Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into worktree/composer-scrollbar-gutter

Browse Source 
# Conflicts:
#	packages/client/ui-conversation/README.i18n.yaml
This commit is contained in:
creatixchu
2026-08-05 15:36:06 +08:00
parent 70ec51b1ba e4d5ec548e
commit 1ed62688ab
1561 changed files with 16596 additions and 5542 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
apps/web/tests/access-confirmation.e2e.ts
View File

@@ -2,7 +2,6 @@
// the same locale-aware, in-page risk confirmation. Zero model calls: the
// scenario boots the shipped Web composition and exercises the real
// permission projection, client command path, HTTP RPC, and pushed update.
import { mkdirSync } from 'node:fs'
import { fileURLToPath } from 'node:url'
import { join } from 'node:path'
import type { Browser, Page } from 'playwright'
@@ -12,27 +11,7 @@ import {
assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
/**
* connectFreshWorkspace twin over the product default Chinese locale (the
* shared helper's anchors assume the English page every other scenario
* boots; this scenario deliberately keeps zh, so the localized picker
* copy is the anchor set).
*/
async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
mkdirSync(join(root, name), { recursive: true })
await page.getByRole('button', { name: '选择工作区' }).click()
const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
await dialog.waitFor({ timeout: 10_000 })
await dialog.getByRole('button', { name: '编辑路径' }).click()
const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
await pathInput.fill(join(root, name))
await pathInput.press('Enter')
await dialog.getByRole('button', { name: '打开', exact: true }).click()
await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
.waitFor({ timeout: 15_000 })
}
import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/access-confirmation', import.meta.url))
const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')

4
apps/web/tests/bash-abort-row.e2e.ts
View File

@@ -56,7 +56,7 @@ describe.skipIf(MODE === 'record')('web e2e: cancelled Bash row disclosure', ()
const row = page.locator('[data-sample="bash"]').first()
const call = row.locator('xpath=..')
await expect.poll(() => row.getAttribute('aria-expanded')).toBe('false')
await expect.poll(() => call.getByText('Error: command aborted', { exact: true }).count()).toBe(1)
await expect.poll(() => call.getByText('Error: tool call aborted', { exact: true }).count()).toBe(1)
await row.click()
await expect.poll(() => row.getAttribute('aria-expanded')).toBe('true')
@@ -64,7 +64,7 @@ describe.skipIf(MODE === 'record')('web e2e: cancelled Bash row disclosure', ()
await call.getByText('OUT', { exact: true }).waitFor()
await call.getByText('Wait until cancellation', { exact: false }).waitFor()
await call.getByText('setInterval(() => {}, 1000)', { exact: false }).waitFor()
await expect.poll(() => call.getByText('Error: command aborted', { exact: true }).count()).toBe(2)
await expect.poll(() => call.getByText('Error: tool call aborted', { exact: true }).count()).toBe(2)
const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
// The borrowed fixture's UTC date is still the previous day in PDT;

9
apps/web/tests/built-boot.snapshot.ts
View File

@@ -7,7 +7,7 @@
// content from the keyless FixtureApiClient transport.
//
// Component behavior remains owned by per-package suites (SlotTestRuntime
// benches over src). This smoke additionally pins the resident approval
// benches over src). This smoke additionally pins the resident interaction
// fixture's cross-plugin projection because only the built connection/runtime/
// workspace graph can prove that transport-to-row path end to end.
import { readFileSync } from 'node:fs'
@@ -105,14 +105,15 @@ it('boots the built plugin graph and renders a fixture session end to end', asyn
const tree = await screen.findByRole('tree', { name: 'Sessions' }, { timeout: 10_000 })
await within(tree).findByText('4 sessions')
// The resident approval fixture proves the assembled workspace plugin
// distinguishes a blocked running session from an ordinarily busy one.
// The resident fixture has both a question and an approval; composer routing
// exposes the question first, and the assembled workspace plugin mirrors that
// actionable wait instead of the underlying running state.
const waitingTitle = await within(tree).findByText('Fixture 历史会话')
const waitingRow = waitingTitle.closest<HTMLElement>('[role="treeitem"]')
if (waitingRow === null) throw new Error('fixture Session title must belong to a tree row')
expect(waitingRow.querySelector('[data-state="warning"]')).not.toBeNull()
expect(waitingRow.querySelector('[data-state="ongoing"]')).toBeNull()
within(waitingRow).getByText('Waiting for approval')
within(waitingRow).getByText('Waiting for answer')
// Opening a session reaches chat content through the fixture transport.
fireEvent.click(waitingTitle)

