paperclip/server/src/__tests__/environment-runtime-driver-contract.test.ts
Devin Foley 70679a3321
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

319 lines
9.8 KiB
TypeScript

import { randomUUID } from "node:crypto";
import { createServer, type Server } from "node:http";
import { mkdtemp, rm } from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterAll, afterEach, beforeAll, describe, expect, it } from "vitest";
import { eq } from "drizzle-orm";
import {
buildSshEnvLabFixtureConfig,
getSshEnvLabSupport,
startSshEnvLabFixture,
stopSshEnvLabFixture,
type SshEnvironmentConfig,
} from "@paperclipai/adapter-utils/ssh";
import {
agents,
companies,
companySecretVersions,
companySecrets,
createDb,
environmentLeases,
environments,
heartbeatRuns,
} from "@paperclipai/db";
import type { Environment } from "@paperclipai/shared";
import {
getEmbeddedPostgresTestSupport,
startEmbeddedPostgresTestDatabase,
} from "./helpers/embedded-postgres.js";
import { environmentRuntimeService } from "../services/environment-runtime.js";
import { secretService } from "../services/secrets.js";
const embeddedPostgresSupport = await getEmbeddedPostgresTestSupport();
const describeEmbeddedPostgres = embeddedPostgresSupport.supported ? describe : describe.skip;
const sshFixtureSupport = await getSshEnvLabSupport();
if (!embeddedPostgresSupport.supported) {
console.warn(
`Skipping environment runtime driver contract tests on this host: ${embeddedPostgresSupport.reason ?? "unsupported environment"}`,
);
}
interface RuntimeContractCase {
name: string;
driver: string;
config: Record<string, unknown>;
setup?: () => Promise<() => Promise<void>>;
expectLease: (lease: {
providerLeaseId: string | null;
metadata: Record<string, unknown> | null;
}, environment: Environment) => void;
}
describeEmbeddedPostgres("environment runtime driver contract", () => {
let stopDb: (() => Promise<void>) | null = null;
let db!: ReturnType<typeof createDb>;
const fixtureRoots: string[] = [];
const servers: Server[] = [];
beforeAll(async () => {
const started = await startEmbeddedPostgresTestDatabase("environment-runtime-contract");
stopDb = started.stop;
db = createDb(started.connectionString);
});
afterEach(async () => {
for (const server of servers.splice(0)) {
await new Promise<void>((resolve) => server.close(() => resolve()));
}
while (fixtureRoots.length > 0) {
const root = fixtureRoots.pop();
if (!root) continue;
await stopSshEnvLabFixture(path.join(root, "state.json")).catch(() => undefined);
await rm(root, { recursive: true, force: true }).catch(() => undefined);
}
await db.delete(environmentLeases);
await db.delete(heartbeatRuns);
await db.delete(agents);
await db.delete(environments);
await db.delete(companySecretVersions);
await db.delete(companySecrets);
await db.delete(companies);
});
afterAll(async () => {
await stopDb?.();
});
async function seedEnvironment(input: {
driver: string;
config: Record<string, unknown>;
}) {
const companyId = randomUUID();
const agentId = randomUUID();
const environmentId = randomUUID();
const runId = randomUUID();
const now = new Date();
let config = input.config;
await db.insert(companies).values({
id: companyId,
name: "Acme",
status: "active",
createdAt: now,
updatedAt: now,
});
await db.insert(agents).values({
id: agentId,
companyId,
name: "Contract Agent",
role: "engineer",
status: "active",
adapterType: "codex_local",
adapterConfig: {},
runtimeConfig: {},
permissions: {},
createdAt: now,
updatedAt: now,
});
if (typeof config.privateKey === "string" && config.privateKey.length > 0) {
const secret = await secretService(db).create(companyId, {
name: `environment-contract-private-key-${randomUUID()}`,
provider: "local_encrypted",
value: config.privateKey,
});
config = {
...config,
privateKey: null,
privateKeySecretRef: {
type: "secret_ref",
secretId: secret.id,
version: "latest",
},
};
}
await db.insert(environments).values({
id: environmentId,
companyId,
name: `${input.driver} contract`,
driver: input.driver,
status: "active",
config,
createdAt: now,
updatedAt: now,
});
await db.insert(heartbeatRuns).values({
id: runId,
companyId,
agentId,
invocationSource: "manual",
status: "running",
createdAt: now,
updatedAt: now,
});
return {
companyId,
issueId: null,
runId,
environment: {
id: environmentId,
companyId,
name: `${input.driver} contract`,
description: null,
