forked from farhoodlabs/paperclip
[codex] Harden heartbeat scheduling and runtime controls (#4223)
## 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
This commit is contained in:
@@ -0,0 +1,338 @@
|
||||
import { randomUUID } from "node:crypto";
|
||||
import { eq, sql } from "drizzle-orm";
|
||||
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
|
||||
import {
|
||||
agents,
|
||||
agentWakeupRequests,
|
||||
companies,
|
||||
createDb,
|
||||
heartbeatRunEvents,
|
||||
heartbeatRuns,
|
||||
} from "@paperclipai/db";
|
||||
import {
|
||||
getEmbeddedPostgresTestSupport,
|
||||
startEmbeddedPostgresTestDatabase,
|
||||
} from "./helpers/embedded-postgres.js";
|
||||
import {
|
||||
BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS,
|
||||
heartbeatService,
|
||||
} from "../services/heartbeat.ts";
|
||||
|
||||
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
||||
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
||||
|
||||
if (!embeddedPostgresSupport.supported) {
|
||||
console.warn(
|
||||
`Skipping embedded Postgres heartbeat retry scheduling tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
||||
);
|
||||
}
|
||||
|
||||
describeEmbeddedPostgres("heartbeat bounded retry scheduling", () => {
|
||||
let db!: ReturnType<typeof createDb>;
|
||||
let heartbeat!: ReturnType<typeof heartbeatService>;
|
||||
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
||||
|
||||
beforeAll(async () => {
|
||||
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-heartbeat-retry-scheduling-");
|
||||
db = createDb(tempDb.connectionString);
|
||||
heartbeat = heartbeatService(db);
|
||||
}, 20_000);
|
||||
|
||||
afterEach(async () => {
|
||||
await db.delete(heartbeatRunEvents);
|
||||
await db.delete(heartbeatRuns);
|
||||
await db.delete(agentWakeupRequests);
|
||||
await db.delete(agents);
|
||||
await db.delete(companies);
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await tempDb?.cleanup();
|
||||
});
|
||||
|
||||
async function seedRetryFixture(input: {
|
||||
runId: string;
|
||||
companyId: string;
|
||||
agentId: string;
|
||||
now: Date;
|
||||
errorCode: string;
|
||||
scheduledRetryAttempt?: number;
|
||||
}) {
|
||||
await db.insert(companies).values({
|
||||
id: input.companyId,
|
||||
name: "Paperclip",
|
||||
issuePrefix: `T${input.companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
||||
requireBoardApprovalForNewAgents: false,
|
||||
});
|
||||
|
||||
await db.insert(agents).values({
|
||||
id: input.agentId,
|
||||
companyId: input.companyId,
|
||||
name: "CodexCoder",
|
||||
role: "engineer",
|
||||
status: "active",
|
||||
adapterType: "codex_local",
|
||||
adapterConfig: {},
|
||||
runtimeConfig: {
|
||||
heartbeat: {
|
||||
wakeOnDemand: true,
|
||||
maxConcurrentRuns: 1,
|
||||
},
|
||||
},
|
||||
permissions: {},
|
||||
});
|
||||
|
||||
await db.insert(heartbeatRuns).values({
|
||||
id: input.runId,
|
||||
companyId: input.companyId,
|
||||
agentId: input.agentId,
|
||||
invocationSource: "assignment",
|
||||
status: "failed",
|
||||
error: "upstream overload",
|
||||
errorCode: input.errorCode,
|
||||
finishedAt: input.now,
|
||||
scheduledRetryAttempt: input.scheduledRetryAttempt ?? 0,
|
||||
scheduledRetryReason: input.scheduledRetryAttempt ? "transient_failure" : null,
|
||||
contextSnapshot: {
|
||||
issueId: randomUUID(),
|
||||
wakeReason: "issue_assigned",
|
||||
},
|
||||
updatedAt: input.now,
|
||||
createdAt: input.now,
|
||||
});
|
||||
}
|
||||
|
||||
it("schedules a retry with durable metadata and only promotes it when due", async () => {
|
||||
