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
This commit is contained in:
Devin Foley 2026-04-23 19:15:22 -07:00 committed by GitHub
parent f98c348e2b
commit e4995bbb1c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
95 changed files with 10162 additions and 315 deletions

View file

@ -0,0 +1,272 @@
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,
} = vi.hoisted(() => ({
runChildProcess: vi.fn(async () => ({
exitCode: 0,
signal: null,
timedOut: false,
stdout: [
JSON.stringify({ type: "system", subtype: "init", session_id: "gemini-session-1", model: "gemini-2.5-pro" }),
JSON.stringify({ type: "assistant", message: { content: [{ type: "output_text", text: "hello" }] } }),
JSON.stringify({
type: "result",
subtype: "success",
session_id: "gemini-session-1",
usage: { promptTokenCount: 1, cachedContentTokenCount: 0, candidatesTokenCount: 1 },
result: "hello",
}),
].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 :: gemini"),
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),
}));
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,
};
});
import { execute } from "./execute.js";
describe("gemini 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 Gemini skills, and restores workspace changes for remote SSH execution", async () => {
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-gemini-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: "Gemini Builder",
adapterType: "gemini_local",
adapterConfig: {},
},
runtime: {
sessionId: null,
sessionParams: null,
sessionDisplayId: null,
taskKey: null,
},
config: {
command: "gemini",
},
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,
paperclipApiUrl: "http://198.51.100.10:3102",
},
},
onLog: async () => {},
});
expect(result.sessionParams).toMatchObject({
sessionId: "gemini-session-1",
cwd: "/remote/workspace",
remoteExecution: {
transport: "ssh",
host: "127.0.0.1",
port: 2222,
username: "fixture",
remoteCwd: "/remote/workspace",
paperclipApiUrl: "http://198.51.100.10:3102",
},
});
expect(prepareWorkspaceForSshExecution).toHaveBeenCalledTimes(1);
expect(syncDirectoryToSsh).toHaveBeenCalledTimes(1);
expect(syncDirectoryToSsh).toHaveBeenCalledWith(expect.objectContaining({
remoteDir: "/remote/workspace/.paperclip-runtime/gemini/skills",
followSymlinks: true,
}));
expect(runSshCommand).toHaveBeenCalledWith(
expect.anything(),
expect.stringContaining(".gemini/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?.[3].env.PAPERCLIP_API_URL).toBe("http://198.51.100.10:3102");
expect(call?.[3].remoteExecution?.remoteCwd).toBe("/remote/workspace");
expect(restoreWorkspaceFromSshExecution).toHaveBeenCalledTimes(1);
});
it("resumes saved Gemini sessions for remote SSH execution only when the identity matches", async () => {
const rootDir = await mkdtemp(path.join(os.tmpdir(), "paperclip-gemini-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: "Gemini Builder",
adapterType: "gemini_local",
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: "gemini",
},
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-gemini-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: "Gemini Builder",
adapterType: "gemini_local",
adapterConfig: {},
},
runtime: {
sessionId: null,
sessionParams: null,
sessionDisplayId: null,
taskKey: null,
},
config: {
command: "gemini",
},
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();
});
});

View file

@ -4,6 +4,22 @@ import os from "node:os";
import path from "node:path";
import { fileURLToPath } from "node:url";
import type { AdapterExecutionContext, AdapterExecutionResult } from "@paperclipai/adapter-utils";
import {
adapterExecutionTargetIsRemote,
adapterExecutionTargetPaperclipApiUrl,
adapterExecutionTargetRemoteCwd,
adapterExecutionTargetSessionIdentity,
adapterExecutionTargetSessionMatches,
adapterExecutionTargetUsesManagedHome,
describeAdapterExecutionTarget,
ensureAdapterExecutionTargetCommandResolvable,
prepareAdapterExecutionTargetRuntime,
readAdapterExecutionTarget,
readAdapterExecutionTargetHomeDir,
resolveAdapterExecutionTargetCommandForLogs,
runAdapterExecutionTargetProcess,
runAdapterExecutionTargetShellCommand,
} from "@paperclipai/adapter-utils/execution-target";
import {
asBoolean,
asNumber,
@ -12,12 +28,10 @@ import {
buildPaperclipEnv,
buildInvocationEnvForLogs,
ensureAbsoluteDirectory,
ensureCommandResolvable,
ensurePaperclipSkillSymlink,
joinPromptSections,
