Files
paperclip/packages/adapters/cursor-local/src/server/test.ts
T
Devin Foley f9cf1d2f6a Add cursor sandbox support and fix SSH workspace sync (#4803)
## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - Agents can run inside sandboxed environments like E2B, or on remote
hosts via SSH
> - The cursor adapter needs to resolve `cursor-agent` inside sandbox
environments where it's installed in `~/.local/bin`
> - But when using the default `agent` command on a sandbox target, the
adapter didn't know to look in `~/.local/bin/cursor-agent`, causing
"command not found" failures
> - Additionally, repeated SSH runs failed because `git checkout` during
workspace sync conflicted with leftover `.paperclip-runtime` files from
previous runs
> - This PR adds sandbox-aware command resolution for cursor and fixes
the SSH workspace sync conflict
> - The benefit is cursor works in E2B sandboxes out of the box, and
repeated SSH runs don't fail on workspace sync

## What Changed

- `cursor-local`: Added `prepareCursorSandboxCommand` — on sandbox
targets, reads the remote `$HOME`, prepends `~/.local/bin` to PATH, and
prefers `~/.local/bin/cursor-agent` when the default command is
requested; tightened the sandbox command probe to validate the binary
exists before launching; preserves explicit custom command overrides
- `adapter-utils/ssh.ts`: Added `--force` to git checkout in SSH
workspace sync to handle `.paperclip-runtime` untracked file conflicts
from previous runs

## Verification

- `pnpm test` — all existing and new tests pass, including cursor
sandbox probe, sandbox execution, and custom command override tests
- `pnpm typecheck` — clean
- Manual: configure an E2B environment, run a cursor-local task, verify
it resolves cursor-agent from the sandbox install path

## Risks

- Low-medium. The `--force` flag on git checkout could discard
uncommitted changes in the remote workspace, but the workspace is
managed by Paperclip and should not contain user edits.

## Model Used

Codex GPT 5.4 high via Paperclip.

