paperclip/packages/adapter-utils/src/command-managed-runtime.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

152 lines
4.9 KiB
TypeScript

import path from "node:path";
import {
prepareSandboxManagedRuntime,
type PreparedSandboxManagedRuntime,
type SandboxManagedRuntimeAsset,
type SandboxManagedRuntimeClient,
type SandboxRemoteExecutionSpec,
} from "./sandbox-managed-runtime.js";
import type { RunProcessResult } from "./server-utils.js";
export interface CommandManagedRuntimeRunner {
execute(input: {
command: string;
args?: string[];
cwd?: string;
env?: Record<string, string>;
stdin?: string;
timeoutMs?: number;
onLog?: (stream: "stdout" | "stderr", chunk: string) => Promise<void>;
onSpawn?: (meta: { pid: number; startedAt: string }) => Promise<void>;
}): Promise<RunProcessResult>;
}
export interface CommandManagedRuntimeSpec {
providerKey?: string | null;
leaseId?: string | null;
remoteCwd: string;
timeoutMs?: number | null;
paperclipApiUrl?: string | null;
}
export type CommandManagedRuntimeAsset = SandboxManagedRuntimeAsset;
function shellQuote(value: string) {
return `'${value.replace(/'/g, `'"'"'`)}'`;
}
function toBuffer(bytes: Buffer | Uint8Array | ArrayBuffer): Buffer {
if (Buffer.isBuffer(bytes)) return bytes;
if (bytes instanceof ArrayBuffer) return Buffer.from(bytes);
return Buffer.from(bytes.buffer, bytes.byteOffset, bytes.byteLength);
}
function requireSuccessfulResult(result: RunProcessResult, action: string): void {
if (result.exitCode === 0 && !result.timedOut) return;
const stderr = result.stderr.trim();
const detail = stderr.length > 0 ? `: ${stderr}` : "";
throw new Error(`${action} failed with exit code ${result.exitCode ?? "null"}${detail}`);
}
function createCommandManagedRuntimeClient(input: {
runner: CommandManagedRuntimeRunner;
remoteCwd: string;
timeoutMs: number;
}): SandboxManagedRuntimeClient {
const runShell = async (script: string, opts: { stdin?: string; timeoutMs?: number } = {}) => {
const result = await input.runner.execute({
command: "sh",
args: ["-lc", script],
cwd: input.remoteCwd,
stdin: opts.stdin,
timeoutMs: opts.timeoutMs ?? input.timeoutMs,
});
requireSuccessfulResult(result, script);
return result;
};
return {
makeDir: async (remotePath) => {
await runShell(`mkdir -p ${shellQuote(remotePath)}`);
},
writeFile: async (remotePath, bytes) => {
const body = toBuffer(bytes).toString("base64");
await runShell(
`mkdir -p ${shellQuote(path.posix.dirname(remotePath))} && base64 -d > ${shellQuote(remotePath)}`,
{ stdin: body },
);
},
readFile: async (remotePath) => {
const result = await runShell(`base64 < ${shellQuote(remotePath)}`);
return Buffer.from(result.stdout.replace(/\s+/g, ""), "base64");
},
remove: async (remotePath) => {
const result = await input.runner.execute({
command: "sh",
args: ["-lc", `rm -rf ${shellQuote(remotePath)}`],
cwd: input.remoteCwd,
timeoutMs: input.timeoutMs,
});
requireSuccessfulResult(result, `remove ${remotePath}`);
},
run: async (command, options) => {
const result = await input.runner.execute({
command: "sh",
args: ["-lc", command],
cwd: input.remoteCwd,
timeoutMs: options.timeoutMs,
});
requireSuccessfulResult(result, command);
},
};
}
export async function prepareCommandManagedRuntime(input: {
runner: CommandManagedRuntimeRunner;
spec: CommandManagedRuntimeSpec;
adapterKey: string;
workspaceLocalDir: string;
workspaceRemoteDir?: string;
workspaceExclude?: string[];
preserveAbsentOnRestore?: string[];
assets?: CommandManagedRuntimeAsset[];
installCommand?: string | null;
}): Promise<PreparedSandboxManagedRuntime> {
const timeoutMs = input.spec.timeoutMs && input.spec.timeoutMs > 0 ? input.spec.timeoutMs : 300_000;
const workspaceRemoteDir = input.workspaceRemoteDir ?? input.spec.remoteCwd;
const runtimeSpec: SandboxRemoteExecutionSpec = {
transport: "sandbox",
provider: input.spec.providerKey ?? "sandbox",
sandboxId: input.spec.leaseId ?? "managed",
remoteCwd: workspaceRemoteDir,
timeoutMs,
apiKey: null,
paperclipApiUrl: input.spec.paperclipApiUrl ?? null,
};
const client = createCommandManagedRuntimeClient({
runner: input.runner,
remoteCwd: workspaceRemoteDir,
timeoutMs,
});
if (input.installCommand?.trim()) {
const result = await input.runner.execute({
command: "sh",
args: ["-lc", input.installCommand.trim()],
cwd: workspaceRemoteDir,
timeoutMs,
});
requireSuccessfulResult(result, input.installCommand.trim());
}
return await prepareSandboxManagedRuntime({
spec: runtimeSpec,
client,
adapterKey: input.adapterKey,
workspaceLocalDir: input.workspaceLocalDir,
workspaceRemoteDir,
workspaceExclude: input.workspaceExclude,
preserveAbsentOnRestore: input.preserveAbsentOnRestore,
assets: input.assets,
});
}