paperclip/server/src/__tests__/sandbox-provider-runtime.test.ts

161 lines
4.5 KiB
TypeScript
Raw Normal View History

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
2026-04-24 12:15:53 -07:00
import { describe, expect, it } from "vitest";
import {
acquireSandboxProviderLease,
findReusableSandboxProviderLeaseId,
getSandboxProvider,
listSandboxProviders,
probeSandboxProvider,
releaseSandboxProviderLease,
sandboxConfigFromLeaseMetadata,
sandboxConfigFromLeaseMetadataLoose,
validateSandboxProviderConfig,
} from "../services/sandbox-provider-runtime.ts";
describe("sandbox provider runtime", () => {
it("exposes fake as the built-in sandbox provider implementation", async () => {
expect(listSandboxProviders().map((provider) => provider.provider).sort()).toEqual(["fake"]);
expect(getSandboxProvider("fake")?.provider).toBe("fake");
expect(getSandboxProvider("fake-plugin")).toBeNull();
await expect(
validateSandboxProviderConfig({
provider: "fake",
image: "ubuntu:24.04",
reuseLease: true,
}),
).resolves.toEqual(
expect.objectContaining({
ok: true,
details: expect.objectContaining({
provider: "fake",
image: "ubuntu:24.04",
}),
}),
);
});
it("does not route plugin-backed providers through the built-in provider helper", async () => {
await expect(probeSandboxProvider({
provider: "fake-plugin",
image: "fake:test",
timeoutMs: 300000,
reuseLease: false,
})).rejects.toThrow('Sandbox provider "fake-plugin" is not registered as a built-in provider.');
});
it("acquires and resumes fake leases deterministically", async () => {
const lease = await acquireSandboxProviderLease({
config: {
provider: "fake",
image: "ubuntu:24.04",
reuseLease: true,
},
environmentId: "env-1",
heartbeatRunId: "run-1",
issueId: "issue-1",
});
expect(lease.providerLeaseId).toBe("sandbox://fake/env-1");
expect(lease.metadata).toEqual(expect.objectContaining({
provider: "fake",
image: "ubuntu:24.04",
reuseLease: true,
}));
const resumed = await acquireSandboxProviderLease({
config: {
provider: "fake",
image: "ubuntu:24.04",
reuseLease: true,
},
environmentId: "env-1",
heartbeatRunId: "run-2",
issueId: "issue-1",
reusableProviderLeaseId: lease.providerLeaseId,
});
expect(resumed.providerLeaseId).toBe(lease.providerLeaseId);
expect(resumed.metadata).toEqual(expect.objectContaining({ resumedLease: true }));
});
it("matches reusable fake leases through the selected provider implementation", () => {
expect(
findReusableSandboxProviderLeaseId({
config: {
provider: "fake",
image: "image-b",
reuseLease: true,
},
leases: [
{
providerLeaseId: "sandbox-image-a",
metadata: {
provider: "fake",
image: "image-a",
reuseLease: true,
},
},
{
providerLeaseId: "sandbox-image-b",
metadata: {
provider: "fake",
image: "image-b",
reuseLease: true,
},
},
],
}),
).toBe("sandbox-image-b");
});
it("reconstructs fake sandbox config from lease metadata for later release", () => {
const metadata = {
provider: "fake",
image: "paperclip-test",
reuseLease: true,
};
expect(sandboxConfigFromLeaseMetadata({ metadata })).toEqual({
provider: "fake",
image: "paperclip-test",
reuseLease: true,
});
expect(sandboxConfigFromLeaseMetadataLoose({ metadata })).toEqual({
provider: "fake",
image: "paperclip-test",
reuseLease: true,
});
});
it("reconstructs plugin-backed sandbox config from lease metadata for runtime recovery", () => {
const metadata = {
provider: "fake-plugin",
reuseLease: true,
timeoutMs: 45_000,
remoteCwd: "/workspace/project",
fakeRootDir: "/tmp/fake-root",
};
expect(sandboxConfigFromLeaseMetadataLoose({ metadata })).toEqual({
provider: "fake-plugin",
reuseLease: true,
timeoutMs: 45_000,
remoteCwd: "/workspace/project",
fakeRootDir: "/tmp/fake-root",
});
});
it("releases fake leases without external side effects", async () => {
await expect(releaseSandboxProviderLease({
config: {
provider: "fake",
image: "ubuntu:24.04",
reuseLease: true,
},
providerLeaseId: "sandbox://fake/env-1",
status: "released",
})).resolves.toBeUndefined();
});
});