dialog.waitFor({ timeout: 10_000 })
expect(await trigger.getAttribute('aria-expanded')).toBe('true')
// General is the active section by default; its skeleton rows plus the
// functional Language and Appearance rows render.
expect(await dialog.getByRole('button', { name: '通用设置' }).getAttribute('aria-current')).toBe('true')
await expect.poll(() => dialog.getByText('语言', { exact: true }).count(), { timeout: 5_000 }).toBe(1)
await expect.poll(() => dialog.getByText('外观', { exact: true }).count(), { timeout: 5_000 }).toBe(1)
// Golden of the freshly opened dialog (default zh, General active).
const snapshot = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(DIALOG_EXPECTED, snapshot, MODE)
// Section switch: aria-current moves; Models is deliberately empty.
await dialog.getByRole('button', { name: '模型' }).click()
await expect.poll(() => dialog.getByRole('button', { name: '模型' }).getAttribute('aria-current'), { timeout: 5_000 }).toBe('true')
expect(await dialog.getByRole('button', { name: '通用设置' }).getAttribute('aria-current')).toBeNull()
// Close path 1: Escape.
await page.keyboard.press('Escape')
await expect.poll(() => page.getByRole('dialog', { name: '设置' }).count(), { timeout: 5_000 }).toBe(0)
expect(await trigger.getAttribute('aria-expanded')).toBe('false')
// Close path 2: the header close button (focus lands there on open).
await trigger.click()
await page.getByRole('dialog', { name: '设置' }).getByRole('button', { name: '关闭' }).click()
await expect.poll(() => page.getByRole('dialog', { name: '设置' }).count(), { timeout: 5_000 }).toBe(0)
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('flips the theme through the Appearance cubes and persists across reload', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-settings-appearance'))
const readState = async (): Promise<{ attr: boolean; token: string; stored: string | null }> =>
await page.evaluate(() => ({
attr: document.body.hasAttribute('data-ds-dark-theme'),
token: getComputedStyle(document.body).getPropertyValue('--dsw-alias-bg-base').trim(),
stored: localStorage.getItem('dsh.theme'),
}))
// Pin the OS scheme to light so the default `system` preference resolves
// light and the dark flip below is unambiguously the gesture's doing.
await page.emulateMedia({ colorScheme: 'light' })
const light = await readState()
expect(light.attr).toBe(false)
await page.getByRole('button', { name: '设置', exact: true }).click()
const dialog = page.getByRole('dialog', { name: '设置' })
await dialog.waitFor({ timeout: 10_000 })
const darkCube = dialog.getByRole('button', { name: '深色' })
expect(await darkCube.getAttribute('aria-pressed')).toBe('false')
await darkCube.click()
// The full cascade: pressed state, persisted preference, body attribute,
// alias token flip — all from one real user gesture.
await expect.poll(() => darkCube.getAttribute('aria-pressed'), { timeout: 5_000 }).toBe('true')
const dark = await readState()
expect(dark.attr).toBe(true)
expect(dark.stored).toBe('dark')
expect(dark.token).not.toBe(light.token)
await page.keyboard.press('Escape')
// Reload: the preference survives boot (restore + presenter initial apply).
await page.reload({ waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
drainReloadWarnings()
await page.emulateMedia({ colorScheme: 'light' })
const reloaded = await readState()
expect(reloaded.attr).toBe(true)
expect(reloaded.stored).toBe('dark')
// `system` follows the emulated OS scheme (dark stays dark, light clears).
await page.getByRole('button', { name: '设置', exact: true }).click()
const systemCube = page.getByRole('dialog', { name: '设置' }).getByRole('button', { name: '跟随系统' })
await systemCube.click()
await expect.poll(() => systemCube.getAttribute('aria-pressed'), { timeout: 5_000 }).toBe('true')
await expect.poll(async () => (await readState()).attr, { timeout: 5_000 }).toBe(false)
await page.emulateMedia({ colorScheme: 'dark' })
await expect.poll(async () => (await readState()).attr, { timeout: 5_000 }).toBe(true)
// Restore for the specs that follow: light preference beats the emulated
// dark OS scheme, leaving the shared page in the light default.