3
apps/web/tests/chat-scroll-contract.e2e.ts
View File

@@ -608,6 +608,9 @@ describe('web e2e: long Chat scroll contract', () => {
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 })
// The narrow breakpoint auto-collapses the sidebar. Re-open it because
// this scenario switches sessions while pinning the narrow Chat scroll owner.
await world.page.getByRole('button', { name: 'Open sidebar', exact: true }).click()
await world.page.getByRole('tab', { name: 'Chat', exact: true }).click()
await nextPaint(world.page)
await expectSameFlowTop(world.page, sessionAnchor)

2
apps/web/tests/chat-scroll-fixture.ts
View File

@@ -179,7 +179,7 @@ function fixtureLog(session: Session): string {
export function createChatScrollFixture(options: ChatScrollFixtureOptions): ChatScrollFixture {
const turns = options.turns ?? DEFAULT_TURNS
const markers = markerHelpers(options.markerPrefix)
const session = new Session(SessionId(`chat-scroll-${options.markerPrefix.toLowerCase()}-template`))
const session = Session.create(SessionId(`chat-scroll-${options.markerPrefix.toLowerCase()}-template`))
for (let turn = 1; turn <= turns; turn += 1) {
session.append('turn/start', {

4
apps/web/tests/complex-history.perf.ts
View File

@@ -319,7 +319,7 @@ function fixtureLog(session: Session): string {
}
function smallSidebarFixture(): string {
const session = new Session(SessionId('perf-small-template'))
const session = Session.create(SessionId('perf-small-template'))
session.append('turn/start', {
turn: 1,
trigger: { kind: 'message', source: { kind: 'user' } },
@@ -342,7 +342,7 @@ function smallSidebarFixture(): string {
}
function longHistoryFixture(): string {
const session = new Session(SessionId(LONG_SESSION_ID))
const session = Session.create(SessionId(LONG_SESSION_ID))
for (let turn = 1; turn <= LONG_HISTORY_TURNS; turn += 1) {
session.append('turn/start', {
turn,

