paperclip/packages/adapters/gemini-local/src/server/test.ts
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

262 lines
9.6 KiB
TypeScript

import path from "node:path";
import type {
AdapterEnvironmentCheck,
AdapterEnvironmentTestContext,
AdapterEnvironmentTestResult,
} from "@paperclipai/adapter-utils";
import {
asBoolean,
asNumber,
asString,
asStringArray,
ensurePathInEnv,
parseObject,
} from "@paperclipai/adapter-utils/server-utils";
import {
ensureAdapterExecutionTargetCommandResolvable,
ensureAdapterExecutionTargetDirectory,
runAdapterExecutionTargetProcess,
describeAdapterExecutionTarget,
resolveAdapterExecutionTargetCwd,
} from "@paperclipai/adapter-utils/execution-target";
import { DEFAULT_GEMINI_LOCAL_MODEL } from "../index.js";
import { detectGeminiAuthRequired, detectGeminiQuotaExhausted, parseGeminiJsonl } from "./parse.js";
import { firstNonEmptyLine } from "./utils.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 commandLooksLike(command: string, expected: string): boolean {
const base = path.basename(command).toLowerCase();
return base === expected || base === `${expected}.cmd` || base === `${expected}.exe`;
}
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 ? `${clean.slice(0, max - 1)}` : clean;
}
export async function testEnvironment(
ctx: AdapterEnvironmentTestContext,
): Promise<AdapterEnvironmentTestResult> {
const checks: AdapterEnvironmentCheck[] = [];
const config = parseObject(ctx.config);
const command = asString(config.command, "gemini");
const target = ctx.executionTarget ?? null;
const targetIsRemote = target?.kind === "remote";
const cwd = resolveAdapterExecutionTargetCwd(target, asString(config.cwd, ""), process.cwd());
const targetLabel = targetIsRemote
? ctx.environmentName ?? describeAdapterExecutionTarget(target)
: null;
const runId = `gemini-envtest-${Date.now()}-${Math.random().toString(16).slice(2)}`;
if (targetLabel) {
checks.push({
code: "gemini_environment_target",
level: "info",
message: `Probing inside environment: ${targetLabel}`,
});
}
try {
await ensureAdapterExecutionTargetDirectory(runId, target, cwd, {
cwd,
env: {},
createIfMissing: true,
});
checks.push({
code: "gemini_cwd_valid",
level: "info",
message: `Working directory is valid: ${cwd}`,
});
} catch (err) {
checks.push({
code: "gemini_cwd_invalid",
level: "error",
message: err instanceof Error ? err.message : "Invalid working directory",
detail: cwd,
});
}
const envConfig = parseObject(config.env);
const env: Record<string, string> = {};
for (const [key, value] of Object.entries(envConfig)) {
if (typeof value === "string") env[key] = value;
}
const runtimeEnv = ensurePathInEnv({ ...process.env, ...env });
try {
await ensureAdapterExecutionTargetCommandResolvable(command, target, cwd, runtimeEnv);
checks.push({
code: "gemini_command_resolvable",
level: "info",
message: `Command is executable: ${command}`,
});
} catch (err) {
checks.push({
code: "gemini_command_unresolvable",
level: "error",
message: err instanceof Error ? err.message : "Command is not executable",
detail: command,
});
}
const configGeminiApiKey = env.GEMINI_API_KEY;
const hostGeminiApiKey = targetIsRemote ? undefined : process.env.GEMINI_API_KEY;
const configGoogleApiKey = env.GOOGLE_API_KEY;
const hostGoogleApiKey = targetIsRemote ? undefined : process.env.GOOGLE_API_KEY;
const hasGca = env.GOOGLE_GENAI_USE_GCA === "true" || (!targetIsRemote && process.env.GOOGLE_GENAI_USE_GCA === "true");
if (
isNonEmpty(configGeminiApiKey) ||
isNonEmpty(hostGeminiApiKey) ||
isNonEmpty(configGoogleApiKey) ||
isNonEmpty(hostGoogleApiKey) ||
hasGca
) {
const source = hasGca
? "Google account login (GCA)"
: isNonEmpty(configGeminiApiKey) || isNonEmpty(configGoogleApiKey)
? "adapter config env"
: "server environment";
checks.push({
code: "gemini_api_key_present",
level: "info",
message: "Gemini API credentials are set for CLI authentication.",
detail: `Detected in ${source}.`,
});
} else {
checks.push({
code: "gemini_api_key_missing",
