Files
PaperClipAI/tests/release-smoke/docker-auth-onboarding.spec.ts
Devin Foley 4af55ba6bd test(release-smoke): follow the onboarding wizard's chat-first rewrite (#11565)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work
> - The release channel system publishes a nightly build only after the
release smoke suite passes against the newest canary
> - The scheduled nightly run has failed every night since August 12, so
no nightly, and therefore no beta candidate, has shipped for six days
> - The failures are stale test locators, not a product regression: the
chat-first onboarding rewrite (#11101) changed wizard copy and the
post-launch destination
> - This pull request updates the smoke spec to match the current wizard
> - The benefit is a green nightly lane and an unblocked beta promotion

## Linked Issues or Issue Description

**What happened?**

The scheduled `Release` nightly run fails in `smoke_nightly / smoke`
every night since 2026-08-12. The failing spec is
`tests/release-smoke/docker-auth-onboarding.spec.ts`. Four assertions no
longer match the product after the chat-first onboarding rewrite
(#11101):

- The step-1 heading is now "Name your organization", not "Name your
company".
- The step-4 hire button is now "Connect", not "Give it a heartbeat".
- The seeded first task is now titled "Paperclip onboarding".
- A successful launch navigates to the seeded task's thread
(`/issues/<ref>`), not `/dashboard`.

**Expected behavior**

The smoke suite passes against a canary that contains the current
onboarding wizard, and the nightly lane publishes again.

**Steps to reproduce**

Run `.github/workflows/release-smoke.yml` against `paperclipai@canary`
(any version at or after the rewrite), or dispatch `release.yml` with
`channel: nightly`. Example red runs: 32014452506 (Aug 17), 31938284401
(Aug 16).

**Paperclip version or commit**

`2026.817.0-canary.12`

Related (not duplicates): #11190 updated this same spec for the
mission-first wizard; this PR is the follow-up for the chat-first
rewrite that landed after it.

## What Changed

- Update the step-1 wizard heading locator to "Name your organization".
- Update the step-4 hire button locator to "Connect" and reword the step
comment.
- Update `FIRST_TASK_TITLE` to "Paperclip onboarding" (the wizard's
current `DEFAULT_TASK_TITLE`).
- Assert the post-launch URL is the seeded task's thread (`/issues/`),
not `/dashboard`.

## Verification

- Local run of the exact CI harness: `scripts/docker-onboard-smoke.sh`
with `PAPERCLIPAI_VERSION=2026.817.0-canary.12`, then `pnpm run
test:release-smoke` against the container — 1 passed.
- The suite's later API assertions (company, CEO agent, mission goal,
seeded issue assignment, assignment-sourced heartbeat run) all pass
unchanged against the current canary.

## Risks

- Low risk: test-only change; no product code is touched.
- The spec remains copy-coupled to the wizard. If wizard copy churn
continues, a follow-up could add stable `data-testid` hooks to the
wizard so the smoke spec stops breaking on wording changes.

## Model Used

Claude Fable 5 (Claude Code)



## Pre-submission checklist

- [x] I have included a thinking path that traces from project context
to this change
- [x] I have specified the model used (with version and capability
details)
- [x] I have checked ROADMAP.md and confirmed this PR does not duplicate
planned core work
- [x] I have searched GitHub for duplicate or related PRs and linked
them above
- [x] I have either (a) linked existing issues with `Fixes: #` / `Closes
#` / `Refs #` OR (b) described the issue in-PR following the relevant
issue template
2026-08-17 16:31:17 -07:00

