mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-14 01:50:39 +09:00
[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>
This commit is contained in:
parent
e89076148a
commit
7f893ac4ec
106 changed files with 4682 additions and 713 deletions
|
|
@ -27,6 +27,7 @@ const mockHeartbeatService = vi.hoisted(() => ({
|
|||
|
||||
const mockAgentService = vi.hoisted(() => ({
|
||||
getById: vi.fn(),
|
||||
resolveByReference: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockLogActivity = vi.hoisted(() => vi.fn(async () => undefined));
|
||||
|
|
@ -82,6 +83,34 @@ vi.mock("../services/index.js", () => ({
|
|||
workProductService: () => ({}),
|
||||
}));
|
||||
|
||||
function registerModuleMocks() {
|
||||
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: () => mockAgentService,
|
||||
documentService: () => ({}),
|
||||
executionWorkspaceService: () => ({}),
|
||||
feedbackService: () => mockFeedbackService,
|
||||
goalService: () => ({}),
|
||||
heartbeatService: () => mockHeartbeatService,
|
||||
instanceSettingsService: () => mockInstanceSettingsService,
|
||||
issueApprovalService: () => ({}),
|
||||
issueService: () => mockIssueService,
|
||||
logActivity: mockLogActivity,
|
||||
projectService: () => ({}),
|
||||
routineService: () => mockRoutineService,
|
||||
workProductService: () => ({}),
|
||||
}));
|
||||
}
|
||||
|
||||
function createApp() {
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
|
|
@ -90,8 +119,8 @@ function createApp() {
|
|||
|
||||
async function installActor(app: express.Express, actor?: Record<string, unknown>) {
|
||||
const [{ issueRoutes }, { errorHandler }] = await Promise.all([
|
||||
import("../routes/issues.js"),
|
||||
import("../middleware/index.js"),
|
||||
vi.importActual<typeof import("../routes/issues.js")>("../routes/issues.js"),
|
||||
vi.importActual<typeof import("../middleware/index.js")>("../middleware/index.js"),
|
||||
]);
|
||||
app.use((req, _res, next) => {
|
||||
(req as any).actor = actor ?? {
|
||||
|
|
@ -135,6 +164,10 @@ function makeIssue(status: "todo" | "done") {
|
|||
describe("issue comment reopen routes", () => {
|
||||
beforeEach(() => {
|
||||
vi.resetModules();
|
||||
vi.doUnmock("../routes/issues.js");
|
||||
vi.doUnmock("../routes/authz.js");
|
||||
vi.doUnmock("../middleware/index.js");
|
||||
registerModuleMocks();
|
||||
vi.resetAllMocks();
|
||||
mockIssueService.getById.mockReset();
|
||||
mockIssueService.assertCheckoutOwner.mockReset();
|
||||
|
|
@ -151,6 +184,7 @@ describe("issue comment reopen routes", () => {
|
|||
mockHeartbeatService.getActiveRunForAgent.mockReset();
|
||||
mockHeartbeatService.cancelRun.mockReset();
|
||||
mockAgentService.getById.mockReset();
|
||||
mockAgentService.resolveByReference.mockReset();
|
||||
mockLogActivity.mockReset();
|
||||
mockFeedbackService.listIssueVotesForUser.mockReset();
|
||||
mockFeedbackService.saveIssueVote.mockReset();
|
||||
|
|
@ -201,6 +235,12 @@ describe("issue comment reopen routes", () => {
|
|||
mockAccessService.canUser.mockResolvedValue(false);
|
||||
mockAccessService.hasPermission.mockResolvedValue(false);
|
||||
mockAgentService.getById.mockResolvedValue(null);
|
||||
mockAgentService.resolveByReference.mockImplementation(async (_companyId: string, reference: string) => ({
|
||||
ambiguous: false,
|
||||
agent: {
|
||||
id: reference,
|
||||
},
|
||||
}));
|
||||
});
|
||||
|
||||
it("treats reopen=true as a no-op when the issue is already open", async () => {
|
||||
|
|
@ -259,6 +299,62 @@ describe("issue comment reopen routes", () => {
|
|||
);
|
||||
});
|
||||
|
||||
it("resolves assignee shortnames before updating an issue", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("todo"));
|
||||
mockIssueService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
|
||||
...makeIssue("todo"),
|
||||
...patch,
|
||||
}));
|
||||
mockAgentService.resolveByReference.mockResolvedValue({
|
||||
ambiguous: false,
|
||||
agent: { id: "33333333-3333-4333-8333-333333333333" },
|
||||
});
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.patch("/api/issues/11111111-1111-4111-8111-111111111111")
|
||||
.send({ comment: "hello", assigneeAgentId: "codexcoder" });
|
||||
|
||||
expect(res.status).toBe(200);
|
||||
expect(mockAgentService.resolveByReference).toHaveBeenCalledWith("company-1", "codexcoder");
|
||||
expect(mockIssueService.update).toHaveBeenCalledWith(
|
||||
"11111111-1111-4111-8111-111111111111",
|
||||
expect.objectContaining({
|
||||
assigneeAgentId: "33333333-3333-4333-8333-333333333333",
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it("rejects ambiguous assignee shortnames", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("todo"));
|
||||
mockAgentService.resolveByReference.mockResolvedValue({
|
||||
ambiguous: true,
|
||||
agent: null,
|
||||
});
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.patch("/api/issues/11111111-1111-4111-8111-111111111111")
|
||||
.send({ assigneeAgentId: "codexcoder" });
|
||||
|
||||
expect(res.status).toBe(409);
|
||||
expect(res.body.error).toContain("ambiguous");
|
||||
expect(mockIssueService.update).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("rejects missing assignee shortnames", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("todo"));
|
||||
mockAgentService.resolveByReference.mockResolvedValue({
|
||||
ambiguous: false,
|
||||
agent: null,
|
||||
});
|
||||
|
||||
const res = await request(await installActor(createApp()))
|
||||
.patch("/api/issues/11111111-1111-4111-8111-111111111111")
|
||||
.send({ assigneeAgentId: "codexcoder" });
|
||||
|
||||
expect(res.status).toBe(404);
|
||||
expect(res.body.error).toBe("Agent not found");
|
||||
expect(mockIssueService.update).not.toHaveBeenCalled();
|
||||
});
|
||||
it("reopens closed issues via the PATCH comment path", async () => {
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("done"));
|
||||
mockIssueService.update.mockImplementation(async (_id: string, patch: Record<string, unknown>) => ({
|
||||
|
|
@ -334,7 +430,6 @@ describe("issue comment reopen routes", () => {
|
|||
expect(res.status).toBe(201);
|
||||
expect(mockIssueService.update).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("interrupts an active run before a combined comment update", async () => {
|
||||
const issue = {
|
||||
...makeIssue("todo"),
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue