076067865f
> **Stacked PR (part 3 of 7).** Depends on: - PR #5114 - PR #5115 > Diff against `master` includes commits from earlier PRs in the stack — the new commit in this PR is the topmost one. ## Thinking Path > - Paperclip orchestrates AI agents for zero-human companies > - Agents executing on a remote SSH-backed environment need a way to call back into > the Paperclip control plane (run events, log streaming, signals) > - When the SSH host can't reach the Paperclip host (NAT, firewalls, or simply not > on the same network), the run silently fails or hangs — a recurring class of > failure during SSH testing > - In sandboxed environments we already solved this with a callback bridge that > tunnels back through the existing connection; SSH was the odd one out > - This PR migrates SSH execution to use the same callback bridge, so every > adapter's remote run uses one consistent reverse-channel. Per-adapter SSH glue > is deleted in favour of a shared `CommandManagedRuntimeRunner` built from the > SSH spec > - The benefit is fewer SSH-specific failure modes, a smaller code surface, and > one place to evolve the callback contract going forward ## What Changed - Added `createSshCommandManagedRuntimeRunner` in `packages/adapter-utils/src/ssh.ts` that adapts an SSH spec into a generic command-managed-runtime runner (with cwd, env, and timeout handling) - Removed `paperclipApiUrl` from `SshRemoteExecutionSpec`; the bridge URL now flows through the shared runner - Reworked `execution-target.ts` to use the SSH runner alongside sandbox runners via a unified `CommandManagedRuntimeRunner` interface - Simplified `remote-managed-runtime.ts` and `sandbox-managed-runtime.ts` to consume the shared runner abstraction - Deleted per-adapter SSH callback wiring from claude-local, codex-local, cursor-local, gemini-local, opencode-local, pi-local execute.ts files - Removed `environment-runtime-driver-contract.test.ts` (the contract is now enforced by `environment-execution-target.test.ts`) - Added/updated `execute.remote.test.ts` cases for each adapter to cover the SSH runner path ## Verification - `pnpm --filter @paperclipai/adapter-utils test` - `pnpm test -- execute.remote` (covers all six local adapters' SSH paths) - Manual QA: ran a claude-local agent against an SSH-backed environment, confirmed the agent successfully called back to `/api/agent-callback/*` endpoints during the run ## Risks - Refactor touches all six local adapters. If any adapter had subtle SSH-specific behaviour that wasn't captured in tests, it could regress. Mitigation: each adapter's `execute.remote.test.ts` was extended. - `paperclipApiUrl` removal from `SshRemoteExecutionSpec` is a breaking type change for any internal consumer. Verified no external plugins consume this type. - The new `CommandManagedRuntimeRunner` shape is a public surface in `@paperclipai/adapter-utils`; downstream plugins implementing custom runners may need updates, but no such plugins exist in this repo. ## Model Used - OpenAI GPT-5.4 (reasoning effort: high) via Codex CLI - Provider: OpenAI - Used to author the code changes in this PR ## 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 — N/A - [ ] I have updated relevant documentation to reflect my changes — N/A - [x] I have considered and documented any risks above - [x] I will address all Greptile and reviewer comments before requesting merge
288 lines
8.9 KiB
TypeScript
288 lines
8.9 KiB
TypeScript
import { mkdir, mkdtemp, rm } from "node:fs/promises";
|
|
import os from "node:os";
|
|
import path from "node:path";
|
|
import { afterEach, describe, expect, it, vi } from "vitest";
|
|
|
|
const {
|
|
runChildProcess,
|
|
ensureCommandResolvable,
|
|
resolveCommandForLogs,
|
|
prepareWorkspaceForSshExecution,
|
|
restoreWorkspaceFromSshExecution,
|
|
runSshCommand,
|
|
syncDirectoryToSsh,
|
|
startAdapterExecutionTargetPaperclipBridge,
|
|
} = vi.hoisted(() => ({
|
|
runChildProcess: vi.fn(async () => ({
|
|
exitCode: 0,
|
|
signal: null,
|
|
timedOut: false,
|
|
stdout: [
|
|
