Merge remote-tracking branch 'origin/master' into worktree/unify-workspace-add
This commit is contained in:
@@ -9,12 +9,18 @@ import type { Browser, Page } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import {
|
||||
assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
|
||||
acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
|
||||
launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { saveFailureShot } from './support.ts'
|
||||
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
|
||||
import {
|
||||
WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
|
||||
WELCOME_NOTICE_VERSION,
|
||||
} from '@deepseek-ai/dsh-client-ui-settings-general'
|
||||
|
||||
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 MODE = webSnapshotMode()
|
||||
|
||||
@@ -26,7 +32,7 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
|
||||
const browserConsole: string[] = []
|
||||
|
||||
beforeAll(async () => {
|
||||
scaffold = await launchWebScaffold({ deepSeekMissingCredential: true })
|
||||
scaffold = await launchWebScaffold({ deepSeekMissingCredential: true, welcomeNoticePending: true })
|
||||
browser = await chromium.launch()
|
||||
page = await browser.newPage({ viewport: { width: 1440, height: 960 } })
|
||||
tripwire = watchConsole(page)
|
||||
@@ -42,16 +48,61 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
|
||||
|
||||
it('stores a key write-only and observes configured state without restarting', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-config'))
|
||||
const dialog = page.getByRole('dialog', { name: '添加一个 API Key 开始使用' })
|
||||
await dialog.waitFor({ timeout: 15_000 })
|
||||
expect(await dialog.getByRole('textbox').count()).toBe(0)
|
||||
const initial = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
|
||||
const welcome = page.getByRole('region', { name: WELCOME_NOTICE_COPY.zh.title })
|
||||
await welcome.waitFor({ timeout: 15_000 })
|
||||
expect(await page.locator('#root').evaluate(root => (root as HTMLElement).inert)).toBe(true)
|
||||
const welcomeAria = await captureStableAria(page, '[role="region"]', scaffold.workspaceCwd)
|
||||
await compareOrRefreshGolden(WELCOME_EXPECTED, welcomeAria, MODE)
|
||||
expect(await welcome.getByRole('button').allTextContents()).toEqual([WELCOME_NOTICE_COPY.zh.continueLabel])
|
||||
expect(await welcome.locator('button').count()).toBe(1)
|
||||
|
||||
const mask = page.locator('[class*="onboardingMask"]')
|
||||
expect(await mask.count()).toBe(1)
|
||||
const maskStyles = await mask.evaluate((mask) => {
|
||||
const style = getComputedStyle(mask)
|
||||
const rect = mask.getBoundingClientRect()
|
||||
return {
|
||||
position: style.position,
|
||||
left: style.left,
|
||||
right: style.right,
|
||||
top: style.top,
|
||||
bottom: style.bottom,
|
||||
background: style.backgroundColor,
|
||||
backdropFilter: style.backdropFilter,
|
||||
rect: { left: rect.left, top: rect.top, right: rect.right, bottom: rect.bottom },
|
||||
}
|
||||
})
|
||||
expect(maskStyles).toEqual({
|
||||
position: 'absolute',
|
||||
left: '0px',
|
||||
right: '0px',
|
||||
top: '80px',
|
||||
bottom: '0px',
|
||||
background: 'rgba(0, 0, 0, 0.24)',
|
||||
backdropFilter: 'blur(2px)',
|
||||
rect: { left: 0, top: 80, right: 1440, bottom: 960 },
|
||||
})
|
||||
|
||||
// Closing the process/page before acknowledgement writes nothing, so the
|
||||
// same durable profile presents the notice again after reload.