184 lines
6.6 KiB
TypeScript

import { expect, test, type Page } from "@playwright/test";
const ADMIN_EMAIL =
process.env.PAPERCLIP_RELEASE_SMOKE_EMAIL ??
process.env.SMOKE_ADMIN_EMAIL ??
"smoke-admin@paperclip.local";
const ADMIN_PASSWORD =
process.env.PAPERCLIP_RELEASE_SMOKE_PASSWORD ??
process.env.SMOKE_ADMIN_PASSWORD ??
"paperclip-smoke-password";
const COMPANY_NAME = `Release-Smoke-${Date.now()}`;
const MISSION = "Ship a reliable release smoke suite for Paperclip.";
const AGENT_NAME = "CEO";
// Seeded by the wizard's launch step (DEFAULT_TASK_TITLE in
// ui/src/components/OnboardingWizard.tsx).
const FIRST_TASK_TITLE = "Paperclip onboarding";
async function signIn(page: Page) {
await page.goto("/");
await expect(page).toHaveURL(/\/auth/);
await page.locator('input[type="email"]').fill(ADMIN_EMAIL);
await page.locator('input[type="password"]').fill(ADMIN_PASSWORD);
await page.getByRole("button", { name: "Sign In" }).click();
await expect(page).not.toHaveURL(/\/auth/, { timeout: 20_000 });
}
async function openOnboarding(page: Page) {
const wizardHeading = page.locator("h3", { hasText: "Name your organization" });
const startButton = page.getByRole("button", { name: "Start Onboarding" });
await expect(wizardHeading.or(startButton)).toBeVisible({ timeout: 20_000 });
if (await startButton.isVisible()) {
await startButton.click();
}
await expect(wizardHeading).toBeVisible({ timeout: 10_000 });
}
test.describe("Docker authenticated onboarding smoke", () => {
test("logs in, completes onboarding, and hires the lead agent", async ({
page,
}) => {
await signIn(page);
await openOnboarding(page);
// Step 1: name the company.
await page.locator('input[placeholder="Acme Corp"]').fill(COMPANY_NAME);
await page.getByRole("button", { name: "Next" }).click();
// Step 2: define the mission directly; confirming creates the company.
await expect(
page.locator("h3", { hasText: "Define your mission" })
).toBeVisible({ timeout: 10_000 });
await page.getByRole("button", { name: "I know my mission" }).click();
await page
.locator('textarea[placeholder="What is your team trying to achieve?"]')
.fill(MISSION);
await page.getByRole("button", { name: "Confirm mission" }).click();
// Step 3: name the team lead.
const leadNameInput = page.locator('input[placeholder="Chief of staff"]');
await expect(leadNameInput).toBeVisible({ timeout: 20_000 });
await leadNameInput.fill(AGENT_NAME);
await page.getByRole("button", { name: "Next" }).click();
// Step 4: keep the default adapter and connect (hire) the lead. The
// adapter environment check runs inside the smoke container, where no
// agent CLIs are installed; an unhealthy report is expected and must not
// block the hire. Allow generous time for the env probe + hire +
// auto-approval.
const connectButton = page.getByRole("button", { name: "Connect" });
await expect(connectButton).toBeVisible({ timeout: 10_000 });
await expect(connectButton).toBeEnabled({ timeout: 30_000 });
await connectButton.click();
// Step 5: review, then launch. "Get started" provisions the onboarding
// goal/project/first task and, only on success, drops the user into the
// seeded first task's thread (not the dashboard).
const getStartedButton = page.getByRole("button", { name: "Get started" });
await expect(getStartedButton).toBeVisible({ timeout: 60_000 });
await expect(getStartedButton).toBeEnabled({ timeout: 10_000 });
await getStartedButton.click();
await expect(page).toHaveURL(/\/issues\//, { timeout: 30_000 });
const baseUrl = new URL(page.url()).origin;
const companiesRes = await page.request.get(`${baseUrl}/api/companies`);
expect(companiesRes.ok()).toBe(true);
const companies = (await companiesRes.json()) as Array<{ id: string; name: string }>;
const company = companies.find((entry) => entry.name === COMPANY_NAME);
expect(company).toBeTruthy();
const agentsRes = await page.request.get(
`${baseUrl}/api/companies/${company!.id}/agents`
);
expect(agentsRes.ok()).toBe(true);
const agents = (await agentsRes.json()) as Array<{
id: string;
name: string;
role: string;
adapterType: string;
}>;
const ceoAgent = agents.find((entry) => entry.name === AGENT_NAME);
expect(ceoAgent).toBeTruthy();
expect(ceoAgent!.role).toBe("ceo");
expect(ceoAgent!.adapterType).not.toBe("process");
const goalsRes = await page.request.get(
`${baseUrl}/api/companies/${company!.id}/goals`
);
expect(goalsRes.ok()).toBe(true);
const goals = (await goalsRes.json()) as Array<{
id: string;
title: string;
level: string;
status: string;
}>;
expect(goals).toEqual(
expect.arrayContaining([
expect.objectContaining({
title: MISSION,
level: "company",
status: "active",
}),
])
);
const issuesRes = await page.request.get(
`${baseUrl}/api/companies/${company!.id}/issues`
);
expect(issuesRes.ok()).toBe(true);
const issues = (await issuesRes.json()) as Array<{
id: string;
identifier: string | null;
title: string;
assigneeAgentId: string | null;
}>;
const seededIssue = issues.find((entry) => entry.title === FIRST_TASK_TITLE);
expect(seededIssue).toBeTruthy();
expect(seededIssue!.assigneeAgentId).toBe(ceoAgent!.id);
// The launch must have landed on the seeded task itself, not merely on
// some issue route.
const seededRef = seededIssue!.identifier ?? seededIssue!.id;
expect(new URL(page.url()).pathname.endsWith(`/issues/${seededRef}`)).toBe(
true
);
await expect.poll(
async () => {
const runsRes = await page.request.get(
`${baseUrl}/api/companies/${company!.id}/heartbeat-runs?agentId=${ceoAgent!.id}`
);
expect(runsRes.ok()).toBe(true);
const runs = (await runsRes.json()) as Array<{
agentId: string;
invocationSource: string;
status: string;
}>;
const latestRun = runs.find((entry) => entry.agentId === ceoAgent!.id);
return latestRun
? {
invocationSource: latestRun.invocationSource,
status: latestRun.status,
}
: null;
},
{
timeout: 30_000,
intervals: [1_000, 2_000, 5_000],
}
).toEqual(
expect.objectContaining({
invocationSource: "assignment",
status: expect.stringMatching(/^(queued|running|succeeded|failed)$/),
})
);
});
});