Files
PaperClipAI/tests/e2e/onboarding.spec.ts
T
Devin FoleyandPaperclip 2a4a001d37 Preserve GitHub access repair guidance for MCP callers (#19655)
Return GitHub permission denials as failed MCP tool results with trusted,
connection-specific recovery guidance. Explain the personal-account and
organization App installation boundary without replaying writes or bypassing
provider-content checks. Align the repair steps with the Permissions UI.

Cover enabled model checks and malicious provider failures across direct
calls, connection tests and stored approvals. Repair the CI-exposed synthetic
onboarding environment fixture without weakening cancellation assertions.

Verified 311 targeted tests, six onboarding Playwright tests, server
typecheck, module boundaries, full CI and Apex 5/5 with all threads resolved.

Co-Authored-By: Paperclip <noreply@paperclip.ing>
2026-11-06 16:32:27 -08:00

792 lines
36 KiB
TypeScript

import { test, expect } from "@playwright/test";
import { mockOnboardingLocalAiConnection } from "./helpers/onboarding-ai-connection";
/**
* E2E: Onboarding wizard flow (NUX Phase 2 expanded wizard).
*
* The wizard now opens on a front door (path picker) and the "Create a new
* company" path runs:
* Step 0 — Front door (Create a new company / Level up existing)
* Step 1a — Name your organization (creates the company)
* Step 2 — Hire your team lead (adapter picker)
* Step 3+ — Launch celebration → CEO chat → hiring plan → orientation
*
* This test covers the deterministic, LLM-free core: it drives the front door
* through company naming (which creates the company) and verifies the wizard
* advances to the team-lead step without asking for a mission.
*
* The tail (CEO chat at step 4, hiring-plan generation at step 5, final
* landing) depends on a live LLM and is verified separately during manual /
* LLM-backed QA — see PAP-50. Surface-level rendering of every step is
* snapshotted by nux-phase4-screenshots.spec.ts.
*/
const COMPANY_NAME = `E2E-Test-${Date.now()}`;
test.describe("Onboarding wizard", () => {
test("create-company path: naming creates the company, and no goal is invented", async ({
page,
}) => {
const pageErrors: string[] = [];
page.on("pageerror", (err) => pageErrors.push(err.message));
// `--data-dir` starts a new server, not a new browser profile. Keep a
// resumable draft here so this ordinary browser condition is covered when
// the company-list invalidation runs after the create request.
await page.addInitScript(() => {
localStorage.setItem("paperclip-onboarding-state", JSON.stringify({
step: 1,
companyName: "",
createdCompanyId: null,
}));
});
let delayCompanyListRefetch = false;
await page.route("**/api/companies", async (route) => {
if (delayCompanyListRefetch && route.request().method() === "GET") {
// Keep the invalidation observable: a background fetch must not reset
// the in-progress wizard.
await new Promise((resolve) => setTimeout(resolve, 250));
}
await route.continue();
});
// New-NUX surfaces are flag-gated default-OFF (PAP-136/137/138): turn the
// experimental flag on for this throwaway instance before driving them.
const flagRes = await page.request.patch("/api/instance/settings/experimental", {
data: { enableConferenceRoomChat: true },
});
expect(flagRes.ok()).toBe(true);
await page.goto("/onboarding");
// The wizard may open on a launcher card or directly on the capsule
// wizard; the front door (step 0) requires a click into the create path.
const startBtn = page.getByRole("button", {
name: /Start Onboarding|New Organization|Add Agent/,
});
if (await startBtn.count()) {
await startBtn.first().click();
}
const createCard = page.getByRole("button", { name: /Build a new organization/ });
if (await createCard.count()) {
await createCard.first().click();
}
// Step 1 — Name your organization.
await expect(
page.getByRole("heading", { name: "What is the name of your organization?" }),
).toBeVisible({ timeout: 15_000 });
await page.getByPlaceholder("e.g. Northwind Labs").fill(COMPANY_NAME);
delayCompanyListRefetch = true;
await page.getByRole("button", { name: /^Continue/ }).click();
// Step 1's "Next" now creates the company and goes straight to the agent.
