mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-12 18:06:11 +02:00
## Thinking Path > - Paperclip helps people manage AI agents and their tasks. > - The dashboard shows recent agent activity in compact cards. > - Those cards use run records, so two runs for one task can create duplicate task cards. > - An operator needs to see each task once when scanning the dashboard. > - This pull request selects one run per linked task before it applies the card limit. > - The live runs page still shows each run for run inspection. ## Linked Issues or Issue Description **What happened?** The dashboard showed the same task in two agent cards when that task had both an active run and a completed run. **Expected behavior** The dashboard should show a linked task at most once. It should keep the active run card when one is present. **Steps to reproduce** 1. Start an agent run for a task that already has a completed run. 2. Open the company dashboard. 3. Observe two cards linked to the same task. **Paperclip version or commit** Reproduced on the pre-change master at `8b4aa0692`. **Deployment mode** Local dev, built from source. The bug is in the core dashboard UI and does not depend on an agent adapter or database mode. ## What Changed - Select distinct linked tasks from capped active and recent run samples before applying the dashboard card limit. - Keep separate cards for runs without a linked task. - Preserve the dashboard's count of additional distinct cards behind the live-runs link. - Add UI and embedded Postgres regression tests for duplicate runs and document the dashboard rule. - Give the existing multi-request cross-tenant authorization test enough time on loaded CI runners. ## Verification - `pnpm --filter @paperclipai/ui exec vitest run src/components/ActiveAgentsPanel.test.tsx` - `pnpm --filter @paperclipai/ui exec vitest run src/api/heartbeats.test.ts` - `pnpm exec vitest run server/src/__tests__/dashboard-service.test.ts server/src/__tests__/agent-live-run-routes.test.ts` - `pnpm exec vitest run server/src/__tests__/agent-cross-tenant-authz-routes.test.ts` - `pnpm --filter @paperclipai/ui typecheck` - `pnpm --filter @paperclipai/server typecheck` - `pnpm --filter @paperclipai/ui build` - `pnpm -r typecheck` - `pnpm build` - `pnpm check:token-gates` - Review the dashboard with an active and a completed run on the same task. Confirm that it shows one card. Open Live agent runs to inspect both run records. ## Risks - A very high volume of recent runs for one task can fill the capped sample and leave older tasks off the dashboard. The Live runs page remains available for full run inspection. - The dashboard may fetch up to 50 distinct run representatives to preserve its overflow count. The default run API response and persisted data are unchanged. > 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 - OpenAI Codex, GPT-6. The runtime does not expose the exact model ID or context window size to this task. The model used reasoning, tool calls, 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 - [x] All Paperclip CI gates are green - [x] Greptile is 5/5 with no open P2s, recommendations, or follow-ups - [x] I will address all Greptile and reviewer comments before requesting merge --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
278 lines
9.4 KiB
TypeScript
278 lines
9.4 KiB
TypeScript
import { randomUUID } from "node:crypto";
|
|
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
|
|
import { agents, companies, createDb, heartbeatRuns } from "@paperclipai/db";
|
|
import {
|
|
getEmbeddedPostgresTestSupport,
|
|
startEmbeddedPostgresTestDatabase,
|
|
} from "./helpers/embedded-postgres.js";
|
|
import { dashboardService, getUtcMonthStart } from "../services/dashboard.ts";
|
|
import { selectDashboardRunIds } from "../services/dashboard-run-selection.ts";
|
|
|
|
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
|
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
|
|
|
if (!embeddedPostgresSupport.supported) {
|
|
console.warn(
|
|
`Skipping embedded Postgres dashboard service tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
);
|
|
}
|
|
|
|
function utcDay(offsetDays: number): Date {
|
