2026-04-04 13:04:34 -05:00
|
|
|
import express from "express";
|
|
|
|
|
import request from "supertest";
|
|
|
|
|
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
|
|
|
|
|
|
|
|
const issueId = "11111111-1111-4111-8111-111111111111";
|
|
|
|
|
const closedWorkspaceId = "33333333-3333-4333-8333-333333333333";
|
|
|
|
|
const nextWorkspaceId = "44444444-4444-4444-8444-444444444444";
|
|
|
|
|
const agentId = "22222222-2222-4222-8222-222222222222";
|
|
|
|
|
|
|
|
|
|
const mockIssueService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(),
|
|
|
|
|
update: vi.fn(),
|
|
|
|
|
checkout: vi.fn(),
|
|
|
|
|
addComment: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockExecutionWorkspaceService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockAccessService = vi.hoisted(() => ({
|
|
|
|
|
canUser: vi.fn(),
|
|
|
|
|
hasPermission: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockHeartbeatService = vi.hoisted(() => ({
|
|
|
|
|
wakeup: vi.fn(async () => undefined),
|
|
|
|
|
reportRunActivity: vi.fn(async () => undefined),
|
|
|
|
|
getRun: vi.fn(async () => null),
|
|
|
|
|
getActiveRunForAgent: vi.fn(async () => null),
|
|
|
|
|
cancelRun: vi.fn(async () => null),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockProjectService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(async () => null),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
const mockLogActivity = vi.hoisted(() => vi.fn(async () => undefined));
|
|
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
function registerServiceMocks() {
|
|
|
|
|
vi.doMock("@paperclipai/shared/telemetry", () => ({
|
|
|
|
|
trackAgentTaskCompleted: vi.fn(),
|
|
|
|
|
trackErrorHandlerCrash: vi.fn(),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
vi.doMock("../telemetry.js", () => ({
|
|
|
|
|
getTelemetryClient: vi.fn(() => ({ track: vi.fn() })),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
vi.doMock("../services/index.js", () => ({
|
|
|
|
|
accessService: () => mockAccessService,
|
|
|
|
|
agentService: () => ({
|
|
|
|
|
getById: vi.fn(async () => null),
|
|
|
|
|
}),
|
|
|
|
|
documentService: () => ({}),
|
|
|
|
|
executionWorkspaceService: () => mockExecutionWorkspaceService,
|
|
|
|
|
feedbackService: () => ({
|
|
|
|
|
listIssueVotesForUser: vi.fn(async () => []),
|
|
|
|
|
saveIssueVote: vi.fn(async () => ({ vote: null, consentEnabledNow: false, sharingEnabled: false })),
|
|
|
|
|
}),
|
|
|
|
|
goalService: () => ({
|
|
|
|
|
getDefaultCompanyGoal: vi.fn(async () => null),
|
|
|
|
|
getById: vi.fn(async () => null),
|
|
|
|
|
}),
|
|
|
|
|
heartbeatService: () => mockHeartbeatService,
|
|
|
|
|
instanceSettingsService: () => ({
|
|
|
|
|
get: vi.fn(async () => ({
|
|
|
|
|
id: "instance-settings-1",
|
|
|
|
|
general: {
|
|
|
|
|
censorUsernameInLogs: false,
|
|
|
|
|
feedbackDataSharingPreference: "prompt",
|
|
|
|
|
},
|
|
|
|
|
})),
|
|
|
|
|
listCompanyIds: vi.fn(async () => ["company-1"]),
|
|
|
|
|
}),
|
|
|
|
|
issueApprovalService: () => ({}),
|
|
|
|
|
issueService: () => mockIssueService,
|
|
|
|
|
logActivity: mockLogActivity,
|
|
|
|
|
projectService: () => mockProjectService,
|
|
|
|
|
routineService: () => ({
|
|
|
|
|
syncRunStatusForIssue: vi.fn(async () => undefined),
|
|
|
|
|
}),
|
|
|
|
|
workProductService: () => ({}),
|
|
|
|
|
}));
|
|
|
|
|
}
|
2026-04-04 13:04:34 -05:00
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
async function createApp() {
|
|
|
|
|
const [{ issueRoutes }, { errorHandler }] = await Promise.all([
|
[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
|
|
|
vi.importActual<typeof import("../routes/issues.js")>("../routes/issues.js"),
|
|
|
|
|
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
2026-04-09 06:12:39 -05:00
|
|
|
]);
|
2026-04-04 13:04:34 -05:00
|
|
|
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", issueRoutes({} as any, {} as any));
|
|
|
|
|
app.use(errorHandler);
|
|
|
|
|
return app;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function makeIssue() {