// The mission step used to sit between them and do the creating; onboarding
// no longer asks for the mission, which is collected later in the app.
await page.waitForSelector("#onboarding-agent-name", {
timeout: 30_000,
});
// Verify the company + company-level goal were persisted.
const baseUrl = page.url().split("/").slice(0, 3).join("/");
const companiesRes = await page.request.get(`${baseUrl}/api/companies`);
expect(companiesRes.ok()).toBe(true);
const companies = await companiesRes.json();
const company = companies.find(
(c: { name: string }) => c.name === COMPANY_NAME,
);
expect(company, `company ${COMPANY_NAME} should exist`).toBeTruthy();
// And no company-level goal, which is the point rather than an omission.
// Onboarding no longer asks for a mission, so writing one here would mean
// inventing a goal the customer never chose. The mission is collected later
// in the app, and the absence is what leaves room for it.
const goalsRes = await page.request.get(
`${baseUrl}/api/companies/${company.id}/goals`,
);
expect(goalsRes.ok()).toBe(true);
const goals = await goalsRes.json();
const companyGoal = (Array.isArray(goals) ? goals : []).find(
(g: { level?: string }) => g.level === "company",
);
expect(
companyGoal,
"onboarding must not invent a mission the customer never gave",
).toBeFalsy();
// Name submission persists an inactive record before the provider question.
await page.locator("#onboarding-agent-name").fill("Ada");
const firstSetupResponse = page.waitForResponse(response =>
response.request().method() === "POST" && response.url().endsWith(`/api/companies/${company.id}/agents`));
await page.getByRole("button", { name: "Next", exact: true }).click();
const firstSetup = await (await firstSetupResponse).json();
expect(firstSetup).toMatchObject({ name: "Ada", pauseReason: "setup", metadata: { setupAdapterPending: true } });
await expect(page.getByRole("radio").first()).toBeVisible();
await expect(page.locator('[role="radio"][aria-checked="true"]')).toHaveCount(0);
// The roster path saves on Choose adapter, then configures that same row.
await page.goto(`/${company.issuePrefix}/agents/all`);
await page.getByRole("toolbar", { name: "Agents controls" }).getByRole("button", { name: "New Agent", exact: true }).click();
await page.getByLabel("Agent name", { exact: true }).fill("Atlas");
const nextSetupResponse = page.waitForResponse(response =>
response.request().method() === "POST" && response.url().endsWith(`/api/companies/${company.id}/agents`));
await page.getByRole("button", { name: "Choose adapter", exact: true }).click();
const nextSetup = await (await nextSetupResponse).json();
expect(nextSetup).toMatchObject({ name: "Atlas", pauseReason: "setup", metadata: { setupAdapterPending: true } });
await expect(page.getByRole("heading", { name: "Choose an adapter", exact: true })).toBeVisible();
await page.keyboard.press("Escape");
await page.getByRole("main").getByRole("link", { name: /^Atlas / }).click();
await expect(page.getByRole("button", { name: "Run now", exact: true })).toHaveCount(0);
await expect(page.getByRole("button", { name: "Resume", exact: true })).toHaveCount(0);
await expect(page.getByRole("button", { name: "Finish setup", exact: true })).toHaveCount(1);
await page.reload();
await expect(page.getByRole("button", { name: "Finish setup", exact: true })).toBeVisible();
await expect(page.getByRole("button", { name: "Run now", exact: true })).toHaveCount(0);
await page.getByRole("button", { name: "Finish setup", exact: true }).click();
await expect(page.getByRole("heading", { name: "Choose an adapter", exact: true })).toBeVisible();
await page.locator("label").filter({ has: page.locator('input[name="new-agent-adapter"][value="codex_local"]') }).click();
await page.getByRole("button", { name: "Configure agent", exact: true }).click();
await expect(page.getByRole("heading", { name: "Connect a model", exact: true })).toBeVisible();
expect(new URL(page.url()).searchParams.get("setupAgentId")).toBe(nextSetup.id);
const saved = await (await page.request.get(`/api/agents/${nextSetup.id}?companyId=${company.id}`)).json();
expect(saved).toMatchObject({ id: nextSetup.id, name: "Atlas", pauseReason: "setup", metadata: { setupAdapterPending: false } });
const records = await (await page.request.get(`/api/companies/${company.id}/agents`)).json();
expect(records.map((agent: { id: string }) => agent.id).sort()).toEqual([firstSetup.id, nextSetup.id].sort());
// The expanded wizard must not crash the app (Rules-of-Hooks regression).
