Files
paperclip/server/src/__tests__/environment-live-ssh.test.ts
T
Devin Foley e4995bbb1c Add SSH environment support (#4358)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - The environments subsystem already models execution environments,
but before this branch there was no end-to-end SSH-backed runtime path
for agents to actually run work against a remote box
> - That meant agents could be configured around environment concepts
without a reliable way to execute adapter sessions remotely, sync
workspace state, and preserve run context across supported adapters
> - We also need environment selection to participate in normal
Paperclip control-plane behavior: agent defaults, project/issue
selection, route validation, and environment probing
> - Because this capability is still experimental, the UI surface should
be easy to hide and easy to remove later without undoing the underlying
implementation
> - This pull request adds SSH environment execution support across the
runtime, adapters, routes, schema, and tests, then puts the visible
environment-management UI behind an experimental flag
> - The benefit is that we can validate real SSH-backed agent execution
now while keeping the user-facing controls safely gated until the
feature is ready to come out of experimentation

## What Changed

- Added SSH-backed execution target support in the shared adapter
runtime, including remote workspace preparation, skill/runtime asset
sync, remote session handling, and workspace restore behavior after
runs.
- Added SSH execution coverage for supported local adapters, plus remote
execution tests across Claude, Codex, Cursor, Gemini, OpenCode, and Pi.
- Added environment selection and environment-management backend support
needed for SSH execution, including route/service work, validation,
probing, and agent default environment persistence.
- Added CLI support for SSH environment lab verification and updated
related docs/tests.
- Added the `enableEnvironments` experimental flag and gated the
environment UI behind it on company settings, agent configuration, and
project configuration surfaces.

## Verification

- `pnpm exec vitest run
packages/adapters/claude-local/src/server/execute.remote.test.ts
packages/adapters/cursor-local/src/server/execute.remote.test.ts
packages/adapters/gemini-local/src/server/execute.remote.test.ts
packages/adapters/opencode-local/src/server/execute.remote.test.ts
packages/adapters/pi-local/src/server/execute.remote.test.ts`
- `pnpm exec vitest run server/src/__tests__/environment-routes.test.ts`
- `pnpm exec vitest run
server/src/__tests__/instance-settings-routes.test.ts`
- `pnpm exec vitest run ui/src/lib/new-agent-hire-payload.test.ts
ui/src/lib/new-agent-runtime-config.test.ts`
- `pnpm -r typecheck`
- `pnpm build`
- Manual verification on a branch-local dev server:
  - enabled the experimental flag
  - created an SSH environment
  - created a Linux Claude agent using that environment
- confirmed a run executed on the Linux box and synced workspace changes
back

## Risks

- Medium: this touches runtime execution flow across multiple adapters,
so regressions would likely show up in remote session setup, workspace
sync, or environment selection precedence.
- The UI flag reduces exposure, but the underlying runtime and route
changes are still substantial and rely on migration correctness.
- The change set is broad across adapters, control-plane services,
migrations, and UI gating, so review should pay close attention to
environment-selection precedence and remote workspace lifecycle
behavior.

## Model Used

- OpenAI Codex via Paperclip's local Codex adapter, GPT-5-class coding
model with tool use and code execution in the local repo workspace. The
local adapter does not surface a more specific public model version
string in this branch workflow.

