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 > - Agents call tools from connected apps through the Paperclip MCP gateway > - Some tool calls take a long time: exports, builds, large searches > - The MCP progress utility lets an app report how far a call is, but Paperclip ignored it > - So the task chat showed only a spinner until the call finished, with no sign of life > - This pull request reads the app's progress and shows it on the tool's row while the call runs > - The benefit is that people can see that a long call is working, how far it is, and how long it has run ## Linked Issues or Issue Description **Subsystem affected** Connected apps (MCP gateway) and the task chat. **Problem or motivation** A long tool call from a connected MCP app shows only a spinner in the task chat. Paperclip does not send a `progressToken`, and it drops `notifications/progress` from the app. **Proposed solution** Send a `progressToken` on each `tools/call` that an agent run makes. Read the app's progress notifications from the call's response stream. Show a progress bar (or an indeterminate sweep), the latest message, and elapsed time on the running tool row. Keep the latest state so that a reload mid-call shows it. **Alternatives considered** A new transport for progress. The existing company live-events socket already carries per-run events with run read checks, so this change uses it. **Additional context** Spec: https://modelcontextprotocol.io/specification/2026-07-28/basic/utilities/progress ## What Changed - `mcp-http.ts`: `mcpHttpRequestInit` can add `_meta.progressToken`. `readMcpHttpResponse` gives each notification on the response stream to an observer before the result. The observer cannot fail or delay the call. New `mcpProgressNotificationOf` matches a notification to its token. - `tool-gateway.ts`: remote HTTP and local stdio `tools/call` from an agent run send a per-call token and forward progress to a reporter. Calls without a run send no token. - New `server/src/services/tool-call-progress.ts`: checks each update (finite, increasing, plain single-line text of at most 200 characters). It publishes a `heartbeat.run.tool_progress` live event at most every 250 ms (latest wins) and saves the latest update on the invocation at most every 1 s. Nothing is awaited by the call. A final `done` event goes out when the call ends. - DB: nullable `tool_invocations.progress` jsonb column (migration `0479`, `ADD COLUMN` only). A save never writes onto a finished call. - Live delivery: the new event follows its run like transcript output. A client gets it only for runs it follows, after the run read check, in the run's company only. - New route `GET /api/issues/:issueId/tool-call-progress` (task read check) returns the latest progress of the task's running calls, for a reload mid-call. Documented in `docs/api/issues.md`. - UI: `ToolCallProgressProvider` (one per chat) keeps the latest update per call. A running tool row subscribes and shows a bar or sweep, the message, the percent and elapsed time (design tokens, reduced motion honored). Finished rows drop it and never fetch or re-render for progress. `LiveUpdatesProvider` ignores the event for query invalidation. - `packages/kv-demo-mcp-server`: new `slow_with_progress` demo tool (`steps`, `stepMs`, `withTotal`) in its own file. - Storybook: `Tasks/Tool progress` stories (running with total, running without total, done). - Docs: new `doc/connections/MCP-PROGRESS.md`; `MCP-PROTOCOL-VERSIONS.md` no longer lists progress as unsupported. ## Verification - Red/green: on the original source, 5 of the new server tests fail (token in `_meta`, SSE with interleaved progress and result, notification matching, run-interest delivery, gateway end-to-end). With this change they pass. - `server/src/__tests__/mcp-http.test.ts` (13), `tool-call-progress.test.ts` (9: throttling, latest wins, bounded text, out-of-order drop, finish, failures never throw, company/run/tool scoping), `tool-call-progress-store.test.ts` (2, embedded Postgres: company and task scoping, no write onto a finished call), `realtime/live-event-delivery.test.ts` (run interest), `tool-gateway.test.ts` end-to-end against the real SDK kv demo server over Streamable HTTP: 6 provider updates over about 1.2 s give 3 to 7 throttled events, all for the right company, run, task and tool, the last one `done`; no event reaches another company; the invocation keeps the progress; the result is unchanged. - UI: `tool-call-progress.test.tsx` (10: name matching, row states, plain-text rendering, drop on complete, restore after reload, no fetch for finished rows). All 67 task-chat test files pass. - `packages/kv-demo-mcp-server`: 13 tests, including progress over HTTP with and without a total. - Storybook: checked the three stories in a browser. The bar fills to 40%, the sweep animates, the elapsed time ticks, and the done row shows no progress. - `pnpm verify`: see the CI checks for the final revision. ## Risks - Low. The migration adds one nullable column. - An SSE response is now bounded per message, not per stream, so handled notifications (such as progress) do not use up the result's size limit. Each message is still bounded. - Progress code runs only while a run's tool call is in flight. It adds a few bytes to the request and throttled, fire-and-forget work. Agent boot and time to first token do not change. - A row finds its call by run and tool name. If one run calls the same tool twice at the same time, both rows show the newer call's progress. - Progress from a call that became an MCP Task is not shown. ## Model Used - Claude Opus 5.5 (`claude-opus-5-5`), Claude Code agent with tool use and code execution. ## 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>
