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
91 lines
2.8 KiB
TypeScript
91 lines
2.8 KiB
TypeScript
/**
|
|
* E2E chat tests — send a message and verify a response appears.
|
|
*
|
|
* Requires the full boot chain to complete (hermes serve + mock inference
|
|
* provider). The mock server returns a canned reply, so we verify the
|
|
* response text shows up in the chat transcript.
|
|
*
|
|
* Prerequisite: `npm run build` must have been run so dist/ exists.
|
|
*/
|
|
|
|
import { 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('chat interaction with mock backend', () => {
|
|
test('send a message and receive a response', async () => {
|
|
const page = fixture!.page
|
|
|
|
// Find the composer — it's a contenteditable textbox.
|
|
const composer = page.locator('[contenteditable="true"]').first()
|
|
await composer.waitFor({ state: 'visible', timeout: 10_000 })
|
|
|
|
// Click to focus, then type the message character by character.
|
|
// Using `type` instead of `fill` because the composer is a
|
|
// contenteditable div with custom keydown handling that tracks
|
|
// IME composition state — `fill` bypasses the event chain.
|
|
await composer.click()
|
|
await composer.type('Hello, can you hear me?', { delay: 20 })
|
|
|
|
// Submit with Enter — the composer's keydown handler intercepts
|
|
// plain Enter (without Shift) and calls submitDraft().
|
|
await page.keyboard.press('Enter')
|
|
|
|
// Wait for the user's message to appear in the transcript.
|
|
// The message renders as an assistant-ui message in the chat view.
|
|
await page.waitForFunction(
|
|
() => {
|
|
const body = document.body
|
|
|
|
if (!body) {
|
|
return false
|
|
}
|
|
|
|
return (body.textContent ?? '').includes('Hello, can you hear me?')
|
|
},
|
|
undefined,
|
|
{ timeout: 15_000 },
|
|
)
|
|
|
|
// Wait for the mock response to appear. The canned reply is:
|
|
// "Hello from the mock inference server! The full boot chain is working."
|
|
// Give it a generous timeout — the inference request goes through the
|
|
// gateway → hermes serve → mock server → streaming SSE back.
|
|
await page.waitForFunction(
|
|
() => {
|
|
const body = document.body
|
|
|
|
if (!body) {
|
|
return false
|
|
}
|
|
|
|
const text = body.textContent ?? ''
|
|
|
|
return text.includes('mock inference server') || text.includes('boot chain is working')
|
|
},
|
|
undefined,
|
|
{ timeout: 60_000 },
|
|
)
|
|
})
|
|
|
|
test('screenshot of chat with messages', async () => {
|
|
await expectVisualSnapshot(fixture!.page, { name: 'chat-with-messages', app: fixture!.app })
|
|
})
|
|
})
|