## 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
2026-04-23 19:15:22 -07:00

184 lines
5.9 KiB
TypeScript

import { readFile } from "node:fs/promises";
import path from "node:path";
import { afterAll, describe, expect, it } from "vitest";
import {
buildSshEnvLabFixtureConfig,
ensureSshWorkspaceReady,
readSshEnvLabFixtureStatus,
runSshCommand,
startSshEnvLabFixture,
stopSshEnvLabFixture,
type SshConnectionConfig,
} from "@paperclipai/adapter-utils/ssh";
async function readOptionalSecret(
value: string | undefined,
filePath: string | undefined,
): Promise<string | null> {
if (value && value.trim().length > 0) {
return value;
}
if (filePath && filePath.trim().length > 0) {
return await readFile(filePath, "utf8");
}
return null;
}
/**
* Resolve the env-lab state path for this instance. Falls back to a temp
* directory scoped to the test run so parallel runs don't collide.
*/
function resolveEnvLabStatePath(): string {
const instanceRoot =
process.env.PAPERCLIP_INSTANCE_ROOT?.trim() ||
path.join(process.env.HOME ?? "/tmp", ".paperclip-worktrees", "instances", "live-ssh-test");
return path.join(instanceRoot, "env-lab", "ssh-fixture", "state.json");
}
/** Attempt to build config from explicit PAPERCLIP_ENV_LIVE_SSH_* env vars. */
function tryExplicitConfig(): {
host: string;
port: number;
username: string;
remoteWorkspacePath: string;
} | null {
const host = process.env.PAPERCLIP_ENV_LIVE_SSH_HOST?.trim() ?? "";
const username = process.env.PAPERCLIP_ENV_LIVE_SSH_USERNAME?.trim() ?? "";
const remoteWorkspacePath =
process.env.PAPERCLIP_ENV_LIVE_SSH_REMOTE_WORKSPACE_PATH?.trim() ?? "";
const port = Number.parseInt(process.env.PAPERCLIP_ENV_LIVE_SSH_PORT ?? "22", 10);
if (!host || !username || !remoteWorkspacePath || !Number.isInteger(port) || port < 1 || port > 65535) {
return null;
}
return { host, port, username, remoteWorkspacePath };
}
/** Try to use an already-running env-lab fixture. */
async function tryEnvLabFixture(): Promise<SshConnectionConfig | null> {
const statePath = resolveEnvLabStatePath();
const status = await readSshEnvLabFixtureStatus(statePath);
if (status.running && status.state) {
return buildSshEnvLabFixtureConfig(status.state);
}
return null;
}
/**
* Start a fresh env-lab SSH fixture for this test run. Returns the config
* and a cleanup function to stop it afterwards.
*/
async function startEnvLabForTest(): Promise<{
config: SshConnectionConfig;
cleanup: () => Promise<void>;
} | null> {
const statePath = resolveEnvLabStatePath();
try {
const state = await startSshEnvLabFixture({ statePath });
const config = await buildSshEnvLabFixtureConfig(state);
return {
config,
cleanup: async () => {
await stopSshEnvLabFixture(statePath);
},
};
} catch {
return null;
}
}
let envLabCleanup: (() => Promise<void>) | null = null;
/**
* Resolve an SSH connection config from (in order):
* 1. Explicit PAPERCLIP_ENV_LIVE_SSH_* env vars
* 2. An already-running env-lab fixture
* 3. Auto-starting an env-lab fixture
*/
async function resolveSshConfig(): Promise<SshConnectionConfig | null> {
// 1. Explicit env vars
const explicit = tryExplicitConfig();
if (explicit) {
return {
...explicit,
privateKey: await readOptionalSecret(
process.env.PAPERCLIP_ENV_LIVE_SSH_PRIVATE_KEY,
process.env.PAPERCLIP_ENV_LIVE_SSH_PRIVATE_KEY_PATH,
),
knownHosts: await readOptionalSecret(
process.env.PAPERCLIP_ENV_LIVE_SSH_KNOWN_HOSTS,
process.env.PAPERCLIP_ENV_LIVE_SSH_KNOWN_HOSTS_PATH,
),
strictHostKeyChecking:
(process.env.PAPERCLIP_ENV_LIVE_SSH_STRICT_HOST_KEY_CHECKING ?? "true").toLowerCase() !== "false",
};
}
// 2. Already-running env-lab
const running = await tryEnvLabFixture();
if (running) return running;
// 3. Auto-start env-lab
if (process.env.PAPERCLIP_ENV_LIVE_SSH_NO_AUTO_FIXTURE !== "true") {
const started = await startEnvLabForTest();
if (started) {
envLabCleanup = started.cleanup;
return started.config;
}
}
return null;
}
let resolvedConfig: SshConnectionConfig | null | undefined;
const describeLiveSsh = (() => {
// Eagerly check explicit env vars for sync skip decision.
// If explicit vars are set, use them. Otherwise, we'll attempt env-lab in beforeAll.
if (tryExplicitConfig()) return describe;
// If NO_AUTO_FIXTURE is set and no explicit config, skip immediately
if (process.env.PAPERCLIP_ENV_LIVE_SSH_NO_AUTO_FIXTURE === "true") {
console.warn(
"Skipping live SSH smoke test. Set PAPERCLIP_ENV_LIVE_SSH_HOST, PAPERCLIP_ENV_LIVE_SSH_USERNAME, and PAPERCLIP_ENV_LIVE_SSH_REMOTE_WORKSPACE_PATH to enable it, or remove PAPERCLIP_ENV_LIVE_SSH_NO_AUTO_FIXTURE to auto-start env-lab.",
);
return describe.skip;
}
// Will attempt env-lab — don't skip yet
return describe;
})();
describeLiveSsh("live SSH environment smoke", () => {
afterAll(async () => {
if (envLabCleanup) {
await envLabCleanup();
envLabCleanup = null;
}
});
it("connects to the configured SSH environment and verifies basic runtime tools", async () => {
if (resolvedConfig === undefined) {
resolvedConfig = await resolveSshConfig();
}
if (!resolvedConfig) {
throw new Error(
"Live SSH smoke test could not resolve SSH config from env vars or env-lab fixture. Set PAPERCLIP_ENV_LIVE_SSH_NO_AUTO_FIXTURE=true to mark this suite skipped intentionally.",
);
}
const config = resolvedConfig;
const ready = await ensureSshWorkspaceReady(config);
const quotedRemoteWorkspacePath = JSON.stringify(config.remoteWorkspacePath);
const result = await runSshCommand(
config,
`sh -lc "cd ${quotedRemoteWorkspacePath} && which git && which tar && pwd"`,
{ timeoutMs: 30000, maxBuffer: 256 * 1024 },
);
expect(ready.remoteCwd).toBe(config.remoteWorkspacePath);
expect(result.stdout).toContain(config.remoteWorkspacePath);
expect(result.stdout).toContain("git");
expect(result.stdout).toContain("tar");
});
});