mirror of
https://github.com/alkimake/paperclip.git
synced 2026-06-15 10:30:37 +09:00
## 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
275 lines
9.8 KiB
TypeScript
275 lines
9.8 KiB
TypeScript
import { execFile } from "node:child_process";
|
|
import { mkdir, mkdtemp, rm, symlink, writeFile } from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, describe, expect, it } from "vitest";
|
|
import {
|
|
buildSshSpawnTarget,
|
|
buildSshEnvLabFixtureConfig,
|
|
getSshEnvLabSupport,
|
|
prepareWorkspaceForSshExecution,
|
|
readSshEnvLabFixtureStatus,
|
|
restoreWorkspaceFromSshExecution,
|
|
runSshCommand,
|
|
syncDirectoryToSsh,
|
|
startSshEnvLabFixture,
|
|
stopSshEnvLabFixture,
|
|
} from "./ssh.js";
|
|
|
|
async function git(cwd: string, args: string[]): Promise<string> {
|
|
return await new Promise((resolve, reject) => {
|
|
execFile("git", ["-C", cwd, ...args], (error, stdout, stderr) => {
|
|
if (error) {
|
|
reject(new Error((stderr || stdout || error.message).trim()));
|
|
return;
|
|
}
|
|
resolve(stdout.trim());
|
|
});
|
|
});
|
|
}
|
|
|
|
describe("ssh env-lab fixture", () => {
|
|
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("starts an isolated sshd fixture and executes commands through it", async () => {
|
|
const support = await getSshEnvLabSupport();
|
|
if (!support.supported) {
|
|
console.warn(
|
|
`Skipping SSH env-lab fixture test: ${support.reason ?? "unsupported environment"}`,
|
|
);
|
|
return;
|
|
}
|
|
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-ssh-fixture-"));
|
|
cleanupDirs.push(rootDir);
|
|
const statePath = path.join(rootDir, "state.json");
|
|
|
|
const started = await startSshEnvLabFixture({ statePath });
|
|
const config = await buildSshEnvLabFixtureConfig(started);
|
|
const quotedWorkspace = JSON.stringify(started.workspaceDir);
|
|
const result = await runSshCommand(
|
|
config,
|
|
`sh -lc 'cd ${quotedWorkspace} && pwd'`,
|
|
);
|
|
|
|
expect(result.stdout.trim()).toBe(started.workspaceDir);
|
|
const status = await readSshEnvLabFixtureStatus(statePath);
|
|
expect(status.running).toBe(true);
|
|
|
|
await stopSshEnvLabFixture(statePath);
|
|
|
|
const stopped = await readSshEnvLabFixtureStatus(statePath);
|
|
expect(stopped.running).toBe(false);
|
|
});
|
|
|
|
it("does not treat an unrelated reused pid as the running fixture", async () => {
|
|
const support = await getSshEnvLabSupport();
|
|
if (!support.supported) {
|
|
console.warn(
|
|
`Skipping SSH env-lab fixture test: ${support.reason ?? "unsupported environment"}`,
|
|
);
|
|
return;
|
|
}
|
|
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-ssh-fixture-"));
|
|
cleanupDirs.push(rootDir);
|
|
const statePath = path.join(rootDir, "state.json");
|
|
|
|
const started = await startSshEnvLabFixture({ statePath });
|
|
await stopSshEnvLabFixture(statePath);
|
|
await mkdir(path.dirname(statePath), { recursive: true });
|
|
|
|
await writeFile(
|
|
statePath,
|
|
JSON.stringify({ ...started, pid: process.pid }, null, 2),
|
|
{ mode: 0o600 },
|
|
);
|
|
|
|
const staleStatus = await readSshEnvLabFixtureStatus(statePath);
|
|
expect(staleStatus.running).toBe(false);
|
|
|
|
const restarted = await startSshEnvLabFixture({ statePath });
|
|
expect(restarted.pid).not.toBe(process.pid);
|
|
|
|
await stopSshEnvLabFixture(statePath);
