Files
paperclip/server/src/__tests__/agent-live-run-routes.test.ts
T
Dotta 7f893ac4ec [codex] Harden execution reliability and heartbeat tooling (#3679)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - Reliable execution depends on heartbeat routing, issue lifecycle
semantics, telemetry, and a fast enough local verification loop to keep
regressions visible
> - The remaining commits on this branch were mostly server/runtime
correctness fixes plus test and documentation follow-ups in that area
> - Those changes are logically separate from the UI-focused
issue-detail and workspace/navigation branches even when they touch
overlapping issue APIs
> - This pull request groups the execution reliability, heartbeat,
telemetry, and tooling changes into one standalone branch
> - The benefit is a focused review of the control-plane correctness
work, including the follow-up fix that restored the implicit
comment-reopen helpers after branch splitting

## What Changed

- Hardened issue/heartbeat execution behavior, including self-review
stage skipping, deferred mention wakes during active execution, stranded
execution recovery, active-run scoping, assignee resolution, and
blocked-to-todo wake resumption
- Reduced noisy polling/logging overhead by trimming issue run payloads,
compacting persisted run logs, silencing high-volume request logs, and
capping heartbeat-run queries in dashboard/inbox surfaces
- Expanded telemetry and status semantics with adapter/model fields on
task completion plus clearer status guidance in docs/onboarding material
- Updated test infrastructure and verification defaults with faster
route-test module isolation, cheaper default `pnpm test`, e2e isolation
from local state, and repo verification follow-ups
- Included docs/release housekeeping from the branch and added a small
follow-up commit restoring the implicit comment-reopen helpers that were
dropped during branch reconstruction

## Verification

- `pnpm vitest run
server/src/__tests__/issue-comment-reopen-routes.test.ts
server/src/__tests__/issue-telemetry-routes.test.ts`
- `pnpm vitest run server/src/__tests__/http-log-policy.test.ts
server/src/__tests__/heartbeat-run-log.test.ts
server/src/__tests__/health.test.ts`
- `server/src/__tests__/activity-service.test.ts`,
`server/src/__tests__/heartbeat-comment-wake-batching.test.ts`, and
`server/src/__tests__/heartbeat-process-recovery.test.ts` were attempted
on this host but the embedded Postgres harness reported
init-script/data-dir problems and skipped or failed to start, so they
are noted as environment-limited

## Risks

- Medium: this branch changes core issue/heartbeat routing and
reopen/wakeup behavior, so regressions would affect agent execution flow
rather than isolated UI polish
- Because it also updates verification infrastructure, reviewers should
pay attention to whether the new tests are asserting the right failure
modes and not just reshaping harness behavior

## Model Used

- OpenAI Codex coding agent (GPT-5-class runtime in Codex CLI; exact
deployed model ID is not exposed in this environment), reasoning
enabled, tool use and local code execution enabled