|
|
|
|
|
return {
|
|
|
|
|
id: issueId,
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
status: "todo",
|
|
|
|
|
priority: "medium",
|
|
|
|
|
assigneeAgentId: agentId,
|
|
|
|
|
assigneeUserId: null,
|
|
|
|
|
createdByUserId: "local-board",
|
|
|
|
|
identifier: "PAP-1085",
|
|
|
|
|
title: "Closed worktree issue",
|
|
|
|
|
projectId: null,
|
|
|
|
|
executionRunId: null,
|
|
|
|
|
checkoutRunId: null,
|
|
|
|
|
executionWorkspaceId: closedWorkspaceId,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
function makeClosedWorkspace() {
|
|
|
|
|
return {
|
|
|
|
|
id: closedWorkspaceId,
|
|
|
|
|
name: "PAP-1085-fix-worktree-guard",
|
|
|
|
|
mode: "isolated_workspace",
|
|
|
|
|
status: "archived",
|
|
|
|
|
closedAt: new Date("2026-04-04T17:00:00.000Z"),
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe("closed isolated workspace issue routes", () => {
|
|
|
|
|
beforeEach(() => {
|
2026-04-09 06:12:39 -05:00
|
|
|
vi.resetModules();
|
[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
|
|
|
vi.doUnmock("@paperclipai/shared/telemetry");
|
|
|
|
|
vi.doUnmock("../telemetry.js");
|
|
|
|
|
vi.doUnmock("../services/index.js");
|
|
|
|
|
vi.doUnmock("../routes/issues.js");
|
|
|
|
|
vi.doUnmock("../routes/authz.js");
|
|
|
|
|
vi.doUnmock("../middleware/index.js");
|
2026-04-09 06:12:39 -05:00
|
|
|
registerServiceMocks();
|
[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
|
|
|
vi.resetAllMocks();
|
2026-04-04 13:04:34 -05:00
|
|
|
mockIssueService.getById.mockResolvedValue(makeIssue());
|
|
|
|
|
mockExecutionWorkspaceService.getById.mockResolvedValue(makeClosedWorkspace());
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("rejects new issue comments when the linked isolated workspace is closed", async () => {
|
2026-04-09 06:12:39 -05:00
|
|
|
const res = await request(await createApp())
|
2026-04-04 13:04:34 -05:00
|
|
|
.post(`/api/issues/${issueId}/comments`)
|
|
|
|
|
.send({ body: "hello" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(409);
|
|
|
|
|
expect(res.body.error).toContain("closed workspace");
|
|
|
|
|
expect(mockIssueService.addComment).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("rejects comment updates when the linked isolated workspace is closed", async () => {
|
2026-04-09 06:12:39 -05:00
|
|
|
const res = await request(await createApp())
|
2026-04-04 13:04:34 -05:00
|
|
|
.patch(`/api/issues/${issueId}`)
|
|
|
|
|
.send({ comment: "hello" });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(409);
|
|
|
|
|
expect(res.body.error).toContain("closed workspace");
|
|
|
|
|
expect(mockIssueService.update).not.toHaveBeenCalled();
|
|
|
|
|
expect(mockIssueService.addComment).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("rejects checkout when the linked isolated workspace is closed", async () => {
|
2026-04-09 06:12:39 -05:00
|
|
|
const res = await request(await createApp())
|
2026-04-04 13:04:34 -05:00
|
|
|
.post(`/api/issues/${issueId}/checkout`)
|
|
|
|
|
.send({
|
|
|
|
|
agentId,
|
|
|
|
|
expectedStatuses: ["todo", "backlog", "blocked"],
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(409);
|
|
|
|
|
expect(res.body.error).toContain("closed workspace");
|
|
|
|
|
expect(mockIssueService.checkout).not.toHaveBeenCalled();
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("still allows non-comment board updates so the issue can be moved to a new workspace", async () => {
|
|
|
|
|
mockIssueService.update.mockResolvedValue({
|
|
|
|
|
...makeIssue(),
|
|
|
|
|
executionWorkspaceId: nextWorkspaceId,
|
|
|
|
|
});
|
|
|
|
|
|
2026-04-09 06:12:39 -05:00
|
|
|
const res = await request(await createApp())
|
2026-04-04 13:04:34 -05:00
|
|
|
.patch(`/api/issues/${issueId}`)
|
|
|
|
|
.send({ executionWorkspaceId: nextWorkspaceId });
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
2026-04-09 06:12:39 -05:00
|
|
|
expect(res.body.executionWorkspaceId).toBe(nextWorkspaceId);
|
2026-04-04 13:04:34 -05:00
|
|
|
});
|
|
|
|
|
});
|