Files
llmx/codex-rs/core/tests/suite/shell_serialization.rs
jif-oai f7b4e29609 feat: feature flag (#4948)
Add proper feature flag instead of having custom flags for everything.
This is just for experimental/wip part of the code
It can be used through CLI:
```bash
codex --enable unified_exec --disable view_image_tool
```

Or in the `config.toml`
```toml
# Global toggles applied to every profile unless overridden.
[features]
apply_patch_freeform = true
view_image_tool = false
```

Follow-up:
In a following PR, the goal is to have a default have `bundles` of
features that we can associate to a model
2025-10-14 17:50:00 +00:00

279 lines
8.1 KiB
Rust

#![cfg(not(target_os = "windows"))]
use anyhow::Result;
use codex_core::features::Feature;
use codex_core::model_family::find_family_for_model;
use codex_core::protocol::AskForApproval;
use codex_core::protocol::EventMsg;
use codex_core::protocol::InputItem;
use codex_core::protocol::Op;
use codex_core::protocol::SandboxPolicy;
use codex_protocol::config_types::ReasoningSummary;
use core_test_support::assert_regex_match;
use core_test_support::responses::ev_assistant_message;
use core_test_support::responses::ev_completed;
use core_test_support::responses::ev_function_call;
use core_test_support::responses::ev_response_created;
use core_test_support::responses::mount_sse_sequence;
use core_test_support::responses::sse;
use core_test_support::responses::start_mock_server;
use core_test_support::skip_if_no_network;
use core_test_support::test_codex::TestCodex;
use core_test_support::test_codex::test_codex;
use core_test_support::wait_for_event;
use serde_json::Value;
use serde_json::json;
async fn submit_turn(test: &TestCodex, prompt: &str, sandbox_policy: SandboxPolicy) -> Result<()> {
let session_model = test.session_configured.model.clone();
test.codex
.submit(Op::UserTurn {
items: vec![InputItem::Text {
text: prompt.into(),
}],
final_output_json_schema: None,
cwd: test.cwd.path().to_path_buf(),
approval_policy: AskForApproval::Never,
sandbox_policy,
model: session_model,
effort: None,
summary: ReasoningSummary::Auto,
})
.await?;
wait_for_event(&test.codex, |event| {
matches!(event, EventMsg::TaskComplete(_))
})
.await;
Ok(())
}
fn request_bodies(requests: &[wiremock::Request]) -> Result<Vec<Value>> {
requests
.iter()
.map(|req| Ok(serde_json::from_slice::<Value>(&req.body)?))
.collect()
}
fn find_function_call_output<'a>(bodies: &'a [Value], call_id: &str) -> Option<&'a Value> {
for body in bodies {
if let Some(items) = body.get("input").and_then(Value::as_array) {
for item in items {
if item.get("type").and_then(Value::as_str) == Some("function_call_output")
&& item.get("call_id").and_then(Value::as_str) == Some(call_id)
{
return Some(item);
}
}
}
}
None
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn shell_output_stays_json_without_freeform_apply_patch() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let mut builder = test_codex().with_config(|config| {
config.features.disable(Feature::ApplyPatchFreeform);
config.model = "gpt-5".to_string();
config.model_family = find_family_for_model("gpt-5").expect("gpt-5 is a model family");
});
let test = builder.build(&server).await?;
let call_id = "shell-json";
let args = json!({
"command": ["/bin/echo", "shell json"],
"timeout_ms": 1_000,
});
let responses = vec![
sse(vec![
ev_response_created("resp-1"),
ev_function_call(call_id, "shell", &serde_json::to_string(&args)?),
ev_completed("resp-1"),
]),
sse(vec![
ev_assistant_message("msg-1", "done"),
ev_completed("resp-2"),
]),
];
mount_sse_sequence(&server, responses).await;
submit_turn(
&test,
"run the json shell command",
SandboxPolicy::DangerFullAccess,
)
.await?;