52
apps/web/tests/composer-tab-geometry.e2e.ts
View File

@@ -79,7 +79,39 @@ const SEED_ID = 'composer-tab-geometry-web-e2e'
/** Viewport widths the scenario measures at: the card capped, and the card shrinking with the column. */
const WIDE_VIEWPORT = { width: 1680, height: 1000 }
const NARROW_VIEWPORT = { width: 900, height: 1000 }
const NARROW_VIEWPORT = { width: 800, height: 1000 }
/**
* Resize to one measurement viewport after the responsive sidebar and center
* column finish their track transition.
* @param page - the page under test.
* @param viewport - the viewport dimensions to apply.
* @param sidebarCollapsed - the sidebar state expected at this width.
*/
async function setMeasuredViewport(
page: Page,
viewport: { width: number; height: number },
sidebarCollapsed: boolean,
): Promise<void> {
await page.setViewportSize(viewport)
await page.locator('[data-sidebar-collapsed="true"]').waitFor({
state: sidebarCollapsed ? 'attached' : 'detached',
timeout: 10_000,
})
await page.locator('[data-conversation-scroll]').evaluate(async (host) => {
const deadline = performance.now() + 5_000
let previous = host.getBoundingClientRect().width
let stableFrames = 0
while (performance.now() < deadline) {
await new Promise<void>((resolve) => { requestAnimationFrame(() => { resolve() }) })
const current = host.getBoundingClientRect().width
stableFrames = Math.abs(current - previous) < 0.01 ? stableFrames + 1 : 0
if (stableFrames >= 3) return
previous = current
}
throw new Error('conversation width did not settle after the viewport changed')
})
}
/**
* The pre-fix cascade, injected into the page: the reservation dropped and the
@@ -289,7 +321,7 @@ describe('web e2e: input card position across view tabs', () => {
it('reserves the same gutter in both tabs while the transcript scrolls', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-band'))
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
// Vacuity guard, in two parts. A transcript that does not overflow gives
// Chat no scrollbar, and a hidden or overlaid bar gives it no width; either
// would make the tabs agree without the reservation doing anything.
@@ -313,7 +345,7 @@ describe('web e2e: input card position across view tabs', () => {
it('holds the input card in place when the tab changes', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-wide'))
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
const comparison = await compareTabs(page)
// The reported symptom as a number. At this viewport the card sits at its
// width cap, so the pre-fix shift showed up as a centring difference — half
@@ -326,9 +358,9 @@ describe('web e2e: input card position across view tabs', () => {
it('holds the input card in place at a viewport where it shrinks with the column', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-narrow'))
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
const capped = await measureTab(page)
await page.setViewportSize(NARROW_VIEWPORT)
await setMeasuredViewport(page, NARROW_VIEWPORT, true)
const comparison = await compareTabs(page)
// The other geometry, and a different failure: below the cap the card takes
// the column's width, so an unreserved gutter changed its WIDTH by the whole
@@ -339,13 +371,13 @@ describe('web e2e: input card position across view tabs', () => {
expect(comparison.leftShift).toBe(0)
expect(comparison.rightShift).toBe(0)
expect(comparison.widthShift).toBe(0)
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('moves the card again once the reservation is removed in the page', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-control'))
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
// The control: without it, equal rectangles could also mean the tab switch
// never reached the layout. Under the pre-fix cascade the Chat scroller keeps
// its bar and the Trajectory branch goes back to a hidden box with none, and
@@ -365,11 +397,11 @@ describe('web e2e: input card position across view tabs', () => {
it('matches the committed tab geometry golden', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-composer-tab-geometry-golden'))
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
const wide = await compareTabs(page)
await page.setViewportSize(NARROW_VIEWPORT)
await setMeasuredViewport(page, NARROW_VIEWPORT, true)
const narrow = await compareTabs(page)
await page.setViewportSize(WIDE_VIEWPORT)
await setMeasuredViewport(page, WIDE_VIEWPORT, false)
const control = await compareTabsWithoutReservation(page)
await compareOrRefreshGolden(GEOMETRY_EXPECTED, renderGeometry(wide, narrow, control), MODE)
expect(tripwire.pageErrors).toEqual([])

4
apps/web/tests/lifecycle-chrome.e2e.ts
View File

@@ -104,6 +104,10 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
await input.press('Enter')
const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' })
await planButton.waitFor({ timeout: 10_000 })
// The golden encodes an empty composer, and the button arriving does not
// mean the submitted text is gone yet: under load the capture caught a
// textbox still holding `/plan`.
await expect.poll(() => input.inputValue(), { timeout: 10_000 }).toBe('')
const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd)
await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE)
const planStyle = await planButton.evaluate((element) => {

2
apps/web/tests/markdown-images.e2e.ts
View File

@@ -82,7 +82,7 @@ async function stopServer(server: Server): Promise<void> {
/** Build one closed, invariant-checked session fixture with remote and local image Markdown. */
function markdownImageFixture(remoteUrl: string): string {
const session = new Session(SessionId('markdown-image-source'))
const session = Session.create(SessionId('markdown-image-source'))
session.append('turn/start', {
turn: 1,
trigger: { kind: 'message', source: { kind: 'user' } },