|
const now = new Date();
|
|
const day = Date.UTC(now.getUTCFullYear(), now.getUTCMonth(), now.getUTCDate() + offsetDays, 12);
|
|
return new Date(day);
|
|
}
|
|
|
|
function utcDateKey(date: Date): string {
|
|
return date.toISOString().slice(0, 10);
|
|
}
|
|
|
|
describe("getUtcMonthStart", () => {
|
|
it("anchors the monthly spend window to UTC month boundaries", () => {
|
|
expect(getUtcMonthStart(new Date("2026-03-31T20:30:00.000-05:00")).toISOString()).toBe(
|
|
"2026-04-01T00:00:00.000Z",
|
|
);
|
|
expect(getUtcMonthStart(new Date("2026-04-01T00:30:00.000+14:00")).toISOString()).toBe(
|
|
"2026-03-01T00:00:00.000Z",
|
|
);
|
|
});
|
|
});
|
|
|
|
describeEmbeddedPostgres("dashboard service", () => {
|
|
let db!: ReturnType<typeof createDb>;
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
|
|
|
beforeAll(async () => {
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-dashboard-service-");
|
|
db = createDb(tempDb.connectionString);
|
|
}, 20_000);
|
|
|
|
afterEach(async () => {
|
|
await db.delete(heartbeatRuns);
|
|
await db.delete(agents);
|
|
await db.delete(companies);
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await tempDb?.cleanup();
|
|
});
|
|
|
|
it("selects distinct task cards before limiting and keeps taskless runs separate", async () => {
|
|
const companyId = randomUUID();
|
|
const otherCompanyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const otherAgentId = randomUUID();
|
|
const repeatedIssueId = randomUUID();
|
|
const otherIssueId = randomUUID();
|
|
const activeRunId = randomUUID();
|
|
const otherTaskRunId = randomUUID();
|
|
const tasklessRunId = randomUUID();
|
|
|
|
await db.insert(companies).values([
|
|
{ id: companyId, name: "Dashboard cards", issuePrefix: "CARDS" },
|
|
{ id: otherCompanyId, name: "Other company", issuePrefix: "OTHER" },
|
|
]);
|
|
await db.insert(agents).values([
|
|
{ id: agentId, companyId, name: "Builder", role: "engineer", adapterType: "codex_local", adapterConfig: {}, runtimeConfig: {}, permissions: {} },
|
|
{ id: otherAgentId, companyId: otherCompanyId, name: "Other", role: "engineer", adapterType: "codex_local", adapterConfig: {}, runtimeConfig: {}, permissions: {} },
|
|
]);
|
|
await db.insert(heartbeatRuns).values([
|
|
...Array.from({ length: 6 }, (_, index) => ({
|
|
id: randomUUID(), companyId, agentId, status: "succeeded",
|
|
contextSnapshot: { issueId: repeatedIssueId },
|
|
createdAt: new Date(`2026-04-10T10:0${index}:00.000Z`),
|
|
})),
|
|
{ id: activeRunId, companyId, agentId, status: "running", contextSnapshot: { issueId: repeatedIssueId }, createdAt: new Date("2026-04-10T08:00:00.000Z") },
|
|
{ id: otherTaskRunId, companyId, agentId, status: "succeeded", contextSnapshot: { issueId: otherIssueId }, createdAt: new Date("2026-04-10T09:04:00.000Z") },
|
|
{ id: tasklessRunId, companyId, agentId, status: "succeeded", createdAt: new Date("2026-04-10T09:03:00.000Z") },
|
|
{ id: randomUUID(), companyId: otherCompanyId, agentId: otherAgentId, status: "running", contextSnapshot: { issueId: otherIssueId }, createdAt: new Date("2026-04-10T11:00:00.000Z") },
|
|
]);
|
|
|
|
expect(await selectDashboardRunIds(db, companyId, 3)).toEqual([
|
|
activeRunId, otherTaskRunId, tasklessRunId,
|
|
]);
|
|
});
|
|
|
|
it("aggregates the full 14-day run activity window without recent-run truncation", async () => {
|
|
const companyId = randomUUID();
|
|
const otherCompanyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const otherAgentId = randomUUID();
|
|
const today = utcDay(0);
|
|
const weekAgo = utcDay(-7);
|
|
|
|
await db.insert(companies).values([
|
|
{
|
|
id: companyId,
|
|
name: "Paperclip",
|
|
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
requireBoardApprovalForNewAgents: false,
|
|
},
|
|
{
|
|
id: otherCompanyId,
|
|
name: "Other",
|
|
issuePrefix: `T${otherCompanyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
requireBoardApprovalForNewAgents: false,
|
|
},
|
|
]);
|
|
|
|
await db.insert(agents).values([
|
|
{
|
|
id: agentId,
|
|
companyId,
|
|
name: "CodexCoder",
|
|
role: "engineer",
|
|
status: "running",
|
|
adapterType: "codex_local",
|
|
adapterConfig: {},
|
|
runtimeConfig: {},
|
|