JSON.stringify({ type: "system", session_id: "cursor-session-1" }),
|
|
JSON.stringify({ type: "assistant", text: "hello" }),
|
|
JSON.stringify({ type: "result", is_error: false, result: "hello", session_id: "cursor-session-1" }),
|
|
].join("\n"),
|
|
stderr: "",
|
|
pid: 123,
|
|
startedAt: new Date().toISOString(),
|
|
})),
|
|
ensureCommandResolvable: vi.fn(async () => undefined),
|
|
resolveCommandForLogs: vi.fn(async () => "ssh://fixture@127.0.0.1:2222/remote/workspace :: agent"),
|
|
prepareWorkspaceForSshExecution: vi.fn(async () => undefined),
|
|
restoreWorkspaceFromSshExecution: vi.fn(async () => undefined),
|
|
runSshCommand: vi.fn(async () => ({
|
|
stdout: "/home/agent",
|
|
stderr: "",
|
|
exitCode: 0,
|
|
})),
|
|
syncDirectoryToSsh: vi.fn(async () => undefined),
|
|
startAdapterExecutionTargetPaperclipBridge: vi.fn(async () => ({
|
|
env: {
|
|
PAPERCLIP_API_URL: "http://127.0.0.1:4310",
|
|
PAPERCLIP_API_KEY: "bridge-token",
|
|
PAPERCLIP_API_BRIDGE_MODE: "queue_v1",
|
|
},
|
|
stop: async () => {},
|
|
})),
|
|
}));
|
|
|
|
vi.mock("@paperclipai/adapter-utils/server-utils", async () => {
|
|
const actual = await vi.importActual<typeof import("@paperclipai/adapter-utils/server-utils")>(
|
|
"@paperclipai/adapter-utils/server-utils",
|
|
);
|
|
return {
|
|
...actual,
|
|
ensureCommandResolvable,
|
|
resolveCommandForLogs,
|
|
runChildProcess,
|
|
};
|
|
});
|
|
|
|
vi.mock("@paperclipai/adapter-utils/ssh", async () => {
|
|
const actual = await vi.importActual<typeof import("@paperclipai/adapter-utils/ssh")>(
|
|
"@paperclipai/adapter-utils/ssh",
|
|
);
|
|
return {
|
|
...actual,
|
|
prepareWorkspaceForSshExecution,
|
|
restoreWorkspaceFromSshExecution,
|
|
runSshCommand,
|
|
syncDirectoryToSsh,
|
|
};
|
|
});
|
|
|
|
vi.mock("@paperclipai/adapter-utils/execution-target", async () => {
|
|
const actual = await vi.importActual<typeof import("@paperclipai/adapter-utils/execution-target")>(
|
|
"@paperclipai/adapter-utils/execution-target",
|
|
);
|
|
return {
|
|
...actual,
|
|
startAdapterExecutionTargetPaperclipBridge,
|
|
};
|
|
});
|
|
|
|
import { execute } from "./execute.js";
|
|
|
|
describe("cursor remote execution", () => {
|
|
const cleanupDirs: string[] = [];
|
|
|
|
afterEach(async () => {
|
|
vi.clearAllMocks();
|
|
while (cleanupDirs.length > 0) {
|
|
const dir = cleanupDirs.pop();
|
|
if (!dir) continue;
|
|
await rm(dir, { recursive: true, force: true }).catch(() => undefined);
|
|
}
|
|
});
|
|
|
|
it("prepares the workspace, syncs Cursor skills, and restores workspace changes for remote SSH execution", async () => {
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-cursor-remote-"));
|
|
cleanupDirs.push(rootDir);
|
|
const workspaceDir = path.join(rootDir, "workspace");
|
|
await mkdir(workspaceDir, { recursive: true });
|
|
|
|
const result = await execute({
|
|
runId: "run-1",
|
|
agent: {
|
|
id: "agent-1",
|
|
companyId: "company-1",
|
|
name: "Cursor Builder",
|
|
adapterType: "cursor",
|
|
adapterConfig: {},
|
|
},
|
|
runtime: {
|
|
sessionId: null,
|
|
sessionParams: null,
|
|
sessionDisplayId: null,
|
|
taskKey: null,
|
|
},
|
|
config: {
|
|
command: "agent",
|
|
},
|
|
context: {
|
|
paperclipWorkspace: {
|
|
cwd: workspaceDir,
|
|
source: "project_primary",
|
|
},
|
|
},
|
|
executionTransport: {
|
|
remoteExecution: {
|
|
host: "127.0.0.1",
|
|
port: 2222,
|
|
username: "fixture",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
remoteCwd: "/remote/workspace",
|
|
privateKey: "PRIVATE KEY",
|
|
knownHosts: "[127.0.0.1]:2222 ssh-ed25519 AAAA",
|
|
strictHostKeyChecking: true,
|
|
},
|
|
},
|
|
onLog: async () => {},
|
|
});
|
|
|
|
expect(result.sessionParams).toMatchObject({
|
|
sessionId: "cursor-session-1",
|
|
cwd: "/remote/workspace",
|
|
remoteExecution: {
|
|
transport: "ssh",
|
|
host: "127.0.0.1",
|
|
port: 2222,
|
|
username: "fixture",
|
|
remoteCwd: "/remote/workspace",
|
|
},
|
|
});
|
|
expect(prepareWorkspaceForSshExecution).toHaveBeenCalledTimes(1);
|
|
expect(syncDirectoryToSsh).toHaveBeenCalledTimes(1);
|
|