|
||||
const firstReloadWarnings = tripwire.warnings.length
|
||||
await page.reload({ waitUntil: 'load' })
|
||||
acknowledgeReloadConnectionLoss(tripwire, firstReloadWarnings)
|
||||
await welcome.waitFor({ timeout: 15_000 })
|
||||
|
||||
await welcome.getByRole('button', { name: WELCOME_NOTICE_COPY.zh.continueLabel }).click()
|
||||
await welcome.waitFor({ state: 'detached', timeout: 15_000 })
|
||||
const credentialStep = page.getByRole('region', { name: '添加一个 API Key 开始使用' })
|
||||
await credentialStep.waitFor({ timeout: 15_000 })
|
||||
expect(await credentialStep.getByRole('textbox').count()).toBe(0)
|
||||
const initial = await captureStableAria(page, '[role="region"]', scaffold.workspaceCwd)
|
||||
await compareOrRefreshGolden(MISSING_EXPECTED, initial, MODE)
|
||||
|
||||
await dialog.getByRole('button', { name: '前往配置' }).click()
|
||||
await dialog.waitFor({ state: 'detached', timeout: 15_000 })
|
||||
await credentialStep.getByRole('button', { name: '前往配置' }).click()
|
||||
await credentialStep.waitFor({ state: 'detached', timeout: 15_000 })
|
||||
const settings = page.getByRole('dialog', { name: '设置' })
|
||||
await settings.waitFor({ timeout: 10_000 })
|
||||
expect(await page.locator('#root').evaluate(root => (root as HTMLElement).inert)).toBe(false)
|
||||
const keyInput = settings.getByLabel('API 密钥', { exact: true })
|
||||
await keyInput.waitFor({ timeout: 10_000 })
|
||||
|
||||
@@ -78,6 +129,29 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
|
||||
{ timeout: 10_000 },
|
||||
).toBe('已配置——输入新值可替换')
|
||||
|
||||
const acknowledgedSettings = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
|
||||
expect(acknowledgedSettings).toContain(`${WELCOME_NOTICE_ACK_FIELD}: ${WELCOME_NOTICE_VERSION}`)
|
||||
|
||||
const secondReloadWarnings = tripwire.warnings.length
|
||||
await page.reload({ waitUntil: 'load' })
|
||||
acknowledgeReloadConnectionLoss(tripwire, secondReloadWarnings)
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 15_000 })
|
||||
expect(await page.getByRole('region', { name: WELCOME_NOTICE_COPY.zh.title }).count()).toBe(0)
|
||||
expect(await page.getByRole('region', { name: '添加一个 API Key 开始使用' }).count()).toBe(0)
|
||||
|
||||
// A different stored copy version represents an intentional version bump:
|
||||
// the welcome step returns even though the credential is already ready.
|
||||
await scaffold.ctx.settings.mutate(settingsNamespace(WELCOME_NOTICE_SETTINGS_NAMESPACE), [{
|
||||
op: 'set', path: [WELCOME_NOTICE_ACK_FIELD], value: 'previous-copy-version',
|
||||
}])
|
||||
const thirdReloadWarnings = tripwire.warnings.length
|
||||
await page.reload({ waitUntil: 'load' })
|
||||
acknowledgeReloadConnectionLoss(tripwire, thirdReloadWarnings)
|
||||
await welcome.waitFor({ timeout: 15_000 })
|
||||
await welcome.getByRole('button', { name: WELCOME_NOTICE_COPY.zh.continueLabel }).click()
|
||||
await welcome.waitFor({ state: 'detached', timeout: 15_000 })
|
||||
expect(await page.getByRole('region', { name: '添加一个 API Key 开始使用' }).count()).toBe(0)
|
||||
|
||||
expect((await page.content()).includes(secret)).toBe(false)
|
||||
expect((await page.locator('body').ariaSnapshot()).includes(secret)).toBe(false)
|
||||
expect(browserConsole.some(line => line.includes(secret))).toBe(false)
|
||||
@@ -86,6 +160,6 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
|
||||
}, 60_000)
|
||||
|
||||
it('keeps the fixture inventory closed', async () => {
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md'])
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md', 'welcome.expected.md'])
|
||||
})
|
||||
})
|
||||
|
||||
@@ -32,6 +32,10 @@ import Loader from '@cordisjs/plugin-loader'
|
||||
import Include, { type PatchOptions } from '@cordisjs/plugin-include'
|
||||
import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot'
|
||||
import { assertEntriesLoaded, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot'
|
||||
import {
|
||||
WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_SETTINGS_NAMESPACE, WELCOME_NOTICE_VERSION,
|
||||
} from '@deepseek-ai/dsh-client-ui-settings-general'
|
||||
import { settingsNamespace } from '@deepseek-ai/dsh-settings'
|
||||
import type { ReplayHandle } from '@deepseek-ai/dsh-llm-replay'
|
||||
import { installLlmReplay, parseSessionLog } from '@deepseek-ai/dsh-llm-replay'
|
||||
import SessionStore, {
|
||||
@@ -135,6 +139,19 @@ export interface LaunchOptions {
|
||||
* keyless first-run configuration lane; the default disables the adapter.