permissions: {},
|
|
},
|
|
{
|
|
id: otherAgentId,
|
|
companyId: otherCompanyId,
|
|
name: "OtherAgent",
|
|
role: "engineer",
|
|
status: "running",
|
|
adapterType: "codex_local",
|
|
adapterConfig: {},
|
|
runtimeConfig: {},
|
|
permissions: {},
|
|
},
|
|
]);
|
|
|
|
await db.insert(heartbeatRuns).values([
|
|
...Array.from({ length: 105 }, () => ({
|
|
id: randomUUID(),
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
status: "succeeded",
|
|
createdAt: today,
|
|
})),
|
|
{
|
|
id: randomUUID(),
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
status: "failed",
|
|
createdAt: weekAgo,
|
|
},
|
|
{
|
|
id: randomUUID(),
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
status: "timed_out",
|
|
createdAt: weekAgo,
|
|
},
|
|
{
|
|
id: randomUUID(),
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
status: "cancelled",
|
|
createdAt: weekAgo,
|
|
},
|
|
{
|
|
id: randomUUID(),
|
|
companyId: otherCompanyId,
|
|
agentId: otherAgentId,
|
|
invocationSource: "assignment",
|
|
status: "succeeded",
|
|
createdAt: weekAgo,
|
|
},
|
|
]);
|
|
|
|
const summary = await dashboardService(db).summary(companyId);
|
|
|
|
expect(summary.runActivity).toHaveLength(14);
|
|
const todayBucket = summary.runActivity.find((bucket) => bucket.date === utcDateKey(today));
|
|
const weekAgoBucket = summary.runActivity.find((bucket) => bucket.date === utcDateKey(weekAgo));
|
|
|
|
expect(todayBucket).toMatchObject({
|
|
succeeded: 105,
|
|
failed: 0,
|
|
recovered: 0,
|
|
other: 0,
|
|
total: 105,
|
|
failedByErrorCode: {},
|
|
});
|
|
expect(weekAgoBucket).toMatchObject({
|
|
succeeded: 0,
|
|
failed: 2,
|
|
recovered: 0,
|
|
other: 1,
|
|
total: 3,
|
|
// failed + timed_out with no error code both bucket under "unknown"
|
|
failedByErrorCode: { unknown: 2 },
|
|
});
|
|
});
|
|
|
|
it("separates recovered restart kills from true failures and breaks failures down by error code", async () => {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const day = utcDay(-2);
|
|
|
|
await db.insert(companies).values({
|
|
id: companyId,
|
|
name: "Paperclip",
|
|
issuePrefix: `T${companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
requireBoardApprovalForNewAgents: false,
|
|
});
|
|
|
|
await db.insert(agents).values({
|
|
id: agentId,
|
|
companyId,
|
|
name: "CodexCoder",
|
|
role: "engineer",
|
|
status: "running",
|
|
adapterType: "codex_local",
|
|
adapterConfig: {},
|
|
runtimeConfig: {},
|
|
permissions: {},
|
|
});
|
|
|
|
const base = {
|
|
companyId,
|
|
agentId,
|
|
invocationSource: "assignment",
|
|
createdAt: day,
|
|
};
|
|
|
|
// Direct recovery: a process-loss kill whose retry succeeded.
|
|
const original = randomUUID();
|
|
const retry = randomUUID();
|
|
// Chained recovery: kill -> failed retry -> succeeded retry (both kills recovered).
|
|
const chainedOriginal = randomUUID();
|
|
const chainedRetry = randomUUID();
|
|
const chainedRetrySuccess = randomUUID();
|
|
// A genuine, unrecovered failure that should remain in the failed count.
|
|
const trueFailure = randomUUID();
|
|
|
|
await db.insert(heartbeatRuns).values([
|
|
{ ...base, id: original, status: "failed", errorCode: "process_lost" },
|
|
{ ...base, id: retry, status: "succeeded", retryOfRunId: original },
|
|
{ ...base, id: chainedOriginal, status: "failed", errorCode: "process_lost" },
|
|
{ ...base, id: chainedRetry, status: "failed", errorCode: "process_lost", retryOfRunId: chainedOriginal },
|
|
{ ...base, id: chainedRetrySuccess, status: "succeeded", retryOfRunId: chainedRetry },
|
|
{ ...base, id: trueFailure, status: "failed", errorCode: "provider_quota" },
|
|
]);
|
|
|
|
const summary = await dashboardService(db).summary(companyId);
|
|
const bucket = summary.runActivity.find((b) => b.date === utcDateKey(day));
|
|
|
|
expect(bucket).toMatchObject({
|
|
succeeded: 2,
|
|
// original + chainedOriginal + chainedRetry all recovered via a later success
|
|
recovered: 3,
|
|
failed: 1,
|
|
other: 0,
|
|
total: 6,
|
|
failedByErrorCode: { provider_quota: 1 },
|
|
});
|
|
// process_lost kills that recovered must not leak into the failed breakdown.
|
|
expect(bucket?.failedByErrorCode.process_lost).toBeUndefined();
|
|
});
|
|
});
|