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
63 lines
2.1 KiB
TypeScript
63 lines
2.1 KiB
TypeScript
/**
|
|
* E2E smoke tests for the dev-mode desktop app.
|
|
*
|
|
* These tests launch the Electron app from the built dist/ (not the
|
|
* packaged binary) with a real `hermes serve` backend pointed at a mock
|
|
* inference server. The full chain is exercised:
|
|
*
|
|
* electron → hermes serve (python) → mock provider → renderer
|
|
*
|
|
* Prerequisite: `npm run build` must have been run so dist/ exists.
|
|
* Run from the nix devshell:
|
|
* npm exec playwright test e2e/boot.spec.ts --reporter=list
|
|
*/
|
|
import { expect, test } from './test'
|
|
|
|
import {
|
|
type MockBackendFixture,
|
|
setupMockBackend,
|
|
waitForAppReady,
|
|
} from './fixtures'
|
|
import { expectVisualSnapshot } from './visual-snapshot'
|
|
|
|
let fixture: MockBackendFixture | null = null
|
|
|
|
test.beforeAll(async () => {
|
|
fixture = await setupMockBackend()
|
|
})
|
|
|
|
test.afterAll(async () => {
|
|
await fixture?.cleanup()
|
|
fixture = null
|
|
})
|
|
|
|
test.describe('dev-mode boot with mock backend', () => {
|
|
test('window opens with Hermes title', async () => {
|
|
const title = await fixture!.page.title()
|
|
expect(title).toContain('Hermes')
|
|
})
|
|
|
|
test('renderer mounts and shows DOM content', async () => {
|
|
const page = fixture!.page
|
|
// Wait for the React root to mount. The app renders into #root
|
|
// (see src/main.tsx), but content may arrive through portals — so
|
|
// check the body for any interactive content instead.
|
|
await page.waitForSelector('body', { state: 'attached' })
|
|
// Wait for the main app shell — the composer is always present.
|
|
await page.waitForSelector('textarea, [contenteditable="true"]', {
|
|
state: 'attached',
|
|
timeout: 30_000,
|
|
})
|
|
})
|
|
|
|
test('backend boots and app becomes ready', async () => {
|
|
// This is the big one — wait for the full boot chain to complete:
|
|
// electron starts → hermes serve is spawned → WS connects → config
|
|
// loaded → sessions loaded → boot overlay dismissed → composer visible.
|
|
await waitForAppReady(fixture!, 120_000)
|
|
})
|
|
|
|
test('screenshot after boot', async () => {
|
|
await expectVisualSnapshot(fixture!.page, { name: 'boot-ready', app: fixture!.app })
|
|
})
|
|
})
|