mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-11 05:11:49 +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 6/8 and focuses on UI API, shared components, and Tools/Profile surfaces > - 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: Operators need typed clients and administration surfaces that compile independently before navigation exposes them. - Proposed solution: Adds UI APIs, hooks, libraries, shared components, Tools/Profiles pages, and the plugin settings consumer required by the new company-scoped API. - 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/05-runtime-integration`. - 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: UXDesigner sanity pass on Tools/Profile surfaces; Greptile on every PR. ## What Changed - Adds UI APIs, hooks, libraries, shared components, Tools/Profiles pages, and the plugin settings consumer required by the new company-scoped API. - 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` - `pnpm check:token-gates` — all gates clean - Focused UI Vitest run with `NODE_ENV=test` — 28 files, 183 tests passed ## Risks - Large dead-code UI additions can drift from activation routes; PR 7 supplies the registration layer and top-level parity catches omissions. - 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. ## UI Evidence QA captured these from the live Garden MCP split stack at 1440px and verified clean rendering:    --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
195 lines
6.2 KiB
TypeScript
195 lines
6.2 KiB
TypeScript
// @vitest-environment jsdom
|
||
|
||
import { flushSync } from "react-dom";
|
||
import type { ReactNode } from "react";
|
||
import { createRoot } from "react-dom/client";
|
||
import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
|
||
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
|
||
import { SmokeLabTab } from "./SmokeLabTab";
|
||
|
||
const getExperimentalMock = vi.hoisted(() => vi.fn());
|
||
const listServicesMock = vi.hoisted(() => vi.fn());
|
||
const listRunsMock = vi.hoisted(() => vi.fn());
|
||
const getRunMock = vi.hoisted(() => vi.fn());
|
||
const createRunMock = vi.hoisted(() => vi.fn());
|
||
const startServicesMock = vi.hoisted(() => vi.fn());
|
||
|
||
vi.mock("@/api/instanceSettings", () => ({
|
||
instanceSettingsApi: { getExperimental: () => getExperimentalMock() },
|
||
}));
|
||
|
||
vi.mock("@/api/smokeLab", () => ({
|
||
smokeLabApi: {
|
||
listServices: (c: string) => listServicesMock(c),
|
||
listRuns: (c: string) => listRunsMock(c),
|
||
getRun: (c: string, r: string) => getRunMock(c, r),
|
||
createRun: (c: string, i: unknown) => createRunMock(c, i),
|
||
startServices: (c: string) => startServicesMock(c),
|
||
stopServices: vi.fn(),
|
||
installFixtures: vi.fn(),
|
||
reset: vi.fn(),
|
||
},
|
||
}));
|
||
|
||
vi.mock("@/lib/router", () => ({
|
||
Link: ({ to, children }: { to: string; children: ReactNode }) => <a href={to}>{children}</a>,
|
||
}));
|
||
|
||
vi.mock("@/context/ToastContext", () => ({
|
||
useToast: () => ({ pushToast: vi.fn() }),
|
||
}));
|
||
|
||
// eslint-disable-next-line @typescript-eslint/no-explicit-any
|
||
(globalThis as any).IS_REACT_ACT_ENVIRONMENT = true;
|
||
|
||
async function act(callback: () => void | Promise<void>) {
|
||
let result: void | Promise<void> = undefined;
|
||
flushSync(() => {
|
||
result = callback();
|
||
});
|
||
await result;
|
||
}
|
||
|
||
async function flushReact() {
|
||
for (let i = 0; i < 3; i += 1) {
|
||
await act(async () => {
|
||
await Promise.resolve();
|
||
await new Promise((resolve) => window.setTimeout(resolve, 0));
|
||
});
|
||
}
|
||
}
|
||
|
||
const RUN = {
|
||
id: "run-1",
|
||
companyId: "company-1",
|
||
trigger: "manual",
|
||
status: "passed",
|
||
startedAt: "2026-07-10T00:00:00Z",
|
||
finishedAt: "2026-07-10T00:05:00Z",
|
||
summary: {},
|
||
createdAt: "2026-07-10T00:00:00Z",
|
||
updatedAt: "2026-07-10T00:05:00Z",
|
||
};
|
||
|
||
const STEPS = [
|
||
{
|
||
id: "s1",
|
||
companyId: "company-1",
|
||
runId: "run-1",
|
||
path: "P1",
|
||
scenarioStep: "oauth-login",
|
||
status: "pass",
|
||
detail: "Signed in via fake OAuth consent page",
