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
87 lines
2.9 KiB
TypeScript
87 lines
2.9 KiB
TypeScript
/**
|
|
* E2E tests asserting the mock backend gets the app past the setup/onboarding
|
|
* screen.
|
|
*
|
|
* The mock backend fixture writes a config.yaml with a pre-configured mock
|
|
* provider pointing at a mock inference server. When the app boots, the
|
|
* runtime readiness check should detect the working provider and dismiss the
|
|
* onboarding overlay — landing straight on the chat UI without ever showing
|
|
* the "Let's get you setup with Hermes Agent" screen.
|
|
*
|
|
* If these tests fail, the mock backend config isn't getting the app past
|
|
* onboarding — the chat interaction tests (chat.spec.ts) will also fail
|
|
* because the composer is blocked by the setup overlay.
|
|
*
|
|
* Prerequisite: `npm run build` must have been run so dist/ exists.
|
|
*/
|
|
|
|
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()
|
|
await waitForAppReady(fixture!, 120_000)
|
|
})
|
|
|
|
test.afterAll(async () => {
|
|
await fixture?.cleanup()
|
|
fixture = null
|
|
})
|
|
|
|
test.describe('mock backend gets past setup screen', () => {
|
|
test('onboarding overlay is not shown', async () => {
|
|
const page = fixture!.page
|
|
|
|
// The onboarding overlay renders "Let's get you setup with Hermes Agent"
|
|
// when the runtime check fails to find a working provider. With the mock
|
|
// backend configured, the runtime check should pass and the overlay
|
|
// returns null — this text should NOT be present in the DOM.
|
|
await page.waitForFunction(
|
|
() => {
|
|
const text = document.body.textContent ?? ''
|
|
|
|
return !text.includes("Let's get you setup")
|
|
},
|
|
undefined,
|
|
{ timeout: 30_000 },
|
|
)
|
|
})
|
|
|
|
test('chat composer is visible', async () => {
|
|
const page = fixture!.page
|
|
|
|
// The composer (contenteditable div) should be visible and not blocked
|
|
// by the onboarding overlay. If the first test passed, the overlay is
|
|
// gone and the composer is the primary interactive surface.
|
|
const composer = page.locator('[contenteditable="true"]').first()
|
|
await expect(composer).toBeVisible()
|
|
})
|
|
|
|
test('can type into the composer', async () => {
|
|
const page = fixture!.page
|
|
|
|
// If the setup overlay is truly gone, the composer accepts input.
|
|
const composer = page.locator('[contenteditable="true"]').first()
|
|
await composer.click()
|
|
await composer.type('hello mock backend', { delay: 20 })
|
|
|
|
// Verify the typed text appears in the DOM.
|
|
await page.waitForFunction(
|
|
() => (document.body.textContent ?? '').includes('hello mock backend'),
|
|
undefined,
|
|
{ timeout: 10_000 },
|
|
)
|
|
})
|
|
|
|
test('screenshot shows chat UI without setup screen', async () => {
|
|
await expectVisualSnapshot(fixture!.page, { name: 'mock-backend-chat-ready', app: fixture!.app })
|
|
})
|
|
})
|