mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-26 02:00:52 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work > - Governed MCP access spans contracts, runtime enforcement, adapters, UI surfaces, and operator verification > - The parity reference PR #9534 is too large for effective automated or human review > - The feature therefore needs a linear stack whose individual diffs stay below the 100-file review limit > - This pull request is split 8/8 and focuses on end-to-end coverage, operator docs, evals, and release notes > - The benefit is a standalone, testable review boundary while preserving byte-for-byte parity at the top of the stack ## Linked Issues or Issue Description - Related parity reference: #9534 - Problem: The complete stack needs discoverable browser scenarios, operator guidance, threat modeling, eval coverage, and a parity proof before merge. - Proposed solution: Adds MCP user-story and Smoke Lab e2e suites, docs/evals/release notes, the skill update, and the root e2e driver script registration. - Alternatives considered: keeping #9534 as one 403-file review, or rewriting the feature to manufacture seams; both were rejected in favor of path extraction plus compile-driven boundary moves. - Roadmap alignment: this advances the existing governed MCP/tool-access work already represented by #9534; it does not introduce a separate roadmap initiative. - Stack position: base branch is `pap10341-split/07-ui-apps-activation`. - Merge policy: merge bottom-up, in order, only after the complete eight-PR stack has been reviewed and the top-of-stack parity gate remains empty. - Requested review: QA for flag audit and e2e/browser acceptance; Greptile on every PR. ## What Changed - Adds MCP user-story and Smoke Lab e2e suites, docs/evals/release notes, the skill update, and the root e2e driver script registration. - Keeps this PR below 100 changed files and independently typecheckable. - Preserves the final tree from #9534 when combined with the other seven stack levels. ## Verification - `pnpm typecheck` - `node --check scripts/e2e-mcp-user-stories.mjs` - `pnpm exec playwright test --config tests/e2e/playwright.config.ts --list` — 43 tests discovered - `git diff pap10341-split/08-e2e-docs 6b40e3876d9297105d4ec306e47e46d351c86172` — empty (0 bytes) ## Risks - Browser suites depend on runtime services and environment setup; this PR validates discovery locally while QA owns full flag-on/flag-off execution. - Stack risk: merging out of order can expose incomplete layers; mitigate by following the documented bottom-up merge policy. - Parity risk: later edits to an intermediate branch can drift from #9534; mitigate by re-running the empty top-of-stack diff before merge. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, exact model ID `gpt-5.4`; runtime-managed context window; medium reasoning with repository, shell, Git, GitHub CLI, and code-execution tools enabled. ## 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 - [x] Internal references are omitted except the execution-plan link explicitly required for this coordinated split stack - [x] My branch name describes the change and contains no internal Paperclip ticket id or instance-derived details - [x] I have run tests locally and they pass - [x] I have added or updated tests where applicable - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [ ] All Paperclip CI gates are green - [ ] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge ## Stack Coordination - Internal execution plan: [PAP-13874](/PAP/issues/PAP-13874#document-plan) - Parity reference: #9534 - Stack: #9556 → #9557 → #9558 → #9559 → #9560 → #9561 → #9562 → #9563 - Merge bottom-up only after full-stack review and an empty parity diff at #9563. --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
155 lines
7.4 KiB
TypeScript
155 lines
7.4 KiB
TypeScript
import { expect, test, type APIRequestContext, type Page } from "@playwright/test";
|
|
|
|
// Current Apps lifecycle coverage. The legacy Tools -> Applications CRUD table
|
|
// was retired; old links now redirect to /apps. Keep this harness focused on
|
|
// the user-visible Connections list plus app detail setup/advanced flows.