|
||
screenshotArtifactRef: null,
|
||
durationMs: 812,
|
||
createdAt: "2026-07-10T00:00:01Z",
|
||
updatedAt: "2026-07-10T00:00:01Z",
|
||
},
|
||
{
|
||
id: "s2",
|
||
companyId: "company-1",
|
||
runId: "run-1",
|
||
path: "P7",
|
||
scenarioStep: "schema-change-quarantine",
|
||
status: "fail",
|
||
detail: "Quarantine not enforced",
|
||
screenshotArtifactRef: null,
|
||
durationMs: 240,
|
||
createdAt: "2026-07-10T00:00:02Z",
|
||
updatedAt: "2026-07-10T00:00:02Z",
|
||
},
|
||
];
|
||
|
||
describe("SmokeLabTab", () => {
|
||
let container: HTMLDivElement;
|
||
let root: ReturnType<typeof createRoot>;
|
||
|
||
beforeEach(() => {
|
||
container = document.createElement("div");
|
||
document.body.appendChild(container);
|
||
getExperimentalMock.mockResolvedValue({ enableSmokeLab: true });
|
||
listServicesMock.mockResolvedValue({
|
||
services: [
|
||
{
|
||
id: "fake-oauth",
|
||
label: "Fake OAuth 2.0 provider",
|
||
status: "running",
|
||
url: "http://127.0.0.1:3100/api/companies/company-1/smoke-lab/oauth/authorize",
|
||
health: { ok: true },
|
||
detail: "In-process deterministic OAuth provider.",
|
||
},
|
||
],
|
||
});
|
||
listRunsMock.mockResolvedValue({ runs: [RUN] });
|
||
getRunMock.mockResolvedValue({ run: RUN, steps: STEPS });
|
||
createRunMock.mockResolvedValue({ run: { ...RUN, id: "run-2", status: "running" } });
|
||
});
|
||
|
||
afterEach(() => {
|
||
flushSync(() => root?.unmount());
|
||
container.remove();
|
||
vi.clearAllMocks();
|
||
});
|
||
|
||
async function render() {
|
||
const client = new QueryClient({ defaultOptions: { queries: { retry: false } } });
|
||
root = createRoot(container);
|
||
await act(async () => {
|
||
root.render(
|
||
<QueryClientProvider client={client}>
|
||
<SmokeLabTab companyId="company-1" />
|
||
</QueryClientProvider>,
|
||
);
|
||
});
|
||
await flushReact();
|
||
}
|
||
|
||
it("hides the lab and shows a flag-off notice when the flag is disabled", async () => {
|
||
getExperimentalMock.mockResolvedValue({ enableSmokeLab: false });
|
||
await render();
|
||
|
||
expect(container.textContent).toContain("Smoke Lab is turned off");
|
||
expect(container.querySelector('[data-testid="smoke-lab-tab"]')).toBeNull();
|
||
expect(container.textContent).not.toContain("Integration matrix");
|
||
expect(listServicesMock).not.toHaveBeenCalled();
|
||
});
|
||
|
||
it("renders services with the resolved URL, demo credentials, and the P1–P7 matrix when enabled", async () => {
|
||
await render();
|
||
|
||
expect(container.querySelector('[data-testid="smoke-lab-tab"]')).not.toBeNull();
|
||
// Resolved URL printed verbatim — never an assumed port.
|
||
expect(container.textContent).toContain(
|
||
"http://127.0.0.1:3100/api/companies/company-1/smoke-lab/oauth/authorize",
|
||
);
|
||
// Demo credentials for the fake OAuth login.
|
||
expect(container.textContent).toContain("smoke@paperclip.test");
|
||
expect(container.textContent).toContain("smoke-password");
|
||
// Matrix rows for every path + a governed lifecycle column.
|
||
expect(container.textContent).toContain("Integration matrix");
|
||
expect(container.textContent).toContain("Remote HTTP · OAuth");
|
||
expect(container.textContent).toContain("Governance surfaces");
|
||
expect(container.textContent).toContain("Schema-change quarantine");
|
||
// Failing path surfaced from the recorded steps.
|
||
expect(container.textContent).toContain("failing: P7");
|
||
// Step drill-down shows the raw scenario step.
|
||
expect(container.textContent).toContain("oauth-login");
|
||
});
|
||
|
||
it("starts a manual run when 'Run browser smoke now' is clicked", async () => {
|
||
await render();
|
||
|
||
const runButton = Array.from(container.querySelectorAll("button")).find(
|
||
(b) => b.textContent?.includes("Run browser smoke now"),
|
||
);
|
||
expect(runButton).toBeTruthy();
|
||
|
||
await act(async () => {
|
||
runButton!.dispatchEvent(new MouseEvent("click", { bubbles: true }));
|
||
});
|
||
await flushReact();
|
||
|
||
expect(createRunMock).toHaveBeenCalledWith("company-1", { trigger: "manual", summary: {} });
|
||
});
|
||
});
|