|
||||
*/
|
||||
deepSeekMissingCredential?: boolean
|
||||
/**
|
||||
* Patch the shipped DeepSeek search row to a deterministic endpoint and
|
||||
* credential reference. Browser search scenarios keep the real provider and
|
||||
* credentials seam while avoiding external search traffic and ambient keys.
|
||||
*/
|
||||
deepSeekSearch?: {
|
||||
/** Anthropic-compatible base URL; the provider appends `/messages`. */
|
||||
baseURL: string
|
||||
/** Credential reference resolved by the shipped search provider. */
|
||||
apiKeyEnv: string
|
||||
}
|
||||
/** Leave the current welcome notice unacknowledged; ordinary scenarios publish it as complete before browser boot. */
|
||||
welcomeNoticePending?: boolean
|
||||
}
|
||||
|
||||
/** Dispose the booted tree and remove both owned temp roots, reporting every independent cleanup failure. */
|
||||
@@ -200,9 +217,9 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
|
||||
...surfacePatches,
|
||||
{ id: 'session-persistence-jsonl', config: { root: persistenceRoot } },
|
||||
{ id: 'session-query-sqlite', config: { path: ':memory:', openAt: 'first-search' } },
|
||||
// storage-json's './.storages' yml default is cwd-relative and resolves
|
||||
// per write; the scaffold restores the original cwd after boot, so the
|
||||
// row gets an absolute temp root (removed with the workspace at close).
|
||||
// storage-json's yml root is anchored to the real $DSH_HOME; pin the row
|
||||
// to an absolute temp root (removed with the workspace at close) so tests
|
||||
// never write the user's harness home.
|
||||
{ id: 'storage-json', config: { root: join(workspaceCwd, '.dsh-storages') } },
|
||||
// Skill discovery is model-visible input. Pin every host-level root inside
|
||||
// the owned temp world so ~/.dsh, ~/.agents, and a bundled-root env setting
|
||||
@@ -241,6 +258,15 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
|
||||
...options.cordisTools === true
|
||||
? [{ insert: [{ id: 'tool-cordis', name: 'cordis:tool-cordis' }] }]
|
||||
: [],
|
||||
...options.deepSeekSearch === undefined
|
||||
? []
|
||||
: [{
|
||||
id: 'web-search-deepseek',
|
||||
config: {
|
||||
apiKeyEnv: options.deepSeekSearch.apiKeyEnv,
|
||||
baseURL: options.deepSeekSearch.baseURL,
|
||||
},
|
||||
}],
|
||||
...mode === 'record' || options.deepSeekMissingCredential === true
|
||||
? []
|
||||
: [{ id: 'llm-deepseek', disabled: true }],
|
||||
@@ -266,6 +292,11 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
|
||||
})
|
||||
await ctx.loader.await()
|
||||
assertEntriesLoaded(ctx, 'web e2e scaffold')
|
||||
if (options.welcomeNoticePending !== true) {
|
||||
await ctx.settings.mutate(settingsNamespace(WELCOME_NOTICE_SETTINGS_NAMESPACE), [{
|
||||
op: 'set', path: [WELCOME_NOTICE_ACK_FIELD], value: WELCOME_NOTICE_VERSION,
|
||||
}])
|
||||
}
|
||||
const boundPort = ctx.get('httpServer')?.port
|
||||
if (boundPort === undefined) {
|
||||
throw new Error('web e2e scaffold: httpServer service missing after settled boot')
|
||||
|
||||
