2026-04-09 10:26:17 -05:00
|
|
|
import express from "express";
|
|
|
|
|
import request from "supertest";
|
|
|
|
|
import { beforeEach, describe, expect, it, vi } from "vitest";
|
|
|
|
|
|
|
|
|
|
const ASSIGNEE_AGENT_ID = "11111111-1111-4111-8111-111111111111";
|
|
|
|
|
|
|
|
|
|
const mockIssueService = vi.hoisted(() => ({
|
|
|
|
|
getById: vi.fn(),
|
|
|
|
|
update: vi.fn(),
|
|
|
|
|
addComment: vi.fn(),
|
|
|
|
|
findMentionedAgents: vi.fn(),
|
|
|
|
|
getRelationSummaries: vi.fn(),
|
|
|
|
|
listWakeableBlockedDependents: vi.fn(),
|
|
|
|
|
getWakeableParentAfterChildCompletion: 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),
|
|
|
|
|
}));
|
|
|
|
|
|
|
|
|
|
vi.mock("../services/index.js", () => ({
|
|
|
|
|
accessService: () => ({
|
|
|
|
|
canUser: vi.fn(async () => true),
|
|
|
|
|
hasPermission: vi.fn(async () => true),
|
|
|
|
|
}),
|
|
|
|
|
agentService: () => ({
|
|
|
|
|
getById: vi.fn(async () => null),
|
[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
|
|
|
resolveByReference: vi.fn(async (_companyId: string, raw: string) => ({
|
|
|
|
|
ambiguous: false,
|
|
|
|
|
agent: { id: raw },
|
|
|
|
|
})),
|
2026-04-09 10:26:17 -05:00
|
|
|
}),
|
|
|
|
|
documentService: () => ({}),
|
|
|
|
|
executionWorkspaceService: () => ({}),
|
|
|
|
|
feedbackService: () => ({
|
|
|
|
|
listIssueVotesForUser: vi.fn(async () => []),
|
|
|
|
|
saveIssueVote: vi.fn(async () => ({ vote: null, consentEnabledNow: false, sharingEnabled: false })),
|
|
|
|
|
}),
|
|
|
|
|
goalService: () => ({}),
|
|
|
|
|
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: vi.fn(async () => undefined),
|
|
|
|
|
projectService: () => ({}),
|
|
|
|
|
routineService: () => ({
|
|
|
|
|
syncRunStatusForIssue: vi.fn(async () => undefined),
|
|
|
|
|
}),
|
|
|
|
|
workProductService: () => ({}),
|
|
|
|
|
}));
|
|
|
|
|
|
[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
|
|
|
function registerModuleMocks() {
|
|
|
|
|
vi.doMock("../services/index.js", () => ({
|
|
|
|
|
accessService: () => ({
|
|
|
|
|
canUser: vi.fn(async () => true),
|
|
|
|
|
hasPermission: vi.fn(async () => true),
|
|
|
|
|
}),
|
|
|
|
|
agentService: () => ({
|
|
|
|
|
getById: vi.fn(async () => null),
|
|
|
|
|
resolveByReference: vi.fn(async (_companyId: string, raw: string) => ({
|
|
|
|
|
ambiguous: false,
|
|
|
|
|
agent: { id: raw },
|
|
|
|
|
})),
|
|
|
|
|
}),
|
|
|
|
|
documentService: () => ({}),
|
|
|
|
|
executionWorkspaceService: () => ({}),
|
|
|
|
|
feedbackService: () => ({
|
|
|
|
|
listIssueVotesForUser: vi.fn(async () => []),
|
|
|
|
|
saveIssueVote: vi.fn(async () => ({ vote: null, consentEnabledNow: false, sharingEnabled: false })),
|
|
|
|
|
}),
|
|
|
|
|
goalService: () => ({}),
|
|
|
|
|
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: vi.fn(async () => undefined),
|
|
|
|
|
projectService: () => ({}),
|
|
|
|
|
routineService: () => ({
|
|
|
|
|
syncRunStatusForIssue: vi.fn(async () => undefined),
|
|
|
|
|
}),
|
|
|
|
|
workProductService: () => ({}),
|
|
|
|
|
}));
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
async function createApp() {
|
|
|
|
|
const [{ errorHandler }, { issueRoutes }] = await Promise.all([
|
|
|
|
|
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
|
|
|
|
vi.importActual<typeof import("../routes/issues.js")>("../routes/issues.js"),
|
|
|
|
|
]);
|
2026-04-09 10:26:17 -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(overrides: Record<string, unknown> = {}) {
|
|
|
|
|
return {
|
|
|
|
|
id: "aaaaaaaa-aaaa-4aaa-8aaa-aaaaaaaaaaaa",
|
|
|
|
|
companyId: "company-1",
|
|
|
|
|
status: "todo",
|
|
|
|
|
priority: "medium",
|
|
|
|
|
projectId: null,
|
|
|
|
|
goalId: null,
|
|
|
|
|
parentId: null,
|
|
|
|
|
assigneeAgentId: null,
|
|
|
|
|
assigneeUserId: "local-board",
|
|
|
|
|
createdByUserId: "local-board",
|
|
|
|
|
identifier: "PAP-999",
|
|
|
|
|
title: "Wake test",
|
|
|
|
|
executionPolicy: null,
|
|
|
|
|
executionState: null,
|
|
|
|
|
hiddenAt: null,
|
|
|
|
|
...overrides,
|
|
|
|
|
};
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
describe("issue update comment wakeups", () => {
|
|
|
|
