mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-16 20:12:20 +01:00
## Thinking Path > - Paperclip is the open source app people use to manage AI agents for work. > - MCP Apps (#21119) show interactive widgets from MCP servers, such as Circleback meeting cards, with the agent's reply in the task chat. > - The first version deferred three parts of the MCP Apps spec. A widget could not propose a chat message (`ui/message`). It could not give the agent context (`ui/update-model-context`). It could not go full screen. > - Paperclip also ignored the `icons` that MCP servers declare on tools (SEP-973). > - The security review of #21119 showed what these features need from day one: explicit consent, untrusted-data labels and strict icon sanitizing. > - This pull request adds the three host features and provider tool icons, with those protections built in. > - The benefit is that widgets can now work with the person and the agent, not only display data. ## Linked Issues or Issue Description Refs #21119 **Subsystem affected** MCP Apps host (task chat widgets), tool catalog, run wake prompt. **Problem or motivation** The MCP Apps host refused `ui/message` (-32601), dropped `ui/update-model-context` and kept every view inline. MCP tool `icons` were not parsed or shown. So widgets could not ask the agent a follow-up, the agent could not see what the person selected in a widget, large widgets were cramped, and tool rows used only generic icons. **Proposed solution** Add consent-gated view messages, per-view app context delivered to the task's next run as untrusted data, a full-screen dialog, and sanitized provider icons. Details are under "What Changed". **Alternatives considered** - Send view messages with a new server route that creates the comment itself. Rejected: comment creation has many rules (agent chat ownership, paused conversations, queued delivery, wakeups, receipts). The widget's Send button uses the same send path as the composer. A small route then records which view the comment came from. - Keep the iframe in place for full screen with CSS. Rejected: chat containers can create containing blocks that break `position: fixed`. A moved iframe always reloads, so the dialog hosts a new frame instead. **Roadmap alignment** Continues the MCP feature work after #21119, #21140 and #21219. It does not touch the MCP Tasks work (gateway `tools/call` polling and elicitation). ## What Changed - **`ui/message`.** The host shows "<App> wants to send: …" with **Send** and **Dismiss** under the widget (and inside the full-screen dialog). Nothing is sent before the click. Send posts the text as the viewer's own comment through the chat's normal send path (`handleThreadAdd`). `POST /api/issues/:issueId/mcp-app-views/:viewId/messages` then logs `issue.mcp_app_message_sent`. It accepts only the caller's own comment on the same task, matched by `clientRequestId`, from the last 10 minutes. One proposal per view can wait at a time. The view gets `{}` after the send, or -32000 "Message sending denied" after Dismiss. Only `user` text up to 8,000 characters is accepted. - **`ui/update-model-context`.** `PUT /api/issues/:issueId/mcp-app-views/:viewId/model-context` stores the latest context per view in `tool_mcp_app_views.model_context` (text blocks and `structuredContent`, 16 KB at most). Updates are applied in order and deduped in the browser and on the server. A change logs `issue.mcp_app_context_updated`, and an empty update clears the context. The task's next run gets the three most recently updated contexts as an `## App context (untrusted)` wake-prompt section. The section quotes the data as JSON and says it is third-party data, not instructions. The read runs in parallel with the other run preparation and never fails the run. CLI adapters and the native runner render it through the same `renderPaperclipWakePrompt`. - **Who may do this.** Messages and context need a signed-in person with `issue:comment` on the task. Agents and API keys get 403. Other tasks and companies get 404. `message` and `updateModelContext` are advertised in `hostCapabilities` only where the viewer can send messages. - **Full screen.