@@ -188,8 +188,12 @@ describe('dsh web keyless CLI smoke', () => {
|
||||
mkdirSync(join(workspace, '.git'))
|
||||
writeFileSync(join(workspace, 'AGENTS.md'), 'web-workspace-context-probe\n')
|
||||
|
||||
let resolveProviderRequest!: (request: { messages?: { role?: string; content?: string }[] }) => void
|
||||
const providerRequest = new Promise<{ messages?: { role?: string; content?: string }[] }>((resolve) => {
|
||||
interface NativeProviderRequest {
|
||||
messages?: { role?: string; content?: string }[]
|
||||
tools?: { function?: { name?: string } }[]
|
||||
}
|
||||
let resolveProviderRequest!: (request: NativeProviderRequest) => void
|
||||
const providerRequest = new Promise<NativeProviderRequest>((resolve) => {
|
||||
resolveProviderRequest = resolve
|
||||
})
|
||||
const provider = createServer((request, response) => {
|
||||
@@ -197,7 +201,7 @@ describe('dsh web keyless CLI smoke', () => {
|
||||
request.setEncoding('utf8')
|
||||
request.on('data', (chunk: string) => { body += chunk })
|
||||
request.on('end', () => {
|
||||
resolveProviderRequest(JSON.parse(body) as { messages?: { role?: string; content?: string }[] })
|
||||
resolveProviderRequest(JSON.parse(body) as NativeProviderRequest)
|
||||
response.writeHead(200, { 'content-type': 'text/event-stream' })
|
||||
response.end([
|
||||
'data: {"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""}}]}',
|
||||
@@ -256,6 +260,13 @@ describe('dsh web keyless CLI smoke', () => {
|
||||
"role": "user",
|
||||
}
|
||||
`)
|
||||
expect(captured.tools?.map(tool => tool.function?.name)
|
||||
.filter(name => name === 'web_search' || name === 'web_fetch'))
|
||||
.toMatchInlineSnapshot(`
|
||||
[
|
||||
"web_search",
|
||||
]
|
||||
`)
|
||||
} finally {
|
||||
const closed = child.exitCode === null
|
||||
? new Promise<void>((resolveClose) => { child.once('close', () => { resolveClose() }) })
|
||||
|
||||
@@ -1,6 +1,5 @@
|
||||
- dialog "添加一个 API Key 开始使用":
|
||||
- region "添加一个 API Key 开始使用":
|
||||
- heading "添加一个 API Key 开始使用" [level=2]
|
||||
- button "稍后配置":
|
||||
- img
|
||||
- paragraph: 配置 DeepSeek 官方模型,即可开始使用。
|
||||
- button "稍后配置"
|
||||
- button "前往配置"
|
||||
|
||||
@@ -0,0 +1,10 @@
|
||||
- region "内测声明":
|
||||
- heading "内测声明" [level=2]
|
||||
- paragraph: 感谢您愿意拨冗试用 DeepSeek Harness。
|
||||
- paragraph: 目前的版本仍处于内部测试阶段,功能仍待完善,体验难免有些粗糙。
|
||||
- blockquote: “如切如磋,如琢如磨。” 产品的成长,离不开一次次真实的碰撞与坦诚的反馈。您在真实使用中发现的问题,也可能促使我们重新审视,甚至推翻已有的设计。
|
||||
- paragraph:
|
||||
- text: 我们尤其希望听见那些失败、困惑与不顺手的时刻——
|
||||
- strong: 如果您有任何反馈与建议,请在企业微信群中留言告诉我们
|
||||
- text: 。每一条反馈,都会帮助我们把它打磨得更好。
|
||||
- button "继续"
|
||||
12
apps/web/tests/snapshots/web-search-round/session.jsonl
Normal file
12
apps/web/tests/snapshots/web-search-round/session.jsonl
Normal file
@@ -0,0 +1,12 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785456000000,"cwd":"{{cwd}}"}
|
||||
