mirror of
https://github.com/openai/codex.git
synced 2026-04-30 11:21:34 +03:00
## Why `#13434` introduces split `FileSystemSandboxPolicy` and `NetworkSandboxPolicy`, but the runtime still made most execution-time sandbox decisions from the legacy `SandboxPolicy` projection. That projection loses information about combinations like unrestricted filesystem access with restricted network access. In practice, that means the runtime can choose the wrong platform sandbox behavior or set the wrong network-restriction environment for a command even when config has already separated those concerns. This PR carries the split policies through the runtime so sandbox selection, process spawning, and exec handling can consult the policy that actually matters. ## What changed - threaded `FileSystemSandboxPolicy` and `NetworkSandboxPolicy` through `TurnContext`, `ExecRequest`, sandbox attempts, shell escalation state, unified exec, and app-server exec overrides - updated sandbox selection in `core/src/sandboxing/mod.rs` and `core/src/exec.rs` to key off `FileSystemSandboxPolicy.kind` plus `NetworkSandboxPolicy`, rather than inferring behavior only from the legacy `SandboxPolicy` - updated process spawning in `core/src/spawn.rs` and the platform wrappers to use `NetworkSandboxPolicy` when deciding whether to set `CODEX_SANDBOX_NETWORK_DISABLED` - kept additional-permissions handling and legacy `ExternalSandbox` compatibility projections aligned with the split policies, including explicit user-shell execution and Windows restricted-token routing - updated callers across `core`, `app-server`, and `linux-sandbox` to pass the split policies explicitly ## Verification - added regression coverage in `core/tests/suite/user_shell_cmd.rs` to verify `RunUserShellCommand` does not inherit `CODEX_SANDBOX_NETWORK_DISABLED` from the active turn - added coverage in `core/src/exec.rs` for Windows restricted-token sandbox selection when the legacy projection is `ExternalSandbox` - updated Linux sandbox coverage in `linux-sandbox/tests/suite/landlock.rs` to exercise the split-policy exec path - verified the current PR state with `just clippy` --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/openai/codex/pull/13439). * #13453 * #13452 * #13451 * #13449 * #13448 * #13445 * #13440 * __->__ #13439 --------- Co-authored-by: viyatb-oai <viyatb@openai.com>
144 lines
4.1 KiB
Rust
144 lines
4.1 KiB
Rust
#![cfg(target_os = "macos")]
|
|
|
|
use std::collections::HashMap;
|
|
use std::string::ToString;
|
|
|
|
use codex_core::exec::ExecParams;
|
|
use codex_core::exec::ExecToolCallOutput;
|
|
use codex_core::exec::SandboxType;
|
|
use codex_core::exec::process_exec_tool_call;
|
|
use codex_core::sandboxing::SandboxPermissions;
|
|
use codex_core::spawn::CODEX_SANDBOX_ENV_VAR;
|
|
use codex_protocol::config_types::WindowsSandboxLevel;
|
|
use codex_protocol::permissions::FileSystemSandboxPolicy;
|
|
use codex_protocol::permissions::NetworkSandboxPolicy;
|
|
use codex_protocol::protocol::SandboxPolicy;
|
|
use tempfile::TempDir;
|
|
|
|
use codex_core::error::Result;
|
|
|
|
use codex_core::get_platform_sandbox;
|
|
|
|
fn skip_test() -> bool {
|
|
if std::env::var(CODEX_SANDBOX_ENV_VAR) == Ok("seatbelt".to_string()) {
|
|
eprintln!("{CODEX_SANDBOX_ENV_VAR} is set to 'seatbelt', skipping test.");
|
|
return true;
|
|
}
|
|
|
|
