Files
PaperClipAI/ui/src/components/task-chat/task-chat-adapter.ts
T
DottaandClaude Opus 5.5 8ff45c0fa9 feat(connections): render MCP Apps views in the task chat, starting with Circleback (#21119)
## Thinking Path

> - Paperclip is the open source app people use to manage AI agents for
work.
> - Agents reach external apps through MCP connections. Paperclip
records each call and shows it as a tool row in the task chat.
> - MCP Apps (SEP-1865, extension `io.modelcontextprotocol/ui`, spec
2026-01-26) lets an MCP server attach an interactive `ui://` view to a
tool. Claude, Claude Code and VS Code render these views in chat.
Circleback uses them to show meeting cards.
> - Paperclip dropped the tool's `_meta.ui` at discovery and the
result's `_meta` at call time. Its gateway reported MCP App UI as
"unsupported". Circleback was reachable only through Composio, whose
toolkit has no `Display*` tools.
> - This pull request makes Paperclip an MCP Apps host. It also adds
Circleback as a native catalog connection.
> - The benefit is that a Circleback recap in a task shows the same
meeting cards as in Claude, and any other MCP server with views works
the same way.

## Linked Issues or Issue Description

**Subsystem affected**
Connections and apps (remote MCP gateway) and the task chat.

**Problem or motivation**
An agent that uses Circleback in Paperclip can only return text. The
same tools in Claude Code show interactive meeting cards
(`DisplayMeetings`). Paperclip discards the MCP Apps metadata, so it
cannot show them.

**Proposed solution**
Paperclip implements the host side of MCP Apps end to end. It keeps the
tool's view declaration and records each call that has a view. It
renders the view under the tool row in a sandboxed iframe that uses the
MCP Apps postMessage protocol. Circleback becomes a native catalog
connection, so its `Display*` tools are available.

**Alternatives considered**
Composio's `circleback_mcp` toolkit has 11 read tools and no `Display*`
tools, and its meta-tools return plain JSON, so it cannot carry views.
The spec's double-iframe sandbox proxy on a separate origin needs a
second origin that Paperclip does not have. A single opaque-origin
`srcdoc` frame with an injected CSP gives the same isolation.

**Roadmap alignment**
This extends the existing Apps catalog and MCP gateway. It adds no new
integration substrate (decision D4 in doc/connections/README.md).

**Additional context**
The standard, the design and the testing plan are in
`doc/connections/MCP-APPS.md`.

## What Changed

- **Shared:** `packages/shared/src/mcp-apps.ts` adds MCP Apps types,
`_meta.ui` and resource parsing (current and legacy keys), and a CSP
builder that keeps only well-formed `https` origins.
- **DB:** migration `0471` (`online_compatible`) adds
`tool_catalog_entries.ui_meta` and a new `tool_mcp_app_views` table.
- **Server, catalog:** discovery keeps each tool's `_meta.ui`. It is not
part of the version hash, so a view never quarantines a reviewed tool.
- **Server, gateway:**
- Paperclip advertises the MCP Apps client capability when it
initializes a session.
  - App-only tools (`visibility: ["app"]`) are hidden from agents.
- The result `_meta` is kept for the view and is not sent to the agent.
- Each successful call to a tool with a view records a view row.
Recording is best effort.
- The gateway's `initialize` now reports `paperclip/mcp-app-ui:
host_rendered`.
- The context protocol (`resources/read`) now uses the injected test
transport, like the other remote calls.
- **Server, routes:** `server/src/routes/mcp-apps.ts`
- `GET /api/issues/:issueId/mcp-app-views` lists a task's views. It
needs task read access.
- `GET /api/issues/:issueId/mcp-app-views/:viewId` returns the view
document, read live through the agent's connection.
- `POST /api/issues/:issueId/mcp-app-views/:viewId/tool-calls` runs the
view's `tools/call`. It needs `tools:use` and reaches only tools of the
same connection that allow `app`. It uses the connection test-call path,
so policy, Ask first and audit apply.
- **UI:** `ui/src/components/mcp-app/`
- The host protocol: `ui/initialize` with theme, style variables and
size limits; tool-input; tool-result; size-changed; `tools/call`;
`ui/open-link` (http and https only); teardown.
- An opaque-origin iframe (`allow-scripts`, never `allow-same-origin`)
with the CSP placed before the view's markup.
- The views of a run render with that run's reply, in the live turn and
in settled history. They are keyed by the reply's run, so history needs
no transcript.
- **Circleback:** a native catalog app (`mcp-oauth`, DCR, `user
user:write`) with:
  - the official logo;
- a reviewed risk classifier (Share* tools are writes, Delete* tools are
destructive, Display* tools are reads);
  - warnings in the sign-in step;
  - `doc/connections/CIRCLEBACK.md`.
  
Search now prefers a native app over an aggregator listing named "X
MCP".
- **Storybook:** `Tasks/MCP App views` shows the tool row with its view,
the ready state (Refresh calls a tool), loading, view unavailable, and a
tool call that needs approval.