75 lines
4.6 KiB
TypeScript
75 lines
4.6 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import { eq } from "drizzle-orm";
|
|
import { afterAll, beforeAll, describe, expect, it } from "vitest";
|
|
import { agents, companies, createDb, heartbeatRuns, issues, toolInvocations, type Db } from "@paperclipai/db";
|
|
import { listToolCallProgress, saveToolCallProgress } from "../services/tool-call-progress.js";
|
|
import { assignedToolName } from "../services/native-runtime/assigned-mcp-tools.js";
|
|
import { startRecoveryPostgres } from "./helpers/recovery-postgres.js";
|
|
|
|
describe("saved tool call progress", () => {
|
|
let temporary: Awaited<ReturnType<typeof startRecoveryPostgres>>;
|
|
let db: Db;
|
|
|
|
beforeAll(async () => {
|
|
temporary = await startRecoveryPostgres("tool-call-progress-");
|
|
db = createDb(temporary.connectionString);
|
|
}, 120_000);
|
|
afterAll(async () => { await temporary?.cleanup(); });
|
|
|
|
async function task(prefix: string) {
|
|
const companyId = randomUUID();
|
|
const issueId = randomUUID();
|
|
await db.insert(companies).values({ id: companyId, name: prefix, issuePrefix: prefix });
|
|
const [agent] = await db.insert(agents).values({ companyId, name: "Agent", adapterType: "process" }).returning();
|
|
const [run] = await db.insert(heartbeatRuns).values({ companyId, agentId: agent!.id, status: "running" }).returning();
|
|
await db.insert(issues).values({ id: issueId, companyId, title: "Export" });
|
|
const call = async (values: Partial<typeof toolInvocations.$inferInsert> = {}) => (await db.insert(toolInvocations).values({
|
|
companyId, issueId, runId: run!.id, agentId: agent!.id, toolName: "kv_demo__slow_with_progress",
|
|
status: "executing", startedAt: new Date("2026-11-13T10:00:00Z"), ...values,
|
|
}).returning())[0]!;
|
|
return { companyId, issueId, runId: run!.id, call };
|
|
}
|
|
const progress = (value: number) => ({ progress: value, total: 10, message: "Exporting", updatedAt: "2026-11-13T10:00:05.000Z" });
|
|
|
|
it("returns a task's running calls with their latest progress, and nothing from another company or task", async () => {
|
|
const mine = await task("PRGA");
|
|
const theirs = await task("PRGB");
|
|
const running = await mine.call();
|
|
await saveToolCallProgress(db, mine.companyId, running.id)(progress(3));
|
|
await saveToolCallProgress(db, mine.companyId, running.id)(progress(4));
|
|
const other = await theirs.call();
|
|
await saveToolCallProgress(db, theirs.companyId, other.id)(progress(9));
|
|
// A write naming the wrong company never lands.
|
|
await saveToolCallProgress(db, mine.companyId, other.id)(progress(1));
|
|
const now = new Date("2026-11-13T10:01:00Z");
|
|
|
|
expect(await listToolCallProgress(db, mine.companyId, mine.issueId, now)).toEqual([{
|
|
invocationId: running.id, runId: mine.runId, toolName: "kv_demo__slow_with_progress",
|
|
nativeToolName: assignedToolName("kv_demo__slow_with_progress"),
|
|
startedAt: "2026-11-13T10:00:00.000Z", progress: 4, total: 10, message: "Exporting",
|
|
updatedAt: "2026-11-13T10:00:05.000Z", done: false,
|
|
}]);
|
|
expect(await listToolCallProgress(db, mine.companyId, theirs.issueId, now)).toEqual([]);
|
|
expect(await listToolCallProgress(db, theirs.companyId, mine.issueId, now)).toEqual([]);
|
|
expect((await db.select().from(toolInvocations).where(eq(toolInvocations.id, other.id)))[0]!.progress).toMatchObject({ progress: 9 });
|
|
});
|
|
|
|
it("never writes progress onto a finished call, and reports it as done", async () => {
|
|
const mine = await task("PRGC");
|
|
const running = await mine.call({ createdAt: new Date() });
|
|
await saveToolCallProgress(db, mine.companyId, running.id)(progress(2));
|
|
expect(await listToolCallProgress(db, mine.companyId, mine.issueId)).toHaveLength(1);
|
|
await db.update(toolInvocations).set({ status: "succeeded", completedAt: new Date() }).where(eq(toolInvocations.id, running.id));
|
|
// A late, throttled save after the result must not overwrite it.
|
|
await saveToolCallProgress(db, mine.companyId, running.id)(progress(8));
|
|
expect((await db.select().from(toolInvocations).where(eq(toolInvocations.id, running.id)))[0]!.progress).toMatchObject({ progress: 2 });
|
|
// A chat that missed the end learns it; a call that never saved progress is reported too.
|
|
const notSaved = await mine.call({ createdAt: new Date() });
|
|
await db.update(toolInvocations).set({ status: "succeeded", completedAt: new Date() }).where(eq(toolInvocations.id, notSaved.id));
|
|
const listed = await listToolCallProgress(db, mine.companyId, mine.issueId);
|
|
expect(listed.map((entry) => [entry.invocationId, entry.done, entry.progress]).sort()).toEqual(
|
|
[[running.id, true, 2], [notSaved.id, true, 0]].sort(),
|
|
);
|
|
});
|
|
});
|