paperclip/packages/adapters/codex-local/src/server/test.ts
Devin Foley 9578dc3da7
Wire per-adapter sandbox install commands through test and execute paths (#5280)
> **Stacked PR.** Sits on top of the e2b sandbox chain — #5278 (stdin
staging) and #5279 (honest-resolvability + login-profiles). The
cumulative diff against `master` includes both of those PRs' content;
the files touched by *this* PR's commit are the new
`maybeRunSandboxInstallCommand` helper in
`packages/adapter-utils/src/execution-target.ts` and the per-adapter
`index.ts`/`server/test.ts`/`server/execute.ts` wiring under
`packages/adapters/{claude,codex,cursor,gemini,opencode,pi}-local/`. The
honest resolvability check from #5279 is what gives this PR's install
command a meaningful "did it actually land on PATH" follow-up.

## Thinking Path

> - Paperclip orchestrates AI agents for zero-human companies
> - Sandbox execution targets are ephemeral — each fresh lease starts
from a template image that may or may not have the agent CLIs
preinstalled
> - When a CLI isn't preinstalled, the resolvability probe fails at
`command -v` and the hello probe never runs
> - There's no shared mechanism for "before you probe or provision,
install the CLI on this sandbox"
> - This pull request adds a `SANDBOX_INSTALL_COMMAND` constant per
adapter and a `maybeRunSandboxInstallCommand` helper that runs it via
the existing sandbox login shell, captures structured output, and never
throws (so the resolvability + hello probe still run after); each
adapter's `test()` and `execute()` share the constant so the two
callsites can't drift
> - The benefit is a fresh sandbox lease without a preinstalled CLI now
installs it once via `sh -lc` before the resolvability probe and before
managed-runtime provisioning, with a uniform
`<adapter>_install_command_run` check on the test report

## What Changed

- `packages/adapter-utils/src/execution-target.ts`: add
`AdapterSandboxInstallCommandCheck` and `maybeRunSandboxInstallCommand`
(runs the install via existing sandbox shell, captures
exit/stdout/stderr, returns a structured info/warn check, never throws)
- Add `SANDBOX_INSTALL_COMMAND` to each adapter's `index.ts` so `test()`
and `execute()` share a single source of truth
- Wire each of the 6 affected adapter `testEnvironment()`s to call
`maybeRunSandboxInstallCommand` before
`ensureAdapterExecutionTargetCommandResolvable`
- Pass `installCommand: SANDBOX_INSTALL_COMMAND` through
`prepareAdapterExecutionTargetRuntime` in each adapter's `execute()`
- Per-adapter install commands use npm globals where possible so
binaries land on a PATH segment the template already exports:
  - claude → `npm install -g @anthropic-ai/claude-code`
  - codex → `npm install -g @openai/codex`
  - cursor → `curl https://cursor.com/install -fsS | bash`
  - gemini → `npm install -g @google/gemini-cli`
  - opencode → `npm install -g opencode-ai`
  - pi → `npm install -g @mariozechner/pi-coding-agent`

SSH and local targets ignore `installCommand` (SSH runtime takes no such
param; local short-circuits before runtime prep), so this is a no-op for
non-sandbox environments.

## Verification

- `pnpm typecheck` clean
- `pnpm vitest run --no-coverage --project @paperclipai/adapter-utils`
and per-adapter projects pass
- Manual sandbox matrix (claude, codex, cursor, gemini, opencode, pi) —
each goes `install_command_run → resolvable → hello_probe_passed` (Codex
and Pi land on `hello_probe_auth_required`, which is the
configured-credentials problem, not an install issue)
- SSH no-regression: SSH Claude still passes; the helper short-circuits
on non-sandbox targets

## Risks

Medium — adds a network/CPU cost (npm install / curl) on every fresh
sandbox lease. Cost is bounded (one-time per lease, typically tens of
seconds for npm globals), and the helper never throws so a failing
install still lets the report run resolvability and hello probes. If a
sandbox image already has the CLI, the install is an idempotent
reinstall.