await page.getByRole('dialog', { name: '设置' }).getByRole('button', { name: '浅色' }).click()
await expect.poll(async () => (await readState()).attr, { timeout: 5_000 }).toBe(false)
await page.keyboard.press('Escape')
expect(tripwire.pageErrors).toEqual([])
}, 90_000)
it('switches the settings surface language and persists dsh.locale', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-settings-language'))
await page.getByRole('button', { name: '设置', exact: true }).click()
const zhDialog = page.getByRole('dialog', { name: '设置' })
await zhDialog.waitFor({ timeout: 10_000 })
// The Language selector pill shows the active locale's own name.
const selector = zhDialog.getByRole('button', { name: '中文' })
expect(await selector.getAttribute('aria-haspopup')).toBe('menu')
await selector.click()
await page.getByRole('menuitem', { name: 'English' }).click()
// The settings-owned copy re-registers localized: dialog title, nav,
// Appearance labels. (Only the settings namespaces are localized today —
// the rest of the app's copy is intentionally out of this row's scope.)
const enDialog = page.getByRole('dialog', { name: 'Settings' })
await enDialog.waitFor({ timeout: 10_000 })
expect(await enDialog.getByRole('button', { name: 'General' }).getAttribute('aria-current')).toBe('true')
await expect.poll(() => enDialog.getByText('Appearance', { exact: true }).count(), { timeout: 5_000 }).toBe(1)
expect(await page.evaluate(() => localStorage.getItem('dsh.locale'))).toBe('en')
// Reload keeps English; then restore zh so shared page state (and the
// other specs' 设置-anchored selectors + goldens) see the default again.
await page.reload({ waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
drainReloadWarnings()
const enTrigger = page.getByRole('button', { name: 'Settings' })
await enTrigger.waitFor({ timeout: 10_000 })
await enTrigger.click()
await page.getByRole('dialog', { name: 'Settings' }).getByRole('button', { name: 'English' }).click()
await page.getByRole('menuitem', { name: '中文' }).click()
await page.getByRole('dialog', { name: '设置' }).waitFor({ timeout: 10_000 })
expect(await page.evaluate(() => localStorage.getItem('dsh.locale'))).toBe('zh')
await page.keyboard.press('Escape')
expect(tripwire.pageErrors).toEqual([])
}, 90_000)
it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
expect(tripwire.warnings).toEqual([])
await assertFixtureInventory(SNAPSHOT_DIR, ['dialog.expected.md'])
})
})

View File

@@ -0,0 +1,30 @@
- dialog "设置":
- navigation:
- text: 设置
- button "通用设置":
- img
- text: 通用设置
- button "模型":
- img
- text: 模型
- button "关闭":
- img
- text: 关闭
- text: 权限 选择默认权限模式
- button "Read only" [disabled]:
- text: Read only
- img
- text: 工具调用 Schema mode Traditional function calling — invoke tools one at a time Code mode Chain multiple tools with code — multi-step orchestration 语言
- button "中文":
- text: 中文
- img
- text: 外观
- button "浅色":
- img
- text: 浅色
- button "深色":
- img
- text: 深色
- button "跟随系统" [pressed]:
- img
- text: 跟随系统

View File

@@ -0,0 +1,169 @@
// Web e2e scenarios: workspace management — the create-by-name dialog, the
// rename round trip over the real wire (workspace.rename RPC + durable
// registry), duplicate-name pre-check, the flat "In one list" view with its
// persisted group-by preference, and the session hover card. Zero model
// calls: workspace.create/rename are host RPCs with no model involvement,
// and the one session row the flat/hover scenarios need comes from a seeded
// fixture (the seeded-history seed reused verbatim — no new recording).