|
|
});
|
|
|
|
it("rejects invalid environment variable keys when constructing SSH spawn targets", async () => {
|
|
await expect(
|
|
buildSshSpawnTarget({
|
|
spec: {
|
|
host: "ssh.example.test",
|
|
port: 22,
|
|
username: "ssh-user",
|
|
remoteCwd: "/srv/paperclip/workspace",
|
|
remoteWorkspacePath: "/srv/paperclip/workspace",
|
|
privateKey: null,
|
|
knownHosts: null,
|
|
strictHostKeyChecking: true,
|
|
},
|
|
command: "env",
|
|
args: [],
|
|
env: {
|
|
"BAD KEY": "value",
|
|
},
|
|
}),
|
|
).rejects.toThrow("Invalid SSH environment variable key: BAD KEY");
|
|
});
|
|
|
|
it("syncs a local directory into the remote fixture workspace", async () => {
|
|
const support = await getSshEnvLabSupport();
|
|
if (!support.supported) {
|
|
console.warn(
|
|
`Skipping SSH env-lab fixture test: ${support.reason ?? "unsupported environment"}`,
|
|
);
|
|
return;
|
|
}
|
|
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-ssh-fixture-"));
|
|
cleanupDirs.push(rootDir);
|
|
const statePath = path.join(rootDir, "state.json");
|
|
const localDir = path.join(rootDir, "local-overlay");
|
|
|
|
await mkdir(localDir, { recursive: true });
|
|
await writeFile(path.join(localDir, "message.txt"), "hello from paperclip\n", "utf8");
|
|
await writeFile(path.join(localDir, "._message.txt"), "should never sync\n", "utf8");
|
|
|
|
const started = await startSshEnvLabFixture({ statePath });
|
|
const config = await buildSshEnvLabFixtureConfig(started);
|
|
const remoteDir = path.posix.join(started.workspaceDir, "overlay");
|
|
|
|
await syncDirectoryToSsh({
|
|
spec: {
|
|
...config,
|
|
remoteCwd: started.workspaceDir,
|
|
},
|
|
localDir,
|
|
remoteDir,
|
|
});
|
|
|
|
const result = await runSshCommand(
|
|
config,
|
|
`sh -lc 'cat ${JSON.stringify(path.posix.join(remoteDir, "message.txt"))} && if [ -e ${JSON.stringify(path.posix.join(remoteDir, "._message.txt"))} ]; then echo appledouble-present; fi'`,
|
|
);
|
|
|
|
expect(result.stdout).toContain("hello from paperclip");
|
|
expect(result.stdout).not.toContain("appledouble-present");
|
|
});
|
|
|
|
it("can dereference local symlinks while syncing to the remote fixture", async () => {
|
|
const support = await getSshEnvLabSupport();
|
|
if (!support.supported) {
|
|
console.warn(
|
|
`Skipping SSH symlink sync test: ${support.reason ?? "unsupported environment"}`,
|
|
);
|
|
return;
|
|
}
|
|
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-ssh-fixture-"));
|
|
cleanupDirs.push(rootDir);
|
|
const statePath = path.join(rootDir, "state.json");
|
|
const sourceDir = path.join(rootDir, "source");
|
|
const localDir = path.join(rootDir, "local-overlay");
|
|
|
|
await mkdir(sourceDir, { recursive: true });
|
|
await mkdir(localDir, { recursive: true });
|
|
await writeFile(path.join(sourceDir, "auth.json"), "{\"token\":\"secret\"}\n", "utf8");
|
|
await symlink(path.join(sourceDir, "auth.json"), path.join(localDir, "auth.json"));
|
|
|
|
const started = await startSshEnvLabFixture({ statePath });
|
|
const config = await buildSshEnvLabFixtureConfig(started);
|
|
const remoteDir = path.posix.join(started.workspaceDir, "overlay-follow-links");
|
|
|
|
await syncDirectoryToSsh({
|
|
spec: {
|
|
...config,
|
|
remoteCwd: started.workspaceDir,
|
|
},
|
|
localDir,
|
|
remoteDir,
|
|
