mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-10-28 20:21:50 +01:00
## Thinking Path
> - Paperclip is the open source app people use to manage AI agents for
work
> - The dashboard success rate counts recovered runs as successes
> - A run is recovered when a later retry in its chain succeeds
> - The summary puts `failed` and `timed_out` into recovered
> - An `interrupted` run, including `server_shutdown_interrupted`, falls
through to other
> - The success rate stays down after the retry succeeds
> - This pull request counts a recovered interrupt in recovered, not in
other
> - The benefit is that a shutdown that was retried successfully no
longer looks like a failed day
## Linked Issues or Issue Description
No open issue covers this. I searched open and closed issues and pull
requests.
**What happened?**
`dashboardService.summary` puts only `failed` and `timed_out` into the
recovered bucket. An `interrupted` run, including
`server_shutdown_interrupted`, goes to other even when `recovered` is
set. The success rate uses `succeeded + recovered`, so the day stays low
after a successful retry.
**Expected behavior**
When the recovered flag is set, count `interrupted` in recovered. An
interrupt with no successful retry stays in other.
**Steps to reproduce**
1. Record an interrupted run with error code
`server_shutdown_interrupted`.
2. Record a succeeded retry of that run.
3. Open the dashboard summary for that day.
4. Observe that the interrupt is in other and the success rate does not
include it.
**Paperclip version or commit**
master at 215586d127
**Deployment mode**
Local dev (pnpm dev)
## What Changed
- When a run is recovered, count status `interrupted` in the recovered
bucket.
- Leave an unrecovered interrupt in other.
- Add a service test for a recovered shutdown and a stranded shutdown.
## Verification
- `pnpm exec vitest run src/__tests__/dashboard-service.test.ts --config
vitest.config.ts` in `server`
- Result: 1 file passed, 5 tests passed
## Risks
- Low risk. Unrecovered interrupts stay in other. Failed and timed-out
runs keep the same buckets.
## Model Used
- No model runtime is part of this change.
## 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
- [ ] 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
328 lines
11 KiB
TypeScript
328 lines
11 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();
|
|
});
|
|
|
|
it("counts a recovered shutdown interrupt toward recovered, not other", async () => {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const day = utcDay(-1);
|
|
const shutdown = randomUUID();
|
|
const shutdownRetry = randomUUID();
|
|
const stranded = randomUUID();
|
|
|
|
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" as const,
|
|
createdAt: day,
|
|
};
|
|
await db.insert(heartbeatRuns).values([
|
|
{ ...base, id: shutdown, status: "interrupted", errorCode: "server_shutdown_interrupted" },
|
|
{ ...base, id: shutdownRetry, status: "succeeded", retryOfRunId: shutdown },
|
|
{ ...base, id: stranded, status: "interrupted", errorCode: "server_shutdown_interrupted" },
|
|
]);
|
|
|
|
const summary = await dashboardService(db).summary(companyId);
|
|
const bucket = summary.runActivity.find((entry) => entry.date === utcDateKey(day));
|
|
expect(bucket).toMatchObject({
|
|
succeeded: 1,
|
|
recovered: 1,
|
|
failed: 0,
|
|
other: 1,
|
|
total: 3,
|
|
failedByErrorCode: {},
|
|
});
|
|
});
|
|
});
|