|
|
|
|
type SeedResult = {
|
|
companyId: string;
|
|
prefix: string;
|
|
};
|
|
|
|
const SCREENSHOT_DIR = "test-results";
|
|
const APP_PREFIX = `QA 10820 ${Date.now().toString(36)}`;
|
|
|
|
async function discoverCompany(request: APIRequestContext): Promise<SeedResult> {
|
|
const res = await request.post("/api/companies", {
|
|
data: { name: `applications lifecycle ${Date.now()}` },
|
|
});
|
|
expect(res.ok(), `create company failed ${res.status()}: ${await res.text()}`).toBe(true);
|
|
const company = await res.json();
|
|
const flags = await request.patch("/api/instance/settings/experimental", { data: { enableApps: true } });
|
|
expect(flags.ok(), `enable apps failed ${flags.status()}: ${await flags.text()}`).toBe(true);
|
|
return {
|
|
companyId: company.id,
|
|
prefix: company.issuePrefix ?? company.prefix ?? company.urlKey ?? "E2E",
|
|
};
|
|
}
|
|
|
|
async function createApplication(
|
|
request: APIRequestContext,
|
|
companyId: string,
|
|
body: { name: string; description?: string; type?: string },
|
|
): Promise<{ id: string; name: string }> {
|
|
const res = await request.post(`/api/companies/${companyId}/tools/applications`, {
|
|
data: { type: "mcp_http", ...body },
|
|
});
|
|
if (!res.ok()) throw new Error(`create app failed ${res.status()}: ${await res.text()}`);
|
|
return res.json();
|
|
}
|
|
|
|
async function createConnection(
|
|
request: APIRequestContext,
|
|
companyId: string,
|
|
data: { applicationName?: string; applicationId?: string; name: string; transport?: string; config?: object },
|
|
): Promise<{ id: string; applicationId: string; name: string }> {
|
|
const res = await request.post(`/api/companies/${companyId}/tools/connections`, {
|
|
data: {
|
|
transport: "remote_http",
|
|
config: { url: "https://fixture.example/mcp" },
|
|
enabled: true,
|
|
status: "active",
|
|
...data,
|
|
},
|
|
});
|
|
if (!res.ok()) throw new Error(`create connection failed ${res.status()}: ${await res.text()}`);
|
|
return res.json();
|
|
}
|
|
|
|
async function gotoApps(page: Page, prefix: string) {
|
|
await page.goto(`/${prefix}/apps`);
|
|
await expect(page.getByRole("heading", { name: "Connections" })).toBeVisible({ timeout: 30_000 });
|
|
}
|
|
|
|
test.describe.serial("applications lifecycle", () => {
|
|
let seed: SeedResult;
|
|
|
|
test.beforeAll(async ({ request }) => {
|
|
seed = await discoverCompany(request);
|
|
});
|
|
|
|
test.afterAll(async ({ request }) => {
|
|
if (!seed?.companyId) return;
|
|
await request.delete(`/api/companies/${seed.companyId}`).catch(() => undefined);
|
|
});
|
|
|
|
test("Connections list surfaces connected and not-connected apps", async ({ page, request }) => {
|
|
const connectedName = `${APP_PREFIX}-connected`;
|
|
const notConnectedName = `${APP_PREFIX}-not-connected`;
|
|
const connected = await createConnection(request, seed.companyId, {
|
|
applicationName: connectedName,
|
|
name: connectedName,
|
|
});
|
|
const notConnected = await createApplication(request, seed.companyId, { name: notConnectedName });
|
|
|
|
await gotoApps(page, seed.prefix);
|
|
|
|
const connectedRow = page.locator("tbody tr", { hasText: connectedName });
|
|
await expect(connectedRow).toBeVisible();
|
|
await expect(connectedRow.getByText("Healthy")).toBeVisible();
|
|
await expect(connectedRow.getByRole("button", { name: "Open" })).toBeVisible();
|
|
|
|
const notConnectedRow = page.locator("tbody tr", { hasText: notConnectedName });
|
|
await expect(notConnectedRow).toBeVisible();
|
|
await expect(notConnectedRow.getByText("Not connected")).toBeVisible();
|
|
await expect(notConnectedRow.getByRole("button", { name: "Connect" })).toBeVisible();
|
|