5
apps/web/tests/message-actions.e2e.ts
View File

@@ -126,9 +126,8 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-message-actions-aria'))
await page.getByRole('button', {
name: 'Select model, current deepseek-v4-flash',
}).waitFor({ timeout: 10_000 })
await page.getByRole('button', { name: 'Select model', exact: true })
.waitFor({ timeout: 10_000 })
// Keep a footer focused so opacity-hidden actions stay in the a11y tree
// as an active/focused control during the capture.
await page.getByRole('button', { name: 'Copy' }).first().focus()

2
apps/web/tests/models-settings.e2e.ts
View File

@@ -58,7 +58,7 @@ describe('web e2e: Models settings page configures a dormant provider', () => {
await dialog.getByText('填入各提供方的 API 密钥即可使用其模型。').waitFor({ timeout: 10_000 })
// The dormant pi-ai adapter contributes its whole installed catalog; no
// provider is configured yet, so the page is one add button.
const add = dialog.getByRole('button', { name: '+ 添加提供方' })
const add = dialog.getByRole('button', { name: '添加提供方' })
await add.waitFor({ timeout: 10_000 })
// The button enables once the dormant catalog lands in the join.
await expect.poll(async () => add.isEnabled(), { timeout: 10_000 }).toBe(true)

58
apps/web/tests/onboarding-deepseek-config.e2e.ts
View File

@@ -12,7 +12,7 @@ import {
acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
} from './scaffold.ts'
import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
import {
WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
@@ -22,6 +22,7 @@ import {
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/onboarding-deepseek-config', import.meta.url))
const WELCOME_EXPECTED = join(SNAPSHOT_DIR, 'welcome.expected.md')
const MISSING_EXPECTED = join(SNAPSHOT_DIR, 'missing.expected.md')
const MODELS_EXPECTED = join(SNAPSHOT_DIR, 'models.expected.md')
const MODE = webSnapshotMode()
describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup', () => {
@@ -160,7 +161,60 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('configures arbitrary DeepSeek models and prompts after the selected model is removed', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-models'))
// Opened here rather than inherited: the credential test reloads the page
// to exercise the welcome step, so nothing carries an open dialog across.
await page.getByRole('button', { name: '设置', exact: true }).click()
const settings = page.getByRole('dialog', { name: '设置' })
await settings.waitFor({ timeout: 10_000 })
await settings.getByRole('button', { name: '模型' }).click()
const deepSeek = settings.getByText('DeepSeek', { exact: true }).first()
await deepSeek.waitFor({ timeout: 10_000 })
await deepSeek.locator('xpath=ancestor::li').getByRole('button', { name: '编辑' }).click()
await settings.getByText('自定义设置').click()
await settings.getByRole('button', { name: /删除模型/ }).first().click()
await settings.getByRole('button', { name: '添加模型' }).click()
const customModelId = settings.getByLabel('模型 ID 2')
await customModelId.fill('private-preview')
await settings.getByLabel('显示名称 2').fill('Private Preview')
// Capacities live behind the row's own disclosure, as in the pi-ai form.
await settings.getByRole('button', { name: '容量 2' }).click()
await settings.getByLabel('上下文窗口 2').fill('131072')
await settings.getByLabel('最大输出 token 数 2').fill('64K')
const modelEditor = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(MODELS_EXPECTED, modelEditor, MODE)
await settings.getByRole('button', { name: '保存', exact: true }).click()
await customModelId.waitFor({ state: 'detached', timeout: 15_000 })
const document = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
expect(document).toContain('id: deepseek-v4-pro')
expect(document).toContain('id: private-preview')
expect(document).toContain('name: Private Preview')
expect(document).toContain('contextWindow: 131072')
expect(document).toContain('maxTokens: 64000')
expect(document).not.toContain('id: deepseek-v4-flash')
await page.keyboard.press('Escape')
// A connected Workspace is what puts a live composer — and its model
// trigger — on the page; the scaffold boots without one.
await connectFreshWorkspaceZh(page, scaffold.workspaceCwd, 'model-fallback-e2e')
const modelTrigger = page.getByRole('button', { name: '选择模型', exact: true })
await modelTrigger.waitFor({ timeout: 10_000 })
await modelTrigger.click()
await page.getByRole('menuitem', { name: /模型/ }).click()
expect(await page.getByText('deepseek-v4-flash', { exact: true }).count()).toBe(0)
await page.getByRole('menuitemradio', { name: 'Private Preview' }).waitFor({ timeout: 10_000 })
expect(tripwire.warnings).toEqual([])
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('keeps the fixture inventory closed', async () => {
await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md', 'welcome.expected.md'])
await assertFixtureInventory(
SNAPSHOT_DIR,
['missing.expected.md', 'models.expected.md', 'welcome.expected.md'],
)
})
})

