mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-17 13:01:05 +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>
146 lines
8.8 KiB
TypeScript
146 lines
8.8 KiB
TypeScript
import { describe, expect, it } from "vitest";
|
|
import { buildNativeContinuationPrompt } from "./native-continuation.js";
|
|
|
|
const issue = { title: "Original task", description: "Retain my long task brief." };
|
|
const message = { id: "new", body: "Yes, please proceed.", authorType: "user", authorId: "board", sourceTrust: "user", createdByRunId: null };
|
|
const wake = {
|
|
reason: "issue_commented",
|
|
executionContinuation: {
|
|
version: 1,
|
|
objective: message.body,
|
|
messages: [{ ...message, id: "old", body: "OLD_HISTORY" }, message],
|
|
resumeDelta: { baseRunId: "prior", messages: [message] },
|
|
completedWork: { summary: "OLD_SUMMARY" },
|
|
humanResponses: [{ id: "old-question", result: { answer: "OLD_ANSWER" } }],
|
|
},
|
|
comments: [message], continuationSummary: { markdown: "OLD_SUMMARY" },
|
|
};
|
|
const build = (value: unknown = wake, previousIssue = issue) => buildNativeContinuationPrompt({ wakePayload: value, previousRunId: "prior", issue, previousIssue });
|
|
|
|
describe("native continuation event projection", () => {
|
|
it("sends a new comment once without the unchanged brief, objective, history or summary", () => {
|
|
const text = build()!;
|
|
expect(text.split(message.body)).toHaveLength(2);
|
|
for (const old of [issue.description, issue.title, "OLD_HISTORY", "OLD_SUMMARY", "OLD_ANSWER"]) expect(text).not.toContain(old);
|
|
expect(JSON.parse(text).messages[0]).toMatchObject({ authorType: "user", body: message.body });
|
|
expect(text.length).toBeLessThan(600);
|
|
});
|
|
it("tells a resumed turn which delivered comments an earlier turn already read", () => {
|
|
const comment = { id: "new", body: message.body, author: { type: "user", id: "board" } };
|
|
const marked = JSON.parse(build({ ...wake, comments: [{ ...comment, readByEarlierTurn: true }] })!);
|
|
expect(marked.readByEarlierTurn).toEqual({ messageIds: ["new"], note: expect.stringContaining("may have applied it") });
|
|
expect(JSON.parse(build({ ...wake, comments: [comment] })!).readByEarlierTurn).toBeUndefined();
|
|
});
|
|
it("keeps the task widgets' app context on a resumed turn", () => {
|
|
const appContext = "## App context (untrusted)\n\n```json\n{\"app\":\"Circleback\",\"text\":\"Selected m2\"}\n```";
|
|
const events = JSON.parse(build({ ...wake, mcpAppContext: appContext })!);
|
|
expect(events.appContext).toBe(appContext);
|
|
expect(events.messages[0]).toMatchObject({ body: message.body });
|
|
expect(JSON.parse(build()!).appContext).toBeUndefined();
|
|
});
|
|
it("only uses a delta whose base matches the actual previous run", () => {
|
|
expect(build({ ...wake, executionContinuation: { ...wake.executionContinuation, resumeDelta: { baseRunId: "different", messages: [message] } } })).toBeNull();
|
|
expect(build({ ...wake, executionContinuation: null })).toBeNull();
|
|
});
|
|
it("delivers the current authenticated answer once, not all prior answers", () => {
|
|
const text = build({ ...wake, interactionId: "new-question", executionContinuation: { ...wake.executionContinuation, resumeDelta: { baseRunId: "prior", messages: [] }, humanResponses: [...wake.executionContinuation.humanResponses, { id: "new-question", kind: "ask_user_questions", status: "answered", resolvedByUserId: "board", result: { answer: "NEW_ANSWER" } }] } })!;
|
|
expect(text.split("NEW_ANSWER")).toHaveLength(2);
|
|
expect(text).not.toContain("OLD_ANSWER");
|
|
expect(JSON.parse(text).humanResponses[0].resolvedByUserId).toBe("board");
|
|
});
|
|
it("includes external child completion and actual brief edits", () => {
|
|
const text = build({ ...wake, reason: "issue_children_completed", childIssueSummaries: [{ id: "child", status: "done", summary: "CHILD_RESULT" }] }, { ...issue, description: "old brief" })!;
|
|
expect(JSON.parse(text).taskChanges).toEqual({ description: issue.description });
|
|
expect(text).toContain("CHILD_RESULT");
|
|
});
|
|
it.each([{ fallbackFetchNeeded: true }, { recovery: { cause: "interrupted" } }, { externalChatExecutionBound: true }, { reason: "issue_assigned" }])("retains bootstrap framing for special wakes: %j", (extra) => {
|
|
expect(build({ ...wake, ...extra })).toBeNull();
|
|
});
|
|
});
|
|
|
|
|
|
describe("plain-text external chat continuation projection", () => {
|
|
const slackComment = { ...message, author: { type: "user", id: "board" } };
|
|
const slackWake = {
|
|
...wake,
|
|
reason: "External chat message received",
|
|