expect(pageErrors, pageErrors.join("\n")).toHaveLength(0);
});
test("connect step starts the sign-in when the source is chosen, rather than hiring, when the signal reports no credential", async ({
page,
}) => {
const pageErrors: string[] = [];
page.on("pageerror", (err) => pageErrors.push(err.message));
const flagRes = await page.request.patch("/api/instance/settings/experimental", {
data: { enableConferenceRoomChat: true },
});
expect(flagRes.ok()).toBe(true);
// The login panel's capability gate requires a sandbox environment with a
// login-capable provider, and this throwaway instance has neither: it
// only auto-creates the local environment. Add one fake sandbox
// environment to the real list, make it the instance default, and declare
// its provider's login pseudo-terminal capability — this reproduces the
// gate a real sandbox-backed instance would already pass, without
// changing any other field the rest of the page depends on.
const FAKE_SANDBOX_ENVIRONMENT_ID = "c0e01740-05eb-41ea-bdbe-6358b712e26f";
const FAKE_SANDBOX_PROVIDER = "e2e-fake-provider";
await page.route("**/environments", async (route) => {
const response = await route.fetch();
const environments = await response.json();
environments.push({
id: FAKE_SANDBOX_ENVIRONMENT_ID,
name: "E2E fake sandbox",
description: null,
driver: "sandbox",
status: "active",
config: { provider: FAKE_SANDBOX_PROVIDER },
envVars: {},
metadata: {},
createdAt: new Date().toISOString(),
updatedAt: new Date().toISOString(),
});
await route.fulfill({ response, json: environments });
});
await page.route("**/environments/capabilities", async (route) => {
const response = await route.fetch();
const capabilities = await response.json();
capabilities.sandboxProviders[FAKE_SANDBOX_PROVIDER] = {
status: "supported",
supportsSavedProbe: true,
supportsUnsavedProbe: true,
supportsRunExecution: true,
supportsReusableLeases: false,
supportsInteractiveSetup: false,
interactiveSetupConnectionTypes: [],
supportsTemplateCapture: false,
supportsTemplateDelete: false,
supportsLoginPty: true,
source: "plugin",
};
await route.fulfill({ response, json: capabilities });
});
await page.route("**/instance/settings", async (route) => {
const response = await route.fetch();
const settings = await response.json();
settings.defaultEnvironmentId = FAKE_SANDBOX_ENVIRONMENT_ID;
await route.fulfill({ response, json: settings });
});
// Report no ready credential, so the wizard shows the login panel right
// after the adapter is picked, before it ever runs an adapter test.
await page.route("**/adapters/*/auth-signal*", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({ status: "absent" }),
}),
);
await page.route("**/api/adapters?**", async (route) => {
const url = new URL(route.request().url());
if (url.searchParams.get("environmentId") !== FAKE_SANDBOX_ENVIRONMENT_ID) return route.continue();
url.searchParams.delete("environmentId");
const response = await route.fetch({ url: url.toString() });
expect(response.ok()).toBe(true);
await route.fulfill({ response });
});
// The sign-in Connect now starts. Stubbed so the card is deterministic:
// the session start answers, and the guarded prompt read hands back an
// authorization URL for the card's link row.
let loginStarts = 0;
await page.route("**/setup-token-login-sessions", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
sessionId: `e2e-setup-token-session-${++loginStarts}`,
status: "pending",
expiresAt: new Date(Date.now() + 600_000).toISOString(),
}),
}),
);
await page.route("**/setup-token-login-sessions/*/prompt", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
authorizationUrl: "https://claude.ai/oauth/authorize?code=true&client=e2e",
transportAdvisory: null,
}),
}),
);
await page.route(/\/setup-token-login-sessions\/e2e-setup-token-session-\d+$/, (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
sessionId: route.request().url().split("/").at(-1),
status: "pending",
expiresAt: new Date(Date.now() + 600_000).toISOString(),
}),
}),
);
// Fail the adapter test the "Connect" button runs, so the hire gate
// blocks the create and this test can prove no agent is hired.
