Merge remote-tracking branch 'origin/master' into xtr/sidebar-workspace-controls

apps/web/tests/goal-command-presentation.e2e.ts

@@ -0,0 +1,123 @@
+// Web e2e: /goal opts its command input into the human transcript while the
+// command remains log-only. The shipped composition runs with no model adapter,
+// so an accidental turn fails loud in addition to the event-level assertions.
+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 type { SessionEvent } from '@deepseek-ai/dsh-session/types'
+import type {} from '@deepseek-ai/dsh-commands/types'
+import {
+  acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria,
+  compareOrRefreshGolden, launchWebScaffold, watchConsole, webSnapshotMode,
+  type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/goal-command-presentation', import.meta.url))
+const UI_EXPECTED = fileURLToPath(new URL(
+  './snapshots/goal-command-presentation/ui.expected.md', import.meta.url,
+))
+const MODE = webSnapshotMode()
+
+describe('web e2e: /goal human transcript presentation', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+  const events: SessionEvent[] = []
+
+  beforeAll(async () => {
+    scaffold = await launchWebScaffold()
+    scaffold.ctx.on('session/event', (_session, event: SessionEvent) => { events.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, scaffold.workspaceCwd)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('shows the bare input and result from a fresh session without a model turn', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-goal-command-presentation'))
+    await expect.poll(() => page.getByText('Into the Unknown', { exact: false }).count(), {
+      timeout: 15_000,
+    }).toBe(1)
+    const input = page.locator('textarea').first()
+    await input.fill('/goal')
+    await input.press('Enter')
+    await expect.poll(() => input.inputValue()).toBe('/goal ')
+    await input.press('Enter')
+
+    const commandInput = page.locator('[data-command-input]')
+    await commandInput.waitFor({ timeout: 10_000 })
+    await expect.poll(() => commandInput.textContent()).toBe('/goal')
+    expect(await commandInput.getAttribute('role')).toBe('group')
+    expect(await commandInput.getAttribute('aria-label')).toBe('Command input')
+    expect(await commandInput.getByRole('button').count()).toBe(0)
+    const typography = await commandInput.evaluate((element) => {
+      const bubble = element.firstElementChild?.firstElementChild
+      if (!(bubble instanceof HTMLElement)) throw new Error('command input bubble is missing')
+      const rootStyle = getComputedStyle(element)
+      const bubbleStyle = getComputedStyle(bubble)
+      return {
+        fontFamily: bubbleStyle.fontFamily,
+        parentFontFamily: rootStyle.fontFamily,
+        fontSize: bubbleStyle.fontSize,
+        lineHeight: bubbleStyle.lineHeight,
+      }
+    })
+    expect(typography).toMatchObject({ fontSize: '14px', lineHeight: '22px' })
+    expect(typography.fontFamily).not.toBe(typography.parentFontFamily)
+    const resultRow = page.locator('[data-variant="others"]').filter({ hasText: 'No goal is currently set.' })
+    await expect.poll(() => resultRow.count(), { timeout: 10_000 }).toBe(1)
+    expect(await resultRow.getByText('goal', { exact: true }).count()).toBe(1)
+    await expect.poll(() => page.locator('[data-phase="active"]').count()).toBe(1)
+    expect(await page.getByText('Into the Unknown', { exact: false }).count()).toBe(0)
+
+    const run = events.find(event => event.type === 'command/run')
+    expect(run).toMatchObject({
+      type: 'command/run',
+      data: { name: 'goal', args: ' ', source: { kind: 'user' } },
+    })
+    expect(events.some(event => event.type === 'command/done')).toBe(true)
+    expect(events.some(event => event.type === 'user/message')).toBe(false)
+    expect(events.some(event => event.type === 'turn/start')).toBe(false)
+    expect(events.some(event => event.type === 'step/start')).toBe(false)
+    expect(events.some(event => event.type === 'request/header')).toBe(false)
+
+    const snapshot = await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+  }, 60_000)
+
+  it('reloads the same bubble and result from the persisted command lifecycle', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-goal-command-presentation-reload'))
+    const warningStart = tripwire.warnings.length
+    await page.reload({ waitUntil: 'load' })
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+
+    await expect.poll(() => page.locator('[data-command-input]').textContent(), { timeout: 15_000 }).toBe('/goal')
+    const resultRow = page.locator('[data-variant="others"]').filter({ hasText: 'No goal is currently set.' })
+    await expect.poll(() => resultRow.count(), { timeout: 10_000 }).toBe(1)
+    await expect.poll(() => page.locator('[data-phase="active"]').count()).toBe(1)
+
+    const sessions = scaffold.ctx.sessions.list()
+    expect(sessions).toHaveLength(1)
+    const persisted = sessions[0]?.events ?? []
+    expect(persisted.filter(event => event.type === 'command/run' || event.type === 'command/done')
+      .map(event => event.type)).toEqual(['command/run', 'command/done'])
+    expect(persisted.some(event => event.type === 'user/message')).toBe(false)
+    expect(persisted.some(event => event.type === 'turn/start')).toBe(false)
+    expect(persisted.some(event => event.type === 'step/start')).toBe(false)
+    expect(persisted.some(event => event.type === 'request/header')).toBe(false)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+    await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
+  }, 90_000)
+})