** The host advertises `availableDisplayModes: ["inline","fullscreen"]` and handles `ui/request-display-mode`. It honors the view's declared modes and answers with the resulting mode. It sends `host-context-changed` with `displayMode` and the container (fixed `height`/`width` in full screen), and again when that container resizes. A new **Open full screen** control sits next to "Widget from …". Full screen is a Paperclip dialog that closes with Exit, Escape or the view's own request. - **Provider tool icons.** `icons` on MCP tool descriptors are sanitized into the new `tool_catalog_entries.icons` column, outside the version hash, so a new icon never quarantines a reviewed tool. Only `https:` URLs and `data:image/*` URIs are kept, and SVG only as `data:`. A `data:` icon is at most 32 KB, a URL at most 2,048 characters, with at most 4 icons per tool. `GET /api/companies/:companyId/tool-icons` lists them keyed by gateway tool name, in one cached request per chat. Task chat tool rows and the app's actions list show them through `ProviderToolIcon`. It renders `<img referrerPolicy="no-referrer">` at a fixed size and never inlines markup. It checks the source again before rendering and falls back to the taxonomy icon. - **Schema.** Migration `0477` adds `tool_catalog_entries.icons`, `tool_mcp_app_views.model_context` and `model_context_updated_at`, all nullable. - **Docs and stories.** `doc/connections/MCP-APPS.md` documents the new behavior, and the finished items are removed from "Limits and follow-ups". `Tasks/MCP App views` has new stories: "View asks to send a message", "Full screen" and "Tool rows with provider icons". The fixture view now uses `ui/message`, `ui/request-display-mode` and `ui/update-model-context`. ## Verification - `pnpm exec vitest run server/src/__tests__/mcp-apps.test.ts server/src/__tests__/tool-catalog-publication.test.ts server/src/__tests__/openapi-routes.test.ts packages/shared/src/mcp-icons.test.ts packages/shared/src/mcp-apps.test.ts`: pass (embedded Postgres). These tests cover: - Context: stored, deduped, logged once, 413 when too large, cleared, scoped to the task and company, refused for agents (403), and rendered into the wake prompt as untrusted data. - Messages: attributed only to the viewer's own recent comment on the same task. A teammate's comment, an unknown request id or an old comment gets 404. An agent gets 403. - Icons: stored sanitized, and the version hash and status do not change. Another company sees nothing. - `cd ui && pnpm exec vitest run src/components/mcp-app/ src/components/ProviderToolIcon.test.tsx src/pages/apps/app-detail/`: 69 pass. These tests cover: - The host protocol for each new method: capabilities, consent wait, one proposal at a time, invalid input, ordered and deduped context, the size limit, and the display-mode rules. - The consent card (nothing sent without Send). - The full-screen dialog (one frame at a time). - Icon rendering (no-referrer `img`, no inline SVG, fallback). - `cd ui && pnpm typecheck` (including Storybook) and `tsc --noEmit` for the server: clean. - Red/green: the new route and host tests fail on `master`, where the routes do not exist and the host answers -32601 or drops updates. The icon descriptor test failed when the publication write was removed. - Not run locally: the full suite, and `packages/adapter-utils/src/server-utils.test.ts › runChildProcess › does not crash when the child closes stdin before a delayed write`. That test times out on this Mac with or without this change, so it is a local platform issue. CI covers both. ## Risks - Migration risk is low: three nullable columns, no backfill. - Every run on a task now does one extra indexed read, in parallel with the other preparation. Errors are logged and the run continues without app context. - If the attribution request fails after the comment is sent, the comment stays without the `mcp_app_message_sent` activity row. This is documented. - Switching between inline and full screen restarts the view, so state inside the widget resets. This is documented as a limit. - Icon names shortened with a hash by the gateway (very long names) do not match, and those rows keep the taxonomy icon. > 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 - Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use and code execution. One subagent (the same model) built the provider-icon part. ## 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] I have not referenced internal/instance-local Paperclip issues or links (only public GitHub `#NNN` / `github.com/paperclipai/paperclip` URLs) - [x] My branch name describes the change (e.g. `docs/...`, `fix/...`) 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 - [ ] I will address all Greptile and reviewer comments before requesting merge 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
156 lines