let requests = server
.received_requests()
.await
.expect("recorded requests present");
let bodies = request_bodies(&requests)?;
let output_item = find_function_call_output(&bodies, call_id).expect("shell output present");
let output = output_item
.get("output")
.and_then(Value::as_str)
.expect("shell output string");
let parsed: Value = serde_json::from_str(output)?;
assert_eq!(
parsed
.get("metadata")
.and_then(|metadata| metadata.get("exit_code"))
.and_then(Value::as_i64),
Some(0),
"expected zero exit code in unformatted JSON output",
);
let stdout = parsed
.get("output")
.and_then(Value::as_str)
.unwrap_or_default();
assert_regex_match(r"(?s)^shell json\n?$", stdout);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn shell_output_is_structured_with_freeform_apply_patch() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let mut builder = test_codex().with_config(|config| {
config.features.enable(Feature::ApplyPatchFreeform);
});
let test = builder.build(&server).await?;
let call_id = "shell-structured";
let args = json!({
"command": ["/bin/echo", "freeform shell"],
"timeout_ms": 1_000,
});
let responses = vec![
sse(vec![
ev_response_created("resp-1"),
ev_function_call(call_id, "shell", &serde_json::to_string(&args)?),
ev_completed("resp-1"),
]),
sse(vec![
ev_assistant_message("msg-1", "done"),
ev_completed("resp-2"),
]),
];
mount_sse_sequence(&server, responses).await;
submit_turn(
&test,
"run the structured shell command",
SandboxPolicy::DangerFullAccess,
)
.await?;
let requests = server
.received_requests()
.await
.expect("recorded requests present");
let bodies = request_bodies(&requests)?;
let output_item =
find_function_call_output(&bodies, call_id).expect("structured output present");
let output = output_item
.get("output")
.and_then(Value::as_str)
.expect("structured output string");
assert!(
serde_json::from_str::<Value>(output).is_err(),
"expected structured shell output to be plain text",
);
let expected_pattern = r"(?s)^Exit code: 0
Wall time: [0-9]+(?:\.[0-9]+)? seconds
Output:
freeform shell
?$";
assert_regex_match(expected_pattern, output);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn shell_output_reserializes_truncated_content() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let mut builder = test_codex().with_config(|config| {
config.model = "gpt-5-codex".to_string();
config.model_family =
find_family_for_model("gpt-5-codex").expect("gpt-5 is a model family");
});
let test = builder.build(&server).await?;
let call_id = "shell-truncated";
let args = json!({
"command": ["/bin/sh", "-c", "seq 1 400"],
"timeout_ms": 5_000,
});
let responses = vec![
sse(vec![
ev_response_created("resp-1"),
ev_function_call(call_id, "shell", &serde_json::to_string(&args)?),
ev_completed("resp-1"),
]),
sse(vec![
ev_assistant_message("msg-1", "done"),
ev_completed("resp-2"),
]),
];
mount_sse_sequence(&server, responses).await;
submit_turn(
&test,
"run the truncation shell command",
SandboxPolicy::DangerFullAccess,
)
.await?;
let requests = server
.received_requests()
.await
.expect("recorded requests present");
let bodies = request_bodies(&requests)?;
let output_item =
find_function_call_output(&bodies, call_id).expect("truncated output present");
let output = output_item
.get("output")
.and_then(Value::as_str)
.expect("truncated output string");
assert!(
serde_json::from_str::<Value>(output).is_err(),
"expected truncated shell output to be plain text",
);
let truncated_pattern = r#"(?s)^Exit code: 0
Wall time: [0-9]+(?:\.[0-9]+)? seconds
Total output lines: 400
Output:
1
2
3
4
5
6
.*
\[\.{3} omitted \d+ of 400 lines \.{3}\]
.*
396
397
398
399
400
$"#;
assert_regex_match(truncated_pattern, output);
Ok(())
}