Files
PaperClipAI/ui/src/components/task-chat/TaskChatToolCard.tsx
T
DottaandClaude Opus 5.5 8af889f612 feat(mcp-apps): view messages with consent, app context, full screen and provider tool icons (#21266)
## 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>
2026-11-13 07:32:48 -06:00

171 lines
6.9 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
import { useTaskChatExpansion } from "./expansion-state";
import { cn } from "@/lib/utils";
import {
Check,
ChevronRight,
Loader2,
ShieldCheck,
ShieldX,
X,
} from "lucide-react";
import type { TaskChatToolItem } from "./task-chat-model";
import { toolTaxonomy } from "./tool-taxonomy";
import { useTaskChatShimmer } from "./TaskChatShimmer";
import { TaskChatDiffCounts, TaskChatDiffView } from "./TaskChatDiffView";
import { useTaskReferenceLabel, withTaskReference } from "./task-reference";
import { ProviderToolIcon, useProviderToolIcons } from "@/components/ProviderToolIcon";
const STATUS_ICON = {
pending: { Icon: Loader2, spin: false, tone: "text-muted-foreground" },
in_progress: {
Icon: Loader2,
spin: true,
tone: "text-(--status-agent-running)",
},
completed: { Icon: Check, spin: false, tone: "text-muted-foreground" },
failed: { Icon: X, spin: false, tone: "text-destructive" },
interrupted: { Icon: X, spin: false, tone: "text-muted-foreground" },
} as const;
function ToolTarget({ text }: { text: string }) {
return (
<span className="task-chat-collapsed-line-fade min-w-0 flex-1 font-mono text-(length:--text-micro) leading-4">
{text}
</span>
);
}
/** Names the task a call is about by identifier; its UUID is never shown. */
function TaskReferenceToolTarget({ taskRefId, target }: { taskRefId: string; target?: string }) {
const taskLabel = useTaskReferenceLabel(taskRefId);
return <ToolTarget text={withTaskReference(target, taskLabel)!} />;
}
/**
* Tool invocation as a flat activity row (v7): [glyph] [name] [mono target] …
* [hover chevron] [status]. No card chrome — activity is metadata, not
* content. Clicking toggles a compact result/change summary (left-rail
* inset). An edit row carries its `+N −M` counts and opens to a compact,
* height-capped diff of that one edit.
*/
export function TaskChatToolCard({ item }: { item: TaskChatToolItem }) {
const { Icon, spin, tone } = STATUS_ICON[item.status];
const shimmer = useTaskChatShimmer(item.id);
const RowIcon = toolTaxonomy(item.rawName ?? item.name).icon;
const providerIcons = useProviderToolIcons(item.rawName ?? item.name);
const [showDetail, setShowDetail] = useTaskChatExpansion(item.id, false);
const expandable = Boolean(item.target || item.detail || item.diff);
return (
<div data-testid="task-chat-tool-card" className="flex min-w-0 max-w-full flex-col text-xs">
<button
type="button"
onClick={expandable ? () => setShowDetail((v) => !v) : undefined}
aria-expanded={expandable ? showDetail : undefined}
className={cn(
"group/tool -mx-1.5 flex min-h-6 w-full min-w-0 max-w-full items-center gap-2 overflow-hidden rounded-sm px-1.5 py-1 text-left leading-none text-muted-foreground",
expandable
? "cursor-pointer transition-colors hover:bg-muted/60 hover:text-foreground"
: "cursor-default",
)}
>
<span className="flex w-5 shrink-0 items-center justify-center">
<ProviderToolIcon
icons={providerIcons}
fallback={RowIcon}
className="h-3.5 w-3.5 shrink-0"
testId="task-chat-tool-icon"
/>
</span>
<span data-conversation-tool-running={item.status === "in_progress" && shimmer ? "true" : undefined} className="flex min-w-0 flex-1 items-baseline gap-2 overflow-hidden">
<span className="shrink-0 font-medium leading-4">{item.name}</span>
{item.taskRefId ? (
<TaskReferenceToolTarget taskRefId={item.taskRefId} target={item.target} />
) : item.target ? (
<ToolTarget text={item.target} />
) : null}
</span>
<span className="ml-auto flex shrink-0 items-center gap-2">
{item.diff && (item.diff.added > 0 || item.diff.removed > 0) ? (
<TaskChatDiffCounts
added={item.diff.added}
removed={item.diff.removed}
className="text-(length:--text-micro)"
/>
) : null}
{item.decision ? (
<span
className={cn(
"flex items-center gap-1 text-(length:--text-micro)",
item.decision === "allowed"
? "text-(--status-task-icon-done)"
: "text-destructive",
)}
>
{item.decision === "allowed" ? (
<ShieldCheck className="h-3 w-3" />
) : (
<ShieldX className="h-3 w-3" />
)}
{item.decision}
</span>
) : null}
{expandable ? (
<ChevronRight
className={cn(
"h-3 w-3 opacity-0 transition-[opacity,transform] group-hover/tool:opacity-80",
showDetail ? "rotate-90" : null,
)}
aria-hidden
/>
) : null}
<Icon
className={cn("h-3.5 w-3.5", tone, spin && "animate-spin")}
aria-hidden
/>
{item.status === "interrupted" ? (
<span className="text-(length:--text-micro) text-muted-foreground">
Interrupted
</span>
) : null}
</span>
</button>
{item.target && showDetail && !item.diff?.lines?.length ? (
<div
className="task-chat-expanded-line-wrap ml-1.5 mt-0.5 min-w-0 max-w-full overflow-hidden border-l-2 border-border py-1 pl-2.5 font-mono text-(length:--text-micro) leading-relaxed text-muted-foreground"
data-testid="task-chat-tool-target-detail"
>
{item.target}
</div>
) : null}
{item.detail && showDetail ? (
<pre className="task-chat-expanded-line-wrap ml-1.5 mt-0.5 min-w-0 max-w-full overflow-hidden whitespace-pre-wrap border-l-2 border-border py-1 pl-2.5 font-mono text-(length:--text-micro) leading-relaxed text-muted-foreground">
{item.detail}
</pre>
) : null}
{item.diff && showDetail ? (
item.diff.lines && item.diff.lines.length > 0 ? (
<div className="ml-1.5 mt-1 min-w-0 max-w-full" data-testid="task-chat-tool-diff">
<TaskChatDiffView lines={item.diff.lines} truncated={item.diff.truncated} />
</div>
) : (
<div
className="ml-1.5 mt-0.5 border-l-2 border-border py-1 pl-2.5"
data-testid="task-chat-tool-change-summary"
>
<div className="flex min-w-0 items-center gap-2 text-(length:--text-micro) text-muted-foreground">
<span className="shrink-0">Changed</span>
{item.diff.path ? (
<span className="min-w-0 truncate font-mono text-foreground">
{item.diff.path}
</span>
) : null}
<TaskChatDiffCounts added={item.diff.added} removed={item.diff.removed} className="ml-auto" />
</div>
</div>
)
) : null}
</div>
);
}