## 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)
- [ ] 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

---------

Co-authored-by: Paperclip <noreply@paperclip.ing>
2026-04-14 13:34:52 -05:00

167 lines
5.4 KiB
TypeScript

import express from "express";
import request from "supertest";
import { beforeEach, describe, expect, it, vi } from "vitest";
const mockAgentService = vi.hoisted(() => ({
getById: vi.fn(),
}));
const mockHeartbeatService = vi.hoisted(() => ({
getRunIssueSummary: vi.fn(),
getActiveRunIssueSummaryForAgent: vi.fn(),
}));
const mockIssueService = vi.hoisted(() => ({
getById: vi.fn(),
getByIdentifier: vi.fn(),
}));
function registerModuleMocks() {
vi.doMock("../services/index.js", () => ({
agentService: () => mockAgentService,
agentInstructionsService: () => ({}),
accessService: () => ({}),
approvalService: () => ({}),
companySkillService: () => ({ listRuntimeSkillEntries: vi.fn() }),
budgetService: () => ({}),
heartbeatService: () => mockHeartbeatService,
issueApprovalService: () => ({}),
issueService: () => mockIssueService,
logActivity: vi.fn(),
secretService: () => ({}),
syncInstructionsBundleConfigFromFilePath: vi.fn((_agent, config) => config),
workspaceOperationService: () => ({}),
}));
vi.doMock("../adapters/index.js", () => ({
findServerAdapter: vi.fn(),
listAdapterModels: vi.fn(),
detectAdapterModel: vi.fn(),
findActiveServerAdapter: vi.fn(),
requireServerAdapter: vi.fn(),
}));
}
async function createApp() {
const [{ agentRoutes }, { errorHandler }] = await Promise.all([
vi.importActual<typeof import("../routes/agents.js")>("../routes/agents.js"),
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
]);
const app = express();
app.use(express.json());
app.use((req, _res, next) => {
(req as any).actor = {
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
};
next();
});
app.use("/api", agentRoutes({} as any));
app.use(errorHandler);
return app;
}
describe("agent live run routes", () => {
beforeEach(() => {
vi.resetModules();
vi.doUnmock("../services/index.js");
vi.doUnmock("../adapters/index.js");
vi.doUnmock("../routes/agents.js");
vi.doUnmock("../routes/authz.js");
vi.doUnmock("../middleware/index.js");
registerModuleMocks();
vi.resetAllMocks();
mockIssueService.getByIdentifier.mockResolvedValue({
id: "issue-1",
companyId: "company-1",
executionRunId: "run-1",
assigneeAgentId: "agent-1",
status: "in_progress",
});
mockIssueService.getById.mockResolvedValue(null);
mockAgentService.getById.mockResolvedValue({
id: "agent-1",
companyId: "company-1",
name: "Builder",
adapterType: "codex_local",
});
mockHeartbeatService.getRunIssueSummary.mockResolvedValue({
id: "run-1",
status: "running",
invocationSource: "on_demand",
triggerDetail: "manual",
startedAt: new Date("2026-04-10T09:30:00.000Z"),
finishedAt: null,
createdAt: new Date("2026-04-10T09:29:59.000Z"),
agentId: "agent-1",
issueId: "issue-1",
});
mockHeartbeatService.getActiveRunIssueSummaryForAgent.mockResolvedValue(null);
});
it("returns a compact active run payload for issue polling", async () => {
const res = await request(await createApp()).get("/api/issues/PAP-1295/active-run");
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(mockIssueService.getByIdentifier).toHaveBeenCalledWith("PAP-1295");
expect(mockHeartbeatService.getRunIssueSummary).toHaveBeenCalledWith("run-1");
expect(res.body).toEqual({
id: "run-1",
status: "running",
invocationSource: "on_demand",
triggerDetail: "manual",
startedAt: "2026-04-10T09:30:00.000Z",
finishedAt: null,
createdAt: "2026-04-10T09:29:59.000Z",
agentId: "agent-1",
issueId: "issue-1",
agentName: "Builder",
adapterType: "codex_local",
});
expect(res.body).not.toHaveProperty("resultJson");
expect(res.body).not.toHaveProperty("contextSnapshot");
expect(res.body).not.toHaveProperty("logRef");
});
it("ignores a stale execution run from another issue and falls back to the assignee's matching run", async () => {
mockHeartbeatService.getRunIssueSummary.mockResolvedValue({
id: "run-foreign",
status: "running",
invocationSource: "assignment",
triggerDetail: "callback",
startedAt: new Date("2026-04-10T10:00:00.000Z"),
finishedAt: null,
createdAt: new Date("2026-04-10T09:59:00.000Z"),
agentId: "agent-1",
issueId: "issue-2",
});
mockHeartbeatService.getActiveRunIssueSummaryForAgent.mockResolvedValue({
id: "run-1",
status: "running",
invocationSource: "on_demand",
triggerDetail: "manual",
startedAt: new Date("2026-04-10T09:30:00.000Z"),
finishedAt: null,
createdAt: new Date("2026-04-10T09:29:59.000Z"),
agentId: "agent-1",
issueId: "issue-1",
});
const res = await request(await createApp()).get("/api/issues/PAP-1295/active-run");
expect(res.status, JSON.stringify(res.body)).toBe(200);
expect(mockHeartbeatService.getRunIssueSummary).toHaveBeenCalledWith("run-1");
expect(mockHeartbeatService.getActiveRunIssueSummaryForAgent).toHaveBeenCalledWith("agent-1");
expect(res.body).toMatchObject({
id: "run-1",
issueId: "issue-1",
agentId: "agent-1",
agentName: "Builder",
adapterType: "codex_local",
});
});
});