await page.route("**/test-environment", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
adapterType: "claude_local",
status: "fail",
checks: [
{
code: "claude_cli_not_found",
level: "fail",
message: "The claude CLI was not found on this host.",
},
],
testedAt: new Date().toISOString(),
}),
}),
);
let hireCalled = false;
await page.route("**/agent-hires", (route) => {
hireCalled = true;
return route.continue();
});
await page.goto("/onboarding");
const startBtn = page.getByRole("button", {
name: /Start Onboarding|New Organization|Add Agent/,
});
if (await startBtn.count()) {
await startBtn.first().click();
}
const createCard = page.getByRole("button", { name: /Build a new organization/ });
if (await createCard.count()) {
await createCard.first().click();
}
await expect(
page.getByRole("heading", { name: "What is the name of your organization?" }),
).toBeVisible({ timeout: 15_000 });
await page.getByPlaceholder("e.g. Northwind Labs").fill(`${COMPANY_NAME}-auth-signal`);
await page.getByRole("button", { name: /^Continue/ }).click();
await page.waitForSelector("#onboarding-agent-name", { timeout: 30_000 });
await page.locator("#onboarding-agent-name").fill("Ada");
await page.getByRole("button", { name: "Next" }).click();
// Step 4 (Connect a model). By role rather than by label, because which
// adapters the row offers depends on the registry this environment reports.
const source = page.getByRole("radio").first();
await source.waitFor({ timeout: 30_000 });
// Nothing before the row is answered: the card is the answer to the tile,
// and the button has nothing to do until there is a source to do it with.
const cardInstruction = page.getByText("then come back and enter authorization code");
await expect(cardInstruction).toHaveCount(0);
await expect(page.getByRole("button", { name: "Next", exact: true })).toBeDisabled();
// Answering the row is what starts the sign-in — this is the ordering the
// step exists to enforce, since a hire here would file an agent with no
// credential to run on. It is also the whole of the interaction: there is
// no second press between choosing a source and being signed in.
await source.click();
await expect(cardInstruction).toBeVisible({ timeout: 30_000 });
// One destination, two ways to it: the card's own link for anyone
// finishing in another browser, and the step's button for the flow.
const cardLink = page.getByRole("link", { name: /^Sign in to / });
await expect(cardLink).toBeVisible({ timeout: 15_000 });
await expect(cardLink).toHaveAttribute("href", /claude\.ai\/oauth\/authorize/);
await expect(
page.getByRole("button", { name: /^Sign in to / }),
).toBeEnabled({ timeout: 15_000 });
// No "Use saved login" here: the hire step applies a stored login itself.
await expect(page.getByRole("button", { name: "Use saved login" })).toHaveCount(0);
expect(hireCalled).toBe(false);
let cancellations = 0;
await page.route("**/setup-token-login-sessions/*/cancel", async route => {
cancellations++;
await route.fulfill({ status: 204 });
});
const back = page.getByRole("button", { name: "Back", exact: true });
await back.click();
await expect(source).toHaveAttribute("aria-checked", "false");
await expect.poll(() => cancellations).toBe(1);
await page.evaluate(() => {
const state = window as typeof window & { cancelledLoginPrompts: number };
state.cancelledLoginPrompts = 0;
const fetch = window.fetch.bind(window);
window.fetch = (input, init) => {
const url = input instanceof Request ? input.url : String(input);
if (url.endsWith("/prompt")) init?.signal?.addEventListener("abort", () => { state.cancelledLoginPrompts++; }, { once: true });
return fetch(input, init);
};
});
let finishPrompt!: () => void;
let promptStarted!: () => void;
const pendingPrompt = new Promise<void>(resolve => { finishPrompt = resolve; });
const promptRequest = new Promise<void>(resolve => { promptStarted = resolve; });
await page.route("**/setup-token-login-sessions/*/prompt", async route => {
promptStarted();
await pendingPrompt;
await route.fulfill({ json: { authorizationUrl: "https://claude.ai/oauth/authorize?late=true", transportAdvisory: null } }).catch(() => {});
});
await source.click();
await promptRequest;
await back.click();