7.6 KiB
TypeScript
156 lines
7.6 KiB
TypeScript
// @vitest-environment jsdom
|
|
import { act } from "react";
|
|
import { createRoot, type Root } from "react-dom/client";
|
|
import { afterEach, describe, expect, it, vi } from "vitest";
|
|
import type { McpIcon } from "@paperclipai/shared";
|
|
import { TaskChatToolCard } from "./task-chat/TaskChatToolCard";
|
|
import {
|
|
gatewayToolNameIn,
|
|
ProviderToolIcon,
|
|
ProviderToolIconsStaticProvider,
|
|
providerToolIconLookup,
|
|
} from "./ProviderToolIcon";
|
|
import { ThemeProvider, useTheme } from "@/context/ThemeContext";
|
|
|
|
(globalThis as { IS_REACT_ACT_ENVIRONMENT?: boolean }).IS_REACT_ACT_ENVIRONMENT = true;
|
|
|
|
function Fallback(props: { className?: string; "data-testid"?: string }) {
|
|
return <span data-fallback="true" data-testid={props["data-testid"]} className={props.className} />;
|
|
}
|
|
|
|
let root: Root | null = null;
|
|
afterEach(() => {
|
|
act(() => root?.unmount());
|
|
root = null;
|
|
});
|
|
|
|
async function render(node: React.ReactNode) {
|
|
const container = document.createElement("div");
|
|
root = createRoot(container);
|
|
await act(async () => root!.render(node));
|
|
return container;
|
|
}
|
|
|
|
const PNG: McpIcon = { src: "https://cdn.example.com/meetings.png", mimeType: "image/png" };
|
|
|
|
describe("ProviderToolIcon", () => {
|
|
it("renders the provider icon as an image without a referrer, never inline markup", async () => {
|
|
const container = await render(<ProviderToolIcon icons={[PNG]} fallback={Fallback} testId="icon" />);
|
|
const img = container.querySelector("img")!;
|
|
expect(img.getAttribute("src")).toBe(PNG.src);
|
|
expect(img.getAttribute("referrerpolicy")).toBe("no-referrer");
|
|
expect(img.getAttribute("alt")).toBe("");
|
|
expect(container.querySelector("svg")).toBeNull();
|
|
expect(container.querySelector("[data-fallback]")).toBeNull();
|
|
});
|
|
|
|
it("keeps an inline SVG icon inside an img", async () => {
|
|
const container = await render(<ProviderToolIcon icons={[{ src: "data:image/svg+xml;base64,PHN2Zy8+" }]} fallback={Fallback} />);
|
|
expect(container.querySelector("img")?.getAttribute("src")).toBe("data:image/svg+xml;base64,PHN2Zy8+");
|
|
expect(container.querySelector("svg")).toBeNull();
|
|
});
|
|
|
|
it("falls back to the taxonomy icon when there is no icon, an unsafe one, or the image fails", async () => {
|
|
expect((await render(<ProviderToolIcon icons={null} fallback={Fallback} />)).querySelector("[data-fallback]")).not.toBeNull();
|
|
act(() => root?.unmount());
|
|
// Re-checked at render time even if a stored value slipped past parsing.
|
|
const unsafe = await render(<ProviderToolIcon icons={[{ src: "javascript:alert(1)" }]} fallback={Fallback} />);
|
|
expect(unsafe.querySelector("img")).toBeNull();
|
|
expect(unsafe.querySelector("[data-fallback]")).not.toBeNull();
|
|
act(() => root?.unmount());
|
|
const failing = await render(<ProviderToolIcon icons={[PNG]} fallback={Fallback} />);
|
|
await act(async () => failing.querySelector("img")!.dispatchEvent(new Event("error")));
|
|
expect(failing.querySelector("img")).toBeNull();
|
|
expect(failing.querySelector("[data-fallback]")).not.toBeNull();
|
|
});
|
|
});
|
|
|
|
describe("provider icons in task chat tool rows", () => {
|
|
const NATIVE = "app_mcp_circleback_1a2b3c4d_displaymeetings_0123456789ab";
|
|
const entries = [{ gatewayToolName: "mcp.circleback-1a2b3c4d:displaymeetings", nativeToolName: NATIVE, icons: [PNG] }];
|
|
|
|
it("finds the gateway tool name inside agent transcript names", () => {
|
|
expect(gatewayToolNameIn("mcp__paperclip__mcp.circleback-1a2b3c4d:displaymeetings")).toBe("mcp.circleback-1a2b3c4d:displaymeetings");
|
|
expect(gatewayToolNameIn("Bash")).toBeNull();
|
|
const lookup = providerToolIconLookup(entries);
|
|
expect(lookup("mcp.circleback-1a2b3c4d:displaymeetings")).toEqual([PNG]);
|
|
// The gateway's duplicate-name suffix still finds the tool.
