Files
llmx/codex-rs/core/tests/exec.rs

127 lines
3.6 KiB
Rust
Raw Normal View History

#![cfg(target_os = "macos")]
#![expect(clippy::unwrap_used, clippy::expect_used)]
use std::collections::HashMap;
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::protocol::SandboxPolicy;
use codex_core::spawn::CODEX_SANDBOX_ENV_VAR;
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
}
async fn run_test_cmd(tmp: TempDir, cmd: Vec<&str>) -> Result<ExecToolCallOutput> {
let sandbox_type = get_platform_sandbox().expect("should be able to get sandbox type");
assert_eq!(sandbox_type, SandboxType::MacosSeatbelt);
let params = ExecParams {
command: cmd.iter().map(|s| s.to_string()).collect(),
cwd: tmp.path().to_path_buf(),
timeout_ms: Some(1000),
env: HashMap::new(),
with_escalated_permissions: None,
justification: None,
};
let policy = SandboxPolicy::new_read_only_policy();
chore: introduce ConversationManager as a clearinghouse for all conversations (#2240) This PR does two things because after I got deep into the first one I started pulling on the thread to the second: - Makes `ConversationManager` the place where all in-memory conversations are created and stored. Previously, `MessageProcessor` in the `codex-mcp-server` crate was doing this via its `session_map`, but this is something that should be done in `codex-core`. - It unwinds the `ctrl_c: tokio::sync::Notify` that was threaded throughout our code. I think this made sense at one time, but now that we handle Ctrl-C within the TUI and have a proper `Op::Interrupt` event, I don't think this was quite right, so I removed it. For `codex exec` and `codex proto`, we now use `tokio::signal::ctrl_c()` directly, but we no longer make `Notify` a field of `Codex` or `CodexConversation`. Changes of note: - Adds the files `conversation_manager.rs` and `codex_conversation.rs` to `codex-core`. - `Codex` and `CodexSpawnOk` are no longer exported from `codex-core`: other crates must use `CodexConversation` instead (which is created via `ConversationManager`). - `core/src/codex_wrapper.rs` has been deleted in favor of `ConversationManager`. - `ConversationManager::new_conversation()` returns `NewConversation`, which is in line with the `new_conversation` tool we want to add to the MCP server. Note `NewConversation` includes `SessionConfiguredEvent`, so we eliminate checks in cases like `codex-rs/core/tests/client.rs` to verify `SessionConfiguredEvent` is the first event because that is now internal to `ConversationManager`. - Quite a bit of code was deleted from `codex-rs/mcp-server/src/message_processor.rs` since it no longer has to manage multiple conversations itself: it goes through `ConversationManager` instead. - `core/tests/live_agent.rs` has been deleted because I had to update a bunch of tests and all the tests in here were ignored, and I don't think anyone ever ran them, so this was just technical debt, at this point. - Removed `notify_on_sigint()` from `util.rs` (and in a follow-up, I hope to refactor the blandly-named `util.rs` into more descriptive files). - In general, I started replacing local variables named `codex` as `conversation`, where appropriate, though admittedly I didn't do it through all the integration tests because that would have added a lot of noise to this PR. --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/openai/codex/pull/2240). * #2264 * #2263 * __->__ #2240
2025-08-13 13:38:18 -07:00
process_exec_tool_call(params, sandbox_type, &policy, &None, 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"];
#[expect(clippy::unwrap_used)]
let output = run_test_cmd(tmp, cmd).await.unwrap();
let expected_output = (1..=256)
.map(|i| format!("{i}\n"))
.collect::<Vec<_>>()
.join("");
assert_eq!(output.stdout.text, expected_output);
assert_eq!(output.stdout.truncated_after_lines, Some(256));
}
/// 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_eq!(output.stdout.text.len(), 10240);
assert_eq!(output.stdout.truncated_after_lines, Some(10));
}
/// 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());
}