{"type":"user/message","seq":0,"time":1785456000001,"data":{"content":[{"type":"text","text":"Use web_search to search exactly \"DeepSeek Harness snapshot search\". Then reply exactly SEARCH_DONE and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"assistant/chunk","seq":1,"time":1785456000002,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1785456000003,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_web_search","name":"web_search","argumentsDelta":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1785456000004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_web_search","name":"web_search","arguments":"{\"query\":\"DeepSeek Harness snapshot search\"}"}}}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1785456000005,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785456000006,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
|
||||
{"type":"assistant/chunk","seq":6,"time":1785456000007,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":7,"time":1785456000008,"data":{"turn":1,"step":2,"chunk":{"type":"text-delta","index":0,"text":"SEARCH_DONE"}}}
|
||||
{"type":"assistant/chunk","seq":8,"time":1785456000009,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"SEARCH_DONE"}}}}
|
||||
{"type":"assistant/chunk","seq":9,"time":1785456000010,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":12,"outputTokens":2}}}}
|
||||
{"type":"assistant/chunk","seq":10,"time":1785456000011,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
35
apps/web/tests/snapshots/web-search-round/ui.expected.md
Normal file
35
apps/web/tests/snapshots/web-search-round/ui.expected.md
Normal file
@@ -0,0 +1,35 @@
|
||||
- banner:
|
||||
- navigation "Session hierarchy":
|
||||
- button "Use web_search to search exactly" [disabled]
|
||||
- tablist:
|
||||
- tab "Chat" [selected]
|
||||
- tab "Trajectory"
|
||||
- text: Use web_search to search exactly "DeepSeek Harness snapshot search". Then reply exactly SEARCH_DONE and stop. {{clock}}
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- button "Edit":
|
||||
- img
|
||||
- img
|
||||
- text: Search DeepSeek Harness snapshot search
|
||||
- list:
|
||||
- listitem:
|
||||
- link "Snapshot Search Result":
|
||||
- /url: https://docs.example.test/search
|
||||
- text: Snapshot search excerpt. 2026-07-31
|
||||
- paragraph: SEARCH_DONE
|
||||
- button "Copy":
|
||||
- img
|
||||
- button "Branch into a new conversation":
|
||||
- img
|
||||
- text: {{clock}}
|
||||
- textbox "Message the agent"
|
||||
- button "Commands":
|
||||
- img
|
||||
- 'button "Access mode, current: Full access"': Full access
|
||||
- button "Select model, current DeepSeek-V4-Flash":
|
||||
- text: DeepSeek-V4-Flash
|
||||
- img
|
||||
- button "Send message" [disabled]
|
||||
- text: 1 turns · 2 steps Tool call {{duration}} Cache hit 0% Input 22 tok · Output 7 tok
|
||||
207
apps/web/tests/web-search-round.e2e.ts
Normal file
207
apps/web/tests/web-search-round.e2e.ts
Normal file
@@ -0,0 +1,207 @@
|
||||
// Web e2e scenario for the shipped default search composition. A real browser
|
||||
// drives `web_search`; the model stream is replayed while the real DeepSeek
|
||||
// provider calls a deterministic local Anthropic-compatible endpoint through
|
||||
// the real credentials service.
