mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-07-23 16:36:23 +00:00
6b54582438
* nix: add `cage` to devShell
* test(desktop): add pre-filled sessions support
Exports createSandbox, writeMockProviderConfig, writeEnvFile,
buildAppEnv, findElectron, and launchDesktop from fixtures.ts so
specs can compose their own seeded-backend fixtures without duplicating
the sandbox/config/launch logic.
* test(desktop): auto-fail e2e tests on error banner
Adds a shared test fixture (e2e/test.ts) that wraps @playwright/test's
page with an error-banner guard. When any [role="alert"] element
(error notification toast) appears in the DOM during a test, the test
fails with the error message text.
The guard uses:
- A MutationObserver (injected via addInitScript) that watches for
[role="alert"] elements appearing at any point during the test
- A final DOM scan in afterEach for alerts still visible at teardown
- Deduplication so the same error text only fires once
All existing e2e specs updated to import { test, expect } from './test'
instead of '@playwright/test'. No per-spec setup needed — the guard is
auto-installed on every page via the extended fixture.
This catches issues like the "resume failed" error banner that can
appear during session loading — previously the test would pass while
an error toast was silently visible on screen.
* fix(state): parse tool_calls JSON string before re-serializing
_insert_message_rows and append_message both do json.dumps(tool_calls)
to serialize the field for SQLite storage. But when tool_calls arrives
as a JSON string (from import_sessions / export_session, which store it
as TEXT), json.dumps double-encodes it — wrapping the already-serialized
string in quotes and escaping the inner quotes.
When _rows_to_conversation later does json.loads(row['tool_calls']),
the double-encoded string parses back to a plain string (not a list).
_history_to_messages then iterates this string character-by-character,
calling tc.get('function', {}) on each char — 'str' object has no
attribute 'get'.
This was a pre-existing bug (on main), but only triggered by the
import_sessions path (the live agent always passes tool_calls as a
Python list). The e2e error-banner guard caught it via the 'Resume
failed' notification toast.
Fix: in both append_message and _insert_message_rows, parse tool_calls
with json.loads first if it's a string, then re-serialize.
* fix(desktop): exempt boot-failure from error guard
- boot-failure: add allowErrorBanners() beforeEach — these tests
deliberately trigger boot errors, so error toasts are expected
- test.ts: export allowErrorBanners() opt-out + reset flag in afterEach
88 lines
2.6 KiB
TypeScript
88 lines
2.6 KiB
TypeScript
import { expect, test } from './test'
|
|
|
|
import {
|
|
PACKAGED_BINARY_PATH,
|
|
type PackagedAppFixture,
|
|
packagedBinaryExists,
|
|
setupPackagedApp,
|
|
} from './fixtures'
|
|
import { expectVisualSnapshot } from './visual-snapshot'
|
|
|
|
/**
|
|
* E2E smoke tests for the packaged Hermes desktop app.
|
|
*
|
|
* Launches the real packaged Electron binary (produced by `npm run pack` →
|
|
* `electron-builder --dir`) with BOOT_FAKE=1 and full sandbox isolation
|
|
* (credential stripping, isolated HERMES_HOME + userData, unique app name).
|
|
*
|
|
* Skips if the packaged binary doesn't exist — run `npm run pack` first.
|
|
*/
|
|
|
|
let fixture: PackagedAppFixture | null = null
|
|
|
|
test.beforeAll(async () => {
|
|
test.skip(
|
|
!packagedBinaryExists(),
|
|
`Built app binary not found: ${PACKAGED_BINARY_PATH}. Run 'npm run pack' first.`,
|
|
)
|
|
|
|
fixture = await setupPackagedApp()
|
|
})
|
|
|
|
test.afterAll(async () => {
|
|
await fixture?.cleanup()
|
|
fixture = null
|
|
})
|
|
|
|
test('window opens with the Hermes title', async () => {
|
|
const title = await fixture!.page.title()
|
|
expect(title).toContain('Hermes')
|
|
})
|
|
|
|
test('renderer loads and shows DOM content', async () => {
|
|
const page = fixture!.page
|
|
await page.waitForSelector('#root', { state: 'attached', timeout: 30_000 })
|
|
const childCount = await page.locator('#root > *').count()
|
|
expect(childCount).toBeGreaterThan(0)
|
|
})
|
|
|
|
test('boot progress overlay fades out or shows error state', async () => {
|
|
const page = fixture!.page
|
|
await page.waitForFunction(
|
|
() => {
|
|
const root = document.getElementById('root')
|
|
|
|
if (!root) {
|
|
return false
|
|
}
|
|
|
|
const text = root.textContent ?? ''
|
|
|
|
// Error path: boot failure overlay renders an error message.
|
|
if (text.includes('error') || text.includes('Error') || text.includes('failed')) {
|
|
return true
|
|
}
|
|
|
|
// Success path: overlay disappears and the app renders. If there's
|
|
// no "boot" / "starting" / "installing" text visible, boot has
|
|
// completed (either to the main UI or to onboarding).
|
|
const bootIndicators = ['starting', 'resolving', 'spawning', 'waiting', 'installing']
|
|
const lower = text.toLowerCase()
|
|
|
|
return !bootIndicators.some((word) => lower.includes(word))
|
|
},
|
|
undefined,
|
|
{ timeout: 60_000 },
|
|
)
|
|
})
|
|
|
|
test('can capture a screenshot for the CI artifact', async () => {
|
|
if (!fixture) {
|
|
test.skip(true, 'Previous test failed — no app running')
|
|
|
|
return
|
|
}
|
|
|
|
// Visual snapshot — won't fail on diff, just logs + generates diff image
|
|
await expectVisualSnapshot(fixture!.page, { name: 'packaged-app-booted', timeout: 10_000, app: fixture!.app })
|
|
})
|