forked from farhoodlabs/paperclip
e4995bbb1c
## 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
119 lines
3.5 KiB
TypeScript
119 lines
3.5 KiB
TypeScript
import path from "node:path";
|
|
import {
|
|
type SshRemoteExecutionSpec,
|
|
prepareWorkspaceForSshExecution,
|
|
restoreWorkspaceFromSshExecution,
|
|
syncDirectoryToSsh,
|
|
} from "./ssh.js";
|
|
|
|
export interface RemoteManagedRuntimeAsset {
|
|
key: string;
|
|
localDir: string;
|
|
followSymlinks?: boolean;
|
|
exclude?: string[];
|
|
}
|
|
|
|
export interface PreparedRemoteManagedRuntime {
|
|
spec: SshRemoteExecutionSpec;
|
|
workspaceLocalDir: string;
|
|
workspaceRemoteDir: string;
|
|
runtimeRootDir: string;
|
|
assetDirs: Record<string, string>;
|
|
restoreWorkspace(): Promise<void>;
|
|
}
|
|
|
|
function asObject(value: unknown): Record<string, unknown> {
|
|
return value && typeof value === "object" && !Array.isArray(value)
|
|
? (value as Record<string, unknown>)
|
|
: {};
|
|
}
|
|
|
|
function asString(value: unknown): string {
|
|
return typeof value === "string" ? value : "";
|
|
}
|
|
|
|
function asNumber(value: unknown): number {
|
|
return typeof value === "number" ? value : Number(value);
|
|
}
|
|
|
|
export function buildRemoteExecutionSessionIdentity(spec: SshRemoteExecutionSpec | null) {
|
|
if (!spec) return null;
|
|
return {
|
|
transport: "ssh",
|
|
host: spec.host,
|
|
port: spec.port,
|
|
username: spec.username,
|
|
remoteCwd: spec.remoteCwd,
|
|
...(spec.paperclipApiUrl ? { paperclipApiUrl: spec.paperclipApiUrl } : {}),
|
|
} as const;
|
|
}
|
|
|
|
export function remoteExecutionSessionMatches(saved: unknown, current: SshRemoteExecutionSpec | null): boolean {
|
|
const currentIdentity = buildRemoteExecutionSessionIdentity(current);
|
|
if (!currentIdentity) return false;
|
|
|
|
const parsedSaved = asObject(saved);
|
|
return (
|
|
asString(parsedSaved.transport) === currentIdentity.transport &&
|
|
asString(parsedSaved.host) === currentIdentity.host &&
|
|
asNumber(parsedSaved.port) === currentIdentity.port &&
|
|
asString(parsedSaved.username) === currentIdentity.username &&
|
|
asString(parsedSaved.remoteCwd) === currentIdentity.remoteCwd &&
|
|
asString(parsedSaved.paperclipApiUrl) === asString(currentIdentity.paperclipApiUrl)
|
|
);
|
|
}
|
|
|
|
export async function prepareRemoteManagedRuntime(input: {
|
|
spec: SshRemoteExecutionSpec;
|
|
adapterKey: string;
|
|
workspaceLocalDir: string;
|
|
workspaceRemoteDir?: string;
|
|
assets?: RemoteManagedRuntimeAsset[];
|
|
}): Promise<PreparedRemoteManagedRuntime> {
|
|
const workspaceRemoteDir = input.workspaceRemoteDir ?? input.spec.remoteCwd;
|
|
const runtimeRootDir = path.posix.join(workspaceRemoteDir, ".paperclip-runtime", input.adapterKey);
|
|
|
|
await prepareWorkspaceForSshExecution({
|
|
spec: input.spec,
|
|
localDir: input.workspaceLocalDir,
|
|
remoteDir: workspaceRemoteDir,
|
|
});
|
|
|
|
const assetDirs: Record<string, string> = {};
|
|
try {
|
|
for (const asset of input.assets ?? []) {
|
|
const remoteDir = path.posix.join(runtimeRootDir, asset.key);
|
|
assetDirs[asset.key] = remoteDir;
|
|
await syncDirectoryToSsh({
|
|
spec: input.spec,
|
|
localDir: asset.localDir,
|
|
remoteDir,
|
|
followSymlinks: asset.followSymlinks,
|
|
exclude: asset.exclude,
|
|
});
|
|
}
|
|
} catch (error) {
|
|
await restoreWorkspaceFromSshExecution({
|
|
spec: input.spec,
|
|
localDir: input.workspaceLocalDir,
|
|
remoteDir: workspaceRemoteDir,
|
|
});
|
|
throw error;
|
|
}
|
|
|
|
return {
|
|
spec: input.spec,
|
|
workspaceLocalDir: input.workspaceLocalDir,
|
|
workspaceRemoteDir,
|
|
runtimeRootDir,
|
|
assetDirs,
|
|
restoreWorkspace: async () => {
|
|
await restoreWorkspaceFromSshExecution({
|
|
spec: input.spec,
|
|
localDir: input.workspaceLocalDir,
|
|
remoteDir: workspaceRemoteDir,
|
|
});
|
|
},
|
|
};
|
|
}
|