apps/web/tests/hmr-live.e2e.ts

@@ -1,4 +1,4 @@
-/** Published dsh web --dev + pnpm dev:web → browser HMR, with no page reload. */
+/** Published dsh web + pnpm dev:web → browser HMR, with no page reload. */
 
 import { existsSync } from 'node:fs'
 import { mkdtemp, readFile, rm, writeFile } from 'node:fs/promises'
@@ -92,14 +92,14 @@ it('hot-reloads a real client-plugin source edit without refreshing the page', a
     watcher = subprocessCtx.subprocess.spawn(spawnSpec(['pnpm', 'run', 'dev:web'], REPO_ROOT))
     await waitForOutput(watcher, /dev-web: watching/, 'pnpm run dev:web')
     host = subprocessCtx.subprocess.spawn(spawnSpec(
-      [process.execPath, binPath, 'web', '--dev', '--port', '0'],
+      [process.execPath, binPath, 'web', '--port', '0'],
       world,
       {
         DEEPSEEK_API_KEY: 'keyless-hmr-no-call',
         DSH_HOME: join(world, '.dsh'),
       },
     ))
-    const baseUrl = await waitForOutput(host, /dsh web: (http:\/\/[^\s]+)/, 'built dsh web --dev')
+    const baseUrl = await waitForOutput(host, /dsh web: (http:\/\/[^\s]+)/, 'built dsh web')
     browser = await chromium.launch()
     const page = await browser.newPage()
     const pageErrors: string[] = []

apps/web/tests/replay-round-trip.e2e.ts

@@ -101,14 +101,14 @@ describe('web e2e: fresh round trip through the real assembly', () => {
       callId: CallId('web-url-probe'),
       name: 'bash',
       arguments: {
-        command: 'printf \'%s\\n%s\\n\' "$DSH_WEB_URL" "$DSH_WEB_MODE"',
+        command: 'printf \'%s\\n\' "$DSH_WEB_URL"',
         description: 'Print current Web runtime',
       },
       agent,
     })
     expect(result.isError).toBe(false)
     expect(result.content.filter(block => block.type === 'text').map(block => block.text).join(''))
-      .toBe(`${scaffold.baseUrl}\nproduction\n`)
+      .toBe(`${scaffold.baseUrl}\n`)
   })
 
   it.skipIf(MODE === 'record')('rendered the settled turn: markdown, tool row, composer restore', async () => {

apps/web/tests/scaffold.ts

@@ -416,7 +416,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
     // (apps/web IS @deepseek-ai/dsh-frontend); only the URL line is silenced.
     // Preserve the composed surface-context choice because a patch replaces
     // the row's complete config.
-    { id: 'web-runtime', config: { mode: 'production', printUrl: false, surfaceContext } },
+    { id: 'web-runtime', config: { printUrl: false, surfaceContext } },
     ...options.remoteAuthority === undefined
       ? []
       : [{ id: 'connection', config: { trustedHosts: [options.remoteAuthority] } }],

apps/web/tests/settings-chrome.e2e.ts

@@ -152,6 +152,67 @@ describe('web e2e: settings modal and General preferences', () => {
     expect(tripwire.pageErrors).toEqual([])
   }, 60_000)
 
