mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-15 02:20:38 +09:00
## Thinking Path > - Paperclip orchestrates AI agents through issue checkout, heartbeat runs, routines, and auditable control-plane state > - The runtime path has to recover from lost local processes, transient adapter failures, blocked dependencies, and routine coalescing without stranding work > - The existing branch carried several reliability fixes across heartbeat scheduling, issue runtime controls, routine dispatch, and operator-facing run state > - These changes belong together because they share backend contracts, migrations, and runtime status semantics > - This pull request groups the control-plane/runtime slice so it can merge independently from board UI polish and adapter sandbox work > - The benefit is safer heartbeat recovery, clearer runtime controls, and more predictable recurring execution behavior ## What Changed - Adds bounded heartbeat retry scheduling, scheduled retry state, and Codex transient failure recovery handling. - Tightens heartbeat process recovery, blocker wake behavior, issue comment wake handling, routine dispatch coalescing, and activity/dashboard bounds. - Adds runtime-control MCP tools and Paperclip skill docs for issue workspace runtime management. - Adds migrations `0061_lively_thor_girl.sql` and `0062_routine_run_dispatch_fingerprint.sql`. - Surfaces retry state in run ledger/agent UI and keeps related shared types synchronized. ## Verification - `pnpm exec vitest run server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/routines-service.test.ts` - `pnpm exec vitest run src/tools.test.ts` from `packages/mcp-server` ## Risks - Medium risk: this touches heartbeat recovery and routine dispatch, which are central execution paths. - Migration order matters if split branches land out of order: merge this PR before branches that assume the new runtime/routine fields. - Runtime retry behavior should be watched in CI and in local operator smoke tests because it changes how transient failures are resumed. > 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-5-based coding agent runtime, shell/git tool use enabled. Exact hosted model build and context window are not exposed in this Paperclip heartbeat environment. ## 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 run tests locally and they pass - [x] I have added or updated tests where applicable - [ ] If this change affects the UI, I have included before/after screenshots - [x] I have updated relevant documentation to reflect my changes - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge
169 lines
4.8 KiB
TypeScript
169 lines
4.8 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";
|
|
|
|
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: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
);
|
|
}
|
|
|
|
function utcDay(offsetDays: number): Date {
|
|
const now = new Date();
|
|
const day = Date.UTC(now.getUTCFullYear(), now.getUTCMonth(), now.getUTCDate() + offsetDays, 12);
|
|
return new Date(day);
|
|
}
|
|
|
|
function utcDateKey(date: Date): string {
|
|
return date.toISOString().slice(0, 10);
|
|
}
|
|
|
|
describe("getUtcMonthStart", () => {
|
|
it("anchors the monthly spend window to UTC month boundaries", () => {
|
|
expect(getUtcMonthStart(new Date("2026-03-31T20:30:00.000-05:00")).toISOString()).toBe(
|
|
"2026-04-01T00:00:00.000Z",
|
|
);
|
|
expect(getUtcMonthStart(new Date("2026-04-01T00:30:00.000+14:00")).toISOString()).toBe(
|
|
"2026-03-01T00:00:00.000Z",
|
|
);
|
|
});
|
|
});
|
|
|
|
describeEmbeddedPostgres("dashboard service", () => {
|
|
let db!: ReturnType<typeof createDb>;
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
|
|
|
beforeAll(async () => {
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-dashboard-service-");
|
|
db = createDb(tempDb.connectionString);
|
|
}, 20_000);
|
|
|
|
afterEach(async () => {
|
|
await db.delete(heartbeatRuns);
|
|
await db.delete(agents);
|
|
await db.delete(companies);
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await tempDb?.cleanup();
|
|
});
|
|
|
|
it("aggregates the full 14-day run activity window without recent-run truncation", async () => {
|
|
const companyId = randomUUID();
|
|
const otherCompanyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const otherAgentId = randomUUID();
|
|
const today = utcDay(0);
|
|
const weekAgo = utcDay(-7);
|
|
|
|
await db.insert(companies).values([
|
|
{
|
|
id: companyId,
|
|
name: "Paperclip",
|
|
issuePrefix: `T${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,
|
|
other: 0,
|
|
total: 105,
|
|
});
|
|
expect(weekAgoBucket).toMatchObject({
|
|
succeeded: 0,
|
|
failed: 2,
|
|
other: 1,
|
|
total: 3,
|
|
});
|
|
});
|
|
});
|