12
apps/web/tests/plan-review.e2e.ts
View File

@@ -25,6 +25,7 @@ const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
// The waiting golden owns the decision card; the approved golden owns the
// transcript the approval leaves behind — the state the card cannot see.
const REVIEW_EXPECTED = join(SNAPSHOT_DIR, 'review.expected.md')
const SIDEBAR_EXPECTED = join(SNAPSHOT_DIR, 'sidebar.expected.md')
const APPROVED_EXPECTED = join(SNAPSHOT_DIR, 'approved.expected.md')
const MODE = webSnapshotMode()
@@ -82,9 +83,15 @@ describe('web e2e: plan review takeover round trip', () => {
expect(await page.locator('[data-question-key]').count()).toBe(0)
await expect.poll(() => card.getByText('Plan review').count(), { timeout: 10_000 }).toBeGreaterThan(0)
const selectedRow = page.locator('[role="treeitem"][aria-selected="true"]')
await expect.poll(() => selectedRow.locator('[data-state="warning"]').count(), { timeout: 10_000 }).toBe(1)
await expect.poll(() => selectedRow.getByText('Plan awaiting review', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
if (MODE !== 'record') {
const snapshot = await captureStableAria(page, '[data-plan-review-key]', scaffold.workspaceCwd)
await compareOrRefreshGolden(REVIEW_EXPECTED, snapshot, MODE)
const sidebar = await captureStableAria(page, '[role="treeitem"][aria-selected="true"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(SIDEBAR_EXPECTED, sidebar, MODE)
}
await card.getByRole('button', { name: 'Approve' }).click()
@@ -100,6 +107,7 @@ describe('web e2e: plan review takeover round trip', () => {
await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
// Card gone; regular input restored.
expect(await page.locator('[data-plan-review-key]').count()).toBe(0)
expect(await selectedRow.locator('[data-state="warning"]').count()).toBe(0)
await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(APPROVED_EXPECTED, snapshot, MODE)
@@ -108,6 +116,8 @@ describe('web e2e: plan review takeover round trip', () => {
}, 200_000)
it.skipIf(MODE === 'record')('keeps the fixture inventory closed', async () => {
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'review.expected.md', 'approved.expected.md'])
await assertFixtureInventory(SNAPSHOT_DIR, [
'session.jsonl', 'review.expected.md', 'sidebar.expected.md', 'approved.expected.md',
])
})
})