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 { chromium } from 'playwright'
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
import {
assertFixtureInventory, launchWebScaffold, seedSession, watchConsole,
webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { saveFailureShot } from './support.ts'
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/workspace-management', import.meta.url))
// The seed is another scenario's committed fixture, reused read-only: this
// spec needs any one cold session row, not new recorded content.
const SEED = fileURLToPath(new URL('./snapshots/seeded-history/seed.jsonl', import.meta.url))
const MODE = webSnapshotMode()
const SEED_ID = 'workspace-management-web-e2e'
describe('web e2e: workspace management (create / rename / flat view / hover card)', () => {
let scaffold: WebScaffold
let browser: Browser
let page: Page
let tripwire: ReturnType<typeof watchConsole>
beforeAll(async () => {
scaffold = await launchWebScaffold({})
// Seed one cold session (Ungrouped bucket) for the flat view + hover card.
const sessionCwd = join(scaffold.workspaceCwd, 'workspace')
await mkdir(sessionCwd, { recursive: true })
await writeFile(join(sessionCwd, 'a.txt'), 'alpha\n')
await writeFile(join(sessionCwd, 'b.txt'), 'beta\n')
await seedSession(scaffold, await readFile(SEED, 'utf8'), SEED_ID)
browser = await chromium.launch()
page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
tripwire = watchConsole(page)
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
}, 120_000)
/**
* An INTENTIONAL reload tears the SSE stream mid-flight, so the dying
* page's reconnect note is expected — drain exactly those entries so the
* tripwire still fails the spec on any UNEXPECTED connection loss.
*/
const drainReloadWarnings = (): void => {
const kept = tripwire.warnings.filter(text => !/connection lost/i.test(text))
tripwire.warnings.length = 0
tripwire.warnings.push(...kept)
}
afterAll(async () => {
await browser?.close()
await scaffold?.close()
})
it('creates two workspaces by name through the region-header dialog', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-create'))
const createByName = async (name: string): Promise<void> => {
await page.getByRole('button', { name: 'Create workspace' }).click()
// The pick menu's Create workspace submenu opens on hover/focus.
await page.getByRole('menuitem', { name: 'Create workspace' }).hover()
await page.getByRole('menuitem', { name: 'Create a new workspace' }).click()
const dialog = page.getByRole('dialog', { name: 'Create a new workspace' })
await dialog.waitFor({ timeout: 10_000 })
await dialog.getByLabel('New workspace name').fill(name)
await dialog.getByRole('button', { name: 'Create workspace' }).click()
await expect.poll(() => page.getByRole('dialog', { name: 'Create a new workspace' }).count(), { timeout: 10_000 }).toBe(0)
// The real workspace materializes in the tree as a group row.
await expect.poll(() => page.getByText(name, { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
}
await createByName('alpha-ws')
await createByName('beta-ws')
// Durable on the host: both registered, newest first (create prepends).
const titles = scaffold.ctx.workspace.list().map(workspace => workspace.title)
expect(titles.slice(0, 2)).toEqual(['beta-ws', 'alpha-ws'])
expect(tripwire.pageErrors).toEqual([])
}, 90_000)
it('renames a workspace over the wire with a duplicate-name pre-check', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-rename'))
// The actions button is display:none until its row hovers — hover the
// group row first, then the revealed button becomes actionable.
await page.locator('[role="treeitem"]').filter({ hasText: 'alpha-ws' }).first().hover()
await page.getByRole('button', { name: 'Workspace actions for alpha-ws' }).click()
await page.getByRole('menuitem', { name: 'Rename' }).click()
const dialog = page.getByRole('dialog', { name: 'Rename workspace' })
await dialog.waitFor({ timeout: 10_000 })
const input = dialog.getByLabel('Workspace name')
// Client pre-check: a name colliding with another live workspace raises
// the inline alert and blocks the primary button before any wire call.