## Model Used

Claude Opus 4.7 (1M context)

## 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
- [x] If this change affects the UI, I have included before/after
screenshots — N/A (no UI)
- [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
2026-05-05 08:29:28 -07:00

289 lines
11 KiB
TypeScript

import type {
AdapterEnvironmentCheck,
AdapterEnvironmentTestContext,
AdapterEnvironmentTestResult,
} from "@paperclipai/adapter-utils";
import {
asString,
parseObject,
ensurePathInEnv,
} from "@paperclipai/adapter-utils/server-utils";
import {
ensureAdapterExecutionTargetCommandResolvable,
ensureAdapterExecutionTargetDirectory,
maybeRunSandboxInstallCommand,
runAdapterExecutionTargetProcess,
describeAdapterExecutionTarget,
resolveAdapterExecutionTargetCwd,
} from "@paperclipai/adapter-utils/execution-target";
import path from "node:path";
import os from "node:os";
import { parseCodexJsonl } from "./parse.js";
import { SANDBOX_INSTALL_COMMAND } from "../index.js";
import { codexHomeDir, readCodexAuthInfo } from "./quota.js";
import { buildCodexExecArgs } from "./codex-args.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 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 ? `${clean.slice(0, max - 1)}` : clean;
}
const CODEX_AUTH_REQUIRED_RE =
/(?:not\s+logged\s+in|login\s+required|authentication\s+required|unauthorized|invalid(?:\s+or\s+missing)?\s+api(?:[_\s-]?key)?|openai[_\s-]?api[_\s-]?key|api[_\s-]?key.*required|please\s+run\s+`?codex\s+login`?)/i;
export async function testEnvironment(
ctx: AdapterEnvironmentTestContext,
): Promise<AdapterEnvironmentTestResult> {
const checks: AdapterEnvironmentCheck[] = [];
const config = parseObject(ctx.config);
const command = asString(config.command, "codex");
const target = ctx.executionTarget ?? null;
const targetIsRemote = target?.kind === "remote";
const cwd = resolveAdapterExecutionTargetCwd(target, asString(config.cwd, ""), process.cwd());
const targetLabel = targetIsRemote
? ctx.environmentName ?? describeAdapterExecutionTarget(target)
: null;
const runId = `codex-envtest-${Date.now()}-${Math.random().toString(16).slice(2)}`;
if (targetLabel) {
checks.push({
code: "codex_environment_target",
level: "info",
message: `Probing inside environment: ${targetLabel}`,
});
}
try {
await ensureAdapterExecutionTargetDirectory(runId, target, cwd, {
cwd,
env: {},
createIfMissing: true,
});
checks.push({
code: "codex_cwd_valid",
level: "info",
message: `Working directory is valid: ${cwd}`,
});
} catch (err) {
checks.push({
code: "codex_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 });
const installCheck = await maybeRunSandboxInstallCommand({
runId,
target,
adapterKey: "codex",
installCommand: SANDBOX_INSTALL_COMMAND,
detectCommand: command,
env,
});
if (installCheck) checks.push(installCheck);
try {
await ensureAdapterExecutionTargetCommandResolvable(command, target, cwd, runtimeEnv);
checks.push({
code: "codex_command_resolvable",
level: "info",
message: `Command is executable: ${command}`,
});
} catch (err) {
checks.push({
code: "codex_command_unresolvable",
level: "error",
message: err instanceof Error ? err.message : "Command is not executable",
detail: command,
});
}
const configOpenAiKey = env.OPENAI_API_KEY;
const hostOpenAiKey = targetIsRemote ? undefined : process.env.OPENAI_API_KEY;
if (isNonEmpty(configOpenAiKey) || isNonEmpty(hostOpenAiKey)) {
const source = isNonEmpty(configOpenAiKey) ? "adapter config env" : "server environment";
checks.push({
code: "codex_openai_api_key_present",
level: "info",
message: "OPENAI_API_KEY is set for Codex authentication.",
detail: `Detected in ${source}.`,
});
} else if (!targetIsRemote) {
// Local-only auth file check. On remote targets, the probe will surface
// any missing-auth errors directly from the remote `codex` invocation.
const codexHome = isNonEmpty(env.CODEX_HOME) ? env.CODEX_HOME : undefined;
const codexAuth = await readCodexAuthInfo(codexHome).catch(() => null);
if (codexAuth) {
checks.push({
code: "codex_native_auth_present",
level: "info",
message: "Codex is authenticated via its own auth configuration.",
detail: codexAuth.email ? `Logged in as ${codexAuth.email}.` : `Credentials found in ${path.join(codexHome ?? codexHomeDir(), "auth.json")}.`,
});
} else {
checks.push({
code: "codex_openai_api_key_missing",
level: "warn",
