8f1cd0474f
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Adapter execution and retry classification decide whether agent work pauses, retries, or recovers automatically > - Transient provider failures need to be classified precisely so Paperclip does not convert retryable upstream conditions into false hard failures > - At the same time, operators need an up-to-date model list for Codex-backed agents and prompts should nudge agents toward targeted verification instead of repo-wide sweeps > - This pull request tightens transient recovery classification for Claude and Codex, updates the agent prompt guidance, and adds Codex model refresh support end-to-end > - The benefit is better automatic retry behavior plus fresher operator-facing model configuration ## What Changed - added Codex usage-limit retry-window parsing and Claude extra-usage transient classification - normalized the heartbeat transient-recovery contract across adapter executions and heartbeat scheduling - documented that deferred comment wakes only reopen completed issues for human/comment-reopen interactions, while system follow-ups leave closed work closed - updated adapter-utils prompt guidance to prefer targeted verification - added Codex model refresh support in the server route, registry, shared types, and agent config form - added adapter/server tests covering the new parsing, retry scheduling, and model-refresh behavior ## Verification - `pnpm exec vitest run --project @paperclipai/adapter-utils packages/adapter-utils/src/server-utils.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-claude-local packages/adapters/claude-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/adapter-codex-local packages/adapters/codex-local/src/server/parse.test.ts` - `pnpm exec vitest run --project @paperclipai/server server/src/__tests__/adapter-model-refresh-routes.test.ts server/src/__tests__/adapter-models.test.ts server/src/__tests__/claude-local-execute.test.ts server/src/__tests__/codex-local-execute.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/heartbeat-retry-scheduling.test.ts` ## Risks - Moderate behavior risk: retry classification affects whether runs auto-recover or block, so mistakes here could either suppress needed retries or over-retry real failures - Low workflow risk: deferred comment wake reopening is intentionally scoped to human/comment-reopen interactions so system follow-ups do not revive completed issues unexpectedly > 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 with tool use and code execution in the Codex CLI 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 - [ ] 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 --------- Co-authored-by: Paperclip <noreply@paperclip.ing>
462 lines
15 KiB
TypeScript
462 lines
15 KiB
TypeScript
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: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
|
);
|
|
}
|
|
|
|
describeEmbeddedPostgres("heartbeat bounded retry scheduling", () => {
|
|
let db!: ReturnType<typeof createDb>;
|
|
let heartbeat!: ReturnType<typeof heartbeatService>;
|
|
let tempDb: Awaited<ReturnType<typeof startEmbeddedPostgresTestDatabase>> | null = null;
|
|
|
|
beforeAll(async () => {
|
|
tempDb = await startEmbeddedPostgresTestDatabase("paperclip-heartbeat-retry-scheduling-");
|
|
db = createDb(tempDb.connectionString);
|
|
heartbeat = heartbeatService(db);
|
|
}, 20_000);
|
|
|
|
afterEach(async () => {
|
|
await db.delete(heartbeatRunEvents);
|
|
await db.delete(heartbeatRuns);
|
|
await db.delete(agentWakeupRequests);
|
|
await db.delete(agents);
|
|
await db.delete(companies);
|
|
});
|
|
|
|
afterAll(async () => {
|
|
await tempDb?.cleanup();
|
|
});
|
|
|
|
async function seedRetryFixture(input: {
|
|
runId: string;
|
|
companyId: string;
|
|
agentId: string;
|
|
now: Date;
|
|
errorCode: string;
|
|
errorFamily?: "transient_upstream" | null;
|
|
retryNotBefore?: string | null;
|
|
scheduledRetryAttempt?: number;
|
|
resultJson?: Record<string, unknown> | null;
|
|
adapterType?: "codex_local" | "claude_local";
|
|
agentName?: string;
|
|
}) {
|
|
const adapterType = input.adapterType ?? "codex_local";
|
|
