paperclip/packages/adapter-utils/src/command-managed-runtime.ts
Devin Foley 076067865f
Migrate SSH environment callback to bridge (#5116)
> **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
2026-05-03 12:43:52 -07:00

186 lines
6.4 KiB
TypeScript

import path from "node:path";
import {
prepareSandboxManagedRuntime,
type PreparedSandboxManagedRuntime,
type SandboxManagedRuntimeAsset,
type SandboxManagedRuntimeClient,
type SandboxRemoteExecutionSpec,
} from "./sandbox-managed-runtime.js";
import { preferredShellForSandbox } from "./sandbox-shell.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;
shellCommand?: "bash" | "sh" | null;
leaseId?: string | null;
remoteCwd: string;
timeoutMs?: number | null;
}
export type CommandManagedRuntimeAsset = SandboxManagedRuntimeAsset;
function shellQuote(value: string) {
return `'${value.replace(/'/g, `'"'"'`)}'`;
}
function mergeRuntimeExcludes(entries: string[] | undefined): string[] {
return [...new Set([".paperclip-runtime", ...(entries ?? [])])];
}
const REMOTE_WRITE_BASE64_CHUNK_SIZE = 32 * 1024;
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}`);
}
export function createCommandManagedRuntimeClient(input: {
runner: CommandManagedRuntimeRunner;
remoteCwd: string;
timeoutMs: number;
shellCommand?: "bash" | "sh" | null;
}): SandboxManagedRuntimeClient {
const shellCommand = preferredShellForSandbox(input.shellCommand);
const runShell = async (script: string, opts: { stdin?: string; timeoutMs?: number } = {}) => {
const result = await input.runner.execute({
command: shellCommand,
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 ${shellQuote(remotePath)}`);
},
writeFile: async (remotePath, bytes) => {
const body = toBuffer(bytes).toString("base64");
const remoteDir = path.posix.dirname(remotePath);
const remoteTempPath = `${remotePath}.paperclip-upload.b64`;
await runShell(
`mkdir -p ${shellQuote(remoteDir)} && rm -f ${shellQuote(remoteTempPath)} && : > ${shellQuote(remoteTempPath)}`,
);
for (let offset = 0; offset < body.length; offset += REMOTE_WRITE_BASE64_CHUNK_SIZE) {
const chunk = body.slice(offset, offset + REMOTE_WRITE_BASE64_CHUNK_SIZE);
await runShell(`printf '%s' ${shellQuote(chunk)} >> ${shellQuote(remoteTempPath)}`);
}
await runShell(
`base64 -d < ${shellQuote(remoteTempPath)} > ${shellQuote(remotePath)} && rm -f ${shellQuote(remoteTempPath)}`,
);
},
readFile: async (remotePath) => {
const result = await runShell(`base64 < ${shellQuote(remotePath)}`);
return Buffer.from(result.stdout.replace(/\s+/g, ""), "base64");
},
listFiles: async (remotePath) => {
const result = await runShell(
`if [ -d ${shellQuote(remotePath)} ]; then ` +
`for entry in ${shellQuote(remotePath)}/*; do ` +
`[ -f "$entry" ] || continue; ` +
`basename "$entry"; ` +
`done; ` +
`fi`,
);
return result.stdout
.split(/\r?\n/)
.map((entry) => entry.trim())
.filter((entry) => entry.length > 0)
.sort((left, right) => left.localeCompare(right));
},
remove: async (remotePath) => {
const result = await input.runner.execute({
command: shellCommand,
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: shellCommand,
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,
};
const client = createCommandManagedRuntimeClient({
runner: input.runner,
remoteCwd: workspaceRemoteDir,
timeoutMs,
shellCommand: input.spec.shellCommand,
});
const shellCommand = preferredShellForSandbox(input.spec.shellCommand);
if (input.installCommand?.trim()) {
const result = await input.runner.execute({
command: shellCommand,
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: mergeRuntimeExcludes(input.workspaceExclude),
preserveAbsentOnRestore: input.preserveAbsentOnRestore,
assets: input.assets,
});
}