+  it('uses the persisted dark preference while plugins are still loading', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-settings-boot-theme'))
+    await page.emulateMedia({ colorScheme: 'light' })
+    await page.getByRole('button', { name: '设置', exact: true }).click()
+    const initialDialog = page.getByRole('dialog', { name: '设置' })
+    const darkCube = initialDialog.getByRole('button', { name: '深色' })
+    await darkCube.click()
+    await expect.poll(() => darkCube.getAttribute('aria-pressed'), { timeout: 5_000 }).toBe('true')
+    await expect.poll(async () => readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8'), { timeout: 5_000 })
+      .toMatch(/ui-theme:\n\s+preference: dark/)
+    await page.keyboard.press('Escape')
+
+    // Hold real plugin bundles so the shell-owned loading page remains observable.
+    const pluginPattern = '**/plugins/**'
+    let releaseBundles = (): void => {}
+    const bundlesReleased = new Promise<void>((resolve) => { releaseBundles = resolve })
+    await page.route(pluginPattern, async (route) => {
+      await bundlesReleased
+      await route.continue()
+    })
+
+    const warningStart = tripwire.warnings.length
+    let reload: ReturnType<Page['reload']> | undefined
+    try {
+      reload = page.reload({ waitUntil: 'domcontentloaded' })
+      const loading = page.getByText('Loading plugins…', { exact: true })
+      await loading.waitFor({ timeout: 10_000 })
+      const state = await loading.evaluate((element) => {
+        const boot = element.parentElement?.parentElement
+        if (boot === undefined || boot === null) throw new Error('loading hint is detached from the boot page')
+        return {
+          attr: document.body.hasAttribute('data-ds-dark-theme'),
+          background: getComputedStyle(boot).backgroundColor,
+          colorScheme: document.documentElement.style.colorScheme,
+        }
+      })
+      expect(state).toEqual({
+        attr: true,
+        background: 'rgb(21, 21, 23)',
+        colorScheme: 'dark',
+      })
+    } finally {
+      releaseBundles()
+      await reload
+      await page.unroute(pluginPattern)
+    }
+
+    await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
+    acknowledgeReloadConnectionLoss(tripwire, warningStart)
+    await page.getByRole('button', { name: '设置', exact: true }).click()
+    const restoredDialog = page.getByRole('dialog', { name: '设置' })
+    const systemCube = restoredDialog.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(() => page.evaluate(() => document.body.hasAttribute('data-ds-dark-theme')), {
+      timeout: 5_000,
+    }).toBe(false)
+    await page.keyboard.press('Escape')
+    expect(tripwire.pageErrors).toEqual([])
+  }, 90_000)
+
   it('flips the theme through the Appearance cubes and persists across reload and a distinct port', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-settings-appearance'))
     interface ThemeState {

apps/web/tests/smoke-real.e2e.ts

@@ -27,7 +27,7 @@ import { chromium } from 'playwright'
 import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
 import { REPO_ROOT, connectFreshWorkspace, newEnglishPage, probeFreePort, requireDist, saveFailureShot } from './support.ts'
 
-const DEVELOPMENT_PROMPT = fileURLToPath(new URL('./snapshots/web-runtime-context/development-prompt.expected.md', import.meta.url))
+const WEB_SURFACE_PROMPT = fileURLToPath(new URL('./snapshots/web-runtime-context/web-surface-prompt.expected.md', import.meta.url))
 
 function waitForReadyLine(child: ChildProcess): Promise<string> {
   return new Promise((resolveReady, reject) => {
@@ -187,7 +187,7 @@ describe('dsh web keyless CLI smoke', () => {
     }
   })
 
-  it('routes --dev runtime context and workspace instructions through the real CLI request', async () => {
+  it('routes web runtime context and workspace instructions through the real CLI request', async () => {
     requireDist()
     const workspace = mkdtempSync(join(tmpdir(), 'dsh-web-workspace-'))
     mkdirSync(join(workspace, '.git'))
@@ -226,7 +226,7 @@ describe('dsh web keyless CLI smoke', () => {
     const tsxLoader = pathToFileURL(createRequire(join(REPO_ROOT, 'package.json')).resolve('tsx')).href
     const child = spawn(
       process.execPath,
-      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0', '--dev'],
+      ['--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', '0'],
       {
         cwd: workspace,
         env: {
@@ -261,7 +261,7 @@ describe('dsh web keyless CLI smoke', () => {
       const workspaceMessage = captured.messages?.find(message =>
         message.role === 'user' && message.content?.includes('web-workspace-context-probe'))
       const systemMessage = captured.messages?.find(message => message.role === 'system')
-      const expectedWebSection = readFileSync(DEVELOPMENT_PROMPT, 'utf8').trimEnd()
+      const expectedWebSection = readFileSync(WEB_SURFACE_PROMPT, 'utf8').trimEnd()
         .replace('{{webUrl}}', baseUrl)
       expect(systemMessage?.content).toContain(expectedWebSection)
       expect(workspaceMessage).toMatchInlineSnapshot(`

apps/web/tests/snapshots/fresh-round-trip/system-prompt.expected.md

@@ -2,6 +2,6 @@ You are an AI agent powered by the DeepSeek Harness SDK.
 
 The DeepSeek Harness implementation checkout is at {{sourceRoot}}. The checkout location and current working directory are separate values and may differ; never infer the working directory from this path. Use pwd to determine the current working directory. Use this checkout only to inspect or extend DSH itself.
 
-You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. This Web process was launched without `--dev`, so HMR is inactive: rebuild the affected Web artifacts and verify this existing URL after a page refresh. If the user wants no-refresh client-plugin updates, explain that this GUI must be restarted with `dsh web --dev` and `pnpm run dev:web` must also run from this same checkout; do not present either command alone as sufficient. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.
+You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. The client-plugin HMR receiver is active, but client-plugin changes reload without a refresh only while `pnpm run dev:web` is also running from this same checkout to rebuild their bundles; verify that watcher before promising automatic updates. Every other change — the apps/web shell and plain packages — requires rebuilding the affected Web artifacts and verifying this existing URL after a page refresh. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.
 