followSymlinks: true,
|
|
});
|
|
|
|
const result = await runSshCommand(
|
|
config,
|
|
`sh -lc 'if [ -L ${JSON.stringify(path.posix.join(remoteDir, "auth.json"))} ]; then echo symlink; else echo regular; fi && cat ${JSON.stringify(path.posix.join(remoteDir, "auth.json"))}'`,
|
|
);
|
|
|
|
expect(result.stdout).toContain("regular");
|
|
expect(result.stdout).toContain("{\"token\":\"secret\"}");
|
|
});
|
|
|
|
it("round-trips a git workspace through the SSH fixture", async () => {
|
|
const support = await getSshEnvLabSupport();
|
|
if (!support.supported) {
|
|
console.warn(
|
|
`Skipping SSH workspace round-trip test: ${support.reason ?? "unsupported environment"}`,
|
|
);
|
|
return;
|
|
}
|
|
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-ssh-fixture-"));
|
|
cleanupDirs.push(rootDir);
|
|
const statePath = path.join(rootDir, "state.json");
|
|
const localRepo = path.join(rootDir, "local-workspace");
|
|
|
|
await mkdir(localRepo, { recursive: true });
|
|
await git(localRepo, ["init", "-b", "main"]);
|
|
await git(localRepo, ["config", "user.name", "Paperclip Test"]);
|
|
await git(localRepo, ["config", "user.email", "test@paperclip.dev"]);
|
|
await writeFile(path.join(localRepo, "tracked.txt"), "base\n", "utf8");
|
|
await writeFile(path.join(localRepo, "._tracked.txt"), "should stay local only\n", "utf8");
|
|
await git(localRepo, ["add", "tracked.txt"]);
|
|
await git(localRepo, ["commit", "-m", "initial"]);
|
|
const originalHead = await git(localRepo, ["rev-parse", "HEAD"]);
|
|
await writeFile(path.join(localRepo, "tracked.txt"), "dirty local\n", "utf8");
|
|
await writeFile(path.join(localRepo, "untracked.txt"), "from local\n", "utf8");
|
|
|
|
const started = await startSshEnvLabFixture({ statePath });
|
|
const config = await buildSshEnvLabFixtureConfig(started);
|
|
const spec = {
|
|
...config,
|
|
remoteCwd: started.workspaceDir,
|
|
} as const;
|
|
|
|
await prepareWorkspaceForSshExecution({
|
|
spec,
|
|
localDir: localRepo,
|
|
remoteDir: started.workspaceDir,
|
|
});
|
|
|
|
const remoteStatus = await runSshCommand(
|
|
config,
|
|
`sh -lc 'cd ${JSON.stringify(started.workspaceDir)} && git status --short'`,
|
|
);
|
|
expect(remoteStatus.stdout).toContain("M tracked.txt");
|
|
expect(remoteStatus.stdout).toContain("?? untracked.txt");
|
|
expect(remoteStatus.stdout).not.toContain("._tracked.txt");
|
|
|
|
await runSshCommand(
|
|
config,
|
|
`sh -lc 'cd ${JSON.stringify(started.workspaceDir)} && git config user.name "Paperclip SSH" && git config user.email "ssh@paperclip.dev" && git add tracked.txt untracked.txt && git commit -m "remote update" >/dev/null && printf "remote dirty\\n" > tracked.txt && printf "remote extra\\n" > remote-only.txt'`,
|
|
{ timeoutMs: 30_000, maxBuffer: 256 * 1024 },
|
|
);
|
|
|
|
await restoreWorkspaceFromSshExecution({
|
|
spec,
|
|
localDir: localRepo,
|
|
remoteDir: started.workspaceDir,
|
|
});
|
|
|
|
const restoredHead = await git(localRepo, ["rev-parse", "HEAD"]);
|
|
expect(restoredHead).not.toBe(originalHead);
|
|
expect(await git(localRepo, ["log", "-1", "--pretty=%s"])).toBe("remote update");
|
|
expect(await git(localRepo, ["status", "--short"])).toContain("M tracked.txt");
|
|
expect(await git(localRepo, ["status", "--short"])).not.toContain("._tracked.txt");
|
|
});
|
|
});
|