Merge pull request #1624 from deepseek-harness/feat/pwsh-ui-parity

feat(pwsh): render pwsh calls as bash-shaped terminal cards in the Web UI

apps/web/package.json

@@ -27,6 +27,7 @@
     "@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
     "@deepseek-ai/dsh-client-ui-slots": "workspace:^",
     "@deepseek-ai/dsh-client-web-react": "workspace:^",
+    "@deepseek-ai/dsh-pwsh-local": "workspace:^",
     "@types/node": "^22.0.0",
     "@types/react": "~18.3.1",
     "@types/react-dom": "~18.3.0",

apps/web/tests/pwsh-terminal.e2e.ts

@@ -0,0 +1,103 @@
+// Keyless browser regression for pwsh UI parity with bash: a seeded session
+// whose pwsh call/result is presented by the REAL tool-pwsh on replay (the
+// api-proxy recomputes presentation views from logged args/result content)
+// must render as a bash-shaped terminal card with the parsed exit-status
+// pill — not the generic console-fenced card the pwsh presenter used to
+// emit. The seed is authored, not recorded: its header line carries no `cwd`
+// field (seedSession writes the session cwd itself, and a Windows temp path
+// substituted into the header would not round-trip through its JSON parse),
+// and no event references the workspace, so the lane replays on any host
+// with a usable `pwsh` — the lane mounts the pwsh stack through an overlay
+// (the shipped tree keeps the bash stack).
+import { spawnSync } from 'node:child_process'
+import { readFile } from 'node:fs/promises'
+import { join } from 'node:path'
+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 { resolvePwshPath } from '@deepseek-ai/dsh-pwsh-local'
+import {
+  assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
+  fixtureUserPrompts, launchWebScaffold, seedSession, webSnapshotMode,
+  type WebScaffold,
+} from './scaffold.ts'
+import { connectFreshWorkspace, newEnglishPage, saveFailureShot } from './support.ts'
+
+const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/pwsh-terminal', import.meta.url))
+const SEED = join(SNAPSHOT_DIR, 'seed.jsonl')
+const TERMINAL_EXPECTED = join(SNAPSHOT_DIR, 'terminal-card.expected.md')
+const OVERLAY = fileURLToPath(new URL('./pwsh-terminal.overlay.yml', import.meta.url))
+const PROMPT = 'Run a PowerShell command that fails, then stop.'
+const SEED_ID = 'pwsh-terminal-web-e2e'
+const MODE = webSnapshotMode()
+
+// The overlay swaps the shipped bash executor for @deepseek-ai/dsh-pwsh-local;
+// a host without a usable `pwsh` cannot boot it, so the lane self-skips,
+// mirroring the pwshOnly ACP scenarios. The probe follows the executor's own
+// resolution (Program Files installs on Windows are found even when bare
+// `pwsh` is not on PATH), the same judgment the tool-pwsh tests reuse; record
+// mode skips the lane anyway, so the probe stays inert there.
+const HAS_PWSH = MODE === 'record' ? false : spawnSync(
+  resolvePwshPath(), ['-NoLogo', '-NoProfile', '-NonInteractive', '-Command', '$true'],
+  { encoding: 'utf8' },
+).status === 0
+