|
beforeEach(() => {
|
[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.resetModules();
|
|
|
|
|
vi.doUnmock("../routes/issues.js");
|
|
|
|
|
vi.doUnmock("../routes/authz.js");
|
|
|
|
|
vi.doUnmock("../middleware/index.js");
|
|
|
|
|
registerModuleMocks();
|
|
|
|
|
vi.resetAllMocks();
|
2026-04-09 10:26:17 -05:00
|
|
|
mockIssueService.findMentionedAgents.mockResolvedValue([]);
|
|
|
|
|
mockIssueService.getRelationSummaries.mockResolvedValue({ blockedBy: [], blocks: [] });
|
|
|
|
|
mockIssueService.listWakeableBlockedDependents.mockResolvedValue([]);
|
|
|
|
|
mockIssueService.getWakeableParentAfterChildCompletion.mockResolvedValue(null);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("includes the new comment in assignment wakes from issue updates", async () => {
|
|
|
|
|
const existing = makeIssue();
|
|
|
|
|
const updated = makeIssue({
|
|
|
|
|
assigneeAgentId: ASSIGNEE_AGENT_ID,
|
|
|
|
|
assigneeUserId: null,
|
|
|
|
|
});
|
|
|
|
|
mockIssueService.getById.mockResolvedValue(existing);
|
|
|
|
|
mockIssueService.update.mockResolvedValue(updated);
|
|
|
|
|
mockIssueService.addComment.mockResolvedValue({
|
|
|
|
|
id: "comment-1",
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
companyId: existing.companyId,
|
|
|
|
|
body: "write the whole thing",
|
|
|
|
|
});
|
|
|
|
|
|
[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
|
|
|
const res = await request(await createApp())
|
2026-04-09 10:26:17 -05:00
|
|
|
.patch(`/api/issues/${existing.id}`)
|
|
|
|
|
.send({
|
|
|
|
|
assigneeAgentId: ASSIGNEE_AGENT_ID,
|
|
|
|
|
assigneeUserId: null,
|
|
|
|
|
comment: "write the whole thing",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(mockHeartbeatService.wakeup).toHaveBeenCalledTimes(1);
|
|
|
|
|
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
|
|
|
|
ASSIGNEE_AGENT_ID,
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
source: "assignment",
|
|
|
|
|
reason: "issue_assigned",
|
|
|
|
|
payload: expect.objectContaining({
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
commentId: "comment-1",
|
|
|
|
|
mutation: "update",
|
|
|
|
|
}),
|
|
|
|
|
contextSnapshot: expect.objectContaining({
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
taskId: existing.id,
|
|
|
|
|
commentId: "comment-1",
|
|
|
|
|
wakeCommentId: "comment-1",
|
|
|
|
|
source: "issue.update",
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
it("wakes the assignee on comment-only issue updates", async () => {
|
|
|
|
|
const existing = makeIssue({
|
|
|
|
|
assigneeAgentId: ASSIGNEE_AGENT_ID,
|
|
|
|
|
assigneeUserId: null,
|
|
|
|
|
status: "in_progress",
|
|
|
|
|
});
|
|
|
|
|
const updated = { ...existing };
|
|
|
|
|
mockIssueService.getById.mockResolvedValue(existing);
|
|
|
|
|
mockIssueService.update.mockResolvedValue(updated);
|
|
|
|
|
mockIssueService.addComment.mockResolvedValue({
|
|
|
|
|
id: "comment-2",
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
companyId: existing.companyId,
|
|
|
|
|
body: "please revise this",
|
|
|
|
|
});
|
|
|
|
|
|
[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
|
|
|
const res = await request(await createApp())
|
2026-04-09 10:26:17 -05:00
|
|
|
.patch(`/api/issues/${existing.id}`)
|
|
|
|
|
.send({
|
|
|
|
|
comment: "please revise this",
|
|
|
|
|
});
|
|
|
|
|
|
|
|
|
|
expect(res.status).toBe(200);
|
|
|
|
|
expect(mockHeartbeatService.wakeup).toHaveBeenCalledTimes(1);
|
|
|
|
|
expect(mockHeartbeatService.wakeup).toHaveBeenCalledWith(
|
|
|
|
|
ASSIGNEE_AGENT_ID,
|
|
|
|
|
expect.objectContaining({
|
|
|
|
|
source: "automation",
|
|
|
|
|
reason: "issue_commented",
|
|
|
|
|
payload: expect.objectContaining({
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
commentId: "comment-2",
|
|
|
|
|
mutation: "comment",
|
|
|
|
|
}),
|
|
|
|
|
contextSnapshot: expect.objectContaining({
|
|
|
|
|
issueId: existing.id,
|
|
|
|
|
taskId: existing.id,
|
|
|
|
|
commentId: "comment-2",
|
|
|
|
|
wakeCommentId: "comment-2",
|
|
|
|
|
wakeReason: "issue_commented",
|
|
|
|
|
source: "issue.comment",
|
|
|
|
|
}),
|
|
|
|
|
}),
|
|
|
|
|
);
|
|
|
|
|
});
|
|
|
|
|
});
|