## 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
2026-04-29 16:12:06 -07:00

291 lines
10 KiB
TypeScript

import type {
AdapterEnvironmentCheck,
AdapterEnvironmentTestContext,
AdapterEnvironmentTestResult,
} from "@paperclipai/adapter-utils";
import {
asString,
asStringArray,
parseObject,
ensurePathInEnv,
} from "@paperclipai/adapter-utils/server-utils";
import {
ensureAdapterExecutionTargetCommandResolvable,
ensureAdapterExecutionTargetDirectory,
runAdapterExecutionTargetProcess,
describeAdapterExecutionTarget,
resolveAdapterExecutionTargetCwd,
} from "@paperclipai/adapter-utils/execution-target";
import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { DEFAULT_CURSOR_LOCAL_MODEL } from "../index.js";
import { parseCursorJsonl } from "./parse.js";
import { isDefaultCursorCommand, prepareCursorSandboxCommand } from "./remote-command.js";
import { hasCursorTrustBypassArg } from "../shared/trust.js";
function summarizeStatus(checks: AdapterEnvironmentCheck[]): AdapterEnvironmentTestResult["status"] {
if (checks.some((check) => check.level === "error")) return "fail";
if (checks.some((check) => check.level === "warn")) return "warn";
return "pass";
}
function isNonEmpty(value: unknown): value is string {
return typeof value === "string" && value.trim().length > 0;
}
function firstNonEmptyLine(text: string): string {
return (
text
.split(/\r?\n/)
.map((line) => line.trim())
.find(Boolean) ?? ""
);
}
function summarizeProbeDetail(stdout: string, stderr: string, parsedError: string | null): string | null {
const raw = parsedError?.trim() || firstNonEmptyLine(stderr) || firstNonEmptyLine(stdout);
if (!raw) return null;
const clean = raw.replace(/\s+/g, " ").trim();
const max = 240;
return clean.length > max ? `${clean.slice(0, max - 1)}` : clean;
}
export interface CursorAuthInfo {
email: string | null;
displayName: string | null;
userId: number | null;
}
export function cursorConfigPath(cursorHome?: string): string {
return path.join(cursorHome ?? path.join(os.homedir(), ".cursor"), "cli-config.json");
}
export async function readCursorAuthInfo(cursorHome?: string): Promise<CursorAuthInfo | null> {
let raw: string;
try {
raw = await fs.readFile(cursorConfigPath(cursorHome), "utf8");
} catch {
return null;
}
let parsed: unknown;
try {
parsed = JSON.parse(raw);
} catch {
return null;
}
if (typeof parsed !== "object" || parsed === null) return null;
const obj = parsed as Record<string, unknown>;
const authInfo = obj.authInfo;
if (typeof authInfo !== "object" || authInfo === null) return null;
const info = authInfo as Record<string, unknown>;
const email = typeof info.email === "string" && info.email.trim().length > 0 ? info.email.trim() : null;
const displayName = typeof info.displayName === "string" && info.displayName.trim().length > 0 ? info.displayName.trim() : null;
const userId = typeof info.userId === "number" ? info.userId : null;
if (!email && !displayName && userId == null) return null;
return { email, displayName, userId };
}
const CURSOR_AUTH_REQUIRED_RE =
/(?:authentication\s+required|not\s+authenticated|not\s+logged\s+in|unauthorized|invalid(?:\s+or\s+missing)?\s+api(?:[_\s-]?key)?|cursor[_\s-]?api[_\s-]?key|run\s+'?agent\s+login'?\s+first|api(?:[_\s-]?key)?(?:\s+is)?\s+required)/i;
export async function testEnvironment(
ctx: AdapterEnvironmentTestContext,
): Promise<AdapterEnvironmentTestResult> {
const checks: AdapterEnvironmentCheck[] = [];
const config = parseObject(ctx.config);
let command = asString(config.command, "agent");
const target = ctx.executionTarget ?? null;
const targetIsRemote = target?.kind === "remote";
const cwd = resolveAdapterExecutionTargetCwd(target, asString(config.cwd, ""), process.cwd());
const targetLabel = targetIsRemote
? ctx.environmentName ?? describeAdapterExecutionTarget(target)
: null;
const runId = `cursor-envtest-${Date.now()}-${Math.random().toString(16).slice(2)}`;
if (targetLabel) {
checks.push({
code: "cursor_environment_target",
level: "info",
message: `Probing inside environment: ${targetLabel}`,
});
}
try {
await ensureAdapterExecutionTargetDirectory(runId, target, cwd, {
cwd,
env: {},
createIfMissing: true,
});
checks.push({
code: "cursor_cwd_valid",
level: "info",
message: `Working directory is valid: ${cwd}`,
});
} catch (err) {
checks.push({
code: "cursor_cwd_invalid",
level: "error",
message: err instanceof Error ? err.message : "Invalid working directory",
detail: cwd,
});
}
const envConfig = parseObject(config.env);
let env: Record<string, string> = {};
for (const [key, value] of Object.entries(envConfig)) {
if (typeof value === "string") env[key] = value;
}
const sandboxCommand = await prepareCursorSandboxCommand({
runId,
target,
command,
cwd,