message: "OPENAI_API_KEY is not set. Codex runs may fail until authentication is configured.",
hint: "Set OPENAI_API_KEY in adapter env, shell environment, or run `codex auth` to log in.",
});
}
}
const canRunProbe =
checks.every((check) => check.code !== "codex_cwd_invalid" && check.code !== "codex_command_unresolvable");
if (canRunProbe) {
if (!commandLooksLike(command, "codex")) {
checks.push({
code: "codex_hello_probe_skipped_custom_command",
level: "info",
message: "Skipped hello probe because command is not `codex`.",
detail: command,
hint: "Use the `codex` CLI command to run the automatic login and installation probe.",
});
} else {
const execArgs = buildCodexExecArgs({ ...config, fastMode: false });
const args = execArgs.args;
if (execArgs.fastModeIgnoredReason) {
checks.push({
code: "codex_fast_mode_unsupported_model",
level: "warn",
message: execArgs.fastModeIgnoredReason,
hint: "Switch the agent model to GPT-5.4 or enter a manual model ID to enable Codex Fast mode.",
});
}
// Codex CLI (>= 0.122) ignores the OPENAI_API_KEY env var and only reads
// credentials from $CODEX_HOME/auth.json. When we have a key available,
// wrap the probe with a shell that materializes a per-run auth.json so
// the CLI can authenticate. The key content is passed via env (not on
// the command line) to avoid leaking it into process listings.
const probeApiKey = isNonEmpty(configOpenAiKey)
? configOpenAiKey
: isNonEmpty(hostOpenAiKey)
? hostOpenAiKey
: null;
let probeCommand = command;
let probeArgs = args;
const probeEnv: Record<string, string> = { ...env };
if (probeApiKey) {
const probeHome = targetIsRemote
? `/tmp/paperclip-codex-probe-${runId}`
: path.join(os.tmpdir(), `paperclip-codex-probe-${runId}`);
probeEnv.CODEX_HOME = probeHome;
probeEnv._PAPERCLIP_CODEX_AUTH_JSON = JSON.stringify({ OPENAI_API_KEY: probeApiKey });
probeCommand = "sh";
// Trap on EXIT removes the probe home (with the API-key auth.json) on
// any exit path; we drop `exec` so the wrapper shell stays alive long
// enough for the trap to fire after the child returns.
probeArgs = [
"-c",
'set -e; mkdir -p "$CODEX_HOME"; umask 077; printf "%s" "$_PAPERCLIP_CODEX_AUTH_JSON" > "$CODEX_HOME/auth.json"; unset _PAPERCLIP_CODEX_AUTH_JSON; trap \'rm -rf "$CODEX_HOME"\' EXIT INT TERM; "$0" "$@"',
command,
...args,
];
}
const probe = await runAdapterExecutionTargetProcess(
runId,
target,
probeCommand,
probeArgs,
{
cwd,
env: probeEnv,
timeoutSec: 45,
graceSec: 5,
stdin: "Respond with hello.",
onLog: async () => {},
},
);
const parsed = parseCodexJsonl(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: "codex_hello_probe_timed_out",
level: "warn",
message: "Codex hello probe timed out.",
hint: "Retry the probe. If this persists, verify Codex 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 ? "codex_hello_probe_passed" : "codex_hello_probe_unexpected_output",
level: hasHello ? "info" : "warn",
message: hasHello
? "Codex hello probe succeeded."
: "Codex probe ran but did not return `hello` as expected.",
...(summary ? { detail: summary.replace(/\s+/g, " ").trim().slice(0, 240) } : {}),
...(hasHello
? {}
: {
hint: "Try the probe manually (`codex exec --json -` then prompt: Respond with hello) to inspect full output.",
}),
});
} else if (CODEX_AUTH_REQUIRED_RE.test(authEvidence)) {
checks.push({
code: "codex_hello_probe_auth_required",
level: "warn",
message: "Codex CLI is installed, but authentication is not ready.",
...(detail ? { detail } : {}),
hint: probeApiKey
? "OPENAI_API_KEY was provided but Codex still rejected the request. Verify the key is valid for the OpenAI Responses API (e.g. `curl -H \"Authorization: Bearer $OPENAI_API_KEY\" https://api.openai.com/v1/models`), or run `codex login` and seed `~/.codex/auth.json`."
: "Codex CLI does not read OPENAI_API_KEY from the environment; set OPENAI_API_KEY in this adapter's config (so Paperclip writes it to `$CODEX_HOME/auth.json`) or run `codex login` on the host first.",
});
} else {
checks.push({
code: "codex_hello_probe_failed",
level: "error",
message: "Codex hello probe failed.",
...(detail ? { detail } : {}),
hint: "Run `codex exec --json -` manually in this working directory and prompt `Respond with hello` to debug.",
});
}
}
}
return {
adapterType: ctx.adapterType,
status: summarizeStatus(checks),
checks,
testedAt: new Date().toISOString(),
};
}