forked from farhoodlabs/paperclip
Add sandbox environment support (#4415)
## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies. > - The environment/runtime layer decides where agent work executes and how the control plane reaches those runtimes. > - Today Paperclip can run locally and over SSH, but sandboxed execution needs a first-class environment model instead of one-off adapter behavior. > - We also want sandbox providers to be pluggable so the core does not hardcode every provider implementation. > - This branch adds the Sandbox environment path, the provider contract, and a deterministic fake provider plugin. > - That required synchronized changes across shared contracts, plugin SDK surfaces, server runtime orchestration, and the UI environment/workspace flows. > - The result is that sandbox execution becomes a core control-plane capability while keeping provider implementations extensible and testable. ## What Changed - Added sandbox runtime support to the environment execution path, including runtime URL discovery, sandbox execution targeting, orchestration, and heartbeat integration. - Added plugin-provider support for sandbox environments so providers can be supplied via plugins instead of hardcoded server logic. - Added the fake sandbox provider plugin with deterministic behavior suitable for local and automated testing. - Updated shared types, validators, plugin protocol definitions, and SDK helpers to carry sandbox provider and workspace-runtime contracts across package boundaries. - Updated server routes and services so companies can create sandbox environments, select them for work, and execute work through the sandbox runtime path. - Updated the UI environment and workspace surfaces to expose sandbox environment configuration and selection. - Added test coverage for sandbox runtime behavior, provider seams, environment route guards, orchestration, and the fake provider plugin. ## Verification - Ran locally before the final fixture-only scrub: - `pnpm -r typecheck` - `pnpm test:run` - `pnpm build` - Ran locally after the final scrub amend: - `pnpm vitest run server/src/__tests__/runtime-api.test.ts` - Reviewer spot checks: - create a sandbox environment backed by the fake provider plugin - run work through that environment - confirm sandbox provider execution does not inherit host secrets implicitly ## Risks - This touches shared contracts, plugin SDK plumbing, server runtime orchestration, and UI environment/workspace flows, so regressions would likely show up as cross-layer mismatches rather than isolated type errors. - Runtime URL discovery and sandbox callback selection are sensitive to host/bind configuration; if that logic is wrong, sandbox-backed callbacks may fail even when execution succeeds. - The fake provider plugin is intentionally deterministic and test-oriented; future providers may expose capability gaps that this branch does not yet cover. ## Model Used - OpenAI Codex coding agent on a GPT-5-class backend in the Paperclip/Codex harness. Exact backend model ID is not exposed in-session. Tool-assisted workflow with shell execution, file editing, git history inspection, and local test execution. ## 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
This commit is contained in:
Devin Foley
@@ -0,0 +1,223 @@
|
||||
import { randomUUID } from "node:crypto";
|
||||
import { mkdtemp, rm } from "node:fs/promises";
|
||||
import os from "node:os";
|
||||
import path from "node:path";
|
||||
import { afterAll, afterEach, beforeAll, describe, expect, it, vi } from "vitest";
|
||||
import {
|
||||
agents,
|
||||
companies,
|
||||
createDb,
|
||||
environments,
|
||||
plugins,
|
||||
projects,
|
||||
projectWorkspaces,
|
||||
} from "@paperclipai/db";
|
||||
import {
|
||||
getEmbeddedPostgresTestSupport,
|
||||
startEmbeddedPostgresTestDatabase,
|
||||
} from "./helpers/embedded-postgres.js";
|
||||
import { heartbeatService } from "../services/heartbeat.ts";
|
||||
import type { PluginWorkerManager } from "../services/plugin-worker-manager.ts";
|
||||
|
||||
const adapterExecute = vi.hoisted(() => vi.fn(async () => ({
|
||||
exitCode: 0,
|
||||
signal: null,
|
||||
timedOut: false,
|
||||
sessionParams: { sessionId: "session-1" },
|
||||
sessionDisplayId: "session-1",
|
||||
provider: "test",
|
||||
model: "test-model",
|
||||
})));
|
||||
|
||||
vi.mock("../adapters/index.js", () => ({
|
||||
getServerAdapter: () => ({
|
||||
type: "codex_local",
|
||||
execute: adapterExecute,
|
||||
supportsLocalAgentJwt: false,
|
||||
}),
|
||||
runningProcesses: new Map(),
|
||||
}));
|
||||
|
||||
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
|
||||
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
|
||||
|
||||
if (!embeddedPostgresSupport.supported) {
|
||||
console.warn(
|
||||
`Skipping embedded Postgres heartbeat plugin environment tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
|
||||
);
|
||||
}
|
||||
|
||||
describeEmbeddedPostgres("heartbeat plugin environments", () => {
|
||||
let stopDb: (() => Promise<void>) | null = null;
|
||||
let db!: ReturnType<typeof createDb>;
|
||||
const tempRoots: string[] = [];