9
apps/web/tests/question-composer.e2e.ts
View File

@@ -23,6 +23,7 @@ import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './suppor
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/question-composer', import.meta.url))
const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
const SIDEBAR_EXPECTED = join(SNAPSHOT_DIR, 'sidebar.expected.md')
const COMPOSED_EXPECTED = join(SNAPSHOT_DIR, 'composed.expected.md')
// Final golden: the answered transcript — the question resolved into its tool
// round trip and the final reply, the state the composer goldens cannot see.
@@ -76,11 +77,17 @@ describe('web e2e: resident question composer round trip', () => {
await composer.waitFor({ timeout: MODE === 'record' ? 120_000 : 30_000 })
await expect.poll(() => composer.getByText('Which color do you prefer?').count(), { timeout: 10_000 }).toBeGreaterThan(0)
const selectedRow = page.locator('[role="treeitem"][aria-selected="true"]')
await expect.poll(() => selectedRow.locator('[data-state="warning"]').count(), { timeout: 10_000 }).toBe(1)
await expect.poll(() => selectedRow.getByText('Waiting for answer', { exact: true }).count(), { timeout: 10_000 }).toBe(1)
if (MODE !== 'record') {
// This golden owns the stable question surface; the answered-state
// golden below owns the resulting transcript.
const snapshot = await captureStableAria(page, '[data-question-key]', scaffold.workspaceCwd)
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
const sidebar = await captureStableAria(page, '[role="treeitem"][aria-selected="true"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(SIDEBAR_EXPECTED, sidebar, MODE)
}
// Squeezed card: the option rows are the capped card's scroll content, so
@@ -155,6 +162,7 @@ describe('web e2e: resident question composer round trip', () => {
await expect.poll(() => page.getByText('DONE', { exact: true }).count(), { timeout: 15_000 }).toBeGreaterThanOrEqual(1)
// Composer gone; regular input restored.
expect(await page.locator('[data-question-key]').count()).toBe(0)
expect(await selectedRow.locator('[data-state="warning"]').count()).toBe(0)
await expect.poll(() => page.locator('textarea').first().isEnabled(), { timeout: 10_000 }).toBe(true)
// Golden of the answered transcript: the ask_user_question round trip
// rendered as history (question tool row + DONE), composer takeover gone.
@@ -168,6 +176,7 @@ describe('web e2e: resident question composer round trip', () => {
await assertFixtureInventory(SNAPSHOT_DIR, [
'session.jsonl',
'ui.expected.md',
'sidebar.expected.md',
'composed.expected.md',
'answered.expected.md',
])

4
apps/web/tests/scaffold.ts
View File

@@ -2,8 +2,8 @@
// .agents/notes/implemented/testing/2026-07-24-web-gui-browser-e2e-lane.md).
// Boots the REAL web composition — the shipped base plus web overlay through
// the vendored Loader (the same include boot AppCLIEntry drives), patched the
// snapshot way — so a real chromium exercises the real HTTP/SSE wire, the
// api-gateway, agent loop, tools, and persistence. Modes ride $DSH_SNAPSHOT:
// snapshot way — so a real chromium exercises the real HTTP uplink/WebSocket
// downlink, api-gateway, agent loop, tools, and persistence. Modes ride $DSH_SNAPSHOT:
// replay (default, keyless: normally disables the llm-deepseek row and
// inserts dsh-llm-replay in providers mode), record (real adapter + key,
// harvests fixtures from live session memory), refresh (keyless replay that

11
apps/web/tests/seeded-history.e2e.ts
View File

@@ -241,12 +241,11 @@ describe('web e2e: seeded history renders through cold resume', () => {
it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-aria'))
await page.getByRole('button', {
// This scenario deliberately leaves the LLM seam open to prove zero
// model calls. History still restores the selected id, but no catalog
// adapter exists to provide its presentation name.
name: 'Select model, current deepseek-v4-flash',
}).waitFor({ timeout: 10_000 })
// This scenario deliberately leaves the LLM seam open to prove zero
// model calls. History still restores the routed id, but without an
// advertised catalog row the selector prompts for a listed replacement.
await page.getByRole('button', { name: 'Select model', exact: true })
.waitFor({ timeout: 10_000 })
const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
.split(SEED_ID).join('{{seededId}}')
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)