|
||||
import { readFile } from 'node:fs/promises'
|
||||
import { createServer, type Server } from 'node:http'
|
||||
import type { AddressInfo } from 'node:net'
|
||||
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 { credentialRef } from '@deepseek-ai/dsh-credentials'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import {
|
||||
assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
|
||||
launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
|
||||
|
||||
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/web-search-round', import.meta.url))
|
||||
const FIXTURE = fileURLToPath(new URL('./snapshots/web-search-round/session.jsonl', import.meta.url))
|
||||
const UI_EXPECTED = fileURLToPath(new URL('./snapshots/web-search-round/ui.expected.md', import.meta.url))
|
||||
const MODE = webSnapshotMode()
|
||||
const QUERY = 'DeepSeek Harness snapshot search'
|
||||
const PROMPT = `Use web_search to search exactly "${QUERY}". Then reply exactly SEARCH_DONE and stop.`
|
||||
const SEARCH_CREDENTIAL_REF = credentialRef('DSH_WEB_SEARCH_E2E_KEY')
|
||||
const SEARCH_CREDENTIAL = 'snapshot-search-key'
|
||||
const RESULT_URL = 'https://docs.example.test/search'
|
||||
|
||||
interface CapturedSearchRequest {
|
||||
path: string
|
||||
apiKey: string | undefined
|
||||
body: unknown
|
||||
}
|
||||
|
||||
/** Start the deterministic DeepSeek Messages double used by the real provider. */
|
||||
async function startSearchServer(captured: CapturedSearchRequest[]): Promise<{ server: Server; baseURL: string }> {
|
||||
const server = createServer((request, response) => {
|
||||
let body = ''
|
||||
request.setEncoding('utf8')
|
||||
request.on('data', (chunk: string) => { body += chunk })
|
||||
request.on('end', () => {
|
||||
captured.push({
|
||||
path: request.url ?? '',
|
||||
apiKey: typeof request.headers['x-api-key'] === 'string' ? request.headers['x-api-key'] : undefined,
|
||||
body: JSON.parse(body) as unknown,
|
||||
})
|
||||
response.writeHead(200, { 'content-type': 'application/json' })
|
||||
response.end(JSON.stringify({
|
||||
content: [
|
||||
{
|
||||
type: 'text',
|
||||
text: 'Found one source.',
|
||||
citations: [{
|
||||
type: 'web_search_result_location',
|
||||
url: RESULT_URL,
|
||||
cited_text: 'Snapshot search excerpt.',
|
||||
}],
|
||||
},
|
||||
{
|
||||
type: 'web_search_tool_result',
|
||||
content: [{
|
||||
type: 'web_search_result',
|
||||
url: RESULT_URL,
|
||||
title: 'Snapshot Search Result',
|
||||
page_age: '2026-07-31',
|
||||
}],
|
||||
},
|
||||
],
|
||||
}))
|
||||
})
|
||||
})
|
||||
await new Promise<void>((resolve, reject) => {
|
||||
server.once('error', reject)
|
||||
server.listen(0, '127.0.0.1', () => {
|
||||
server.off('error', reject)
|
||||
resolve()
|
||||
})
|
||||
})
|
||||
const address = server.address() as AddressInfo
|
||||
return { server, baseURL: `http://127.0.0.1:${address.port}` }
|
||||
}
|
||||
|
||||
describe('web e2e: shipped default web search', () => {
|
||||
let scaffold: WebScaffold
|
||||
let browser: Browser
|
||||
let page: Page
|
||||
let searchServer: Server | undefined
|
||||
let searchBaseURL: string
|
||||
let tripwire: ReturnType<typeof watchConsole>
|
||||
const searchRequests: CapturedSearchRequest[] = []
|
||||
const sessionEvents: SessionEvent[] = []
|
||||
|
||||
beforeAll(async () => {
|
||||
const search = await startSearchServer(searchRequests)
|
||||
searchServer = search.server
|
||||
searchBaseURL = search.baseURL
|
||||
scaffold = await launchWebScaffold({
|
||||
deepSeekSearch: {
|
||||
baseURL: search.baseURL,
|
||||
apiKeyEnv: SEARCH_CREDENTIAL_REF,
|
||||
},
|
||||
...(MODE === 'record' ? {} : { replayFixture: FIXTURE, paceMs: 15 }),
|
||||
})
|
||||
await scaffold.ctx.credentials.set(SEARCH_CREDENTIAL_REF, SEARCH_CREDENTIAL)
|
||||
scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { sessionEvents.push(event) })
|
||||
browser = await chromium.launch()
|
||||
page = await newEnglishPage(browser)
|
||||
tripwire = watchConsole(page)