## Verification

- `pnpm exec vitest run packages/shared/src/mcp-apps.test.ts
ui/src/components/mcp-app/`: 19 passed.
- `pnpm exec vitest run server/src/__tests__/mcp-apps.test.ts`: 3
passed, on embedded Postgres. The test connects Circleback through the
catalog with DCR OAuth against a fake Circleback MCP server. It checks:
  - `ui_meta` is stored;
  - an app-only tool is hidden from the agent;
- an agent call records one view with arguments, structured content and
`_meta`;
  - a call without a view records nothing;
  - the routes serve the view's HTML and CSP;
  - the view's tool call works and a model-only tool is refused;
  - another task, another company and an agent actor are refused.
- Circleback connector: 13 focused files, 645 tests passed. These are
the app definitions, search, aggregator fallback, connection intents,
tool policy, `AppsConnect` and `Browse`.
- Typecheck passed for `@paperclipai/shared`, `@paperclipai/server` and
`@paperclipai/ui`. `node scripts/storybook-catalog.mjs` and the
migration compatibility check also passed.
- Storybook check in the browser:
- In both themes, the view runs the handshake, renders the meeting cards
from `structuredContent`, picks up the theme variables, and resizes to
its content.
  - Refresh sends `tools/call` and re-renders the cards.
- **Live Circleback end to end** on a local instance, with a real
Circleback account:
- Connected through the catalog entry with Circleback's dynamic client
registration and OAuth.
  - Discovery stored the real view declarations:
    - `DisplayMeetings` uses `ui://circleback/meetings.v2.html`.
    - `DisplayActionItems` and `DisplayCalendarEvents` also have views.
- `ListAssigneeOptions` and `SetCalendarEventRecording` are app-only
helpers with no view. They are hidden from agents.
  - A `claude_local` agent called `DisplayMeetings` on two tasks.
- The real 3.5 MB Circleback view rendered the meeting cards with the
agent's reply.
- Clicking a card opened that meeting in Circleback through
`ui/open-link`.
- The live run found two bugs, both fixed in this PR, each with a
regression test:
    - The 1 MB tool-result limit blocked the view document.
    - Views were hidden inside the folded tool history.

## Risks

- **New migration:** a new table and a nullable column. It is
`online_compatible`.
- **Existing connections:** tools get `ui_meta` on the next catalog
refresh. Until then, no view shows and the tool row is unchanged.
- **Untrusted provider HTML:** the view runs as provider HTML in an
opaque-origin sandbox. It cannot reach Paperclip's session, DOM or API.
Its network access is limited to the origins its server declared. A
view's tool calls use the viewer's permissions and the normal policy and
Ask-first path.
- **Agent tool lists:** app-only tools are removed from them. No current
provider marks tools app-only, so no listed tool disappears.
- **Search:** the change that prefers a native app over an "X MCP"
aggregator listing affects every app.

## Model Used

- Claude Opus 5.5 (`claude-opus-5-5`) in Claude Code, with tool use and
subagents (one subagent authored the Circleback catalog connector).