10
apps/web/tests/snapshots/bash-abort-row/ui.expected.md
View File

@@ -14,10 +14,10 @@
- img
- img
- text: Context injection
- 'button "Failed Bash Error: command aborted" [expanded]':
- 'button "Failed Bash Error: tool call aborted" [expanded]':
- img
- text: "Failed Bash Error: command aborted"
- text: "IN { \"command\": \"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\", \"description\": \"Wait until cancellation\" } OUT Error: command aborted"
- text: "Failed Bash Error: tool call aborted"
- text: "IN { \"command\": \"node -e \\\"require('node:fs').writeFileSync('started.txt', 'started'); setInterval(() => {}, 1000)\\\"\", \"description\": \"Wait until cancellation\" } OUT Error: tool call aborted"
- button "Inspect"
- 'button "Failed Bash Error: tool call aborted before dispatch"':
- img
@@ -26,8 +26,8 @@
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: 1 turns · 1 steps Tool call {{duration}} Cache hit 0% Input 10 tok · Output 10 tok

2
apps/web/tests/snapshots/composer-tab-geometry/geometry.expected.md
View File

@@ -12,7 +12,7 @@
- input card right edge moves between tabs: 0px
- input card width changes between tabs: 0px
## Narrow viewport (900px, card shrinking with the column)
## Narrow viewport (800px, card shrinking with the column)
- Chat: scrollbar-gutter stable, overflow auto/auto
- Chat scroller scrolls: true

1
apps/web/tests/snapshots/lifecycle-chrome/hero.expected.md
View File

@@ -28,6 +28,7 @@
- textbox "Describe what you want to build"
- button "Commands":
- img
- tooltip "Commands"
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Select model, current DeepSeek-V4-Flash":
- text: DeepSeek-V4-Flash

4
apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md
View File

@@ -30,8 +30,8 @@
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Plan mode on, press to turn off": Plan
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: Details

4
apps/web/tests/snapshots/markdown-images/ui.expected.md
View File

@@ -24,8 +24,8 @@
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: 1 turns · 1 steps Input 0 tok · Output 0 tok

4
apps/web/tests/snapshots/message-actions/ui.expected.md
View File

@@ -51,8 +51,8 @@
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: 2 turns · 3 steps Tool call {{duration}} Cache hit 98% Input 7.8K tok · Output 103 tok

4
apps/web/tests/snapshots/models-settings/configured.expected.md
View File

@@ -17,4 +17,6 @@
- text: minimax-cn
- button "编辑"
- button "删除"
- button "+ 添加提供方"
- button "添加提供方":
- img
- text: 添加提供方

70
apps/web/tests/snapshots/onboarding-deepseek-config/models.expected.md Normal file
View File

@@ -0,0 +1,70 @@
- 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
- heading "模型" [level=2]
- paragraph: 填入各提供方的 API 密钥即可使用其模型。
- list:
- listitem:
- text: DeepSeek
- button "编辑"
- text: DeepSeek deepseek-official API 密钥
- textbox "API 密钥":
- /placeholder: 已配置——输入新值可替换
- group:
- text: 自定义设置 API 地址
- textbox "API 地址":
- /placeholder: https://api.deepseek.com
- text: 推理强度
- combobox "推理强度":
- option "默认" [selected]
- option "off"
- option "high"
- option "max"
- region "模型目录":
- text: 模型目录 已自定义模型目录
- button "恢复默认模型"
- textbox "模型 ID 1":
- /placeholder: 模型 ID
- text: deepseek-v4-pro
- textbox "显示名称 1":
- /placeholder: 显示名称
- text: DeepSeek-V4-Pro
- button "容量 1":
- img
- button "删除模型 1":
- img
- textbox "模型 ID 2":
- /placeholder: 模型 ID
- text: private-preview
- textbox "显示名称 2":
- /placeholder: 显示名称
- text: Private Preview
- button "容量 2" [expanded]:
- img
- button "删除模型 2":
- img
- text: 上下文窗口
- textbox "上下文窗口 2":
- /placeholder: 1M
- text: "131072"
- text: 最大输出 token 数
- textbox "最大输出 token 数 2":
- /placeholder: 256K
- text: 64K
- button "添加模型":
- img
- text: 添加模型
- button "取消"
- button "保存"
- button "添加提供方":
- img
- text: 添加提供方