await expect.poll(() => page.evaluate(() => (window as typeof window & { cancelledLoginPrompts: number }).cancelledLoginPrompts)).toBe(1);
finishPrompt();
await expect(source).toHaveAttribute("aria-checked", "false");
await expect.poll(() => cancellations).toBe(2);
await expect(cardInstruction).toHaveCount(0);
await expect(page.getByRole("button", { name: "Next", exact: true })).toBeDisabled();
expect(hireCalled).toBe(false);
expect(pageErrors, pageErrors.join("\n")).toHaveLength(0);
});
test("a reload during a login resumes the same session", async ({ page }) => {
const pageErrors: string[] = [];
page.on("pageerror", (err) => pageErrors.push(err.message));
const loginSessionReads: string[] = [];
page.on("request", (request) => {
const match = new URL(request.url()).pathname.match(/\/setup-token-login-sessions\/([^/]+)(?:\/prompt)?$/);
if (match && match[1] !== "active") loginSessionReads.push(match[1]);
});
let hireCalls = 0;
await page.route("**/agent-hires", (route) => {
hireCalls += 1;
return route.fulfill({ status: 400, json: { error: "Unexpected hire while login is pending." } });
});
const flagRes = await page.request.patch("/api/instance/settings/experimental", {
data: { enableConferenceRoomChat: true },
});
expect(flagRes.ok()).toBe(true);
const FAKE_SANDBOX_ENVIRONMENT_ID = "a6d2e530-1e8b-4f0b-9c94-42f1d23e8750";
const FAKE_SANDBOX_PROVIDER = "e2e-fake-provider-reload";
await page.route("**/environments", async (route) => {
const response = await route.fetch();
const environments = await response.json();
environments.push({
id: FAKE_SANDBOX_ENVIRONMENT_ID,
name: "E2E fake sandbox",
description: null,
driver: "sandbox",
status: "active",
config: { provider: FAKE_SANDBOX_PROVIDER },
envVars: {},
metadata: {},
createdAt: new Date().toISOString(),
updatedAt: new Date().toISOString(),
});
await route.fulfill({ response, json: environments });
});
await page.route("**/environments/capabilities", async (route) => {
const response = await route.fetch();
const capabilities = await response.json();
capabilities.sandboxProviders[FAKE_SANDBOX_PROVIDER] = {
status: "supported",
supportsSavedProbe: true,
supportsUnsavedProbe: true,
supportsRunExecution: true,
supportsReusableLeases: false,
supportsInteractiveSetup: false,
interactiveSetupConnectionTypes: [],
supportsTemplateCapture: false,
supportsTemplateDelete: false,
supportsLoginPty: true,
source: "plugin",
};
await route.fulfill({ response, json: capabilities });
});
await page.route("**/instance/settings", async (route) => {
const response = await route.fetch();
const settings = await response.json();
settings.defaultEnvironmentId = FAKE_SANDBOX_ENVIRONMENT_ID;
await route.fulfill({ response, json: settings });
});
await page.route("**/adapters/*/auth-signal*", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({ status: "absent" }),
}),
);
await page.route("**/api/adapters?**", async (route) => {
const url = new URL(route.request().url());
if (url.searchParams.get("environmentId") !== FAKE_SANDBOX_ENVIRONMENT_ID) return route.continue();
url.searchParams.delete("environmentId");
const response = await route.fetch({ url: url.toString() });
expect(response.ok()).toBe(true);
await route.fulfill({ response });
});
// The synthetic sandbox only drives the login UI; persist configuration
// against the real local default so a failed fixture write cannot mask restore behavior.
await page.route("**/api/agents/*", async (route) => {
if (route.request().method() !== "PATCH") return route.continue();
const body = route.request().postDataJSON();
if (body.defaultEnvironmentId !== FAKE_SANDBOX_ENVIRONMENT_ID) return route.continue();
const response = await route.fetch({ postData: JSON.stringify({ ...body, defaultEnvironmentId: null }) });
await route.fulfill({ response });
});
const SESSION_ID = "e2e-reload-setup-token-session";
const AUTHORIZATION_URL = "https://claude.ai/oauth/authorize?code=true&client=e2e-reload";
let startCalls = 0;
// Flips once the login actually starts, so the owner-scoped resume read
// below answers "no active session" until then — matching the real
// route, and keeping the pre-Connect part of this test the same as the
// ordinary sign-in test above.