## 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>
2026-11-12 13:28:05 -06:00

160 lines
6.9 KiB
TypeScript

/**
* Live adapter: normalize the existing IssueChatComment stream (including
* optimistic echoes) into the redesign's TaskChatItem[] model. This is the
* seam that lets the new render layer show live task data without touching the
* comment data pipeline. Rich agent-run streaming (thinking/tool/diff) is
* demonstrated in the harness and layered onto this adapter as a later step;
* the baseline live thread renders the author-typed message history + optimistic
* echo, which is the core legibility win.
*/
import type { Agent } from "@paperclipai/shared";
import type { IssueChatComment } from "@/lib/issue-chat-messages";
import { resolveCommentAttribution } from "@/lib/comment-attribution";
import { resolveIssueChatHumanAuthor } from "@/lib/issue-chat-human-author";
import type { CompanyUserProfile } from "@/lib/company-members";
import type { TaskChatAuthorKind, TaskChatItem, TaskChatMessageItem } from "./task-chat-model";
export interface TaskChatAdapterContext {
agentMap?: Map<string, Agent>;
userLabelMap?: ReadonlyMap<string, string> | null;
userProfileMap?: ReadonlyMap<string, CompanyUserProfile> | null;
currentUserId?: string | null;
/**
* Task's current assignee. Agent comments from anyone else are cross-issue
* writes and get a "for {user}" attribution chip (the open cross-task write design (attribution)).
*/
issueAssigneeAgentId?: string | null;
verificationCaveatsByRunId?: ReadonlyMap<string, TaskChatMessageItem["verificationCaveats"]>;
}
function effectiveAgentId(comment: IssueChatComment): string | null {
return comment.authorAgentId ?? comment.derivedAuthorAgentId ?? null;
}
function authorKind(comment: IssueChatComment): TaskChatAuthorKind {
// The server-authored presentation contract wins over attribution. Some
// control-plane notices keep the run agent as their author for audit and
// authorization, but they must still use the system-notice renderer.
// System authorship also wins over any derivable run→agent linkage
// (PAP-443): recovery notices carry a derivedAuthorAgentId but must not
// render as agent bubbles.
if (
comment.presentation?.kind === "system_notice" ||
comment.authorType === "system"
) {
return "system";
}
if (effectiveAgentId(comment)) return "agent";
if (comment.authorType === "user") return "human";
return "agent";
}
/** Shared bubble-footer time format ("2:34 PM") — also used by the description bubble (PAP-375). */
export function formatTaskChatTimestamp(value: unknown): string | undefined {
if (!value) return undefined;
const d = value instanceof Date ? value : new Date(value as string);
if (Number.isNaN(d.getTime())) return undefined;
return d.toLocaleTimeString([], { hour: "numeric", minute: "2-digit" });
}
/** Keep every comment footer on the same compact, user-visible timestamp. */
export function formatTaskChatCommentTimestamp(
comment: IssueChatComment,
_kind: TaskChatAuthorKind,
): string | undefined {
return formatTaskChatTimestamp(comment.createdAt);
}
export function commentsToTaskChatItems(
comments: IssueChatComment[],
ctx: TaskChatAdapterContext = {},
): TaskChatItem[] {
const items: TaskChatItem[] = [];
for (const comment of comments) {
if (comment.deletedAt) continue;
if (comment.conversationSessionGeneration != null) {
items.push({ id: comment.id, kind: "marker", variant: "session_start", label: "New session",
detail: "Earlier messages and files are still available.", createdAtIso: new Date(comment.createdAt).toISOString() });
continue;
}
const kind = authorKind(comment);
let authorName: string | undefined;
let agentIcon: string | null | undefined;
let onBehalfOfUserName: string | undefined;
const humanAuthor = kind === "human" ? resolveIssueChatHumanAuthor({
authorUserId: comment.authorUserId,
authorName: comment.authorUserId ? ctx.userLabelMap?.get(comment.authorUserId) : null,
currentUserId: ctx.currentUserId,
userProfileMap: ctx.userProfileMap,
}) : undefined;
if (kind === "agent") {
const agentId = effectiveAgentId(comment);
authorName = (agentId && ctx.agentMap?.get(agentId)?.name) || "Agent";
agentIcon = agentId ? ctx.agentMap?.get(agentId)?.icon : undefined;
onBehalfOfUserName = resolveCommentAttribution({
authorAgentId: agentId,
onBehalfOfUserId: comment.onBehalfOfUserId ?? null,
issueAssigneeAgentId: ctx.issueAssigneeAgentId,
resolveUserLabel: (userId) => ctx.userLabelMap?.get(userId),
})?.userName;
} else if (kind === "human") {
authorName = humanAuthor!.authorName;
}
const queued = comment.queueState === "queued" || comment.clientStatus === "queued";
const optimistic =
queued
? "queued"
: comment.clientStatus === "pending"
? "pending"
: undefined;
const createdAtIso =
comment.createdAt instanceof Date
? comment.createdAt.toISOString()
: comment.createdAt
? String(comment.createdAt)
: undefined;
// Durable run-authored comments already carry their source run directly.
// Activity-derived `runId` is a useful fallback for older rows, but it may
// arrive later (or be omitted entirely for server-materialized final
// replies). Prefer the stored provenance so settled-response decorations
// such as verification caveats are never lost.
const sourceRunId = comment.createdByRunId
?? comment.runId
?? comment.derivedCreatedByRunId
?? null;
items.push({
id: comment.id || comment.clientId || `${comment.createdAt}`,
renderKey: comment.clientId ?? comment.id,
kind: "message",
author: kind,
authorName,
...(humanAuthor ? {
authorUserId: comment.authorUserId,
authorAvatarUrl: humanAuthor.avatarUrl,
isCurrentUser: humanAuthor.isCurrentUser,
} : {}),
agent: effectiveAgentId(comment) ? ctx.agentMap?.get(effectiveAgentId(comment)!) ?? { id: effectiveAgentId(comment)! } : undefined,
text: comment.body,
origin: comment.origin ?? "comment",
chatMessage: comment.metadata?.chatMessage,
sourceChannel: kind === "human" ? comment.metadata?.sourceChannel : undefined,
timestamp: formatTaskChatCommentTimestamp(comment, kind),
optimistic,
queueTargetRunId: queued ? comment.queueTargetRunId ?? null : null,
verificationCaveats: sourceRunId
? ctx.verificationCaveatsByRunId?.get(sourceRunId)
: undefined,
agentIcon,
onBehalfOfUserName,
...(kind === "agent" && sourceRunId ? { sourceRunId } : {}),
// System notices carry their structured hints through to the render
// layer (PAP-443); other authors keep the item lean.
presentation: kind === "system" ? comment.presentation ?? null : undefined,
metadata: kind === "system" ? comment.metadata ?? null : undefined,
runAgentId: kind === "system" ? comment.runAgentId ?? null : undefined,
createdAtIso,
});
}
return items;
}