1
apps/web/tests/snapshots/plan-review/sidebar.expected.md Normal file
View File

@@ -0,0 +1 @@
- 'treeitem "Plan awaiting review Plan a small change: add now" [selected]'

1
apps/web/tests/snapshots/question-composer/sidebar.expected.md Normal file
View File

@@ -0,0 +1 @@
- treeitem "Waiting for answer Use the ask_user_question tool to now" [selected]

1
apps/web/tests/snapshots/queue-actions/editing.expected.md
View File

@@ -30,6 +30,7 @@
- textbox "Edit queued message": Edited queue item
- button "Save queued message":
- img
- tooltip "Save queued message"
- button "Cancel editing":
- img
- textbox "Message the agent"

2
apps/web/tests/snapshots/queue-actions/layout.expected.md
View File

@@ -23,7 +23,7 @@
- paragraph: partial
- status: Deep diving...
- region "To-dos":
- button "To-dos 1/2 tasks · 1 in progress"
- button "To-dos 1 completed · 1 in progress"
- img
- text: Ongoing Goal Keep the composer context panels aligned
- button "Pause goal":

1
apps/web/tests/snapshots/queue-actions/ui.expected.md
View File

@@ -21,6 +21,7 @@
- text: Edited queue item
- button "Edit queued message":
- img
- tooltip "Edit queued message"
- button "Remove queued message":
- img
- button "Steer queued message":

4
apps/web/tests/snapshots/seeded-history/command-row.expected.md
View File

@@ -47,8 +47,8 @@
- button "Commands":
- img
- 'button "Access mode, current: Read Only"': Read Only
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

4
apps/web/tests/snapshots/seeded-history/ui.expected.md
View File

@@ -45,8 +45,8 @@
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- button "Select model, current deepseek-v4-flash":
- text: deepseek-v4-flash
- button "Select model":
- text: Select model
- img
- button "Send message" [disabled]
- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

4
apps/web/tests/snapshots/sidebar-scrollbar/geometry.expected.md
View File

@@ -28,8 +28,8 @@
- scrollbar-width: auto
- scrollbar-color: auto
- ::-webkit-scrollbar-thumb:hover declarations: var(--dsh-scrollbar-thumb-hover)
- --dsh-scrollbar-thumb, pointer over the list: rgb(60, 60, 61)
- --dsh-scrollbar-thumb-hover, pointer over the list: rgb(84, 85, 87)
- --dsh-scrollbar-thumb, pointer over the list: rgb(84, 85, 87)
- --dsh-scrollbar-thumb-hover, pointer over the list: rgb(101, 103, 107)
- list overflows: true
- reserved band: 8px
- scrollbar inset from the sidebar edge: 2px

22
apps/web/tests/support.ts
View File

@@ -88,6 +88,28 @@ export async function connectFreshWorkspace(page: Page, root: string, name = 'wo
.waitFor({ timeout: 15_000 })
}
/**
* {@link connectFreshWorkspace} over the product default Chinese locale: the
* English helper's anchors assume the locale every other scenario boots, so a
* scenario that deliberately keeps zh needs the localized picker copy.
* @param page - the browser page under test.
* @param root - workspace parent directory.
* @param name - directory created under `root` and connected.
*/
export async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
mkdirSync(join(root, name), { recursive: true })
await page.getByRole('button', { name: '选择工作区' }).click()
const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
await dialog.waitFor({ timeout: 10_000 })
await dialog.getByRole('button', { name: '编辑路径' }).click()
const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
await pathInput.fill(join(root, name))
await pathInput.press('Enter')
await dialog.getByRole('button', { name: '打开', exact: true }).click()
await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
.waitFor({ timeout: 15_000 })
}
/** Failure evidence goes to the gitignored .artifacts/ (repo convention). */
export async function saveFailureShot(page: Page, name: string): Promise<void> {
const dir = fileURLToPath(new URL('../../../.artifacts', import.meta.url))