let sessionStarted = false;
const resumedCompanyIds: string[] = [];
let aiConnection: Record<string, unknown> | undefined;
await page.route("**/setup-token-login-sessions", (route) => {
if (route.request().method() === "POST") {
startCalls += 1;
sessionStarted = true;
aiConnection = route.request().postDataJSON().aiConnection;
}
return route.fulfill({
contentType: "application/json",
body: JSON.stringify({
sessionId: SESSION_ID,
environmentId: FAKE_SANDBOX_ENVIRONMENT_ID,
aiConnection,
status: "pending",
expiresAt: new Date(Date.now() + 600_000).toISOString(),
}),
});
});
await page.route(`**/setup-token-login-sessions/${SESSION_ID}/prompt`, (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
authorizationUrl: AUTHORIZATION_URL,
transportAdvisory: null,
}),
}),
);
await page.route(`**/setup-token-login-sessions/${SESSION_ID}`, (route) => {
if (route.request().method() !== "GET") return route.continue();
return route.fulfill({
contentType: "application/json",
body: JSON.stringify({
sessionId: SESSION_ID,
environmentId: FAKE_SANDBOX_ENVIRONMENT_ID,
aiConnection,
status: "pending",
expiresAt: new Date(Date.now() + 600_000).toISOString(),
}),
});
});
// The owner-scoped resume read. Both the wizard's own step-restore effect
// and the panel's own resume-on-mount read use this, with no session id
// in the URL — the caller rediscovers its own session.
await page.route("**/setup-token-login-sessions/active", (route) => {
if (!sessionStarted) {
return route.fulfill({
status: 404,
contentType: "application/json",
body: JSON.stringify({ error: "Setup-token login session not found." }),
});
}
resumedCompanyIds.push(new URL(route.request().url()).pathname.split("/")[3]);
return route.fulfill({
contentType: "application/json",
body: JSON.stringify({
sessionId: SESSION_ID,
environmentId: FAKE_SANDBOX_ENVIRONMENT_ID,
aiConnection,
status: "pending",
expiresAt: new Date(Date.now() + 600_000).toISOString(),
panelMode: "submitted_browser_code",
prompt: { authorizationUrl: AUTHORIZATION_URL, transportAdvisory: null },
}),
});
});
await page.goto("/onboarding");
const startBtn = page.getByRole("button", {
name: /Start Onboarding|New Organization|Add Agent/,
});
if (await startBtn.count()) {
await startBtn.first().click();
}
const createCard = page.getByRole("button", { name: /Build a new organization/ });
if (await createCard.count()) {
await createCard.first().click();
}
await expect(
page.getByRole("heading", { name: "What is the name of your organization?" }),
).toBeVisible({ timeout: 15_000 });
await page.getByPlaceholder("e.g. Northwind Labs").fill(`${COMPANY_NAME}-reload`);
await page.getByRole("button", { name: /^Continue/ }).click();
await page.waitForSelector("#onboarding-agent-name", { timeout: 30_000 });
await page.locator("#onboarding-agent-name").fill("Ada");
await page.getByRole("button", { name: "Next" }).click();
const source = page.getByRole("radio").first();
await source.waitFor({ timeout: 30_000 });
// Answering the row is what starts the sign-in now — there is no separate
// Connect press between choosing a source and being signed in.
await source.click();
const cardInstruction = page.getByText("then come back and enter authorization code");
const authorizationLink = page.getByRole("link", { name: /^Sign in to / });
await expect(cardInstruction).toBeVisible({ timeout: 30_000 });
await expect(authorizationLink).toBeVisible({ timeout: 15_000 });
await expect(authorizationLink).toHaveAttribute("href", AUTHORIZATION_URL);
expect(startCalls).toBe(1);
const companiesRes = await page.request.get("/api/companies");
expect(companiesRes.ok()).toBe(true);
const companies = await companiesRes.json();
const company = companies.find(
(c: { name: string }) => c.name === `${COMPANY_NAME}-reload`,
);
expect(company, "the created company should exist").toBeTruthy();
const savedSelection = {
step: 4,
companyName: `${COMPANY_NAME}-reload`,
agentName: "Ada",
adapterType: "claude_local",
runner: "auto",
credentialMode: "subscription",
credentialModeChoice: null,
createdCompanyId: company.id,
createdCompanyPrefix: company.issuePrefix,
createdAgentId: null,
};
const readDraft = () => page.evaluate(() => JSON.parse(localStorage.getItem("paperclip-onboarding-state") ?? "null"));
await expect.poll(readDraft).toMatchObject(savedSelection);
