mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-20 00:53:46 +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>
113 lines
4.7 KiB
TypeScript
113 lines
4.7 KiB
TypeScript
import { createContext, useContext, useMemo, useState, type ComponentType, type ReactNode, type SVGProps } from "react";
|
|
import { useQuery } from "@tanstack/react-query";
|
|
import { pickMcpIcon, sanitizeMcpIconSrc, type McpIcon, type ProviderToolIconEntry } from "@paperclipai/shared";
|
|
import { toolsApi } from "@/api/tools";
|
|
import { queryKeys } from "@/lib/queryKeys";
|
|
import { useResolvedTheme } from "@/context/ThemeContext";
|
|
import { cn } from "@/lib/utils";
|
|
|
|
type IconComponent = ComponentType<SVGProps<SVGSVGElement>>;
|
|
|
|
/**
|
|
* A provider's tool icon (MCP SEP-973) with the taxonomy icon as fallback.
|
|
* The icon is always an `<img>` with no referrer, never inlined markup, so an
|
|
* SVG icon's scripts never run. The source is re-checked at render time and
|
|
* a failed load falls back to the taxonomy icon.
|
|
*/
|
|
export function ProviderToolIcon({
|
|
icons,
|
|
fallback: Fallback,
|
|
className,
|
|
testId,
|
|
}: {
|
|
icons: readonly McpIcon[] | null | undefined;
|
|
fallback: IconComponent;
|
|
className?: string;
|
|
testId?: string;
|
|
}) {
|
|
// Subscribed, so a theme switch re-picks the icon for the new theme.
|
|
const icon = pickMcpIcon(icons, useResolvedTheme());
|
|
const src = icon ? sanitizeMcpIconSrc(icon.src, icon.mimeType) : null;
|
|
const [failedSrc, setFailedSrc] = useState<string | null>(null);
|
|
if (!src || failedSrc === src) {
|
|
return <Fallback className={className} aria-hidden data-testid={testId} />;
|
|
}
|
|
return (
|
|
<img
|
|
src={src}
|
|
alt=""
|
|
aria-hidden
|
|
referrerPolicy="no-referrer"
|
|
loading="lazy"
|
|
decoding="async"
|
|
draggable={false}
|
|
width={14}
|
|
height={14}
|
|
data-testid={testId}
|
|
data-provider-icon="true"
|
|
onError={() => setFailedSrc(src)}
|
|
className={cn("object-contain", className)}
|
|
/>
|
|
);
|
|
}
|
|
|
|
/** Gateway tool name (`mcp.<app>-<connection>:<tool>`) inside a transcript tool name. */
|
|
const GATEWAY_TOOL_NAME = /(?:mcp|app)\.[a-z0-9-]+-[a-z0-9]{1,8}:[a-z0-9-]+/i;
|
|
|
|
export function gatewayToolNameIn(rawName: string | null | undefined): string | null {
|
|
return rawName ? GATEWAY_TOOL_NAME.exec(rawName)?.[0]?.toLowerCase() ?? null : null;
|
|
}
|
|
|
|
/** Native runner tool name (`app_<name>_<12-hex digest>`) inside a transcript tool name. */
|
|
const NATIVE_TOOL_NAME = /app_[A-Za-z0-9_]*_[0-9a-f]{12}(?![0-9a-f])/;
|
|
|
|
export function nativeToolNameIn(rawName: string | null | undefined): string | null {
|
|
return rawName ? NATIVE_TOOL_NAME.exec(rawName)?.[0] ?? null : null;
|
|
}
|
|
|
|
export type ProviderToolIconLookup = (rawName: string | null | undefined) => McpIcon[] | null;
|
|
|
|
export function providerToolIconLookup(entries: readonly ProviderToolIconEntry[]): ProviderToolIconLookup {
|
|
const byName = new Map(entries.map((entry) => [entry.gatewayToolName.toLowerCase(), entry.icons]));
|
|
const byNativeName = new Map(entries.flatMap((entry) => entry.nativeToolName ? [[entry.nativeToolName, entry.icons] as const] : []));
|
|
return (rawName) => {
|
|
const name = gatewayToolNameIn(rawName);
|
|
if (!name) {
|
|
// Native runners name tools `app_<name>_<digest>` in their transcripts.
|
|
const native = nativeToolNameIn(rawName);
|
|
return native ? byNativeName.get(native) ?? null : null;
|
|
}
|
|
// Same-named tools on one connection get a `-<id>` suffix from the gateway.
|
|
return byName.get(name) ?? byName.get(name.replace(/-[0-9a-f]{8}$/, "")) ?? null;
|
|
};
|
|
}
|
|
|
|
const NO_ICONS: ProviderToolIconLookup = () => null;
|
|
const ProviderToolIconsContext = createContext<ProviderToolIconLookup>(NO_ICONS);
|
|
|
|
/**
|
|
* Loads a company's provider tool icons once (one small, cached request) so
|
|
* every tool row in the chat finds its icon without a request of its own.
|
|
*/
|
|
export function ProviderToolIconsProvider({ companyId, children }: { companyId: string | null | undefined; children: ReactNode }) {
|
|
const query = useQuery({
|
|
queryKey: queryKeys.tools.providerIcons(companyId ?? ""),
|
|
queryFn: () => toolsApi.listProviderToolIcons(companyId!),
|
|
enabled: Boolean(companyId),
|
|
staleTime: 10 * 60_000,
|
|
});
|
|
const entries = query.data?.icons;
|
|
const lookup = useMemo(() => (entries?.length ? providerToolIconLookup(entries) : NO_ICONS), [entries]);
|
|
return <ProviderToolIconsContext.Provider value={lookup}>{children}</ProviderToolIconsContext.Provider>;
|
|
}
|
|
|
|
/** Static icons, for stories and tests. */
|
|
export function ProviderToolIconsStaticProvider({ entries, children }: { entries: readonly ProviderToolIconEntry[]; children: ReactNode }) {
|
|
const lookup = useMemo(() => providerToolIconLookup(entries), [entries]);
|
|
return <ProviderToolIconsContext.Provider value={lookup}>{children}</ProviderToolIconsContext.Provider>;
|
|
}
|
|
|
|
export function useProviderToolIcons(rawName: string | null | undefined): McpIcon[] | null {
|
|
return useContext(ProviderToolIconsContext)(rawName);
|
|
}
|