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
@@ -1,16 +1,25 @@
|
||||
import { beforeEach, describe, expect, it, vi } from "vitest";
|
||||
|
||||
const mockEnsureSshWorkspaceReady = vi.hoisted(() => vi.fn());
|
||||
const mockProbePluginEnvironmentDriver = vi.hoisted(() => vi.fn());
|
||||
const mockProbePluginSandboxProviderDriver = vi.hoisted(() => vi.fn());
|
||||
|
||||
vi.mock("@paperclipai/adapter-utils/ssh", () => ({
|
||||
ensureSshWorkspaceReady: mockEnsureSshWorkspaceReady,
|
||||
}));
|
||||
|
||||
vi.mock("../services/plugin-environment-driver.js", () => ({
|
||||
probePluginEnvironmentDriver: mockProbePluginEnvironmentDriver,
|
||||
probePluginSandboxProviderDriver: mockProbePluginSandboxProviderDriver,
|
||||
}));
|
||||
|
||||
import { probeEnvironment } from "../services/environment-probe.ts";
|
||||
|
||||
describe("probeEnvironment", () => {
|
||||
beforeEach(() => {
|
||||
mockEnsureSshWorkspaceReady.mockReset();
|
||||
mockProbePluginEnvironmentDriver.mockReset();
|
||||
mockProbePluginSandboxProviderDriver.mockReset();
|
||||
});
|
||||
|
||||
it("reports local environments as immediately available", async () => {
|
||||
@@ -75,6 +84,123 @@ describe("probeEnvironment", () => {
|
||||
expect(mockEnsureSshWorkspaceReady).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it("reports fake sandbox environments as ready without external calls", async () => {
|
||||
const result = await probeEnvironment({} as any, {
|
||||
id: "env-sandbox",
|
||||
companyId: "company-1",
|
||||
name: "Fake Sandbox",
|
||||
description: null,
|
||||
driver: "sandbox",
|
||||
status: "active",
|
||||
config: {
|
||||
provider: "fake",
|
||||
image: "ubuntu:24.04",
|
||||
reuseLease: true,
|
||||
},
|
||||
metadata: null,
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
});
|
||||
|
||||
expect(result).toEqual({
|
||||
ok: true,
|
||||
driver: "sandbox",
|
||||
summary: "Fake sandbox provider is ready for image ubuntu:24.04.",
|
||||
details: {
|
||||
provider: "fake",
|
||||
image: "ubuntu:24.04",
|
||||
reuseLease: true,
|
||||
},
|
||||
});
|
||||
expect(mockEnsureSshWorkspaceReady).not.toHaveBeenCalled();
|
||||
});
|
||||
|
||||
it("routes plugin-backed sandbox provider probes through plugin workers", async () => {
|
||||
mockProbePluginSandboxProviderDriver.mockResolvedValue({
|
||||
ok: true,
|
||||
driver: "sandbox",
|
||||
summary: "Fake plugin probe passed.",
|
||||
details: {
|
||||
provider: "fake-plugin",
|
||||
metadata: { ready: true },
|
||||
},
|
||||
});
|
||||
const workerManager = {} as any;
|
||||
|
||||
const result = await probeEnvironment({} as any, {
|
||||
id: "env-sandbox-plugin",
|
||||
companyId: "company-1",
|
||||
name: "Fake Plugin Sandbox",
|
||||
description: null,
|
||||
driver: "sandbox",
|
||||
status: "active",
|
||||
config: {
|
||||
provider: "fake-plugin",
|
||||
image: "fake:test",
|
||||
reuseLease: false,
|
||||
},
|
||||
metadata: null,
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
}, { pluginWorkerManager: workerManager });
|
||||
|
||||
expect(result.ok).toBe(true);
|
||||
expect(mockProbePluginSandboxProviderDriver).toHaveBeenCalledWith({
|
||||
db: expect.anything(),
|
||||
workerManager,
|
||||
companyId: "company-1",
|
||||
environmentId: "env-sandbox-plugin",
|
||||
provider: "fake-plugin",
|
||||
config: {
|
||||
provider: "fake-plugin",
|
||||
image: "fake:test",
|
||||
reuseLease: false,
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("routes plugin environment probes through the plugin worker host", async () => {
|
||||
mockProbePluginEnvironmentDriver.mockResolvedValue({
|
||||
ok: true,
|
||||
driver: "plugin",
|
||||
summary: "Plugin probe passed.",
|
||||
details: {
|
||||
metadata: { ready: true },
|
||||
},
|
||||
});
|
||||
const workerManager = {} as any;
|
||||
|
||||
const result = await probeEnvironment({} as any, {
|
||||
id: "env-plugin",
|
||||
companyId: "company-1",
|
||||
name: "Plugin Sandbox",
|
||||
description: null,
|
||||
driver: "plugin",
|
||||
status: "active",
|
||||
config: {
|
||||
pluginKey: "acme.environments",
|
||||
driverKey: "sandbox",
|
||||
driverConfig: { template: "base" },
|
||||
},
|
||||
metadata: null,
|
||||
createdAt: new Date(),
|
||||
updatedAt: new Date(),
|
||||
}, { pluginWorkerManager: workerManager });
|
||||
|
||||
expect(result.ok).toBe(true);
|
||||
expect(mockProbePluginEnvironmentDriver).toHaveBeenCalledWith({
|
||||
db: expect.anything(),
|
||||
workerManager,
|
||||
companyId: "company-1",
|
||||
environmentId: "env-plugin",
|
||||
config: {
|
||||
pluginKey: "acme.environments",
|
||||
driverKey: "sandbox",
|
||||
driverConfig: { template: "base" },
|
||||
},
|
||||
});
|
||||
});
|
||||
|
||||
it("captures SSH probe failures without throwing", async () => {
|
||||
mockEnsureSshWorkspaceReady.mockRejectedValue(
|
||||
Object.assign(new Error("Permission denied"), {
|
||||
|
||||
Reference in New Issue
Block a user