Files
paperclip/packages/adapter-utils/src/sandbox-managed-runtime.test.ts
T
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

127 lines
6.3 KiB
TypeScript

import { lstat, mkdir, mkdtemp, readFile, rm, symlink, writeFile } from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { execFile as execFileCallback } from "node:child_process";
import { promisify } from "node:util";
import { afterEach, describe, expect, it } from "vitest";
import {
mirrorDirectory,
prepareSandboxManagedRuntime,
type SandboxManagedRuntimeClient,
} from "./sandbox-managed-runtime.js";
const execFile = promisify(execFileCallback);
describe("sandbox managed runtime", () => {
const cleanupDirs: string[] = [];
afterEach(async () => {
while (cleanupDirs.length > 0) {
const dir = cleanupDirs.pop();
if (!dir) continue;
await rm(dir, { recursive: true, force: true }).catch(() => undefined);
}
});
it("preserves excluded local workspace artifacts during restore mirroring", async () => {
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-sandbox-restore-"));
cleanupDirs.push(rootDir);
const sourceDir = path.join(rootDir, "source");
const targetDir = path.join(rootDir, "target");
await mkdir(path.join(sourceDir, "src"), { recursive: true });
await mkdir(path.join(targetDir, ".claude"), { recursive: true });
await mkdir(path.join(targetDir, ".paperclip-runtime"), { recursive: true });
await writeFile(path.join(sourceDir, "src", "app.ts"), "export const value = 2;\n", "utf8");
await writeFile(path.join(targetDir, "stale.txt"), "remove me\n", "utf8");
await writeFile(path.join(targetDir, ".claude", "settings.json"), "{\"keep\":true}\n", "utf8");
await writeFile(path.join(targetDir, ".claude.json"), "{\"keep\":true}\n", "utf8");
await writeFile(path.join(targetDir, ".paperclip-runtime", "state.json"), "{}\n", "utf8");
await mirrorDirectory(sourceDir, targetDir, {
preserveAbsent: [".paperclip-runtime", ".claude", ".claude.json"],
});
await expect(readFile(path.join(targetDir, "src", "app.ts"), "utf8")).resolves.toBe("export const value = 2;\n");
await expect(readFile(path.join(targetDir, ".claude", "settings.json"), "utf8")).resolves.toBe("{\"keep\":true}\n");
await expect(readFile(path.join(targetDir, ".claude.json"), "utf8")).resolves.toBe("{\"keep\":true}\n");
await expect(readFile(path.join(targetDir, ".paperclip-runtime", "state.json"), "utf8")).resolves.toBe("{}\n");
await expect(readFile(path.join(targetDir, "stale.txt"), "utf8")).rejects.toMatchObject({ code: "ENOENT" });
});
it("syncs workspace and assets through a provider-neutral sandbox client", async () => {
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-sandbox-managed-"));
cleanupDirs.push(rootDir);
const localWorkspaceDir = path.join(rootDir, "local-workspace");
const remoteWorkspaceDir = path.join(rootDir, "remote-workspace");
const localAssetsDir = path.join(rootDir, "local-assets");
const linkedAssetPath = path.join(rootDir, "linked-skill.md");
await mkdir(path.join(localWorkspaceDir, ".claude"), { recursive: true });
await mkdir(localAssetsDir, { recursive: true });
await writeFile(path.join(localWorkspaceDir, "README.md"), "local workspace\n", "utf8");
await writeFile(path.join(localWorkspaceDir, "._README.md"), "appledouble\n", "utf8");
await writeFile(path.join(localWorkspaceDir, ".claude", "settings.json"), "{\"local\":true}\n", "utf8");
await writeFile(linkedAssetPath, "skill body\n", "utf8");
await symlink(linkedAssetPath, path.join(localAssetsDir, "skill.md"));
const client: SandboxManagedRuntimeClient = {
makeDir: async (remotePath) => {
await mkdir(remotePath, { recursive: true });
},
writeFile: async (remotePath, bytes) => {
await mkdir(path.dirname(remotePath), { recursive: true });
await writeFile(remotePath, Buffer.from(bytes));
},
readFile: async (remotePath) => await readFile(remotePath),
remove: async (remotePath) => {
await rm(remotePath, { recursive: true, force: true });
},
run: async (command) => {
await execFile("sh", ["-lc", command], {
maxBuffer: 32 * 1024 * 1024,
});
},
};
const prepared = await prepareSandboxManagedRuntime({
spec: {
transport: "sandbox",
provider: "test",
sandboxId: "sandbox-1",
remoteCwd: remoteWorkspaceDir,
timeoutMs: 30_000,
apiKey: null,
},
adapterKey: "test-adapter",
client,
workspaceLocalDir: localWorkspaceDir,
workspaceExclude: [".claude"],
preserveAbsentOnRestore: [".claude"],
assets: [{
key: "skills",
localDir: localAssetsDir,
followSymlinks: true,
}],
});
await expect(readFile(path.join(remoteWorkspaceDir, "README.md"), "utf8")).resolves.toBe("local workspace\n");
await expect(readFile(path.join(remoteWorkspaceDir, "._README.md"), "utf8")).rejects.toMatchObject({ code: "ENOENT" });
await expect(readFile(path.join(remoteWorkspaceDir, ".claude", "settings.json"), "utf8")).rejects.toMatchObject({ code: "ENOENT" });
await expect(readFile(path.join(prepared.assetDirs.skills, "skill.md"), "utf8")).resolves.toBe("skill body\n");
expect((await lstat(path.join(prepared.assetDirs.skills, "skill.md"))).isFile()).toBe(true);
await writeFile(path.join(remoteWorkspaceDir, "README.md"), "remote workspace\n", "utf8");
await writeFile(path.join(remoteWorkspaceDir, "remote-only.txt"), "sync back\n", "utf8");
await mkdir(path.join(localWorkspaceDir, ".paperclip-runtime"), { recursive: true });
await writeFile(path.join(localWorkspaceDir, ".paperclip-runtime", "state.json"), "{}\n", "utf8");
await writeFile(path.join(localWorkspaceDir, "local-stale.txt"), "remove\n", "utf8");
await prepared.restoreWorkspace();
await expect(readFile(path.join(localWorkspaceDir, "README.md"), "utf8")).resolves.toBe("remote workspace\n");
await expect(readFile(path.join(localWorkspaceDir, "remote-only.txt"), "utf8")).resolves.toBe("sync back\n");
await expect(readFile(path.join(localWorkspaceDir, "local-stale.txt"), "utf8")).rejects.toMatchObject({ code: "ENOENT" });
await expect(readFile(path.join(localWorkspaceDir, ".claude", "settings.json"), "utf8")).resolves.toBe("{\"local\":true}\n");
await expect(readFile(path.join(localWorkspaceDir, ".paperclip-runtime", "state.json"), "utf8")).resolves.toBe("{}\n");
});
});