|
||||
|
||||
beforeAll(async () => {
|
||||
const started = await startEmbeddedPostgresTestDatabase("heartbeat-plugin-environment");
|
||||
stopDb = started.stop;
|
||||
db = createDb(started.connectionString);
|
||||
}, 20_000);
|
||||
|
||||
afterEach(async () => {
|
||||
adapterExecute.mockClear();
|
||||
while (tempRoots.length > 0) {
|
||||
const root = tempRoots.pop();
|
||||
if (root) await rm(root, { recursive: true, force: true }).catch(() => undefined);
|
||||
}
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await stopDb?.();
|
||||
});
|
||||
|
||||
it("acquires plugin environment leases through the heartbeat execution path", async () => {
|
||||
const companyId = randomUUID();
|
||||
const projectId = randomUUID();
|
||||
const workspaceId = randomUUID();
|
||||
const environmentId = randomUUID();
|
||||
const pluginId = randomUUID();
|
||||
const agentId = randomUUID();
|
||||
const workspaceRoot = await mkdtemp(path.join(os.tmpdir(), "paperclip-plugin-env-heartbeat-"));
|
||||
tempRoots.push(workspaceRoot);
|
||||
const workerManager = {
|
||||
isRunning: vi.fn((id: string) => id === pluginId),
|
||||
call: vi.fn(async (_pluginId: string, method: string) => {
|
||||
if (method === "environmentAcquireLease") {
|
||||
return {
|
||||
providerLeaseId: "plugin-heartbeat-lease",
|
||||
metadata: {
|
||||
remoteCwd: "/workspace/project",
|
||||
},
|
||||
};
|
||||
}
|
||||
if (method === "environmentReleaseLease") {
|
||||
return undefined;
|
||||
}
|
||||
throw new Error(`Unexpected plugin environment method: ${method}`);
|
||||
}),
|
||||
} as unknown as PluginWorkerManager;
|
||||
|
||||
await db.insert(companies).values({
|
||||
id: companyId,
|
||||
name: "Acme",
|
||||
status: "active",
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
await db.insert(projects).values({
|
||||
id: projectId,
|
||||
companyId,
|
||||
name: "Plugin Environment Heartbeat",
|
||||
status: "active",
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
await db.insert(projectWorkspaces).values({
|
||||
id: workspaceId,
|
||||
companyId,
|
||||
projectId,
|
||||
name: "Primary",
|
||||
cwd: workspaceRoot,
|
||||
isPrimary: true,
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
await db.insert(plugins).values({
|
||||
id: pluginId,
|
||||
pluginKey: "acme.environments",
|
||||
packageName: "@acme/paperclip-environments",
|
||||
version: "1.0.0",
|
||||
apiVersion: 1,
|
||||
categories: ["automation"],
|
||||
manifestJson: {
|
||||
id: "acme.environments",
|
||||
apiVersion: 1,
|
||||
version: "1.0.0",
|
||||
displayName: "Acme Environments",
|
||||
description: "Test plugin environment driver",
|
||||
author: "Acme",
|
||||
categories: ["automation"],
|
||||
capabilities: ["environment.drivers.register"],
|
||||
entrypoints: { worker: "dist/worker.js" },
|
||||
environmentDrivers: [
|
||||
{
|
||||
driverKey: "sandbox",
|
||||
displayName: "Sandbox",
|
||||
configSchema: { type: "object" },
|
||||
},
|
||||
],
|
||||
},
|
||||
status: "ready",
|
||||
installOrder: 1,
|
||||
updatedAt: new Date(),
|
||||
} as any);
|
||||
await db.insert(environments).values({
|
||||
id: environmentId,
|
||||
companyId,
|
||||
name: "Plugin Sandbox",
|
||||
driver: "plugin",
|
||||
status: "active",
|
||||
config: {
|
||||
pluginKey: "acme.environments",
|
||||
driverKey: "sandbox",
|
||||
driverConfig: {
|
||||
template: "base",
|
||||
},
|
||||
},
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
await db.insert(agents).values({
|
||||
id: agentId,
|
||||
companyId,
|
||||
name: "CodexCoder",
|
||||
role: "engineer",
|
||||
status: "idle",
|
||||
adapterType: "codex_local",
|
||||
adapterConfig: {},
|
||||
runtimeConfig: {},
|
||||
defaultEnvironmentId: environmentId,
|
||||
permissions: {},
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
|
||||
const heartbeat = heartbeatService(db, { pluginWorkerManager: workerManager });
|
||||
const run = await heartbeat.wakeup(agentId, {
|
||||
source: "on_demand",
|
||||
triggerDetail: "manual",
|
||||
contextSnapshot: { projectId },
|
||||
});
|
||||
|
||||
expect(run).not.toBeNull();
|
||||
await vi.waitFor(async () => {
|
||||
const latest = await heartbeat.getRun(run!.id);
|
||||
expect(latest?.status).toBe("succeeded");
|
||||
}, { timeout: 5_000 });
|
||||
|
||||
expect(workerManager.call).toHaveBeenCalledWith(pluginId, "environmentAcquireLease", {
|
||||
driverKey: "sandbox",
|
||||
companyId,
|
||||
environmentId,
|
||||
config: { template: "base" },
|
||||
runId: run!.id,
|
||||
workspaceMode: "shared_workspace",
|
||||
});
|
||||
await vi.waitFor(() => {
|
||||
expect(workerManager.call).toHaveBeenCalledWith(pluginId, "environmentReleaseLease", {
|
||||
driverKey: "sandbox",
|
||||
companyId,
|
||||
environmentId,
|
||||
config: { template: "base" },
|
||||
providerLeaseId: "plugin-heartbeat-lease",
|
||||
leaseMetadata: expect.objectContaining({
|
||||
driver: "plugin",
|
||||
pluginId,
|
||||
pluginKey: "acme.environments",
|
||||
driverKey: "sandbox",
|
||||
}),
|
||||
});
|
||||
}, { timeout: 5_000 });
|
||||
expect(adapterExecute).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user