const { setupAgentId } = await readDraft();
await expect.poll(async () => (await (await page.request.get(`/api/agents/${setupAgentId}?companyId=${company.id}`)).json()).metadata?.setupAdapterPending).toBe(false);
const setupResponse = await page.request.get(`/api/agents/${setupAgentId}?companyId=${company.id}`);
expect(setupResponse.ok()).toBe(true);
const setup = await setupResponse.json();
expect(setup).toMatchObject({ id: setupAgentId, name: "Ada", pauseReason: "setup" });
const resumedSelection = { ...savedSelection, setupAgentId,
runner: setup.adapterType === "paperclip_runner" ? "paperclip" : "legacy" };
const assertResumedLogin = async () => {
await expect(page.getByRole("heading", { name: "Connect a model", exact: true })).toBeVisible({ timeout: 15_000 });
await expect(page.getByTestId("onboarding-wizard").getByText("Ada", { exact: true })).toBeVisible();
await expect(page.getByRole("radio", { name: "Claude Subscription", exact: true })).toBeChecked();
await expect(cardInstruction).toBeVisible({ timeout: 15_000 });
await expect(authorizationLink).toBeVisible({ timeout: 15_000 });
await expect(authorizationLink).toHaveAttribute("href", AUTHORIZATION_URL);
await expect.poll(readDraft).toMatchObject(resumedSelection);
expect(startCalls, "reopening must resume the session without a second source choice").toBe(1);
expect(hireCalls, "a pending login must not hire an agent").toBe(0);
expect(loginSessionReads.length).toBeGreaterThan(0);
expect(new Set(loginSessionReads)).toEqual(new Set([SESSION_ID]));
expect(new Set(resumedCompanyIds)).toEqual(new Set([company.id]));
};
const beforeReopenReads = resumedCompanyIds.length;
await page.goto(`/${company.issuePrefix}/onboarding`);
await expect.poll(() => resumedCompanyIds.length, { timeout: 15_000 }).toBeGreaterThan(beforeReopenReads);
await assertResumedLogin();
const beforeReloadReads = resumedCompanyIds.length;
await page.reload();
await expect.poll(() => resumedCompanyIds.length, { timeout: 15_000 }).toBeGreaterThan(beforeReloadReads);
await assertResumedLogin();
expect(pageErrors, pageErrors.join("\n")).toHaveLength(0);
});
test("connect step blocks the hire when the environment probe fails after account connection", async ({
page,
}) => {
// A successful local account connection still requires a passing
// environment probe before the wizard may hire the agent.
await mockOnboardingLocalAiConnection(page);
const pageErrors: string[] = [];
page.on("pageerror", (err) => pageErrors.push(err.message));
const flagRes = await page.request.patch("/api/instance/settings/experimental", {
data: { enableConferenceRoomChat: true },
});
expect(flagRes.ok()).toBe(true);
await page.route("**/test-environment", (route) =>
route.fulfill({
contentType: "application/json",
body: JSON.stringify({
adapterType: "claude_local",
status: "fail",
checks: [
{
code: "claude_cli_not_found",
level: "fail",
message: "The claude CLI was not found on this host.",
},
],
testedAt: new Date().toISOString(),
}),
}),
);
let hireCalled = false;
await page.route("**/agent-hires", (route) => {
hireCalled = true;
return route.continue();
});
await page.goto("/onboarding");
const startBtn = page.getByRole("button", {
name: /Start Onboarding|New Organization|Add Agent/,
});
if (await startBtn.count()) {
await startBtn.first().click();
}
const createCard = page.getByRole("button", { name: /Build a new organization/ });
if (await createCard.count()) {
await createCard.first().click();
}
await expect(
page.getByRole("heading", { name: "What is the name of your organization?" }),
).toBeVisible({ timeout: 15_000 });
await page.getByPlaceholder("e.g. Northwind Labs").fill(`${COMPANY_NAME}-probe-gate`);
await page.getByRole("button", { name: /^Continue/ }).click();
await page.waitForSelector("#onboarding-agent-name", { timeout: 30_000 });
await page.locator("#onboarding-agent-name").fill("Ada");
await page.getByRole("button", { name: "Next" }).click();
const source = page.getByRole("radio").first();
await source.waitFor({ timeout: 30_000 });
await source.click();
const connect = page.getByRole("button", { name: "Connect", exact: true });
await expect(connect).toBeEnabled({ timeout: 30_000 });
await connect.click();
// The failed probe blocks the hire and shows its own checks.
