paperclip/server/src/__tests__/plugin-environment-driver-seam.test.ts

169 lines
5.7 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 { PassThrough } from "node:stream";
import { describe, expect, it } from "vitest";
import {
PLUGIN_RPC_ERROR_CODES,
createRequest,
isJsonRpcErrorResponse,
isJsonRpcSuccessResponse,
parseMessage,
serializeMessage,
} from "../../../packages/plugins/sdk/src/protocol.js";
import { definePlugin } from "../../../packages/plugins/sdk/src/define-plugin.js";
import { startWorkerRpcHost } from "../../../packages/plugins/sdk/src/worker-rpc-host.js";
import { pluginManifestV1Schema, type PaperclipPluginManifestV1 } from "@paperclipai/shared";
import { pluginCapabilityValidator } from "../services/plugin-capability-validator.js";
const baseManifest: PaperclipPluginManifestV1 = {
id: "test.environment-driver",
apiVersion: 1,
version: "1.0.0",
displayName: "Environment Driver",
description: "Test environment driver plugin",
author: "Paperclip",
categories: ["automation"],
capabilities: ["environment.drivers.register"],
entrypoints: { worker: "dist/worker.js" },
environmentDrivers: [
{
driverKey: "fake-plugin",
displayName: "Fake plugin",
configSchema: {
type: "object",
properties: {
template: { type: "string" },
},
required: ["template"],
},
},
],
};
describe("plugin environment driver seam", () => {
it("validates environment driver manifest declarations", () => {
expect(pluginManifestV1Schema.safeParse(baseManifest).success).toBe(true);
const missingCapability = pluginManifestV1Schema.safeParse({
...baseManifest,
capabilities: ["http.outbound"],
});
expect(missingCapability.success).toBe(false);
expect(JSON.stringify(missingCapability.error?.issues)).toContain(
"environment.drivers.register",
);
const duplicateDriver = pluginManifestV1Schema.safeParse({
...baseManifest,
environmentDrivers: [
baseManifest.environmentDrivers![0],
{ ...baseManifest.environmentDrivers![0], displayName: "Duplicate" },
],
});
expect(duplicateDriver.success).toBe(false);
expect(JSON.stringify(duplicateDriver.error?.issues)).toContain(
"Duplicate environment driver keys",
);
});
it("enforces environment driver capability requirements", () => {
const validator = pluginCapabilityValidator();
expect(validator.getRequiredCapabilities("environment.acquireLease")).toEqual([
"environment.drivers.register",
]);
expect(validator.checkOperation(baseManifest, "environment.execute").allowed).toBe(true);
const withoutCapability = {
...baseManifest,
capabilities: ["http.outbound"],
} satisfies PaperclipPluginManifestV1;
expect(validator.checkOperation(withoutCapability, "environment.execute")).toMatchObject({
allowed: false,
missing: ["environment.drivers.register"],
});
expect(validator.validateManifestCapabilities(withoutCapability)).toMatchObject({
allowed: false,
missing: ["environment.drivers.register"],
});
});
it("dispatches environment driver worker hooks and reports support", async () => {
const plugin = definePlugin({
async setup() {},
async onEnvironmentProbe(params) {
return {
ok: true,
summary: `probed ${params.driverKey}`,
metadata: { environmentId: params.environmentId },
};
},
});
const stdin = new PassThrough();
const stdout = new PassThrough();
const host = startWorkerRpcHost({ plugin, stdin, stdout });
const responses: unknown[] = [];
stdout.on("data", (chunk) => {
const lines = String(chunk).split("\n").filter(Boolean);
for (const line of lines) {
responses.push(parseMessage(line));
}
});
stdin.write(serializeMessage(createRequest("initialize", {
manifest: baseManifest,
config: {},
instanceInfo: { instanceId: "instance-1", hostVersion: "1.0.0" },
apiVersion: 1,
}, 1)));
await waitForResponses(responses, 1);
const initializeResponse = responses[0];
expect(isJsonRpcSuccessResponse(initializeResponse)).toBe(true);
if (!isJsonRpcSuccessResponse(initializeResponse)) return;
expect(initializeResponse.result.supportedMethods).toContain("environmentProbe");
stdin.write(serializeMessage(createRequest("environmentProbe", {
driverKey: "fake-plugin",
companyId: "company-1",
environmentId: "environment-1",
config: { template: "base" },
}, 2)));
await waitForResponses(responses, 2);
const probeResponse = responses[1];
expect(isJsonRpcSuccessResponse(probeResponse)).toBe(true);
if (!isJsonRpcSuccessResponse(probeResponse)) return;
expect(probeResponse.result).toMatchObject({
ok: true,
summary: "probed fake-plugin",
metadata: { environmentId: "environment-1" },
});
stdin.write(serializeMessage(createRequest("environmentExecute", {
driverKey: "fake-plugin",
companyId: "company-1",
environmentId: "environment-1",
config: { template: "base" },
lease: { providerLeaseId: "lease-1" },
command: "echo",
}, 3)));
await waitForResponses(responses, 3);
const executeResponse = responses[2];
expect(isJsonRpcErrorResponse(executeResponse)).toBe(true);
if (!isJsonRpcErrorResponse(executeResponse)) return;
expect(executeResponse.error.code).toBe(PLUGIN_RPC_ERROR_CODES.METHOD_NOT_IMPLEMENTED);
expect(executeResponse.error.message).toContain("environmentExecute");
host.stop();
});
});
async function waitForResponses(responses: unknown[], count: number): Promise<void> {
const deadline = Date.now() + 1_000;
while (responses.length < count && Date.now() < deadline) {
await new Promise((resolve) => setTimeout(resolve, 5));
}
expect(responses.length).toBeGreaterThanOrEqual(count);
}