await page.screenshot({ path: `${SCREENSHOT_DIR}/applications-crud-current-list.png`, fullPage: true });
|
|
|
|
await connectedRow.getByRole("button", { name: "Open" }).click();
|
|
await expect(page).toHaveURL(new RegExp(`/${seed.prefix}/apps/${connected.id}`), { timeout: 20_000 });
|
|
|
|
await gotoApps(page, seed.prefix);
|
|
await notConnectedRow.getByRole("button", { name: "Connect" }).click();
|
|
await expect(page).toHaveURL(new RegExp(`/${seed.prefix}/apps/app/${notConnected.id}`), { timeout: 20_000 });
|
|
});
|
|
|
|
test("connected app detail supports pause, rename, and removal", async ({ page, request }) => {
|
|
const appName = `${APP_PREFIX}-detail-app`;
|
|
const renamed = `${APP_PREFIX}-renamed-app`;
|
|
const connection = await createConnection(request, seed.companyId, {
|
|
applicationName: appName,
|
|
name: appName,
|
|
});
|
|
|
|
await page.goto(`/${seed.prefix}/apps/${connection.id}/setup`);
|
|
await expect(page.getByRole("heading", { name: appName })).toBeVisible({ timeout: 30_000 });
|
|
await expect(page.getByRole("heading", { name: "Agents can use this app" })).toBeVisible();
|
|
|
|
await page.getByRole("switch", { name: "Pause this app" }).click();
|
|
await expect(page.getByRole("heading", { name: "This app is paused" })).toBeVisible({ timeout: 15_000 });
|
|
await page.getByRole("switch", { name: "Resume this app" }).click();
|
|
await expect(page.getByRole("heading", { name: "Agents can use this app" })).toBeVisible({ timeout: 15_000 });
|
|
|
|
await page.getByRole("button", { name: "Rename app" }).click();
|
|
await page.getByLabel("App name").fill(renamed);
|
|
await page.getByRole("button", { name: "Save", exact: true }).click();
|
|
await expect(page.getByRole("heading", { name: renamed })).toBeVisible({ timeout: 15_000 });
|
|
await page.screenshot({ path: `${SCREENSHOT_DIR}/applications-crud-current-detail.png`, fullPage: true });
|
|
|
|
await page.goto(`/${seed.prefix}/apps/${connection.id}/advanced`);
|
|
await expect(page.getByText("Danger zone")).toBeVisible({ timeout: 15_000 });
|
|
await page.getByRole("button", { name: "Remove app", exact: true }).click();
|
|
await expect(page.getByRole("button", { name: "Yes, remove it" })).toBeVisible();
|
|
await page.screenshot({ path: `${SCREENSHOT_DIR}/applications-crud-current-remove-connected.png`, fullPage: true });
|
|
await page.getByRole("button", { name: "Yes, remove it" }).click();
|
|
await expect(page).toHaveURL(new RegExp(`/${seed.prefix}/apps$`), { timeout: 20_000 });
|
|
await expect(page.getByText("App removed").first()).toBeVisible({ timeout: 20_000 });
|
|
await expect(page.locator("tbody tr", { hasText: renamed })).toHaveCount(0);
|
|
});
|
|
|
|
test("not-connected app advanced page removes the application", async ({ page, request }) => {
|
|
const cleanAppName = `${APP_PREFIX}-clean-remove-app`;
|
|
const cleanApp = await createApplication(request, seed.companyId, { name: cleanAppName });
|
|
|
|
await page.goto(`/${seed.prefix}/apps/app/${cleanApp.id}/advanced`);
|
|
await expect(page.getByRole("heading", { name: cleanAppName })).toBeVisible({ timeout: 30_000 });
|
|
await expect(page.getByText("Danger zone")).toBeVisible();
|
|
await page.getByRole("button", { name: "Remove app", exact: true }).click();
|
|
await page.screenshot({ path: `${SCREENSHOT_DIR}/applications-crud-current-remove-not-connected.png`, fullPage: true });
|
|
await page.getByRole("button", { name: "Yes, remove it" }).click();
|
|
await expect(page).toHaveURL(new RegExp(`/${seed.prefix}/apps$`), { timeout: 20_000 });
|
|
await expect(page.getByText("App removed").first()).toBeVisible({ timeout: 20_000 });
|
|
await expect(page.locator("tbody tr", { hasText: cleanAppName })).toHaveCount(0);
|
|
});
|
|
});
|