paperclip/packages/mcp-server/src/tools.test.ts

319 lines
10 KiB
TypeScript
Raw Normal View History

import { beforeEach, describe, expect, it, vi } from "vitest";
import { PaperclipApiClient } from "./client.js";
import { createToolDefinitions } from "./tools.js";
function makeClient() {
return new PaperclipApiClient({
apiUrl: "http://localhost:3100/api",
apiKey: "token-123",
companyId: "11111111-1111-1111-1111-111111111111",
agentId: "22222222-2222-2222-2222-222222222222",
runId: "33333333-3333-3333-3333-333333333333",
});
}
function getTool(name: string) {
const tool = createToolDefinitions(makeClient()).find((candidate) => candidate.name === name);
if (!tool) throw new Error(`Missing tool ${name}`);
return tool;
}
function mockJsonResponse(body: unknown, status = 200) {
return new Response(JSON.stringify(body), {
status,
headers: { "Content-Type": "application/json" },
});
}
describe("paperclip MCP tools", () => {
beforeEach(() => {
vi.restoreAllMocks();
});
it("adds auth headers and run id to mutating requests", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ ok: true }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipUpdateIssue");
await tool.execute({
issueId: "PAP-1135",
status: "done",
});
expect(fetchMock).toHaveBeenCalledTimes(1);
const [url, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(String(url)).toBe("http://localhost:3100/api/issues/PAP-1135");
expect(init.method).toBe("PATCH");
expect((init.headers as Record<string, string>)["Authorization"]).toBe("Bearer token-123");
expect((init.headers as Record<string, string>)["X-Paperclip-Run-Id"]).toBe(
"33333333-3333-3333-3333-333333333333",
);
});
it("uses default company id for company-scoped list tools", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse([{ id: "issue-1" }]),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipListIssues");
const response = await tool.execute({});
expect(fetchMock).toHaveBeenCalledTimes(1);
const [url] = fetchMock.mock.calls[0] as [string];
expect(String(url)).toBe(
"http://localhost:3100/api/companies/11111111-1111-1111-1111-111111111111/issues",
);
expect(response.content[0]?.text).toContain("issue-1");
});
it("uses default agent id for checkout requests", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ id: "PAP-1135", status: "in_progress" }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipCheckoutIssue");
await tool.execute({
issueId: "PAP-1135",
});
const [, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(JSON.parse(String(init.body))).toEqual({
agentId: "22222222-2222-2222-2222-222222222222",
expectedStatuses: ["todo", "backlog", "blocked"],
});
});
it("defaults issue document format to markdown", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ key: "plan", latestRevisionNumber: 2 }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipUpsertIssueDocument");
await tool.execute({
issueId: "PAP-1135",
key: "plan",
body: "# Updated",
});
const [, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(JSON.parse(String(init.body))).toEqual({
format: "markdown",
body: "# Updated",
});
});
[codex] Harden heartbeat scheduling and runtime controls (#4223) ## Thinking Path > - Paperclip orchestrates AI agents through issue checkout, heartbeat runs, routines, and auditable control-plane state > - The runtime path has to recover from lost local processes, transient adapter failures, blocked dependencies, and routine coalescing without stranding work > - The existing branch carried several reliability fixes across heartbeat scheduling, issue runtime controls, routine dispatch, and operator-facing run state > - These changes belong together because they share backend contracts, migrations, and runtime status semantics > - This pull request groups the control-plane/runtime slice so it can merge independently from board UI polish and adapter sandbox work > - The benefit is safer heartbeat recovery, clearer runtime controls, and more predictable recurring execution behavior ## What Changed - Adds bounded heartbeat retry scheduling, scheduled retry state, and Codex transient failure recovery handling. - Tightens heartbeat process recovery, blocker wake behavior, issue comment wake handling, routine dispatch coalescing, and activity/dashboard bounds. - Adds runtime-control MCP tools and Paperclip skill docs for issue workspace runtime management. - Adds migrations `0061_lively_thor_girl.sql` and `0062_routine_run_dispatch_fingerprint.sql`. - Surfaces retry state in run ledger/agent UI and keeps related shared types synchronized. ## Verification - `pnpm exec vitest run server/src/__tests__/heartbeat-retry-scheduling.test.ts server/src/__tests__/heartbeat-process-recovery.test.ts server/src/__tests__/routines-service.test.ts` - `pnpm exec vitest run src/tools.test.ts` from `packages/mcp-server` ## Risks - Medium risk: this touches heartbeat recovery and routine dispatch, which are central execution paths. - Migration order matters if split branches land out of order: merge this PR before branches that assume the new runtime/routine fields. - Runtime retry behavior should be watched in CI and in local operator smoke tests because it changes how transient failures are resumed. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5-based coding agent runtime, shell/git tool use enabled. Exact hosted model build and context window are not exposed in this Paperclip heartbeat environment. ## 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) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] 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
2026-04-21 12:24:11 -05:00
it("controls issue workspace services through the current execution workspace", async () => {
const fetchMock = vi.fn()
.mockResolvedValueOnce(mockJsonResponse({
currentExecutionWorkspace: {
id: "44444444-4444-4444-8444-444444444444",
runtimeServices: [],
},
}))
.mockResolvedValueOnce(mockJsonResponse({
operation: { id: "operation-1" },
workspace: {
id: "44444444-4444-4444-8444-444444444444",
runtimeServices: [
{
id: "55555555-5555-4555-8555-555555555555",
serviceName: "web",
status: "running",
url: "http://127.0.0.1:5173",
},
],
},
}));
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipControlIssueWorkspaceServices");
await tool.execute({
issueId: "PAP-1135",
action: "restart",
workspaceCommandId: "web",
});
expect(fetchMock).toHaveBeenCalledTimes(2);
const [lookupUrl, lookupInit] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(String(lookupUrl)).toBe("http://localhost:3100/api/issues/PAP-1135/heartbeat-context");
expect(lookupInit.method).toBe("GET");
const [controlUrl, controlInit] = fetchMock.mock.calls[1] as [string, RequestInit];
expect(String(controlUrl)).toBe(
"http://localhost:3100/api/execution-workspaces/44444444-4444-4444-8444-444444444444/runtime-services/restart",
);
expect(controlInit.method).toBe("POST");
expect(JSON.parse(String(controlInit.body))).toEqual({
workspaceCommandId: "web",
});
});
it("waits for an issue workspace runtime service URL", async () => {
const fetchMock = vi.fn()
.mockResolvedValueOnce(mockJsonResponse({
currentExecutionWorkspace: {
id: "44444444-4444-4444-8444-444444444444",
runtimeServices: [
{
id: "55555555-5555-4555-8555-555555555555",
serviceName: "web",
status: "running",
healthStatus: "healthy",
url: "http://127.0.0.1:5173",
},
],
},
}));
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipWaitForIssueWorkspaceService");
const response = await tool.execute({
issueId: "PAP-1135",
serviceName: "web",
timeoutSeconds: 1,
});
expect(fetchMock).toHaveBeenCalledTimes(1);
expect(response.content[0]?.text).toContain("http://127.0.0.1:5173");
});
[codex] Add structured issue-thread interactions (#4244) ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - Operators supervise that work through issues, comments, approvals, and the board UI. > - Some agent proposals need structured board/user decisions, not hidden markdown conventions or heavyweight governed approvals. > - Issue-thread interactions already provide a natural thread-native surface for proposed tasks and questions. > - This pull request extends that surface with request confirmations, richer interaction cards, and agent/plugin/MCP helpers. > - The benefit is that plan approvals and yes/no decisions become explicit, auditable, and resumable without losing the single-issue workflow. ## What Changed - Added persisted issue-thread interactions for suggested tasks, structured questions, and request confirmations. - Added board UI cards for interaction review, selection, question answers, and accept/reject confirmation flows. - Added MCP and plugin SDK helpers for creating interaction cards from agents/plugins. - Updated agent wake instructions, onboarding assets, Paperclip skill docs, and public docs to prefer structured confirmations for issue-scoped decisions. - Rebased the branch onto `public-gh/master` and renumbered branch migrations to `0063` and `0064`; the idempotency migration uses `ADD COLUMN IF NOT EXISTS` for old branch users. ## Verification - `git diff --check public-gh/master..HEAD` - `pnpm exec vitest run packages/adapter-utils/src/server-utils.test.ts packages/mcp-server/src/tools.test.ts packages/shared/src/issue-thread-interactions.test.ts ui/src/lib/issue-thread-interactions.test.ts ui/src/lib/issue-chat-messages.test.ts ui/src/components/IssueThreadInteractionCard.test.tsx ui/src/components/IssueChatThread.test.tsx server/src/__tests__/issue-thread-interaction-routes.test.ts server/src/__tests__/issue-thread-interactions-service.test.ts server/src/services/issue-thread-interactions.test.ts` -> 