test(web): cover skill invocation policy on real host

This commit is contained in:
Tianyi Cui
2026-07-29 22:58:46 +08:00
parent 12832886c5
commit 039547979d
5 changed files with 125 additions and 5 deletions
@@ -0,0 +1,115 @@
// Web e2e scenario: the real host filters skill.list to the model-and-user
// intersection before the browser slash source renders candidates. A real
// chromium connects a fresh workspace seeded with all four policy quadrants;
// no model call is issued, so a stray stream fails loud on the open LLM seam.
import { mkdir, writeFile } 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,
launchWebScaffold,
watchConsole,
webSnapshotMode,
type WebScaffold,
} from './scaffold.ts'
import { connectFreshWorkspace, saveFailureShot } from './support.ts'
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/skill-invocation-policy', import.meta.url))
const MENU_EXPECTED = join(SNAPSHOT_DIR, 'menu.expected.md')
const MODE = webSnapshotMode()
interface SeedSkill {
name: string
description: string
frontmatter: string
}
const SKILLS: readonly SeedSkill[] = [
{
name: 'policy-shared',
description: 'Available to both model and user invocation',
frontmatter: '',
},
{
name: 'policy-model-only',
description: 'Available only to model invocation',
frontmatter: 'user-invocable: false\n',
},
{
name: 'policy-user-only',
description: 'Available only to user invocation',
frontmatter: 'disable-model-invocation: true\n',
},
{
name: 'policy-trusted-only',
description: 'Available only to trusted internal callers',
frontmatter: 'disable-model-invocation: true\nuser-invocable: false\n',
},
]
async function seedSkills(workspaceCwd: string): Promise<void> {
for (const skill of SKILLS) {
const directory = join(workspaceCwd, 'workspace', '.agents', 'skills', skill.name)
await mkdir(directory, { recursive: true })
const policyLines = skill.frontmatter === '' ? [] : skill.frontmatter.trimEnd().split('\n')
await writeFile(join(directory, 'SKILL.md'), [
'---',
`name: ${skill.name}`,
`description: ${skill.description}`,
...policyLines,
'---',
'',
`# ${skill.name}`,
'',
].join('\n'))
}
}
describe('web e2e: skill invocation policy through the real host', () => {
let scaffold: WebScaffold
let browser: Browser
let page: Page
let tripwire: ReturnType<typeof watchConsole>
beforeAll(async () => {
scaffold = await launchWebScaffold({})
await seedSkills(scaffold.workspaceCwd)
browser = await chromium.launch()
page = await browser.newPage({ viewport: { width: 1680, height: 1000 } })
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()
})
it('renders only the model-and-user intersection in slash candidates', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-skill-invocation-policy'))
const input = page.locator('textarea').first()
await input.fill('/policy')
const menu = page.getByRole('listbox', { name: 'Trigger suggestions' })
await expect.poll(
() => menu.getByRole('option', { name: /policy-shared/ }).count(),
{ timeout: 10_000 },
).toBe(1)
expect(await menu.getByRole('option', { name: /policy-model-only/ }).count()).toBe(0)
expect(await menu.getByRole('option', { name: /policy-user-only/ }).count()).toBe(0)
expect(await menu.getByRole('option', { name: /policy-trusted-only/ }).count()).toBe(0)
const snapshot = await captureStableAria(page, '[role="listbox"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(MENU_EXPECTED, snapshot, MODE)
expect(tripwire.pageErrors).toEqual([])
expect(tripwire.warnings).toEqual([])
await assertFixtureInventory(SNAPSHOT_DIR, ['menu.expected.md'])
})
})
+5 -4
View File
@@ -2,7 +2,7 @@
// Assembled keyless snapshot of the slash/input/session convergence under the
// agent-parity model: the New Session view state locks the composer until a
// Workspace is picked (connectWorkspace materializes the full Session+Agent),
// the '/' menu serves the session's filtered skill and wire command catalogs
// the '/' menu renders the session's skill and wire command catalogs
// (sessions are always agent-backed — no draft/materialized split), a skill
// pick inserts its reference, a leadingInput command claims,
// submits over the wire, and notices its result, and the SAME composer
@@ -141,9 +141,10 @@ it('locked view state, skill discovery, /echo claim chain, and blank-on-acceptan
)
expect(composer.disabled).toBe(false)
// The built skill plugin prewarms the session-addressed catalog; querying
// it exercises the assembled discovery path and picking inserts the literal
// reference into the resident composer.
// The built skill plugin prewarms the fixture's session-addressed catalog;
// this pins client rendering and picking, while the real-host browser lane
// owns policy filtering. Picking inserts the literal reference into the
// resident composer.
await typeComposer(composer, '/fixture')
const skillMenu = await screen.findByRole('listbox', { name: 'Trigger suggestions' })
const skillOption = await within(skillMenu).findByRole('option', { name: /fixture-demo/ })
@@ -0,0 +1,2 @@
- listbox "Trigger suggestions":
- option "policy-shared Available to both model and user invocation" [selected]
+2 -1
View File
@@ -36,7 +36,8 @@
"tests/sidebar-scrollbar.e2e.ts",
"tests/code-mode-round.e2e.ts",
"tests/cordis-tool-round.e2e.ts",
"tests/message-actions.e2e.ts"
"tests/message-actions.e2e.ts",
"tests/skill-invocation-policy.e2e.ts"
],
"references": [
{
+1
View File
@@ -24,6 +24,7 @@
"apps/web/tests/code-mode-round.e2e.ts",
"apps/web/tests/cordis-tool-round.e2e.ts",
"apps/web/tests/message-actions.e2e.ts",
"apps/web/tests/skill-invocation-policy.e2e.ts",
"apps/cli/tests/**/*.ts",
"examples/*/src/**/*.ts",
"examples/*/start.ts",