ensurePathInEnv,
readPaperclipRuntimeSkillEntries,
resolveCommandForLogs,
resolvePaperclipDesiredSkillNames,
removeMaintainerOnlySkillSymlinks,
parseObject,
@ -136,8 +150,28 @@ async function ensureGeminiSkillsInjected(
}
}
async function buildGeminiSkillsDir(
config: Record<string, unknown>,
): Promise<string> {
const tmp = await fs.mkdtemp(path.join(os.tmpdir(), "paperclip-gemini-skills-"));
const target = path.join(tmp, "skills");
await fs.mkdir(target, { recursive: true });
const availableEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredNames = new Set(resolvePaperclipDesiredSkillNames(config, availableEntries));
for (const entry of availableEntries) {
if (!desiredNames.has(entry.key)) continue;
await fs.symlink(entry.source, path.join(target, entry.runtimeName));
}
return target;
}
export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExecutionResult> {
const { runId, agent, runtime, config, context, onLog, onMeta, onSpawn, authToken } = ctx;
const executionTarget = readAdapterExecutionTarget({
executionTarget: ctx.executionTarget,
legacyRemoteExecution: ctx.executionTransport?.remoteExecution,
});
const executionTargetIsRemote = adapterExecutionTargetIsRemote(executionTarget);
const promptTemplate = asString(
config.promptTemplate,
@ -166,7 +200,9 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
await ensureAbsoluteDirectory(cwd, { createIfMissing: true });
const geminiSkillEntries = await readPaperclipRuntimeSkillEntries(config, __moduleDir);
const desiredGeminiSkillNames = resolvePaperclipDesiredSkillNames(config, geminiSkillEntries);
await ensureGeminiSkillsInjected(onLog, geminiSkillEntries, desiredGeminiSkillNames);
if (!executionTargetIsRemote) {
await ensureGeminiSkillsInjected(onLog, geminiSkillEntries, desiredGeminiSkillNames);
}
const envConfig = parseObject(config.env);
const hasExplicitApiKey =
@ -211,6 +247,8 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
if (workspaceRepoRef) env.PAPERCLIP_WORKSPACE_REPO_REF = workspaceRepoRef;
if (agentHome) env.AGENT_HOME = agentHome;
if (workspaceHints.length > 0) env.PAPERCLIP_WORKSPACES_JSON = JSON.stringify(workspaceHints);
const targetPaperclipApiUrl = adapterExecutionTargetPaperclipApiUrl(executionTarget);
if (targetPaperclipApiUrl) env.PAPERCLIP_API_URL = targetPaperclipApiUrl;
for (const [key, value] of Object.entries(envConfig)) {
if (typeof value === "string") env[key] = value;
@ -225,8 +263,8 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
);
const billingType = resolveGeminiBillingType(effectiveEnv);
const runtimeEnv = ensurePathInEnv(effectiveEnv);
await ensureCommandResolvable(command, cwd, runtimeEnv);
const resolvedCommand = await resolveCommandForLogs(command, cwd, runtimeEnv);
await ensureAdapterExecutionTargetCommandResolvable(command, executionTarget, cwd, runtimeEnv);
const resolvedCommand = await resolveAdapterExecutionTargetCommandForLogs(command, executionTarget, cwd, runtimeEnv);
const loggedEnv = buildInvocationEnvForLogs(env, {
runtimeEnv,
includeRuntimeKeys: ["HOME"],
@ -240,18 +278,78 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
if (fromExtraArgs.length > 0) return fromExtraArgs;
return asStringArray(config.args);
})();
const effectiveExecutionCwd = adapterExecutionTargetRemoteCwd(executionTarget, cwd);
let restoreRemoteWorkspace: (() => Promise<void>) | null = null;
let remoteSkillsDir: string | null = null;
let localSkillsDir: string | null = null;
if (executionTargetIsRemote) {
try {
localSkillsDir = await buildGeminiSkillsDir(config);
await onLog(
"stdout",
`[paperclip] Syncing workspace and Gemini runtime assets to ${describeAdapterExecutionTarget(executionTarget)}.\n`,
);
const preparedExecutionTargetRuntime = await prepareAdapterExecutionTargetRuntime({
target: executionTarget,
adapterKey: "gemini",
workspaceLocalDir: cwd,
assets: [{
key: "skills",
localDir: localSkillsDir,
followSymlinks: true,
}],
});
restoreRemoteWorkspace = () => preparedExecutionTargetRuntime.restoreWorkspace();
const managedHome = adapterExecutionTargetUsesManagedHome(executionTarget);
if (managedHome && preparedExecutionTargetRuntime.runtimeRootDir) {
env.HOME = preparedExecutionTargetRuntime.runtimeRootDir;
}
const remoteHomeDir = managedHome && preparedExecutionTargetRuntime.runtimeRootDir
? preparedExecutionTargetRuntime.runtimeRootDir
: await readAdapterExecutionTargetHomeDir(runId, executionTarget, {