+describe.skipIf(MODE === 'record' || !HAS_PWSH)('web e2e: pwsh calls render as bash-shaped terminal cards', () => {
+  let scaffold: WebScaffold
+  let browser: Browser
+  let page: Page
+
+  beforeAll(async () => {
+    const fixture = await readFile(SEED, 'utf8')
+    expect(fixtureUserPrompts(fixture), 'seed fixture must carry the single drive prompt').toEqual([PROMPT])
+    scaffold = await launchWebScaffold({ extraOverlayPath: OVERLAY })
+    await seedSession(scaffold, fixture, SEED_ID)
+    browser = await chromium.launch()
+    page = await newEnglishPage(browser)
+    await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
+    await connectFreshWorkspace(page, scaffold.workspaceCwd)
+  }, 120_000)
+
+  afterAll(async () => {
+    await browser?.close()
+    await scaffold?.close()
+  })
+
+  it('renders the seeded pwsh call as a terminal card with the parsed exit pill', async () => {
+    onTestFailed(() => saveFailureShot(page, 'web-e2e-pwsh-terminal'))
+    // Open the seeded session through content search: the sidebar groups
+    // sessions by workspace and its row order is world-dependent, while the
+    // search index covers the seeded log deterministically.
+    const search = page.getByPlaceholder('Search name, keywords', { exact: false })
+    await search.fill('Run a PowerShell command')
+    const result = page.getByRole('tree', { name: 'Search results' }).getByRole('treeitem')
+    await expect.poll(() => result.count(), { timeout: 15_000 }).toBe(1)
+    await result.click()
+    await page.getByRole('tab', { name: 'Chat', exact: true }).waitFor({ timeout: 15_000 })
+    // The tool row is expand-gated: the settled bash-shaped row carries the
+    // shell-family variant, and the terminal card lives in the expanded body.
+    const row = page.locator('[data-tool="pwsh"]').first()
+    await row.waitFor({ timeout: 15_000 })
+    if (await row.getAttribute('aria-expanded') !== 'true') await row.click()
+    const card = page.locator('[data-terminal]').first()
+    await card.waitFor({ timeout: 15_000 })
+    // The parsed exit pill replaces the `[exit code: 1]` marker in the output
+    // body — the bash tool's terminal presentation, not the generic fence.
+    const text = await card.textContent()
+    expect(text).toContain('exit code 1')
+    expect(text).toContain('Get-Item : Cannot find path')
+    expect(text).not.toContain('[exit code: 1]')
+    const snapshot = (await captureStableAria(page, '[data-terminal]', scaffold.workspaceCwd))
+      // normalizeAria collapses the workspace basename with a '/' split, which
+      // misses Windows temp paths; collapse it here too (a no-op on POSIX) so
+      // the golden is platform-independent.
+      .split(scaffold.workspaceCwd.split(/[\\/]/).pop()!).join('{{workspace}}')
+      .split(SEED_ID).join('{{seededId}}')
+    await compareOrRefreshGolden(TERMINAL_EXPECTED, snapshot, MODE)
+  }, 60_000)
+
+  it('guards the lane fixture inventory', async () => {
+    await assertFixtureInventory(SNAPSHOT_DIR, ['seed.jsonl', 'terminal-card.expected.md'])
+  })
+})