await input.fill('beta-ws')
await expect.poll(() => dialog.getByRole('alert').count(), { timeout: 5_000 }).toBe(1)
expect(await dialog.getByRole('button', { name: 'Rename' }).isDisabled()).toBe(true)
// A fresh name goes through workspace.rename to the durable registry.
await input.fill('gamma-ws')
await expect.poll(() => dialog.getByRole('alert').count(), { timeout: 5_000 }).toBe(0)
await dialog.getByRole('button', { name: 'Rename' }).click()
await expect.poll(() => page.getByRole('dialog', { name: 'Rename workspace' }).count(), { timeout: 10_000 }).toBe(0)
await expect.poll(() => page.getByText('gamma-ws', { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
expect(await page.getByText('alpha-ws', { exact: true }).count()).toBe(0)
// Host durability, then reload: the projection is rebuilt from the wire.
expect(scaffold.ctx.workspace.list().map(workspace => workspace.title)).toContain('gamma-ws')
await page.reload({ waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
drainReloadWarnings()
await expect.poll(() => page.getByText('gamma-ws', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
expect(tripwire.pageErrors).toEqual([])
}, 90_000)
it('switches to the flat "In one list" view and persists the preference', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-flat'))
// Grouped default: workspace group rows render (the seeded session sits
// under Ungrouped; the created workspaces are empty groups).
await expect.poll(() => page.getByText('Workspaces', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
await page.getByRole('button', { name: 'Group by' }).click()
await page.getByRole('menuitem', { name: 'In one list' }).click()
// Flat mode: the section label flips and the seeded session is a
// top-level row with no group headers above it.
await expect.poll(() => page.getByText('Sessions', { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 5_000 }).toBe(0)
await expect.poll(() => page.locator('[role="treeitem"]').count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
expect(await page.evaluate(() => localStorage.getItem('dsh.workspace.view'))).toContain('flat')
// Persisted across reload; then restore grouped for inter-spec hygiene.
await page.reload({ waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
drainReloadWarnings()
await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 15_000 }).toBe(0)
await page.getByRole('button', { name: 'Group by' }).click()
await page.getByRole('menuitem', { name: 'WorkSpace' }).click()
await expect.poll(() => page.getByText('Ungrouped', { exact: true }).count(), { timeout: 10_000 }).toBeGreaterThanOrEqual(1)
expect(tripwire.pageErrors).toEqual([])
}, 90_000)
it('shows the session hover card after a dwell on the row', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-ws-hover'))
// Expand Ungrouped to reveal the seeded session row, then dwell on it
// (the card opens after a 500ms hover delay, portaled to body).
await page.getByText('Ungrouped', { exact: true }).click()
// A cold summary carries no durable title, so the row falls back to a
// cwd-derived display title — anchored on the run-local workspace-root
// basename rather than a literal.
const wsBase = scaffold.workspaceCwd.split('/').pop()!
const sessionRow = page.locator('[role="treeitem"]').filter({ hasText: wsBase }).first()
await sessionRow.waitFor({ timeout: 10_000 })
await sessionRow.hover()
// Card content: the full title plus the Idle status line (display-only
// card; no aria role — text anchors are the stable selector).
await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBeGreaterThanOrEqual(1)
// Leaving the anchor closes it with no delay.
await page.getByRole('button', { name: '设置' }).hover()
await expect.poll(() => page.getByText('Idle', { exact: true }).count(), { timeout: 5_000 }).toBe(0)
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it.skipIf(MODE === 'record')('issued zero model calls and stayed clean', async () => {
expect(tripwire.warnings).toEqual([])
// This spec mints no fixture directory contents of its own; the seed it
// reuses is owned (and inventory-guarded) by seeded-history.
await assertFixtureInventory(SNAPSHOT_DIR, ['.gitkeep'])
})
})