 You are a coding agent powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.

apps/web/tests/snapshots/goal-command-presentation/ui.expected.md

@@ -0,0 +1,21 @@
+- banner:
+  - navigation "Session hierarchy":
+    - button "workspace" [disabled]
+  - img
+  - text: Standard mode
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- group "Command input": /goal
+- 'button "goal No goal is currently set. Usage: /goal [<objective>|clear|edit <objective>|pause|resume]"':
+  - img
+  - img
+  - text: "goal No goal is currently set. Usage: /goal [<objective>|clear|edit <objective>|pause|resume]"
+- textbox "Message the agent"
+- button "Commands":
+  - img
+- 'button "Access mode, current: Workspace Write"': Workspace Write
+- button "Select model, current DeepSeek-V4-Flash":
+  - text: DeepSeek-V4-Flash
+  - img
+- button "Send message" [disabled]

apps/web/tests/snapshots/goal-multi-turn-actions/ui.expected.md

@@ -6,6 +6,7 @@
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
+- group "Command input": /goal 做两个turn，每个turn输出随机一个包的文件结构。注意你做完一个turn之后，直接输出内容，停止，我们的系统会帮你再开一个turn，你看着做一个类似的
 - 'button "goal Goal created Status: active Objective: 做两个turn，每个turn输出随机一个包的文件结构。注意你做完一个turn之后，直接输出内容，停止，我们的系统会帮你再开一个turn，你看着做一个类似的 Rounds: 0/256 Activation: armed Commands: /goal edit <objective>, /goal pause, /goal clear"':
   - img
   - img

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

@@ -6,6 +6,7 @@
   - tablist:
     - tab "Chat" [selected]
     - tab "Trajectory"
+- group "Command input": /goal Keep the composer context panels aligned
 - 'button "goal Goal created Status: active Objective: Keep the composer context panels aligned Rounds: 0/256 Activation: armed Commands: /goal edit <objective>, /goal pause, /goal clear"':
   - img
   - img

apps/web/tests/snapshots/web-runtime-context/development-prompt.expected.md

@@ -1 +0,0 @@
-You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. This Web process was launched with `dsh web --dev`, so its client-plugin HMR receiver is active. No-refresh updates occur only when `pnpm run dev:web` is also running from this same checkout to rebuild client-plugin bundles; verify that watcher before promising automatic updates. Client-plugin changes then reload automatically, while apps/web shell and other plain-package changes still require a rebuild and page refresh. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.

apps/web/tests/snapshots/web-runtime-context/web-surface-prompt.expected.md

@@ -0,0 +1 @@
+You are interacting with the user through the DeepSeek Harness Web GUI at {{webUrl}}. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context. The client-plugin HMR receiver is active, but client-plugin changes reload without a refresh only while `pnpm run dev:web` is also running from this same checkout to rebuild their bundles; verify that watcher before promising automatic updates. Every other change — the apps/web shell and plain packages — requires rebuilding the affected Web artifacts and verifying this existing URL after a page refresh. Starting another server does not update this GUI. The apps/web Vite entry builds the shell but is not a standalone application because only dsh web injects window.__DSH_BOOT__. Do not start a replacement server unless the user asks; if one is needed, use a managed background task and verify its exact URL.

apps/web/tsconfig.json

@@ -70,6 +70,7 @@
     "tests/produced-files.e2e.ts",
     "tests/produced-file-mentions.e2e.ts",
     "tests/goal-bar.e2e.ts",
+    "tests/goal-command-presentation.e2e.ts",
     "tests/subagent-conversation.e2e.ts",
     "tests/subagent-interrupt.e2e.ts",
     "tests/subagent-interrupt-ui.e2e.ts",

apps/web/vite.config.ts

@@ -6,7 +6,7 @@ import react from '@vitejs/plugin-react'
 const src = (rel: string): string => fileURLToPath(new URL(rel, import.meta.url))
 const STANDALONE_ERROR = 'apps/web is not a standalone application: bare Vite cannot inject window.__DSH_BOOT__. '
   + 'From a repository checkout, run `pnpm dsh web`; an installed package uses `dsh web`. '
-  + 'For client-plugin HMR, run `pnpm dsh web --dev` together with `pnpm run dev:web`.'
+  + 'For client-plugin HMR, run `pnpm dsh web` together with `pnpm run dev:web`.'
 
 /** Fail before a Vite dev or preview server can expose the boot-manifest-free shell. */
 function rejectStandaloneServe(): Plugin {