await expect(page.getByText("The claude CLI was not found on this host.")).toBeVisible({
timeout: 15_000,
});
expect(hireCalled).toBe(false);
expect(pageErrors, pageErrors.join("\n")).toHaveLength(0);
});
test("name-only setup saves the advanced Grok ACPX adapter on the same record", async ({ page }) => {
const previous = await (await page.request.get("/api/instance/settings/experimental")).json();
await page.request.patch("/api/instance/settings/experimental", { data: { enableNativeRunner: true } });
try {
const response = await page.request.post("/api/companies", { data: { name: `${COMPANY_NAME}-grok-setup` } });
expect(response.ok()).toBe(true);
const company = await response.json();
await page.goto(`/${company.issuePrefix}/agents/all`);
await page.getByRole("toolbar", { name: "Agents controls" }).getByRole("button", { name: "New Agent", exact: true }).click();
await page.getByLabel("Agent name", { exact: true }).fill("Galen");
const setupResponse = page.waitForResponse(result => result.request().method() === "POST"
&& result.url().endsWith(`/api/companies/${company.id}/agents`));
await page.getByRole("button", { name: "Choose adapter", exact: true }).click();
const setup = await (await setupResponse).json();
await page.locator("summary").filter({ hasText: "Advanced" }).click();
await page.getByRole("button", { name: "Experimental harness", exact: true }).click();
await page.getByRole("option", { name: "Grok Build (Paperclip Runner)", exact: true }).click();
await page.getByRole("button", { name: "Configure agent", exact: true }).click();
await expect(page.getByRole("heading", { name: "Connect a model", exact: true })).toBeVisible();
expect(new URL(page.url()).searchParams.get("setupAgentId")).toBe(setup.id);
const saved = await (await page.request.get(`/api/agents/${setup.id}?companyId=${company.id}`)).json();
expect(saved).toMatchObject({ id: setup.id, adapterType: "paperclip_runner", pauseReason: "setup",
adapterConfig: { provider: "acpx", acpxAgent: "grok", model: "grok-4.7" }, metadata: { setupAdapterPending: false } });
} finally {
await page.request.patch("/api/instance/settings/experimental", { data: { enableNativeRunner: previous.enableNativeRunner === true } });
}
});
test("duplicate name drafts can select Copilot before connecting a GitHub account", async ({ page }) => {
const response = await page.request.post("/api/companies", { data: { name: `${COMPANY_NAME}-duplicate-copilot` } });
expect(response.ok()).toBe(true);
const company = await response.json();
await page.goto(`/${company.issuePrefix}/agents/all`);
let duplicate: { id: string; name: string };
for (let attempt = 0; attempt < 2; attempt++) {
await page.getByRole("toolbar", { name: "Agents controls" }).getByRole("button", { name: "New Agent", exact: true }).click();
await page.getByLabel("Agent name", { exact: true }).fill("Echo");
const setupResponse = page.waitForResponse(result => result.request().method() === "POST" && result.url().endsWith(`/api/companies/${company.id}/agents`));
await page.getByRole("button", { name: "Choose adapter", exact: true }).click();
duplicate = await (await setupResponse).json();
await expect(page.getByRole("heading", { name: "Choose an adapter", exact: true })).toBeVisible();
if (attempt === 0) await page.keyboard.press("Escape");
}
expect(duplicate!.name).toBe("Echo 2");
await expect(page.getByText("How should Echo 2 work?", { exact: true })).toBeVisible();
await page.locator("label").filter({ has: page.locator('input[name="new-agent-adapter"][value="copilot_runtime"]') }).click();
await page.getByRole("button", { name: "Configure agent", exact: true }).click();
await expect(page.getByRole("heading", { name: "Configure your agent", exact: true })).toBeVisible();
expect(new URL(page.url()).searchParams.get("setupAgentId")).toBe(duplicate!.id);
const saved = await (await page.request.get(`/api/agents/${duplicate!.id}?companyId=${company.id}`)).json();
expect(saved).toMatchObject({ id: duplicate!.id, name: "Echo 2", pauseReason: "setup", adapterConfig: { provider: "acpx", acpxAgent: "copilot" } });
expect(saved.runtimeConfig.aiConnection).toBeUndefined();
});
});