9 files / 79 tests passed - `pnpm -r typecheck` -> passed, including `packages/db` migration numbering check ## Risks - Medium: this adds a new issue-thread interaction model across db/shared/server/ui/plugin surfaces. - Migration risk is reduced by placing this branch after current master migrations (`0063`, `0064`) and making the idempotency column add idempotent for users who applied the old branch numbering. - UI interaction behavior is covered by component tests, but this PR does not include browser screenshots. > For core feature work, check [`ROADMAP.md`](ROADMAP.md) first and discuss it in `#dev` before opening the PR. Feature PRs that overlap with planned core work may need to be redirected — check the roadmap first. See `CONTRIBUTING.md`. ## Model Used - OpenAI Codex, GPT-5-class coding agent runtime. Exact model ID and context window are not exposed in this Paperclip run; tool use and local shell/code execution were 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) - [x] I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work - [x] 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>
2026-04-21 20:15:11 -05:00
it("creates suggest_tasks interactions with the expected issue-scoped payload", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ id: "interaction-1", kind: "suggest_tasks" }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipSuggestTasks");
await tool.execute({
issueId: "PAP-1135",
idempotencyKey: "run-1:suggest",
payload: {
version: 1,
tasks: [{ clientKey: "task-1", title: "One" }],
},
});
const [url, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(String(url)).toBe("http://localhost:3100/api/issues/PAP-1135/interactions");
expect(init.method).toBe("POST");
expect(JSON.parse(String(init.body))).toEqual({
kind: "suggest_tasks",
continuationPolicy: "wake_assignee",
idempotencyKey: "run-1:suggest",
payload: {
version: 1,
tasks: [{ clientKey: "task-1", title: "One" }],
},
});
});
it("creates request_confirmation interactions with plan target payloads", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ id: "interaction-1", kind: "request_confirmation" }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipRequestConfirmation");
await tool.execute({
issueId: "PAP-1135",
idempotencyKey: "confirmation:PAP-1135:plan:33333333-3333-4333-8333-333333333333",
title: "Plan approval",
payload: {
version: 1,
prompt: "Accept this plan?",
acceptLabel: "Accept plan",
allowDeclineReason: true,
rejectLabel: "Request changes",
rejectRequiresReason: true,
supersedeOnUserComment: true,
target: {
type: "issue_document",
key: "plan",
revisionId: "33333333-3333-4333-8333-333333333333",
revisionNumber: 3,
},
},
});
const [url, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(String(url)).toBe("http://localhost:3100/api/issues/PAP-1135/interactions");
expect(init.method).toBe("POST");
expect(JSON.parse(String(init.body))).toEqual({
kind: "request_confirmation",
continuationPolicy: "none",
idempotencyKey: "confirmation:PAP-1135:plan:33333333-3333-4333-8333-333333333333",
title: "Plan approval",
payload: {
version: 1,
prompt: "Accept this plan?",
acceptLabel: "Accept plan",
allowDeclineReason: true,
rejectLabel: "Request changes",
rejectRequiresReason: true,
supersedeOnUserComment: true,
target: {
type: "issue_document",
key: "plan",
revisionId: "33333333-3333-4333-8333-333333333333",
revisionNumber: 3,
},
},
});
});
it("creates approvals with the expected company-scoped payload", async () => {
const fetchMock = vi.fn().mockResolvedValue(
mockJsonResponse({ id: "approval-1" }),
);
vi.stubGlobal("fetch", fetchMock);
const tool = getTool("paperclipCreateApproval");
await tool.execute({
type: "hire_agent",
payload: { branch: "pap-1167" },
issueIds: ["44444444-4444-4444-4444-444444444444"],
});
expect(fetchMock).toHaveBeenCalledTimes(1);
const [url, init] = fetchMock.mock.calls[0] as [string, RequestInit];
expect(String(url)).toBe(
"http://localhost:3100/api/companies/11111111-1111-1111-1111-111111111111/approvals",
);
expect(init.method).toBe("POST");
expect(JSON.parse(String(init.body))).toEqual({
type: "hire_agent",
payload: { branch: "pap-1167" },
issueIds: ["44444444-4444-4444-4444-444444444444"],
});
});
it("rejects invalid generic request paths", async () => {
vi.stubGlobal("fetch", vi.fn());
const tool = getTool("paperclipApiRequest");
const response = await tool.execute({
method: "GET",
path: "issues",
});
expect(response.content[0]?.text).toContain("path must start with /");
});
it("rejects generic request paths that escape /api", async () => {
vi.stubGlobal("fetch", vi.fn());
const tool = getTool("paperclipApiRequest");
const response = await tool.execute({
method: "GET",
path: "/../../secret",
});
expect(response.content[0]?.text).toContain("must not contain '..'");
});
});