const companyId = randomUUID();
|
||||
const agentId = randomUUID();
|
||||
const sourceRunId = randomUUID();
|
||||
const now = new Date("2026-04-20T12:00:00.000Z");
|
||||
|
||||
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: "active",
|
||||
adapterType: "codex_local",
|
||||
adapterConfig: {},
|
||||
runtimeConfig: {
|
||||
heartbeat: {
|
||||
wakeOnDemand: true,
|
||||
maxConcurrentRuns: 1,
|
||||
},
|
||||
},
|
||||
permissions: {},
|
||||
});
|
||||
|
||||
await db.insert(heartbeatRuns).values({
|
||||
id: sourceRunId,
|
||||
companyId,
|
||||
agentId,
|
||||
invocationSource: "assignment",
|
||||
status: "failed",
|
||||
error: "upstream overload",
|
||||
errorCode: "adapter_failed",
|
||||
finishedAt: now,
|
||||
contextSnapshot: {
|
||||
issueId: randomUUID(),
|
||||
wakeReason: "issue_assigned",
|
||||
},
|
||||
updatedAt: now,
|
||||
createdAt: now,
|
||||
});
|
||||
|
||||
const scheduled = await heartbeat.scheduleBoundedRetry(sourceRunId, {
|
||||
now,
|
||||
random: () => 0.5,
|
||||
});
|
||||
|
||||
expect(scheduled.outcome).toBe("scheduled");
|
||||
if (scheduled.outcome !== "scheduled") return;
|
||||
|
||||
const expectedDueAt = new Date(now.getTime() + BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS[0]);
|
||||
expect(scheduled.attempt).toBe(1);
|
||||
expect(scheduled.dueAt.toISOString()).toBe(expectedDueAt.toISOString());
|
||||
|
||||
const retryRun = await db
|
||||
.select()
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
||||
.then((rows) => rows[0] ?? null);
|
||||
|
||||
expect(retryRun).toMatchObject({
|
||||
status: "scheduled_retry",
|
||||
retryOfRunId: sourceRunId,
|
||||
scheduledRetryAttempt: 1,
|
||||
scheduledRetryReason: "transient_failure",
|
||||
});
|
||||
expect(retryRun?.scheduledRetryAt?.toISOString()).toBe(expectedDueAt.toISOString());
|
||||
|
||||
const earlyPromotion = await heartbeat.promoteDueScheduledRetries(new Date("2026-04-20T12:01:59.000Z"));
|
||||
expect(earlyPromotion).toEqual({ promoted: 0, runIds: [] });
|
||||
|
||||
const stillScheduled = await db
|
||||
.select({ status: heartbeatRuns.status })
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
||||
.then((rows) => rows[0] ?? null);
|
||||
expect(stillScheduled?.status).toBe("scheduled_retry");
|
||||
|
||||
const duePromotion = await heartbeat.promoteDueScheduledRetries(expectedDueAt);
|
||||
expect(duePromotion).toEqual({ promoted: 1, runIds: [scheduled.run.id] });
|
||||
|
||||
const promotedRun = await db
|
||||
.select({ status: heartbeatRuns.status })
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
||||
.then((rows) => rows[0] ?? null);
|
||||
expect(promotedRun?.status).toBe("queued");
|
||||
});
|
||||
|
||||
it("exhausts bounded retries after the hard cap", async () => {
|
||||
const companyId = randomUUID();
|
||||
const agentId = randomUUID();
|
||||
const cappedRunId = randomUUID();
|
||||
const now = new Date("2026-04-20T18:00:00.000Z");
|
||||
|
||||
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: "active",
|
||||
adapterType: "codex_local",
|
||||
adapterConfig: {},
|
||||
runtimeConfig: {
|
||||
heartbeat: {
|
||||
wakeOnDemand: true,
|
||||
maxConcurrentRuns: 1,
|
||||
},
|
||||
},
|
||||
permissions: {},
|
||||
});
|
||||
|
||||
await db.insert(heartbeatRuns).values({
|
||||
id: cappedRunId,
|
||||
companyId,
|
||||
agentId,
|
||||
invocationSource: "automation",
|
||||
status: "failed",
|
||||
error: "still transient",
|
||||
errorCode: "adapter_failed",
|
||||
finishedAt: now,
|
||||
scheduledRetryAttempt: BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS.length,
