mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-17 11:20:37 +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:
Dotta
GitHub
parent
e89076148a
commit
7f893ac4ec
106 changed files with 4682 additions and 713 deletions
|
|
@ -1,8 +1,6 @@
|
|||
import express from "express";
|
||||
import request from "supertest";
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
import { errorHandler } from "../middleware/index.js";
|
||||
import { issueRoutes } from "../routes/issues.js";
|
||||
|
||||
const mockIssueService = vi.hoisted(() => ({
|
||||
getById: vi.fn(),
|
||||
|
|
@ -18,39 +16,41 @@ const mockAgentService = vi.hoisted(() => ({
|
|||
const mockTrackAgentTaskCompleted = vi.hoisted(() => vi.fn());
|
||||
const mockGetTelemetryClient = vi.hoisted(() => vi.fn());
|
||||
|
||||
vi.mock("@paperclipai/shared/telemetry", () => ({
|
||||
trackAgentTaskCompleted: mockTrackAgentTaskCompleted,
|
||||
trackErrorHandlerCrash: vi.fn(),
|
||||
}));
|
||||
function registerModuleMocks() {
|
||||
vi.doMock("@paperclipai/shared/telemetry", () => ({
|
||||
trackAgentTaskCompleted: mockTrackAgentTaskCompleted,
|
||||
trackErrorHandlerCrash: vi.fn(),
|
||||
}));
|
||||
|
||||
vi.mock("../telemetry.js", () => ({
|
||||
getTelemetryClient: mockGetTelemetryClient,
|
||||
}));
|
||||
vi.doMock("../telemetry.js", () => ({
|
||||
getTelemetryClient: mockGetTelemetryClient,
|
||||
}));
|
||||
|
||||
vi.mock("../services/index.js", () => ({
|
||||
accessService: () => ({
|
||||
canUser: vi.fn(),
|
||||
hasPermission: vi.fn(),
|
||||
}),
|
||||
agentService: () => mockAgentService,
|
||||
documentService: () => ({}),
|
||||
executionWorkspaceService: () => ({}),
|
||||
feedbackService: () => ({}),
|
||||
goalService: () => ({}),
|
||||
heartbeatService: () => ({
|
||||
wakeup: vi.fn(async () => undefined),
|
||||
reportRunActivity: vi.fn(async () => undefined),
|
||||
}),
|
||||
instanceSettingsService: () => ({}),
|
||||
issueApprovalService: () => ({}),
|
||||
issueService: () => mockIssueService,
|
||||
logActivity: vi.fn(async () => undefined),
|
||||
projectService: () => ({}),
|
||||
routineService: () => ({
|
||||
syncRunStatusForIssue: vi.fn(async () => undefined),
|
||||
}),
|
||||
workProductService: () => ({}),
|
||||
}));
|
||||
vi.doMock("../services/index.js", () => ({
|
||||
accessService: () => ({
|
||||
canUser: vi.fn(),
|
||||
hasPermission: vi.fn(),
|
||||
}),
|
||||
agentService: () => mockAgentService,
|
||||
documentService: () => ({}),
|
||||
executionWorkspaceService: () => ({}),
|
||||
feedbackService: () => ({}),
|
||||
goalService: () => ({}),
|
||||
heartbeatService: () => ({
|
||||
wakeup: vi.fn(async () => undefined),
|
||||
reportRunActivity: vi.fn(async () => undefined),
|
||||
}),
|
||||
instanceSettingsService: () => ({}),
|
||||
issueApprovalService: () => ({}),
|
||||
issueService: () => mockIssueService,
|
||||
logActivity: vi.fn(async () => undefined),
|
||||
projectService: () => ({}),
|
||||
routineService: () => ({
|
||||
syncRunStatusForIssue: vi.fn(async () => undefined),
|
||||
}),
|
||||
workProductService: () => ({}),
|
||||
}));
|
||||
}
|
||||
|
||||
function makeIssue(status: "todo" | "done") {
|
||||
return {
|
||||
|
|
@ -65,7 +65,11 @@ function makeIssue(status: "todo" | "done") {
|
|||
};
|
||||
}
|
||||
|
||||
function createApp(actor: Record<string, unknown>) {
|
||||
async function createApp(actor: Record<string, unknown>) {
|
||||
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"),
|
||||
]);
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
app.use((req, _res, next) => {
|
||||
|
|
@ -79,6 +83,14 @@ function createApp(actor: Record<string, unknown>) {
|
|||
|
||||
describe("issue telemetry routes", () => {
|
||||
beforeEach(() => {
|
||||
vi.resetModules();
|
||||
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");
|
||||
registerModuleMocks();
|
||||
vi.resetAllMocks();
|
||||
mockGetTelemetryClient.mockReturnValue({ track: vi.fn() });
|
||||
mockIssueService.getById.mockResolvedValue(makeIssue("todo"));
|
||||
|
|
@ -90,15 +102,16 @@ describe("issue telemetry routes", () => {
|
|||
}));
|
||||
});
|
||||
|
||||
it("emits task-completed telemetry with the agent role", async () => {
|
||||
it("emits task-completed telemetry with the agent role, adapter type, and model", async () => {
|
||||
mockAgentService.getById.mockResolvedValue({
|
||||
id: "agent-1",
|
||||
companyId: "company-1",
|
||||
role: "engineer",
|
||||
adapterType: "codex_local",
|
||||
adapterConfig: { model: "claude-sonnet-4-6" },
|
||||
});
|
||||
|
||||
const app = createApp({
|
||||
const app = await createApp({
|
||||
type: "agent",
|
||||
agentId: "agent-1",
|
||||
companyId: "company-1",
|
||||
|
|
@ -112,12 +125,15 @@ describe("issue telemetry routes", () => {
|
|||
await vi.waitFor(() => {
|
||||
expect(mockTrackAgentTaskCompleted).toHaveBeenCalledWith(expect.anything(), {
|
||||
agentRole: "engineer",
|
||||
agentId: "agent-1",
|
||||
adapterType: "codex_local",
|
||||
model: "claude-sonnet-4-6",
|
||||
});
|
||||
});
|
||||
}, 10_000);
|
||||
|
||||
it("does not emit agent task-completed telemetry for board-driven completions", async () => {
|
||||
const app = createApp({
|
||||
const app = await createApp({
|
||||
type: "board",
|
||||
userId: "local-board",
|
||||
companyIds: ["company-1"],
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue