paperclip/server/src/__tests__/company-skills-routes.test.ts

297 lines
9.4 KiB
TypeScript
Raw Normal View History

import express from "express";
import request from "supertest";
import { beforeEach, describe, expect, it, vi } from "vitest";
const mockAgentService = vi.hoisted(() => ({
getById: vi.fn(),
}));
const mockAccessService = vi.hoisted(() => ({
canUser: vi.fn(),
hasPermission: vi.fn(),
}));
const mockCompanySkillService = vi.hoisted(() => ({
importFromSource: vi.fn(),
deleteSkill: vi.fn(),
}));
const mockLogActivity = vi.hoisted(() => vi.fn());
const mockTrackSkillImported = vi.hoisted(() => vi.fn());
const mockGetTelemetryClient = vi.hoisted(() => vi.fn());
vi.mock("@paperclipai/shared/telemetry", () => ({
trackSkillImported: mockTrackSkillImported,
trackErrorHandlerCrash: vi.fn(),
}));
vi.mock("../telemetry.js", () => ({
getTelemetryClient: mockGetTelemetryClient,
}));
vi.mock("../services/index.js", () => ({
accessService: () => mockAccessService,
agentService: () => mockAgentService,
companySkillService: () => mockCompanySkillService,
logActivity: mockLogActivity,
}));
async function createApp(actor: Record<string, unknown>) {
const [{ companySkillRoutes }, { 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/company-skills.js")>("../routes/company-skills.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 = actor;
next();
});
app.use("/api", companySkillRoutes({} as any));
app.use(errorHandler);
return app;
}
describe("company skill mutation permissions", () => {
beforeEach(() => {
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("../routes/company-skills.js");
vi.doUnmock("../routes/authz.js");
vi.doUnmock("../middleware/index.js");
vi.resetAllMocks();
mockGetTelemetryClient.mockReturnValue({ track: vi.fn() });
mockCompanySkillService.importFromSource.mockResolvedValue({
imported: [],
warnings: [],
});
mockCompanySkillService.deleteSkill.mockResolvedValue({
id: "skill-1",
slug: "find-skills",
name: "Find Skills",
});
mockLogActivity.mockResolvedValue(undefined);
mockAccessService.canUser.mockResolvedValue(true);
mockAccessService.hasPermission.mockResolvedValue(false);
});
it("allows local board operators to mutate company skills", async () => {
const res = await request(await createApp({
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://github.com/vercel-labs/agent-browser" });
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockCompanySkillService.importFromSource).toHaveBeenCalledWith(
"company-1",
"https://github.com/vercel-labs/agent-browser",
);
});
it("tracks public GitHub skill imports with an explicit skill reference", async () => {
mockCompanySkillService.importFromSource.mockResolvedValue({
imported: [
{
id: "skill-1",
companyId: "company-1",
key: "vercel-labs/agent-browser/find-skills",
slug: "find-skills",
name: "Find Skills",
description: null,
markdown: "# Find Skills",
sourceType: "github",
sourceLocator: "https://github.com/vercel-labs/agent-browser",
sourceRef: null,
trustLevel: "markdown_only",
compatibility: "compatible",
fileInventory: [],
metadata: {
hostname: "github.com",
owner: "vercel-labs",
repo: "agent-browser",
},
createdAt: new Date(),
updatedAt: new Date(),
},
],
warnings: [],
});
const res = await request(await createApp({
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://github.com/vercel-labs/agent-browser" });
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockTrackSkillImported).toHaveBeenCalledWith(expect.anything(), {
sourceType: "github",
skillRef: "vercel-labs/agent-browser/find-skills",
});
});
it("does not expose a skill reference for non-public skill imports", async () => {
mockCompanySkillService.importFromSource.mockResolvedValue({
imported: [
{
id: "skill-1",
companyId: "company-1",
key: "private-skill",
slug: "private-skill",
name: "Private Skill",
description: null,
markdown: "# Private Skill",
sourceType: "github",
sourceLocator: "https://ghe.example.com/acme/private-skill",
sourceRef: null,
trustLevel: "markdown_only",
compatibility: "compatible",
fileInventory: [],
metadata: {
hostname: "ghe.example.com",
owner: "acme",
repo: "private-skill",
},
createdAt: new Date(),
updatedAt: new Date(),
},
],
warnings: [],
});
const res = await request(await createApp({
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://ghe.example.com/acme/private-skill" });
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockTrackSkillImported).toHaveBeenCalledWith(expect.anything(), {
sourceType: "github",
skillRef: null,
});
});
it("does not expose a skill reference when GitHub metadata is missing", async () => {
mockCompanySkillService.importFromSource.mockResolvedValue({
imported: [
{
id: "skill-1",
companyId: "company-1",
key: "unknown/private-skill",
slug: "private-skill",
name: "Private Skill",
description: null,
markdown: "# Private Skill",
sourceType: "github",
sourceLocator: "https://github.com/acme/private-skill",
sourceRef: null,
trustLevel: "markdown_only",
compatibility: "compatible",
fileInventory: [],
metadata: null,
createdAt: new Date(),
updatedAt: new Date(),
},
],
warnings: [],
});
const res = await request(await createApp({
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://github.com/acme/private-skill" });
[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
expect([200, 201], JSON.stringify(res.body)).toContain(res.status);
expect(mockTrackSkillImported).toHaveBeenCalledWith(expect.anything(), {
sourceType: "github",
skillRef: null,
});
});
it("blocks same-company agents without management permission from mutating company skills", async () => {
mockAgentService.getById.mockResolvedValue({
id: "agent-1",
companyId: "company-1",
permissions: {},
});
const res = await request(await createApp({
type: "agent",
agentId: "agent-1",
companyId: "company-1",
runId: "run-1",
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://github.com/vercel-labs/agent-browser" });
expect(res.status, JSON.stringify(res.body)).toBe(403);
expect(mockCompanySkillService.importFromSource).not.toHaveBeenCalled();
});
it("allows agents with canCreateAgents to mutate company skills", async () => {
mockAgentService.getById.mockResolvedValue({
id: "agent-1",
companyId: "company-1",
permissions: { canCreateAgents: true },
});
const res = await request(await createApp({
type: "agent",
agentId: "agent-1",
companyId: "company-1",
runId: "run-1",
}))
.post("/api/companies/company-1/skills/import")
.send({ source: "https://github.com/vercel-labs/agent-browser" });
expect(res.status, JSON.stringify(res.body)).toBe(201);
expect(mockCompanySkillService.importFromSource).toHaveBeenCalledWith(
"company-1",
"https://github.com/vercel-labs/agent-browser",
);
});
it("returns a blocking error when attempting to delete a skill still used by agents", async () => {
const { unprocessable } = await import("../errors.js");
mockCompanySkillService.deleteSkill.mockImplementationOnce(async () => {
throw unprocessable(
'Cannot delete skill "Find Skills" while it is still used by Builder, Reviewer. Detach it from those agents first.',
);
});
const res = await request(await createApp({
type: "board",
userId: "local-board",
companyIds: ["company-1"],
source: "local_implicit",
isInstanceAdmin: false,
}))
.delete("/api/companies/company-1/skills/skill-1");
expect(res.status, JSON.stringify(res.body)).toBe(422);
expect(res.body).toEqual({
error: 'Cannot delete skill "Find Skills" while it is still used by Builder, Reviewer. Detach it from those agents first.',
});
expect(mockCompanySkillService.deleteSkill).toHaveBeenCalledWith("company-1", "skill-1");
expect(mockLogActivity).not.toHaveBeenCalled();
});
});