level: "info",
message: "No explicit API key detected. Gemini CLI may still authenticate via `gemini auth login` (OAuth).",
hint: "If the hello probe fails with an auth error, set GEMINI_API_KEY or GOOGLE_API_KEY in adapter env, or run `gemini auth login`.",
});
}
const canRunProbe =
checks.every((check) => check.code !== "gemini_cwd_invalid" && check.code !== "gemini_command_unresolvable");
if (canRunProbe) {
if (!commandLooksLike(command, "gemini")) {
checks.push({
code: "gemini_hello_probe_skipped_custom_command",
level: "info",
message: "Skipped hello probe because command is not `gemini`.",
detail: command,
hint: "Use the `gemini` CLI command to run the automatic installation and auth probe.",
});
} else {
const model = asString(config.model, DEFAULT_GEMINI_LOCAL_MODEL).trim();
const approvalMode = asString(config.approvalMode, asBoolean(config.yolo, false) ? "yolo" : "default");
const sandbox = asBoolean(config.sandbox, false);
const helloProbeTimeoutSec = Math.max(1, asNumber(config.helloProbeTimeoutSec, 10));
const extraArgs = (() => {
const fromExtraArgs = asStringArray(config.extraArgs);
if (fromExtraArgs.length > 0) return fromExtraArgs;
return asStringArray(config.args);
})();
const args = ["--output-format", "stream-json", "--prompt", "Respond with hello."];
if (model && model !== DEFAULT_GEMINI_LOCAL_MODEL) args.push("--model", model);
if (approvalMode !== "default") args.push("--approval-mode", approvalMode);
if (sandbox) {
args.push("--sandbox");
} else {
args.push("--sandbox=none");
}
if (extraArgs.length > 0) args.push(...extraArgs);
const probe = await runAdapterExecutionTargetProcess(
runId,
target,
command,
args,
{
cwd,
env,
timeoutSec: helloProbeTimeoutSec,
graceSec: 5,
onLog: async () => { },
},
);
const parsed = parseGeminiJsonl(probe.stdout);
const detail = summarizeProbeDetail(probe.stdout, probe.stderr, parsed.errorMessage);
const authMeta = detectGeminiAuthRequired({
parsed: parsed.resultEvent,
stdout: probe.stdout,
stderr: probe.stderr,
});
const quotaMeta = detectGeminiQuotaExhausted({
parsed: parsed.resultEvent,
stdout: probe.stdout,
stderr: probe.stderr,
});
if (quotaMeta.exhausted) {
checks.push({
code: "gemini_hello_probe_quota_exhausted",
level: "warn",
message: probe.timedOut
? "Gemini CLI is retrying after quota exhaustion."
: "Gemini CLI authentication is configured, but the current account or API key is over quota.",
...(detail ? { detail } : {}),
hint: "The configured Gemini account or API key is over quota. Check ai.google.dev usage/billing, then retry the probe.",
});
} else if (probe.timedOut) {
checks.push({
code: "gemini_hello_probe_timed_out",
level: "warn",
message: "Gemini hello probe timed out.",
hint: "Retry the probe. If this persists, verify Gemini can run `Respond with hello.` from this directory manually.",
});
} else if ((probe.exitCode ?? 1) === 0) {
const summary = parsed.summary.trim();
const hasHello = /\bhello\b/i.test(summary);
checks.push({
code: hasHello ? "gemini_hello_probe_passed" : "gemini_hello_probe_unexpected_output",
level: hasHello ? "info" : "warn",
message: hasHello
? "Gemini hello probe succeeded."
: "Gemini probe ran but did not return `hello` as expected.",
...(summary ? { detail: summary.replace(/\s+/g, " ").trim().slice(0, 240) } : {}),
...(hasHello
? {}
: {
hint: "Try `gemini --output-format json \"Respond with hello.\"` manually to inspect full output.",
}),
});
} else if (authMeta.requiresAuth) {
checks.push({
code: "gemini_hello_probe_auth_required",
level: "warn",
message: "Gemini CLI is installed, but authentication is not ready.",
...(detail ? { detail } : {}),
hint: "Run `gemini auth` or configure GEMINI_API_KEY / GOOGLE_API_KEY in adapter env/shell, then retry the probe.",
});
} else {
checks.push({
code: "gemini_hello_probe_failed",
level: "error",
message: "Gemini hello probe failed.",
...(detail ? { detail } : {}),
hint: "Run `gemini --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(),
};
}