mirror of
https://github.com/openai/codex.git
synced 2026-04-26 23:55:25 +00:00
Promote shared helpers for suite tests (#6460)
## Summary - add `TestCodex::submit_turn_with_policies` and extend the response helpers with reusable tool-call utilities - update the grep_files, read_file, list_dir, shell_serialization, and tools suites to rely on the shared helpers instead of local copies - make the list_dir helper return `anyhow::Result` so clippy no longer warns about `expect` ## Testing - `just fix -p codex-core` - `cargo test -p codex-core --test all suite::grep_files::grep_files_tool_collects_matches` - `cargo test -p codex-core suite::grep_files::grep_files_tool_collects_matches -- --ignored` (filter requests ignored tests so nothing runs, but the build stays clean) ------ [Codex Task](https://chatgpt.com/codex/tasks/task_i_69112d53abac83219813cab4d7cb6446)
This commit is contained in:
@@ -1,25 +1,11 @@
|
||||
#![cfg(not(target_os = "windows"))]
|
||||
|
||||
use codex_core::protocol::AskForApproval;
|
||||
use codex_core::protocol::EventMsg;
|
||||
use codex_core::protocol::Op;
|
||||
use codex_core::protocol::SandboxPolicy;
|
||||
use codex_protocol::config_types::ReasoningSummary;
|
||||
use codex_protocol::user_input::UserInput;
|
||||
use core_test_support::responses;
|
||||
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::sse;
|
||||
use core_test_support::responses::mount_function_call_agent_response;
|
||||
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 pretty_assertions::assert_eq;
|
||||
use serde_json::Value;
|
||||
use wiremock::matchers::any;
|
||||
use serde_json::json;
|
||||
|
||||
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
|
||||
#[ignore = "disabled until we enable read_file tool"]
|
||||
@@ -27,72 +13,29 @@ async fn read_file_tool_returns_requested_lines() -> anyhow::Result<()> {
|
||||
skip_if_no_network!(Ok(()));
|
||||
|
||||
let server = start_mock_server().await;
|
||||
let test = test_codex().build(&server).await?;
|
||||
|
||||
let TestCodex {
|
||||
codex,
|
||||
cwd,
|
||||
session_configured,
|
||||
..
|
||||
} = test_codex().build(&server).await?;
|
||||
|
||||
let file_path = cwd.path().join("sample.txt");
|
||||
let file_path = test.cwd.path().join("sample.txt");
|
||||
std::fs::write(&file_path, "first\nsecond\nthird\nfourth\n")?;
|
||||
let file_path = file_path.to_string_lossy().to_string();
|
||||
|
||||
let call_id = "read-file-call";
|
||||
let arguments = serde_json::json!({
|
||||
let arguments = json!({
|
||||
"file_path": file_path,
|
||||
"offset": 2,
|
||||
"limit": 2,
|
||||
})
|
||||
.to_string();
|
||||
|
||||
let first_response = sse(vec![
|
||||
ev_response_created("resp-1"),
|
||||
ev_function_call(call_id, "read_file", &arguments),
|
||||
ev_completed("resp-1"),
|
||||
]);
|
||||
responses::mount_sse_once_match(&server, any(), first_response).await;
|
||||
let mocks = mount_function_call_agent_response(&server, call_id, &arguments, "read_file").await;
|
||||
|
||||
let second_response = sse(vec![
|
||||
ev_assistant_message("msg-1", "done"),
|
||||
ev_completed("resp-2"),
|
||||
]);
|
||||
let second_mock = responses::mount_sse_once_match(&server, any(), second_response).await;
|
||||
test.submit_turn("please inspect sample.txt").await?;
|
||||
|
||||
let session_model = session_configured.model.clone();
|
||||
|
||||
codex
|
||||
.submit(Op::UserTurn {
|
||||
items: vec![UserInput::Text {
|
||||
text: "please inspect sample.txt".into(),
|
||||
}],
|
||||
final_output_json_schema: None,
|
||||
cwd: cwd.path().to_path_buf(),
|
||||
approval_policy: AskForApproval::Never,
|
||||
sandbox_policy: SandboxPolicy::DangerFullAccess,
|
||||
model: session_model,
|
||||
effort: None,
|
||||
summary: ReasoningSummary::Auto,
|
||||
})
|
||||
.await?;
|
||||
|
||||
wait_for_event(&codex, |ev| matches!(ev, EventMsg::TaskComplete(_))).await;
|
||||
|
||||
let req = second_mock.single_request();
|
||||
let tool_output_item = req.function_call_output(call_id);
|
||||
assert_eq!(
|
||||
tool_output_item.get("call_id").and_then(Value::as_str),
|
||||
Some(call_id)
|
||||
);
|
||||
let output_text = tool_output_item
|
||||
.get("output")
|
||||
.and_then(|value| match value {
|
||||
Value::String(text) => Some(text.as_str()),
|
||||
Value::Object(obj) => obj.get("content").and_then(Value::as_str),
|
||||
_ => None,
|
||||
})
|
||||
.expect("output text present");
|
||||
let req = mocks.completion.single_request();
|
||||
let (output_text_opt, _) = req
|
||||
.function_call_output_content_and_success(call_id)
|
||||
.expect("output present");
|
||||
let output_text = output_text_opt.expect("output text present");
|
||||
assert_eq!(output_text, "L2: second\nL3: third");
|
||||
|
||||
Ok(())
|
||||
|
||||
Reference in New Issue
Block a user