Files
llmx/codex-rs/core/tests/previous_response_id.rs
Michael Bolin fde48aaa0d feat: experimental env var: CODEX_SANDBOX_NETWORK_DISABLED (#879)
When using Codex to develop Codex itself, I noticed that sometimes it
would try to add `#[ignore]` to the following tests:

```
keeps_previous_response_id_between_tasks()
retries_on_early_close()
```

Both of these tests start a `MockServer` that launches an HTTP server on
an ephemeral port and requires network access to hit it, which the
Seatbelt policy associated with `--full-auto` correctly denies. If I
wasn't paying attention to the code that Codex was generating, one of
these `#[ignore]` annotations could have slipped into the codebase,
effectively disabling the test for everyone.

To that end, this PR enables an experimental environment variable named
`CODEX_SANDBOX_NETWORK_DISABLED` that is set to `1` if the
`SandboxPolicy` used to spawn the process does not have full network
access. I say it is "experimental" because I'm not convinced this API is
quite right, but we need to start somewhere. (It might be more
appropriate to have an env var like `CODEX_SANDBOX=full-auto`, but the
challenge is that our newer `SandboxPolicy` abstraction does not map to
a simple set of enums like in the TypeScript CLI.)

We leverage this new functionality by adding the following code to the
aforementioned tests as a way to "dynamically disable" them:

```rust
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
    println!(
        "Skipping test because it cannot execute when network is disabled in a Codex sandbox."
    );
    return;
}
```

We can use the `debug seatbelt --full-auto` command to verify that
`cargo test` fails when run under Seatbelt prior to this change:

```
$ cargo run --bin codex -- debug seatbelt --full-auto -- cargo test
---- keeps_previous_response_id_between_tasks stdout ----

thread 'keeps_previous_response_id_between_tasks' panicked at /Users/mbolin/.cargo/registry/src/index.crates.io-1949cf8c6b5b557f/wiremock-0.6.3/src/mock_server/builder.rs:107:46:
Failed to bind an OS port for a mock server.: Os { code: 1, kind: PermissionDenied, message: "Operation not permitted" }
note: run with `RUST_BACKTRACE=1` environment variable to display a backtrace


failures:
    keeps_previous_response_id_between_tasks

test result: FAILED. 0 passed; 1 failed; 0 ignored; 0 measured; 0 filtered out; finished in 0.00s

error: test failed, to rerun pass `-p codex-core --test previous_response_id`
```

Though after this change, the above command succeeds! This means that,
going forward, when Codex operates on Codex itself, when it runs `cargo
test`, only "real failures" should cause the command to fail.

As part of this change, I decided to tighten up the codepaths for
running `exec()` for shell tool calls. In particular, we do it in `core`
for the main Codex business logic itself, but we also expose this logic
via `debug` subcommands in the CLI in the `cli` crate. The logic for the
`debug` subcommands was not quite as faithful to the true business logic
as I liked, so I:

* refactored a bit of the Linux code, splitting `linux.rs` into
`linux_exec.rs` and `landlock.rs` in the `core` crate.
* gating less code behind `#[cfg(target_os = "linux")]` because such
code does not get built by default when I develop on Mac, which means I
either have to build the code in Docker or wait for CI signal
* introduced `macro_rules! configure_command` in `exec.rs` so we can
have both sync and async versions of this code. The synchronous version
seems more appropriate for straight threads or potentially fork/exec.
2025-05-09 18:29:34 -07:00

160 lines
4.8 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
use std::time::Duration;
use codex_core::Codex;
use codex_core::ModelProviderInfo;
use codex_core::config::Config;
use codex_core::exec::CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use serde_json::Value;
use tokio::time::timeout;
use wiremock::Match;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::Request;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;
/// Matcher asserting that JSON body has NO `previous_response_id` field.
struct NoPrevId;
impl Match for NoPrevId {
fn matches(&self, req: &Request) -> bool {
serde_json::from_slice::<Value>(&req.body)
.map(|v| v.get("previous_response_id").is_none())
.unwrap_or(false)
}
}
/// Matcher asserting that JSON body HAS a `previous_response_id` field.
struct HasPrevId;
impl Match for HasPrevId {
fn matches(&self, req: &Request) -> bool {
serde_json::from_slice::<Value>(&req.body)
.map(|v| v.get("previous_response_id").is_some())
.unwrap_or(false)
}
}
/// Build minimal SSE stream with completed marker.
fn sse_completed(id: &str) -> String {
format!(
"event: response.completed\n\
data: {{\"type\":\"response.completed\",\"response\":{{\"id\":\"{}\",\"output\":[]}}}}\n\n\n",
id
)
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn keeps_previous_response_id_between_tasks() {
#![allow(clippy::unwrap_used)]
if std::env::var(CODEX_SANDBOX_NETWORK_DISABLED_ENV_VAR).is_ok() {
println!(
"Skipping test because it cannot execute when network is disabled in a Codex sandbox."
);
return;
}
// Mock server
let server = MockServer::start().await;
// First request must NOT include `previous_response_id`.
let first = ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(sse_completed("resp1"), "text/event-stream");
Mock::given(method("POST"))
.and(path("/v1/responses"))
.and(NoPrevId)
.respond_with(first)
.expect(1)
.mount(&server)
.await;
// Second request MUST include `previous_response_id`.
let second = ResponseTemplate::new(200)
.insert_header("content-type", "text/event-stream")
.set_body_raw(sse_completed("resp2"), "text/event-stream");
Mock::given(method("POST"))
.and(path("/v1/responses"))
.and(HasPrevId)
.respond_with(second)
.expect(1)
.mount(&server)
.await;
// Environment
// Update environment `set_var` is `unsafe` starting with the 2024
// edition so we group the calls into a single `unsafe { … }` block.
unsafe {
std::env::set_var("OPENAI_REQUEST_MAX_RETRIES", "0");
std::env::set_var("OPENAI_STREAM_MAX_RETRIES", "0");
}
let model_provider = ModelProviderInfo {
name: "openai".into(),
base_url: format!("{}/v1", server.uri()),
// Environment variable that should exist in the test environment.
// ModelClient will return an error if the environment variable for the
// provider is not set.
env_key: Some("PATH".into()),
env_key_instructions: None,
wire_api: codex_core::WireApi::Responses,
};
// Init session
let mut config = Config::load_default_config_for_test();
config.model_provider = model_provider;
let ctrl_c = std::sync::Arc::new(tokio::sync::Notify::new());
let (codex, _init_id) = Codex::spawn(config, ctrl_c.clone()).await.unwrap();
// Task 1 triggers first request (no previous_response_id)
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: "hello".into(),
}],
})
.await
.unwrap();
// Wait for TaskComplete
loop {
let ev = timeout(Duration::from_secs(1), codex.next_event())
.await
.unwrap()
.unwrap();
if matches!(ev.msg, codex_core::protocol::EventMsg::TaskComplete) {
break;
}
}
// Task 2 should include `previous_response_id` (triggers second request)
codex
.submit(Op::UserInput {
items: vec![InputItem::Text {
text: "again".into(),
}],
})
.await
.unwrap();
// Wait for TaskComplete or error
loop {
let ev = timeout(Duration::from_secs(1), codex.next_event())
.await
.unwrap()
.unwrap();
match ev.msg {
codex_core::protocol::EventMsg::TaskComplete => break,
codex_core::protocol::EventMsg::Error { message } => {
panic!("unexpected error: {message}")
}
_ => (),
}
}
}