|
||||
scheduledRetryReason: "transient_failure",
|
||||
contextSnapshot: {
|
||||
wakeReason: "transient_failure_retry",
|
||||
},
|
||||
updatedAt: now,
|
||||
createdAt: now,
|
||||
});
|
||||
|
||||
const exhausted = await heartbeat.scheduleBoundedRetry(cappedRunId, {
|
||||
now,
|
||||
random: () => 0.5,
|
||||
});
|
||||
|
||||
expect(exhausted).toEqual({
|
||||
outcome: "retry_exhausted",
|
||||
attempt: BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS.length + 1,
|
||||
maxAttempts: BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS.length,
|
||||
});
|
||||
|
||||
const runCount = await db
|
||||
.select({ count: sql<number>`count(*)::int` })
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.companyId, companyId))
|
||||
.then((rows) => rows[0]?.count ?? 0);
|
||||
expect(runCount).toBe(1);
|
||||
|
||||
const exhaustionEvent = await db
|
||||
.select({
|
||||
message: heartbeatRunEvents.message,
|
||||
payload: heartbeatRunEvents.payload,
|
||||
})
|
||||
.from(heartbeatRunEvents)
|
||||
.where(eq(heartbeatRunEvents.runId, cappedRunId))
|
||||
.orderBy(sql`${heartbeatRunEvents.id} desc`)
|
||||
.then((rows) => rows[0] ?? null);
|
||||
|
||||
expect(exhaustionEvent?.message).toContain("Bounded retry exhausted");
|
||||
expect(exhaustionEvent?.payload).toMatchObject({
|
||||
retryReason: "transient_failure",
|
||||
scheduledRetryAttempt: BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS.length,
|
||||
maxAttempts: BOUNDED_TRANSIENT_HEARTBEAT_RETRY_DELAYS_MS.length,
|
||||
});
|
||||
});
|
||||
|
||||
it("advances codex transient fallback stages across bounded retry attempts", async () => {
|
||||
const fallbackModes = [
|
||||
"same_session",
|
||||
"safer_invocation",
|
||||
"fresh_session",
|
||||
"fresh_session_safer_invocation",
|
||||
] as const;
|
||||
|
||||
for (const [index, expectedMode] of fallbackModes.entries()) {
|
||||
const companyId = randomUUID();
|
||||
const agentId = randomUUID();
|
||||
const runId = randomUUID();
|
||||
const now = new Date(`2026-04-20T1${index}:00:00.000Z`);
|
||||
|
||||
await seedRetryFixture({
|
||||
runId,
|
||||
companyId,
|
||||
agentId,
|
||||
now,
|
||||
errorCode: "codex_transient_upstream",
|
||||
scheduledRetryAttempt: index,
|
||||
});
|
||||
|
||||
const scheduled = await heartbeat.scheduleBoundedRetry(runId, {
|
||||
now,
|
||||
random: () => 0.5,
|
||||
});
|
||||
|
||||
expect(scheduled.outcome).toBe("scheduled");
|
||||
if (scheduled.outcome !== "scheduled") continue;
|
||||
|
||||
const retryRun = await db
|
||||
.select({
|
||||
contextSnapshot: heartbeatRuns.contextSnapshot,
|
||||
wakeupRequestId: heartbeatRuns.wakeupRequestId,
|
||||
})
|
||||
.from(heartbeatRuns)
|
||||
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
||||
.then((rows) => rows[0] ?? null);
|
||||
expect((retryRun?.contextSnapshot as Record<string, unknown> | null)?.codexTransientFallbackMode).toBe(expectedMode);
|
||||
|
||||
const wakeupRequest = await db
|
||||
.select({ payload: agentWakeupRequests.payload })
|
||||
.from(agentWakeupRequests)
|
||||
.where(eq(agentWakeupRequests.id, retryRun?.wakeupRequestId ?? ""))
|
||||
.then((rows) => rows[0] ?? null);
|
||||
expect((wakeupRequest?.payload as Record<string, unknown> | null)?.codexTransientFallbackMode).toBe(expectedMode);
|
||||
|
||||
await db.delete(heartbeatRunEvents);
|
||||
await db.delete(heartbeatRuns);
|
||||
await db.delete(agentWakeupRequests);
|
||||
await db.delete(agents);
|
||||
await db.delete(companies);
|
||||
}
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user