env,
timeoutSec: 45,
graceSec: 5,
});
command = sandboxCommand.command;
env = sandboxCommand.env;
const runtimeEnv = ensurePathInEnv({ ...process.env, ...env });
try {
await ensureAdapterExecutionTargetCommandResolvable(command, target, cwd, runtimeEnv);
checks.push({
code: "cursor_command_resolvable",
level: "info",
message: `Command is executable: ${command}`,
});
} catch (err) {
checks.push({
code: "cursor_command_unresolvable",
level: "error",
message: err instanceof Error ? err.message : "Command is not executable",
detail: command,
});
}
const configCursorApiKey = env.CURSOR_API_KEY;
const hostCursorApiKey = targetIsRemote ? undefined : process.env.CURSOR_API_KEY;
if (isNonEmpty(configCursorApiKey) || isNonEmpty(hostCursorApiKey)) {
const source = isNonEmpty(configCursorApiKey) ? "adapter config env" : "server environment";
checks.push({
code: "cursor_api_key_present",
level: "info",
message: "CURSOR_API_KEY is set for Cursor authentication.",
detail: `Detected in ${source}.`,
});
} else if (!targetIsRemote) {
const cursorHome = isNonEmpty(env.CURSOR_HOME) ? env.CURSOR_HOME : undefined;
const cursorAuth = await readCursorAuthInfo(cursorHome).catch(() => null);
if (cursorAuth) {
checks.push({
code: "cursor_native_auth_present",
level: "info",
message: "Cursor is authenticated via `agent login`.",
detail: cursorAuth.email
? `Logged in as ${cursorAuth.email}.`
: `Credentials found in ${cursorConfigPath(cursorHome)}.`,
});
} else {
checks.push({
code: "cursor_api_key_missing",
level: "warn",
message: "CURSOR_API_KEY is not set. Cursor runs may fail until authentication is configured.",
hint: "Set CURSOR_API_KEY in adapter env or run `agent login`.",
});
}
}
const canRunProbe =
checks.every((check) => check.code !== "cursor_cwd_invalid" && check.code !== "cursor_command_unresolvable");
if (canRunProbe) {
if (!isDefaultCursorCommand(command)) {
checks.push({
code: "cursor_hello_probe_skipped_custom_command",
level: "info",
message: "Skipped hello probe because command is not a default Cursor CLI entrypoint.",
detail: command,
hint: "Use `agent` or `cursor-agent` to run the automatic installation and auth probe.",
});
} else {
const model = asString(config.model, DEFAULT_CURSOR_LOCAL_MODEL).trim();
const extraArgs = (() => {
const fromExtraArgs = asStringArray(config.extraArgs);
if (fromExtraArgs.length > 0) return fromExtraArgs;
return asStringArray(config.args);
})();
const autoTrustEnabled = !hasCursorTrustBypassArg(extraArgs);
const args = ["-p", "--mode", "ask", "--output-format", "json", "--workspace", cwd];
if (model) args.push("--model", model);
if (autoTrustEnabled) args.push("--yolo");
if (extraArgs.length > 0) args.push(...extraArgs);
args.push("Respond with hello.");
const probe = await runAdapterExecutionTargetProcess(
runId,
target,
command,
args,
{
cwd,
env,
timeoutSec: 45,
graceSec: 5,
onLog: async () => {},
},
);
const parsed = parseCursorJsonl(probe.stdout);
const detail = summarizeProbeDetail(probe.stdout, probe.stderr, parsed.errorMessage);
const authEvidence = `${parsed.errorMessage ?? ""}\n${probe.stdout}\n${probe.stderr}`.trim();
if (probe.timedOut) {
checks.push({
code: "cursor_hello_probe_timed_out",
level: "warn",
message: "Cursor hello probe timed out.",
hint: "Retry the probe. If this persists, verify `agent -p --mode ask --output-format json \"Respond with hello.\"` manually.",
});
} else if ((probe.exitCode ?? 1) === 0) {
const summary = parsed.summary.trim();
const hasHello = /\bhello\b/i.test(summary);
checks.push({
code: hasHello ? "cursor_hello_probe_passed" : "cursor_hello_probe_unexpected_output",
level: hasHello ? "info" : "warn",
message: hasHello
? "Cursor hello probe succeeded."
: "Cursor probe ran but did not return `hello` as expected.",
...(summary ? { detail: summary.replace(/\s+/g, " ").trim().slice(0, 240) } : {}),
...(hasHello
? {}
: {
hint: "Try `agent -p --mode ask --output-format json \"Respond with hello.\"` manually to inspect full output.",
}),
});
} else if (CURSOR_AUTH_REQUIRED_RE.test(authEvidence)) {
checks.push({
code: "cursor_hello_probe_auth_required",
level: "warn",
message: "Cursor CLI is installed, but authentication is not ready.",
...(detail ? { detail } : {}),
hint: "Run `agent login` or configure CURSOR_API_KEY in adapter env/shell, then retry the probe.",
});
} else {
checks.push({
code: "cursor_hello_probe_failed",
level: "error",
message: "Cursor hello probe failed.",
...(detail ? { detail } : {}),
hint: "Run `agent -p --mode ask --output-format json \"Respond with hello.\"` manually in this working directory to debug.",
});
}
}
}
return {
adapterType: ctx.adapterType,
status: summarizeStatus(checks),
checks,
testedAt: new Date().toISOString(),
};
}