issue: { id: "task", title: "OLD_EXACT_REPLY", description: "Started from Slack", workMode: "standard" },
|
|
externalChatProvider: "slack", checkedOutByHarness: true,
|
|
comments: [slackComment],
|
|
commentIds: [message.id], latestCommentId: message.id,
|
|
commentWindow: { requestedCount: 1, includedCount: 1, missingCount: 0 },
|
|
attachmentOmissions: [],
|
|
};
|
|
const buildChat = (value: unknown = slackWake) => buildNativeContinuationPrompt({
|
|
wakePayload: value, previousRunId: "prior", issue: slackWake.issue,
|
|
previousIssue: slackWake.issue,
|
|
allowExternalChat: true,
|
|
});
|
|
it.each(["slack", "github"])("sends the new %s message once without prior titles, history or instructions", (externalChatProvider) => {
|
|
const text = buildChat({ ...slackWake, externalChatProvider })!;
|
|
expect(text).not.toBeNull();
|
|
expect(JSON.parse(text)).toEqual({ messages: [message] });
|
|
expect(text).not.toContain("OLD_EXACT_REPLY");
|
|
expect(text).not.toContain("OLD_HISTORY");
|
|
expect(text.length).toBeLessThan(600);
|
|
});
|
|
it("excludes edited history and prior agent output outside the current Slack delivery", () => {
|
|
const text = buildChat({ ...slackWake, executionContinuation: {
|
|
...wake.executionContinuation,
|
|
resumeDelta: { baseRunId: "prior", messages: [
|
|
{ ...message, id: "old-edited", body: "STALE_DIRECTION" },
|
|
{ ...message, id: "old-reply", authorType: "agent", body: "OLD_AGENT_REPLY" },
|
|
message,
|
|
] },
|
|
} });
|
|
expect(JSON.parse(text!).messages).toEqual([message]);
|
|
expect(text).not.toContain("STALE_DIRECTION");
|
|
expect(text).not.toContain("OLD_AGENT_REPLY");
|
|
});
|
|
it("preserves an actual task brief edit beside the current message", () => {
|
|
const text = buildNativeContinuationPrompt({
|
|
wakePayload: slackWake, previousRunId: "prior", allowExternalChat: true,
|
|
issue: { ...slackWake.issue, description: "Updated scope" }, previousIssue: slackWake.issue,
|
|
});
|
|
expect(JSON.parse(text!).taskChanges).toEqual({ description: "Updated scope" });
|
|
});
|
|
it("delivers changed GitHub configuration while retaining unchanged configuration in the provider session", () => {
|
|
const config = { key: "a".repeat(64), instructions: "CURRENT_REVIEW_POLICY" };
|
|
const args = { wakePayload: { ...slackWake, externalChatProvider: "github", githubReviewConfigurations: [config] },
|
|
previousRunId: "prior", issue: slackWake.issue, previousIssue: slackWake.issue, allowExternalChat: true };
|
|
const changed = buildNativeContinuationPrompt(args)!;
|
|
expect(JSON.parse(changed).reviewConfigurations).toEqual([config]);
|
|
const unchanged = buildNativeContinuationPrompt({ ...args, previousGitHubReviewConfigurationKeys: [config.key] })!;
|
|
expect(unchanged).not.toContain(config.instructions);
|
|
expect(JSON.parse(unchanged).messages).toEqual([message]);
|
|
expect(buildNativeContinuationPrompt({ ...args, previousRunId: "wrong" })).toBeNull();
|
|
});
|
|
it("accepts the verified non-assignee chat binding", () => {
|
|
expect(buildChat({ ...slackWake, checkedOutByHarness: false, externalChatExecutionBound: true })).not.toBeNull();
|
|
});
|
|
it.each([
|
|
{ comments: [{ ...slackComment, attachments: [{ id: "file" }] }] },
|
|
{ comments: [{ ...slackComment, attachments: "malformed" }] },
|
|
{ comments: [{ ...slackComment, body: "EDITED_SINCE_DELTA" }] },
|
|
{ comments: [{ ...slackComment, author: { type: "user", id: "different-user" } }] },
|
|
{ attachmentOmissions: [{ commentId: message.id, notice: "Unavailable input" }] },
|
|
{ externalChatProvider: "discord" },
|
|
{ checkedOutByHarness: false },
|
|
{ truncated: true },
|
|
{ fallbackFetchNeeded: true },
|
|
{ comments: [{ ...slackComment, bodyTruncated: true }] },
|
|
{ interactionId: "approval", interactionKind: "request_confirmation" },
|
|
{ recovery: { cause: "interrupted" } },
|
|
{ executionContinuation: { ...wake.executionContinuation, resumeDelta: { baseRunId: "wrong", messages: [message] } } },
|
|
{ executionContinuation: { ...wake.executionContinuation, resumeDelta: { baseRunId: "prior", messages: [] } } },
|
|
{ commentIds: [message.id, "missing"], latestCommentId: "missing" },
|
|
{ commentIds: [message.id, message.id], latestCommentId: message.id },
|
|
{ executionContinuation: { ...wake.executionContinuation, resumeDelta: { baseRunId: "prior", messages: [message, message] } } },
|
|
])("keeps specialized or incomplete input on the full path: %j", (extra) => {
|
|
expect(buildChat({ ...slackWake, ...extra })).toBeNull();
|
|
});
|
|
it("requires the constructor to explicitly opt into chat continuation", () => {
|
|
expect(build(slackWake)).toBeNull();
|
|
});
|
|
});
|