apps/web/tests/pwsh-terminal.overlay.yml

@@ -0,0 +1,20 @@
+# The pwsh terminal-card lane swaps the shipped bash stack for the PowerShell
+# twin: the bash executor row is disabled (patches cannot rename a row — `name`
+# is a guard) and the pwsh executor + tool are inserted. The permission service
+# refuses an unconfined executor by design (presets bundle a sandbox mode), so
+# its row is disabled too — this lane renders a seeded session, never a
+# permission decision. The seeded scenario renders the logged pwsh call/result
+# through the real tools on replay; no command executes, but the composition
+# must boot the pwsh executor, so the lane skips on hosts without a usable
+# `pwsh`.
+- id: bash-sandbox
+  name: '@deepseek-ai/dsh-bash-sandbox'
+  disabled: true
+- id: permission
+  name: '@deepseek-ai/dsh-permission'
+  disabled: true
+- insert:
+    - id: pwsh-local
+      name: '@deepseek-ai/dsh-pwsh-local'
+    - id: tool-pwsh
+      name: '@deepseek-ai/dsh-tool-pwsh'

apps/web/tests/snapshots/pwsh-terminal/seed.jsonl

@@ -0,0 +1,19 @@
+{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1784974100747}
+{"type":"turn/start","seq":0,"time":1784974200000,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user","rpcId":"{{rpcId}}"}}}}
+{"type":"user/message","seq":1,"time":1784974200001,"data":{"content":[{"type":"text","text":"Run a PowerShell command that fails, then stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
+{"type":"session/title","seq":2,"time":1784974200002,"data":{"title":"Run a PowerShell command","messageSeqs":[1],"source":{"kind":"fallback"}}}
+{"type":"step/start","seq":3,"time":1784974200010,"data":{"turn":1,"step":1}}
+{"type":"request/header","seq":4,"time":1784974200011,"data":{"header":{"config":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}","messagePrefix":["{{messagePrefix}}"]},"reason":"initial"}}
+{"type":"assistant/chunk","seq":5,"time":1784974200200,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}}
+{"type":"assistant/chunk","seq":6,"time":1784974200201,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Run the failing pwsh command."}}}
+{"type":"assistant/chunk","seq":7,"time":1784974200201,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"Run the failing pwsh command."}}}}
+{"type":"assistant/chunk","seq":8,"time":1784974200300,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}}
+{"type":"assistant/chunk","seq":9,"time":1784974200301,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":1,"id":"call_pwsh_fail_0001","name":"pwsh","argumentsDelta":"{\"command\": \"Get-Item missing.txt\", \"description\": \"Fail deliberately\"}"}}}
+{"type":"assistant/chunk","seq":10,"time":1784974200301,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_pwsh_fail_0001","name":"pwsh","arguments":"{\"command\": \"Get-Item missing.txt\", \"description\": \"Fail deliberately\"}"}}}}
+{"type":"assistant/chunk","seq":11,"time":1784974200302,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":96,"outputTokens":64,"cacheReadTokens":0,"reasoningTokens":10}}}}
+{"type":"assistant/chunk","seq":12,"time":1784974200302,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}}
+{"type":"assistant/message","seq":13,"time":1784974200310,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Run the failing pwsh command."},{"type":"tool-call","id":"call_pwsh_fail_0001","name":"pwsh","arguments":"{\"command\": \"Get-Item missing.txt\", \"description\": \"Fail deliberately\"}"}],"provenance":{"provider":"deepseek-official","model":"deepseek-v4-flash"},"usage":{"inputTokens":96,"outputTokens":64,"cacheReadTokens":0,"reasoningTokens":10}},"sourceEventSeqs":[5,6,7,8,9,10,11,12],"surfaceOp":"append"}
+{"type":"tool/call","seq":14,"time":1784974200311,"data":{"turn":1,"step":1,"callId":"call_pwsh_fail_0001","name":"pwsh","arguments":"{\"command\": \"Get-Item missing.txt\", \"description\": \"Fail deliberately\"}"}}
+{"type":"tool/result","seq":15,"time":1784974200500,"data":{"turn":1,"step":1,"callId":"call_pwsh_fail_0001","content":[{"type":"text","text":"[stderr]\nGet-Item : Cannot find path 'missing.txt' because it does not exist.\n[exit code: 1]"}],"isError":false},"sourceEventSeqs":[14],"surfaceOp":"append"}
+{"type":"step/end","seq":16,"time":1784974200501,"data":{"turn":1,"step":1}}
+{"type":"turn/end","seq":17,"time":1784974200501,"data":{"turn":1,"reason":{"kind":"completed"}}}

apps/web/tests/snapshots/pwsh-terminal/terminal-card.expected.md

@@ -0,0 +1,3 @@
+- text: Failed {{workspace}} Get-Item missing.txt exit code 1
+- button "Copy"
+- text: "[stderr] Get-Item : Cannot find path 'missing.txt' because it does not exist."

apps/web/tsconfig.json

@@ -65,7 +65,8 @@
     "tests/chat-long-interactions.e2e.ts",
     "tests/chat-continuous-conversation.e2e.ts",
     "tests/composer-tab-geometry.e2e.ts",
-    "tests/complex-history.perf.ts"
+    "tests/complex-history.perf.ts",
+    "tests/pwsh-terminal.e2e.ts"
   ],
   "references": [
     {