false
|
|
}
|
|
|
|
#[expect(clippy::expect_used)]
|
|
async fn run_test_cmd(tmp: TempDir, cmd: Vec<&str>) -> Result<ExecToolCallOutput> {
|
|
let sandbox_type = get_platform_sandbox(false).expect("should be able to get sandbox type");
|
|
assert_eq!(sandbox_type, SandboxType::MacosSeatbelt);
|
|
|
|
let params = ExecParams {
|
|
command: cmd.iter().map(ToString::to_string).collect(),
|
|
cwd: tmp.path().to_path_buf(),
|
|
expiration: 1000.into(),
|
|
env: HashMap::new(),
|
|
network: None,
|
|
sandbox_permissions: SandboxPermissions::UseDefault,
|
|
windows_sandbox_level: WindowsSandboxLevel::Disabled,
|
|
justification: None,
|
|
arg0: None,
|
|
};
|
|
|
|
let policy = SandboxPolicy::new_read_only_policy();
|
|
|
|
process_exec_tool_call(
|
|
params,
|
|
&policy,
|
|
&FileSystemSandboxPolicy::from(&policy),
|
|
NetworkSandboxPolicy::from(&policy),
|
|
tmp.path(),
|
|
&None,
|
|
false,
|
|
None,
|
|
)
|
|
.await
|
|
}
|
|
|
|
/// Command succeeds with exit code 0 normally
|
|
#[tokio::test]
|
|
async fn exit_code_0_succeeds() {
|
|
if skip_test() {
|
|
return;
|
|
}
|
|
|
|
let tmp = TempDir::new().expect("should be able to create temp dir");
|
|
let cmd = vec!["echo", "hello"];
|
|
|
|
let output = run_test_cmd(tmp, cmd).await.unwrap();
|
|
assert_eq!(output.stdout.text, "hello\n");
|
|
assert_eq!(output.stderr.text, "");
|
|
assert_eq!(output.stdout.truncated_after_lines, None);
|
|
}
|
|
|
|
/// Command succeeds with exit code 0 normally
|
|
#[tokio::test]
|
|
async fn truncates_output_lines() {
|
|
if skip_test() {
|
|
return;
|
|
}
|
|
|
|
let tmp = TempDir::new().expect("should be able to create temp dir");
|
|
let cmd = vec!["seq", "300"];
|
|
|
|
let output = run_test_cmd(tmp, cmd).await.unwrap();
|
|
|
|
let expected_output = (1..=300)
|
|
.map(|i| format!("{i}\n"))
|
|
.collect::<Vec<_>>()
|
|
.join("");
|
|
assert_eq!(output.stdout.text, expected_output);
|
|
assert_eq!(output.stdout.truncated_after_lines, None);
|
|
}
|
|
|
|
/// Command succeeds with exit code 0 normally
|
|
#[tokio::test]
|
|
async fn truncates_output_bytes() {
|
|
if skip_test() {
|
|
return;
|
|
}
|
|
|
|
let tmp = TempDir::new().expect("should be able to create temp dir");
|
|
// each line is 1000 bytes
|
|
let cmd = vec!["bash", "-lc", "seq 15 | awk '{printf \"%-1000s\\n\", $0}'"];
|
|
|
|
let output = run_test_cmd(tmp, cmd).await.unwrap();
|
|
|
|
assert!(output.stdout.text.len() >= 15000);
|
|
assert_eq!(output.stdout.truncated_after_lines, None);
|
|
}
|
|
|
|
/// Command not found returns exit code 127, this is not considered a sandbox error
|
|
#[tokio::test]
|
|
async fn exit_command_not_found_is_ok() {
|
|
if skip_test() {
|
|
return;
|
|
}
|
|
|
|
let tmp = TempDir::new().expect("should be able to create temp dir");
|
|
let cmd = vec!["/bin/bash", "-c", "nonexistent_command_12345"];
|
|
run_test_cmd(tmp, cmd).await.unwrap();
|
|
}
|
|
|
|
/// Writing a file fails and should be considered a sandbox error
|
|
#[tokio::test]
|
|
async fn write_file_fails_as_sandbox_error() {
|
|
if skip_test() {
|
|
return;
|
|
}
|
|
|
|
let tmp = TempDir::new().expect("should be able to create temp dir");
|
|
let path = tmp.path().join("test.txt");
|
|
let cmd = vec![
|
|
"/user/bin/touch",
|
|
path.to_str().expect("should be able to get path"),
|
|
];
|
|
|
|
assert!(run_test_cmd(tmp, cmd).await.is_err());
|
|
}
|