driver: input.driver,
status: "active",
config,
metadata: null,
createdAt: now,
updatedAt: now,
} as Environment,
};
}
async function startHealthServer() {
const server = createServer((req, res) => {
if (req.url === "/api/health") {
res.writeHead(200, { "content-type": "application/json" });
res.end(JSON.stringify({ status: "ok" }));
return;
}
res.writeHead(404).end();
});
await new Promise<void>((resolve, reject) => {
server.once("error", reject);
server.listen(0, "127.0.0.1", () => resolve());
});
servers.push(server);
const address = server.address();
if (!address || typeof address === "string") {
throw new Error("Expected health server to listen on a TCP port.");
}
return `http://127.0.0.1:${address.port}`;
}
async function runContract(testCase: RuntimeContractCase) {
const cleanup = await testCase.setup?.();
try {
const runtime = environmentRuntimeService(db);
const { companyId, environment, issueId, runId } = await seedEnvironment({
driver: testCase.driver,
config: testCase.config,
});
const acquired = await runtime.acquireRunLease({
companyId,
environment,
issueId,
heartbeatRunId: runId,
persistedExecutionWorkspace: null,
});
expect(acquired.environment.id).toBe(environment.id);
expect(acquired.lease.companyId).toBe(companyId);
expect(acquired.lease.environmentId).toBe(environment.id);
expect(acquired.lease.issueId).toBeNull();
expect(acquired.lease.heartbeatRunId).toBe(runId);
expect(acquired.lease.status).toBe("active");
expect(acquired.leaseContext).toEqual({
executionWorkspaceId: null,
executionWorkspaceMode: null,
});
expect(acquired.lease.metadata).toMatchObject({
driver: testCase.driver,
executionWorkspaceMode: null,
});
testCase.expectLease(acquired.lease, environment);
const released = await runtime.releaseRunLeases(runId);
expect(released).toHaveLength(1);
expect(released[0]?.environment.id).toBe(environment.id);
expect(released[0]?.lease.id).toBe(acquired.lease.id);
expect(released[0]?.lease.status).toBe("released");
const activeRows = await db
.select()
.from(environmentLeases)
.where(eq(environmentLeases.status, "active"));
expect(activeRows).toHaveLength(0);
await expect(runtime.releaseRunLeases(runId)).resolves.toEqual([]);
} finally {
await cleanup?.();
}
}
const contractCases: RuntimeContractCase[] = [
{
name: "local",
driver: "local",
config: {},
expectLease: (lease) => {
expect(lease.providerLeaseId).toBeNull();
},
},
{
name: "fake sandbox",
driver: "sandbox",
config: {
provider: "fake",
image: "ubuntu:24.04",
reuseLease: false,
},
expectLease: (lease) => {
expect(lease.providerLeaseId).toMatch(/^sandbox:\/\/fake\/[0-9a-f-]+\/[0-9a-f-]+$/);
expect(lease.metadata).toMatchObject({
provider: "fake",
image: "ubuntu:24.04",
reuseLease: false,
});
},
},
];
for (const testCase of contractCases) {
it(`${testCase.name} satisfies the acquire/release host contract`, async () => {
await runContract(testCase);
});
}
it("SSH satisfies the acquire/release host contract", async () => {
if (!sshFixtureSupport.supported) {
console.warn(`Skipping SSH driver contract test: ${sshFixtureSupport.reason ?? "unsupported environment"}`);
return;
}
const fixtureRoot = await mkdtemp(path.join(os.tmpdir(), "paperclip-env-runtime-contract-ssh-"));
fixtureRoots.push(fixtureRoot);
const fixture = await startSshEnvLabFixture({ statePath: path.join(fixtureRoot, "state.json") });
const sshConfig = await buildSshEnvLabFixtureConfig(fixture);
const runtimeApiUrl = await startHealthServer();
const previousCandidates = process.env.PAPERCLIP_RUNTIME_API_CANDIDATES_JSON;
process.env.PAPERCLIP_RUNTIME_API_CANDIDATES_JSON = JSON.stringify([runtimeApiUrl]);
await runContract({
name: "ssh",
driver: "ssh",
config: sshConfig as SshEnvironmentConfig as unknown as Record<string, unknown>,
expectLease: (lease) => {
expect(lease.providerLeaseId).toContain(`ssh://${sshConfig.username}@${sshConfig.host}:${sshConfig.port}`);
expect(lease.metadata).toMatchObject({
host: sshConfig.host,
port: sshConfig.port,
username: sshConfig.username,
remoteWorkspacePath: sshConfig.remoteWorkspacePath,
remoteCwd: sshConfig.remoteWorkspacePath,
paperclipApiUrl: runtimeApiUrl,
});
},
setup: async () => async () => {
if (previousCandidates === undefined) {
delete process.env.PAPERCLIP_RUNTIME_API_CANDIDATES_JSON;
} else {
process.env.PAPERCLIP_RUNTIME_API_CANDIDATES_JSON = previousCandidates;
}
},
});
});
});