expect(syncDirectoryToSsh).toHaveBeenCalledWith(expect.objectContaining({
|
|
remoteDir: "/remote/workspace/.paperclip-runtime/cursor/skills",
|
|
followSymlinks: true,
|
|
}));
|
|
expect(runSshCommand).toHaveBeenCalledWith(
|
|
expect.anything(),
|
|
expect.stringContaining(".cursor/skills"),
|
|
expect.anything(),
|
|
);
|
|
const call = runChildProcess.mock.calls[0] as unknown as
|
|
| [string, string, string[], { env: Record<string, string>; remoteExecution?: { remoteCwd: string } | null }]
|
|
| undefined;
|
|
expect(call?.[2]).toContain("--workspace");
|
|
expect(call?.[2]).toContain("/remote/workspace");
|
|
expect(call?.[3].env.PAPERCLIP_API_URL).toBe("http://127.0.0.1:4310");
|
|
expect(call?.[3].env.PAPERCLIP_API_BRIDGE_MODE).toBe("queue_v1");
|
|
expect(call?.[3].remoteExecution?.remoteCwd).toBe("/remote/workspace");
|
|
expect(startAdapterExecutionTargetPaperclipBridge).toHaveBeenCalledTimes(1);
|
|
expect(restoreWorkspaceFromSshExecution).toHaveBeenCalledTimes(1);
|
|
});
|
|
|
|
it("resumes saved Cursor sessions for remote SSH execution only when the identity matches", async () => {
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-cursor-remote-resume-"));
|
|
cleanupDirs.push(rootDir);
|
|
const workspaceDir = path.join(rootDir, "workspace");
|
|
await mkdir(workspaceDir, { recursive: true });
|
|
|
|
await execute({
|
|
runId: "run-ssh-resume",
|
|
agent: {
|
|
id: "agent-1",
|
|
companyId: "company-1",
|
|
name: "Cursor Builder",
|
|
adapterType: "cursor",
|
|
adapterConfig: {},
|
|
},
|
|
runtime: {
|
|
sessionId: "session-123",
|
|
sessionParams: {
|
|
sessionId: "session-123",
|
|
cwd: "/remote/workspace",
|
|
remoteExecution: {
|
|
transport: "ssh",
|
|
host: "127.0.0.1",
|
|
port: 2222,
|
|
username: "fixture",
|
|
remoteCwd: "/remote/workspace",
|
|
},
|
|
},
|
|
sessionDisplayId: "session-123",
|
|
taskKey: null,
|
|
},
|
|
config: {
|
|
command: "agent",
|
|
},
|
|
context: {
|
|
paperclipWorkspace: {
|
|
cwd: workspaceDir,
|
|
source: "project_primary",
|
|
},
|
|
},
|
|
executionTransport: {
|
|
remoteExecution: {
|
|
host: "127.0.0.1",
|
|
port: 2222,
|
|
username: "fixture",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
remoteCwd: "/remote/workspace",
|
|
privateKey: "PRIVATE KEY",
|
|
knownHosts: "[127.0.0.1]:2222 ssh-ed25519 AAAA",
|
|
strictHostKeyChecking: true,
|
|
},
|
|
},
|
|
onLog: async () => {},
|
|
});
|
|
|
|
const call = runChildProcess.mock.calls[0] as unknown as [string, string, string[]] | undefined;
|
|
expect(call?.[2]).toContain("--resume");
|
|
expect(call?.[2]).toContain("session-123");
|
|
});
|
|
|
|
it("restores the remote workspace if skills sync fails after workspace prep", async () => {
|
|
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-cursor-remote-sync-fail-"));
|
|
cleanupDirs.push(rootDir);
|
|
const workspaceDir = path.join(rootDir, "workspace");
|
|
await mkdir(workspaceDir, { recursive: true });
|
|
syncDirectoryToSsh.mockRejectedValueOnce(new Error("sync failed"));
|
|
|
|
await expect(execute({
|
|
runId: "run-sync-fail",
|
|
agent: {
|
|
id: "agent-1",
|
|
companyId: "company-1",
|
|
name: "Cursor Builder",
|
|
adapterType: "cursor",
|
|
adapterConfig: {},
|
|
},
|
|
runtime: {
|
|
sessionId: null,
|
|
sessionParams: null,
|
|
sessionDisplayId: null,
|
|
taskKey: null,
|
|
},
|
|
config: {
|
|
command: "agent",
|
|
},
|
|
context: {
|
|
paperclipWorkspace: {
|
|
cwd: workspaceDir,
|
|
source: "project_primary",
|
|
},
|
|
},
|
|
executionTransport: {
|
|
remoteExecution: {
|
|
host: "127.0.0.1",
|
|
port: 2222,
|
|
username: "fixture",
|
|
remoteWorkspacePath: "/remote/workspace",
|
|
remoteCwd: "/remote/workspace",
|
|
privateKey: "PRIVATE KEY",
|
|
knownHosts: "[127.0.0.1]:2222 ssh-ed25519 AAAA",
|
|
strictHostKeyChecking: true,
|
|
},
|
|
},
|
|
onLog: async () => {},
|
|
})).rejects.toThrow("sync failed");
|
|
|
|
expect(prepareWorkspaceForSshExecution).toHaveBeenCalledTimes(1);
|
|
expect(restoreWorkspaceFromSshExecution).toHaveBeenCalledTimes(1);
|
|
expect(runChildProcess).not.toHaveBeenCalled();
|
|
});
|
|
});
|