const agentName = input.agentName ?? (adapterType === "claude_local" ? "ClaudeCoder" : "CodexCoder");
|
|
await db.insert(companies).values({
|
|
id: input.companyId,
|
|
name: "Paperclip",
|
|
issuePrefix: `T${input.companyId.replace(/-/g, "").slice(0, 6).toUpperCase()}`,
|
|
requireBoardApprovalForNewAgents: false,
|
|
});
|
|
|
|
await db.insert(agents).values({
|
|
id: input.agentId,
|
|
companyId: input.companyId,
|
|
name: agentName,
|
|
role: "engineer",
|
|
status: "active",
|
|
adapterType,
|
|
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,
|
|
resultJson: input.resultJson ?? {
|
|
...(input.errorFamily ? { errorFamily: input.errorFamily } : {}),
|
|
...(input.retryNotBefore
|
|
? {
|
|
retryNotBefore: input.retryNotBefore,
|
|
transientRetryNotBefore: input.retryNotBefore,
|
|
}
|
|
: {}),
|
|
},
|
|
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: "adapter_failed",
|
|
errorFamily: "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);
|
|
}
|
|
});
|
|
|
|
it("honors codex retry-not-before timestamps when they exceed the default bounded backoff", async () => {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const runId = randomUUID();
|
|
const now = new Date(2026, 3, 22, 22, 29, 0);
|
|
const retryNotBefore = new Date(2026, 3, 22, 23, 31, 0);
|
|
|
|
await seedRetryFixture({
|
|
runId,
|
|
companyId,
|
|
agentId,
|
|
now,
|
|
errorCode: "adapter_failed",
|
|
errorFamily: "transient_upstream",
|
|
retryNotBefore: retryNotBefore.toISOString(),
|
|
});
|
|
|
|
const scheduled = await heartbeat.scheduleBoundedRetry(runId, {
|
|
now,
|
|
random: () => 0.5,
|
|
});
|
|
|
|
expect(scheduled.outcome).toBe("scheduled");
|
|
if (scheduled.outcome !== "scheduled") return;
|
|
expect(scheduled.dueAt.getTime()).toBe(retryNotBefore.getTime());
|
|
|
|
const retryRun = await db
|
|
.select({
|
|
contextSnapshot: heartbeatRuns.contextSnapshot,
|
|
scheduledRetryAt: heartbeatRuns.scheduledRetryAt,
|
|
wakeupRequestId: heartbeatRuns.wakeupRequestId,
|
|
})
|
|
.from(heartbeatRuns)
|
|
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
|
.then((rows) => rows[0] ?? null);
|
|
|
|
expect(retryRun?.scheduledRetryAt?.getTime()).toBe(retryNotBefore.getTime());
|
|
expect((retryRun?.contextSnapshot as Record<string, unknown> | null)?.transientRetryNotBefore).toBe(
|
|
retryNotBefore.toISOString(),
|
|
);
|
|
|
|
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)?.transientRetryNotBefore).toBe(
|
|
retryNotBefore.toISOString(),
|
|
);
|
|
});
|
|
|
|
it("schedules bounded retries for claude_transient_upstream and honors its retry-not-before hint", async () => {
|
|
const companyId = randomUUID();
|
|
const agentId = randomUUID();
|
|
const runId = randomUUID();
|
|
const now = new Date(2026, 3, 22, 10, 0, 0);
|
|
const retryNotBefore = new Date(2026, 3, 22, 16, 0, 0);
|
|
|
|
await seedRetryFixture({
|
|
runId,
|
|
companyId,
|
|
agentId,
|
|
now,
|
|
errorCode: "adapter_failed",
|
|
errorFamily: "transient_upstream",
|
|
adapterType: "claude_local",
|
|
retryNotBefore: retryNotBefore.toISOString(),
|
|
});
|
|
|
|
const scheduled = await heartbeat.scheduleBoundedRetry(runId, {
|
|
now,
|
|
random: () => 0.5,
|
|
});
|
|
|
|
expect(scheduled.outcome).toBe("scheduled");
|
|
if (scheduled.outcome !== "scheduled") return;
|
|
expect(scheduled.dueAt.getTime()).toBe(retryNotBefore.getTime());
|
|
|
|
const retryRun = await db
|
|
.select({
|
|
contextSnapshot: heartbeatRuns.contextSnapshot,
|
|
scheduledRetryAt: heartbeatRuns.scheduledRetryAt,
|
|
wakeupRequestId: heartbeatRuns.wakeupRequestId,
|
|
})
|
|
.from(heartbeatRuns)
|
|
.where(eq(heartbeatRuns.id, scheduled.run.id))
|
|
.then((rows) => rows[0] ?? null);
|
|
|
|
expect(retryRun?.scheduledRetryAt?.getTime()).toBe(retryNotBefore.getTime());
|
|
const contextSnapshot = (retryRun?.contextSnapshot as Record<string, unknown> | null) ?? {};
|
|
expect(contextSnapshot.transientRetryNotBefore).toBe(retryNotBefore.toISOString());
|
|
// Claude does not participate in the Codex fallback-mode ladder.
|
|
expect(contextSnapshot.codexTransientFallbackMode ?? null).toBeNull();
|
|
|
|
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)?.transientRetryNotBefore).toBe(
|
|
retryNotBefore.toISOString(),
|
|
);
|
|
});
|
|
});
|