Merge pull request #1173 from deepseek-harness/agent/web-bash-error-expand

fix(web): expand aborted Bash rows

apps/web/tests/bash-abort-row.e2e.ts

@@ -0,0 +1,82 @@
+// Web e2e scenario: a cancelled Bash call can settle without terminal-card
+// material. Borrow the real cancellation fixture and prove the keyed Bash row
+// still exposes the recorded command and full error without any model call.
+import { readFile } 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, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
+  launchWebScaffold, seedSession, watchConsole, webSnapshotMode, type WebScaffold,
+} from './scaffold.ts'
+import { newEnglishPage, saveFailureShot } from './support.ts'
+
+const FIXTURE = fileURLToPath(new URL('../../../examples/acp-agent/tests/snapshots/cancel-tool-calls/session.jsonl', import.meta.url))
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/bash-abort-row', import.meta.url))
+const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')
+const MODE = webSnapshotMode()
+const SEED_ID = 'bash-abort-row-web-e2e'
+const PROMPT = 'Run two shell commands: wait for cancellation, then write skipped.txt.'
+
+describe.skipIf(MODE === 'record')('web e2e: cancelled Bash row disclosure', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+  let tripwire: ReturnType<typeof watchConsole>
+
+  beforeAll(async () => {
+    const fixture = await readFile(FIXTURE, 'utf8')
+    expect(fixtureUserPrompts(fixture)).toEqual([PROMPT])
+    scaffold = await launchWebScaffold({})
+    await seedSession(scaffold, fixture, SEED_ID)
+    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 })
+
+    const groupRow = page.locator('[role="treeitem"]').first()
+    await groupRow.waitFor({ timeout: 15_000 })
+    await groupRow.click()
+    const sessionRow = page.locator('[role="treeitem"]').nth(1)
+    await sessionRow.waitFor({ timeout: 10_000 })
+    await sessionRow.click()
+    await page.locator('[data-sample="bash"]').nth(1).waitFor({ timeout: 15_000 })
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('expands the aborted row to its command and full error', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-bash-abort-row'))
+    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 row.click()
+
+    await expect.poll(() => row.getAttribute('aria-expanded')).toBe('true')
+    await call.getByText('IN', { exact: true }).waitFor()
+    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)
+
+    const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
+      // The borrowed fixture's UTC date is still the previous day in PDT;
+      // the disclosure golden must not depend on the runner timezone.
+      .replace(/\b\d{1,2}\/\d{1,2}(?= \{\{clock\}\})/g, '{{date}}')
+      .split(SEED_ID).join('{{seededId}}')
+    await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)
+    expect(tripwire.pageErrors).toEqual([])
+    expect(tripwire.warnings).toEqual([])
+  }, 60_000)
+
+  it('keeps its snapshot inventory closed', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['ui.expected.md'])
+  })
+})

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

@@ -0,0 +1,32 @@
+- banner:
+  - navigation "Session hierarchy":
+    - 'button "Run two shell commands: wait" [disabled]'
+  - tablist:
+    - tab "Chat" [selected]
+    - tab "Trajectory"
+- text: "Run two shell commands: wait for cancellation, then write skipped.txt. {{date}} {{clock}}"
+- button "Copy":
+  - img
+- button "Branch into a new conversation":
+  - img
+- button "Context injection":
+  - img
+  - img
+  - text: Context injection
+- 'button "Failed Bash Error: command 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"
+- button "Inspect"
+- 'button "Failed Bash Error: tool call aborted before dispatch"':
+  - img
+  - text: "Failed Bash Error: tool call aborted before dispatch"
+- 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]
+- text: 1 turns · 1 steps Tool call {{duration}} Cache hit 0% Input 10 tok · Output 10 tok

apps/web/tsconfig.json

@@ -53,7 +53,8 @@
     "tests/shipped-composition.e2e.ts",
     "tests/goal-bar.e2e.ts",
     "tests/startup-auto-selection.e2e.ts",
-    "tests/subagent-conversation.e2e.ts"
+    "tests/subagent-conversation.e2e.ts",
+    "tests/bash-abort-row.e2e.ts"
   ],
   "references": [
     {