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

packages/adapters/codex-local/src/index.ts

@@ -3,6 +3,8 @@ import type { AdapterModelProfileDefinition } from "@paperclipai/adapter-utils";
 export const type = "codex_local";
 export const label = "Codex (local)";
 
+export const SANDBOX_INSTALL_COMMAND = "npm install -g @openai/codex";
+
 export const DEFAULT_CODEX_LOCAL_MODEL = "gpt-5.3-codex";
 export const DEFAULT_CODEX_LOCAL_BYPASS_APPROVALS_AND_SANDBOX = true;
 export const CODEX_LOCAL_FAST_MODE_SUPPORTED_MODELS = ["gpt-5.4"] as const;

packages/adapters/codex-local/src/server/execute.ts

@@ -45,6 +45,7 @@ import {
 import { pathExists, prepareManagedCodexHome, resolveManagedCodexHomeDir, resolveSharedCodexHomeDir } from "./codex-home.js";
 import { resolveCodexDesiredSkillNames } from "./skills.js";
 import { buildCodexExecArgs } from "./codex-args.js";
+import { SANDBOX_INSTALL_COMMAND } from "../index.js";
 
 const __moduleDir = path.dirname(fileURLToPath(import.meta.url));
 const CODEX_ROLLOUT_NOISE_RE =
@@ -374,6 +375,8 @@ export async function execute(ctx: AdapterExecutionContext): Promise<AdapterExec
           target: executionTarget,
           adapterKey: "codex",
           workspaceLocalDir: cwd,
+          installCommand: SANDBOX_INSTALL_COMMAND,
+          detectCommand: command,
           assets: [
             {
               key: "home",

packages/adapters/codex-local/src/server/test.ts

@@ -11,6 +11,7 @@ import {
 import {
   ensureAdapterExecutionTargetCommandResolvable,
   ensureAdapterExecutionTargetDirectory,
+  maybeRunSandboxInstallCommand,
   runAdapterExecutionTargetProcess,
   describeAdapterExecutionTarget,
   resolveAdapterExecutionTargetCwd,
@@ -18,6 +19,7 @@ import {
 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";
 
@@ -104,6 +106,15 @@ export async function testEnvironment(
     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({