Files
PaperClipAI/server/src/services/native-runtime/native-continuation.ts
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

97 lines
6.4 KiB
TypeScript

import { isPaperclipExternalChatContractTurn, normalizePaperclipWakePayload, PAPERCLIP_EARLIER_READ_COMMENT_NOTE } from "@paperclipai/adapter-utils/server-utils";
import type { CaseExecutionContext, projectCaseContinuation } from "../case-context.js";
import { caseInstructionAlreadyRepresented } from "../case-context.js";
/** Only new, authorized events belong in an already retained provider conversation.
* Full bootstrap input is kept separately for an actual provider resume failure.
*/
export function buildNativeContinuationPrompt(input: {
wakePayload: unknown;
previousRunId: string;
issue: { title: string; description: string | null };
previousIssue: { title: string; description: string | null };
/** The constructor opts complete plain-text chat batches into the resume protocol. */
allowExternalChat?: boolean;
caseContext?: CaseExecutionContext | null;
workflowCase?: ReturnType<typeof projectCaseContinuation>;
previousGitHubReviewConfigurationKeys?: readonly string[];
}): string | null {
const wake = normalizePaperclipWakePayload(input.wakePayload);
const continuation = wake?.executionContinuation;
const delta = continuation?.resumeDelta;
if (!wake || !delta || delta.baseRunId !== input.previousRunId) return null;
if (input.caseContext && !input.workflowCase) return null;
const rawWake = input.wakePayload && typeof input.wakePayload === "object"
? input.wakePayload as Record<string, unknown> : {};
// Attachment descriptors are intentionally omitted by the generic normalizer.
// Retain the complete bootstrap framing whenever current input needs them or
// an omission notice. The compact path never guesses an unavailable file.
const hasAttachmentContext =
(rawWake.attachmentOmissions != null &&
(!Array.isArray(rawWake.attachmentOmissions) || rawWake.attachmentOmissions.length > 0)) ||
(Array.isArray(rawWake.comments) && rawWake.comments.some((comment) =>
comment && typeof comment === "object" &&
(comment as Record<string, unknown>).attachments != null &&
(!Array.isArray((comment as Record<string, unknown>).attachments) ||
((comment as Record<string, unknown>).attachments as unknown[]).length > 0)));
const externalChat = input.allowExternalChat === true &&
(wake.externalChatProvider === "slack" || wake.externalChatProvider === "github") &&
isPaperclipExternalChatContractTurn(input.wakePayload) &&
!hasAttachmentContext && wake.commentIds.length > 0 &&
wake.latestCommentId === wake.commentIds.at(-1) &&
new Set(wake.commentIds).size === wake.commentIds.length &&
wake.commentIds.every((id) => {
const comments = wake.comments.filter((entry) => entry.id === id);
const messages = delta.messages.filter((entry) => entry.id === id);
return comments.length === 1 && messages.length === 1 &&
messages[0]!.body === comments[0]!.body &&
messages[0]!.authorType === comments[0]!.authorType &&
messages[0]!.authorId === comments[0]!.authorId;
});
const caseHandoff = wake.reason === "case_handoff" && !!input.workflowCase && !!input.caseContext?.incomingHandoff;
// Other provider, attachment, question, approval, and recovery paths keep
// their specialized framing. A matching prior run still gates every delta.
if (rawWake.chatCompletionUpdates || (wake.externalChatProvider && !externalChat) ||
(!['issue_commented', 'issue_children_completed'].includes(wake.reason ?? '') && !caseHandoff &&
!(externalChat && wake.reason === "External chat message received")) ||
wake.fallbackFetchNeeded || wake.truncated || wake.recovery || continuation?.interruptedRunId ||
(wake.externalChatExecutionBound && !externalChat) || wake.externalChatQuestionResponse ||
wake.taskWatchdog || wake.livenessContinuation || wake.activeTreeHold ||
wake.skillTest || wake.executionStage || wake.agentMessage ||
wake.documentReviewContext || wake.planReviewContext || wake.annotationDeltas.length > 0
) return null;
const taskChanges = Object.fromEntries(
(["title", "description"] as const)
.filter((key) => input.issue[key] !== input.previousIssue[key])
.map((key) => [key, input.issue[key]]),
);
const humanResponses = (continuation?.humanResponses ?? []).filter((answer) => answer.id === wake.interactionId);
// Do not substitute an unverified interaction outcome for an authorized answer.
if (wake.interactionId && humanResponses.length === 0) return null;
const events = {
...(wake.githubReviewConfigurations.some((config) => !input.previousGitHubReviewConfigurationKeys?.includes(config.key))
? { reviewConfigurations: wake.githubReviewConfigurations.filter((config) => !input.previousGitHubReviewConfigurationKeys?.includes(config.key)) }
: {}),
// Only the current authenticated chat delivery belongs to this turn.
// The generic delta can also include edited historical comments or an old
// agent response; neither becomes a new provider instruction.
messages: externalChat
? wake.commentIds.map((id) => delta.messages.find((message) => message.id === id)!)
: delta.messages.filter(message => !input.workflowCase || !caseInstructionAlreadyRepresented(input.caseContext, message)),
...(input.workflowCase ? { workflowCase: input.workflowCase } : {}),
...(humanResponses.length ? { humanResponses } : {}),
...(Object.keys(taskChanges).length ? { taskChanges } : {}),
...(wake.childIssueSummaries.length ? { childResults: wake.childIssueSummaries } : {}),
...(wake.childIssueSummaryTruncated ? { childResultsTruncated: true } : {}),
...(wake.unresolvedBlockerIssueIds.length ? { unresolvedBlockerIssueIds: wake.unresolvedBlockerIssueIds } : {}),
// Server-rendered "App context (untrusted)" from the task's MCP Apps widgets:
// a resumed turn sees the current selection as well as the new comment.
...(typeof rawWake.mcpAppContext === "string" && rawWake.mcpAppContext.trim() ? { appContext: rawWake.mcpAppContext.trim() } : {}),
};
const earlierRead = wake.comments.filter((comment) => comment.readByEarlierTurn && comment.id
&& events.messages.some((message) => message.id === comment.id)).map((comment) => comment.id!);
if (earlierRead.length > 0) Object.assign(events, { readByEarlierTurn: { messageIds: earlierRead, note: PAPERCLIP_EARLIER_READ_COMMENT_NOTE } });
if (!events.messages.length && !humanResponses.length && !wake.childIssueSummaries.length && !Object.keys(taskChanges).length && !input.workflowCase) return null;
return JSON.stringify(events);
}