|
||||
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
|
||||
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
|
||||
await connectFreshWorkspace(page)
|
||||
}, 120_000)
|
||||
|
||||
afterAll(async () => {
|
||||
await browser?.close()
|
||||
await scaffold?.close()
|
||||
await new Promise<void>((resolve, reject) => {
|
||||
if (searchServer === undefined) {
|
||||
resolve()
|
||||
return
|
||||
}
|
||||
searchServer.close((error) => {
|
||||
if (error === undefined) resolve()
|
||||
else reject(error)
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
it('drives the recorded search to a settled turn (all modes)', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-search-drive'))
|
||||
if (MODE !== 'record') {
|
||||
expect(fixtureUserPrompts(await readFile(FIXTURE, 'utf8'))).toEqual([PROMPT])
|
||||
}
|
||||
const input = page.locator('textarea').first()
|
||||
await input.waitFor({ timeout: 10_000 })
|
||||
const settled = scaffold.whenTurnSettled()
|
||||
await input.fill(PROMPT)
|
||||
await input.press('Enter')
|
||||
const sessionId = await settled
|
||||
if (MODE === 'record') await recordFixture(scaffold, sessionId, FIXTURE)
|
||||
}, 200_000)
|
||||
|
||||
it.skipIf(MODE === 'record')('uses the real provider and persists the structured result', () => {
|
||||
expect(searchRequests).toHaveLength(1)
|
||||
expect(searchRequests[0]).toMatchObject({
|
||||
path: '/messages',
|
||||
apiKey: SEARCH_CREDENTIAL,
|
||||
body: {
|
||||
messages: [{
|
||||
role: 'user',
|
||||
content: [{ type: 'text', text: `Perform a web search for the query: ${QUERY}` }],
|
||||
}],
|
||||
tools: [{ type: 'web_search_20250305', name: 'web_search' }],
|
||||
},
|
||||
})
|
||||
|
||||
const auxiliaryRequest = sessionEvents.find(
|
||||
(event): event is Extract<SessionEvent, { type: 'web/deepseek-search-llm-request' }> =>
|
||||
event.type === 'web/deepseek-search-llm-request',
|
||||
)
|
||||
expect(auxiliaryRequest?.data).toEqual({
|
||||
endpoint: `${searchBaseURL}/messages`,
|
||||
apiVersion: '2023-06-01',
|
||||
body: searchRequests[0]?.body,
|
||||
})
|
||||
|
||||
const searchCall = sessionEvents.find(
|
||||
(event): event is Extract<SessionEvent, { type: 'tool/call' }> =>
|
||||
event.type === 'tool/call' && event.data.name === 'web_search',
|
||||
)
|
||||
if (searchCall === undefined) throw new Error('the replayed turn did not call web_search')
|
||||
const searchResult = sessionEvents.find(
|
||||
(event): event is Extract<SessionEvent, { type: 'tool/result' }> =>
|
||||
event.type === 'tool/result' && event.data.message.source.callId === searchCall.data.callId,
|
||||
)
|
||||
if (searchResult === undefined) throw new Error('web_search produced no durable result')
|
||||
const content = searchResult.data.message.content[0]
|
||||
expect(content.isError).toBe(false)
|
||||
expect(content.content.filter(block => block.type === 'text').map(block => block.text).join(''))
|
||||
.toContain(`[Snapshot Search Result](${RESULT_URL})`)
|
||||
expect(searchResult.data.meta).toMatchObject({
|
||||
sources: [{
|
||||
url: RESULT_URL,
|
||||
title: 'Snapshot Search Result',
|
||||
snippet: 'Snapshot search excerpt.',
|
||||
publishedAt: '2026-07-31',
|
||||
}],
|
||||
truncated: false,
|
||||
})
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('matches the settled search card aria golden', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-search-aria'))
|
||||
await expect.poll(() => page.getByText('SEARCH_DONE', { exact: true }).count(), { timeout: 15_000 })
|
||||
.toBeGreaterThanOrEqual(1)
|
||||
await page.locator('[data-tool="web_search"]').waitFor({ timeout: 10_000 })
|
||||
const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
|
||||
await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('stayed clean and kept the exact fixture inventory', async () => {
|
||||
expect(tripwire.pageErrors).toEqual([])
|
||||
expect(tripwire.warnings).toEqual([])
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user