cwd,
env,
timeoutSec,
graceSec,
onLog,
});
if (remoteHomeDir && preparedExecutionTargetRuntime.assetDirs.skills) {
remoteSkillsDir = path.posix.join(remoteHomeDir, ".gemini", "skills");
await runAdapterExecutionTargetShellCommand(
runId,
executionTarget,
`mkdir -p ${JSON.stringify(path.posix.dirname(remoteSkillsDir))} && rm -rf ${JSON.stringify(remoteSkillsDir)} && cp -a ${JSON.stringify(preparedExecutionTargetRuntime.assetDirs.skills)} ${JSON.stringify(remoteSkillsDir)}`,
{ cwd, env, timeoutSec, graceSec, onLog },
);
}
} catch (error) {
await Promise.allSettled([
restoreRemoteWorkspace?.(),
localSkillsDir ? fs.rm(path.dirname(localSkillsDir), { recursive: true, force: true }).catch(() => undefined) : Promise.resolve(),
]);
throw error;
}
}
const runtimeSessionParams = parseObject(runtime.sessionParams);
const runtimeSessionId = asString(runtimeSessionParams.sessionId, runtime.sessionId ?? "");
const runtimeSessionCwd = asString(runtimeSessionParams.cwd, "");
const runtimeRemoteExecution = parseObject(runtimeSessionParams.remoteExecution);
const canResumeSession =
runtimeSessionId.length > 0 &&
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(cwd));
(runtimeSessionCwd.length === 0 || path.resolve(runtimeSessionCwd) === path.resolve(effectiveExecutionCwd)) &&
adapterExecutionTargetSessionMatches(runtimeRemoteExecution, executionTarget);
const sessionId = canResumeSession ? runtimeSessionId : null;
if (runtimeSessionId && !canResumeSession) {
if (executionTargetIsRemote && runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] Gemini session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${cwd}".\n`,
`[paperclip] Gemini session "${runtimeSessionId}" does not match the current remote execution identity and will not be resumed in "${effectiveExecutionCwd}". Starting a fresh remote session.\n`,
);
} else if (runtimeSessionId && !canResumeSession) {
await onLog(
"stdout",
`[paperclip] Gemini session "${runtimeSessionId}" was saved for cwd "${runtimeSessionCwd}" and will not be resumed in "${effectiveExecutionCwd}".\n`,
);
}
@ -350,7 +448,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
await onMeta({
adapterType: "gemini_local",
command: resolvedCommand,
cwd,
cwd: effectiveExecutionCwd,
commandNotes,
commandArgs: args.map((value, index) => (
index === args.length - 1 ? `<prompt ${prompt.length} chars>` : value
@ -362,7 +460,7 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
});
}
const proc = await runChildProcess(runId, command, args, {
const proc = await runAdapterExecutionTargetProcess(runId, executionTarget, command, args, {
cwd,
env,
timeoutSec,
@ -416,10 +514,15 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
const resolvedSessionParams = resolvedSessionId
? ({
sessionId: resolvedSessionId,
cwd,
cwd: effectiveExecutionCwd,
...(workspaceId ? { workspaceId } : {}),
...(workspaceRepoUrl ? { repoUrl: workspaceRepoUrl } : {}),
...(workspaceRepoRef ? { repoRef: workspaceRepoRef } : {}),
...(executionTargetIsRemote
? {
remoteExecution: adapterExecutionTargetSessionIdentity(executionTarget),
}
: {}),
} as Record<string, unknown>)
: null;
const parsedError = typeof attempt.parsed.errorMessage === "string" ? attempt.parsed.errorMessage.trim() : "";
@ -458,20 +561,27 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
};
};
const initial = await runAttempt(sessionId);
if (
sessionId &&
!initial.proc.timedOut &&
(initial.proc.exitCode ?? 0) !== 0 &&
isGeminiUnknownSessionError(initial.proc.stdout, initial.proc.stderr)
) {
await onLog(
"stdout",
`[paperclip] Gemini resume session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
);
const retry = await runAttempt(null);
return toResult(retry, true, true);
}
try {
const initial = await runAttempt(sessionId);
if (
sessionId &&
!initial.proc.timedOut &&
(initial.proc.exitCode ?? 0) !== 0 &&
isGeminiUnknownSessionError(initial.proc.stdout, initial.proc.stderr)
) {
await onLog(
"stdout",
`[paperclip] Gemini resume session "${sessionId}" is unavailable; retrying with a fresh session.\n`,
);
const retry = await runAttempt(null);
return toResult(retry, true, true);
}
return toResult(initial);
return toResult(initial);
} finally {
await Promise.all([
restoreRemoteWorkspace?.(),
localSkillsDir ? fs.rm(path.dirname(localSkillsDir), { recursive: true, force: true }).catch(() => undefined) : Promise.resolve(),
]);
}
}