|
|
expect(lookup("mcp.circleback-1a2b3c4d:displaymeetings-0f0f0f0f")).toEqual([PNG]);
|
|
expect(lookup("mcp.other-99999999:displaymeetings")).toBeNull();
|
|
});
|
|
|
|
it("shows the provider icon on a matching row and the taxonomy icon elsewhere", async () => {
|
|
const container = await render(
|
|
<ProviderToolIconsStaticProvider entries={entries}>
|
|
<TaskChatToolCard item={{ kind: "tool", id: "t1", name: "Display meetings", rawName: "mcp__paperclip__mcp.circleback-1a2b3c4d:displaymeetings", status: "completed" }} />
|
|
<TaskChatToolCard item={{ kind: "tool", id: "t2", name: "Bash", rawName: "Bash", status: "completed" }} />
|
|
</ProviderToolIconsStaticProvider>,
|
|
);
|
|
const icons = container.querySelectorAll("[data-testid='task-chat-tool-icon']");
|
|
expect(icons).toHaveLength(2);
|
|
expect(icons[0]!.tagName).toBe("IMG");
|
|
expect(icons[0]!.getAttribute("referrerpolicy")).toBe("no-referrer");
|
|
expect(icons[1]!.tagName.toLowerCase()).toBe("svg");
|
|
});
|
|
|
|
it("indexes a company's icons once and finds each row's icon in constant work at realistic size", async () => {
|
|
const ENTRIES = 500;
|
|
const ROWS = 600;
|
|
const big = Array.from({ length: ENTRIES }, (_, index) => ({
|
|
gatewayToolName: `mcp.app${index % 25}-${(index % 25).toString(16).padStart(8, "0")}:tool-${index}`,
|
|
icons: [PNG],
|
|
}));
|
|
const rawName = (index: number) => `mcp__paperclip__mcp.app${index % 25}-${(index % 25).toString(16).padStart(8, "0")}:tool-${index % ENTRIES}`;
|
|
const set = vi.spyOn(Map.prototype, "set");
|
|
const lookup = providerToolIconLookup(big);
|
|
// The index is built once: one insert per entry.
|
|
expect(set.mock.calls.length).toBe(ENTRIES);
|
|
set.mockRestore();
|
|
const get = vi.spyOn(Map.prototype, "get");
|
|
let found = 0;
|
|
for (let index = 0; index < ROWS; index += 1) if (lookup(rawName(index))) found += 1;
|
|
// At most two index reads per row (exact name, then without a duplicate suffix); no scans.
|
|
expect(get.mock.calls.length).toBeLessThanOrEqual(2 * ROWS);
|
|
get.mockRestore();
|
|
expect(found).toBe(ROWS);
|
|
|
|
const container = await render(
|
|
<ProviderToolIconsStaticProvider entries={big}>
|
|
{Array.from({ length: 300 }, (_, index) => (
|
|
<TaskChatToolCard key={index} item={{ kind: "tool", id: `t${index}`, name: `Tool ${index}`, rawName: rawName(index), status: "completed" }} />
|
|
))}
|
|
</ProviderToolIconsStaticProvider>,
|
|
);
|
|
expect(container.querySelectorAll("img[data-provider-icon=true]")).toHaveLength(300);
|
|
});
|
|
|
|
it("re-picks the icon when the theme changes", async () => {
|
|
const themed: McpIcon[] = [
|
|
{ src: "https://cdn.example.com/light.png", theme: "light" },
|
|
{ src: "https://cdn.example.com/dark.png", theme: "dark" },
|
|
];
|
|
let setTheme!: (theme: "light" | "dark") => void;
|
|
function Toggle() { setTheme = useTheme().setTheme; return null; }
|
|
const container = await render(
|
|
<ThemeProvider><Toggle /><ProviderToolIcon icons={themed} fallback={Fallback} /></ThemeProvider>,
|
|
);
|
|
await act(async () => setTheme("light"));
|
|
expect(container.querySelector("img")!.getAttribute("src")).toBe("https://cdn.example.com/light.png");
|
|
await act(async () => setTheme("dark"));
|
|
expect(container.querySelector("img")!.getAttribute("src")).toBe("https://cdn.example.com/dark.png");
|
|
});
|
|
|
|
it("finds icons for native runner tool names", async () => {
|
|
const lookup = providerToolIconLookup(entries);
|
|
expect(lookup(NATIVE)).toEqual([PNG]);
|
|
expect(lookup(`mcp__paperclip__${NATIVE}`)).toEqual([PNG]);
|
|
expect(lookup("app_mcp_circleback_1a2b3c4d_displaymeetings_ffffffffffff")).toBeNull();
|
|
const container = await render(
|
|
<ProviderToolIconsStaticProvider entries={entries}>
|
|
<TaskChatToolCard item={{ kind: "tool", id: "n1", name: "Display meetings", rawName: NATIVE, status: "completed" }} />
|
|
</ProviderToolIconsStaticProvider>,
|
|
);
|
|
expect(container.querySelector("[data-testid='task-chat-tool-icon']")!.tagName).toBe("IMG");
|
|
});
|
|
});
|