Files
codex/codex-rs/core/tests/suite/override_updates.rs
Ahmed Ibrahim 69cfc73dc6 change collaboration mode to struct (#9793)
Shouldn't cause behavioral change
2026-01-23 17:00:23 -08:00

224 lines
7.2 KiB
Rust

use anyhow::Result;
use codex_core::config::Constrained;
use codex_core::protocol::AskForApproval;
use codex_core::protocol::COLLABORATION_MODE_CLOSE_TAG;
use codex_core::protocol::COLLABORATION_MODE_OPEN_TAG;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Op;
use codex_core::protocol::RolloutItem;
use codex_core::protocol::RolloutLine;
use codex_core::protocol::ENVIRONMENT_CONTEXT_OPEN_TAG;
use codex_protocol::config_types::CollaborationMode;
use codex_protocol::config_types::ModeKind;
use codex_protocol::config_types::Settings;
use codex_protocol::models::ContentItem;
use codex_protocol::models::ResponseItem;
use core_test_support::responses::start_mock_server;
use core_test_support::skip_if_no_network;
use core_test_support::test_codex::test_codex;
use core_test_support::wait_for_event;
use pretty_assertions::assert_eq;
use std::collections::HashSet;
use std::path::Path;
use std::time::Duration;
use tempfile::TempDir;
fn collab_mode_with_instructions(instructions: Option<&str>) -> CollaborationMode {
CollaborationMode {
mode: ModeKind::Custom,
settings: Settings {
model: "gpt-5.1".to_string(),
reasoning_effort: None,
developer_instructions: instructions.map(str::to_string),
},
}
}
fn collab_xml(text: &str) -> String {
format!("{COLLABORATION_MODE_OPEN_TAG}{text}{COLLABORATION_MODE_CLOSE_TAG}")
}
async fn read_rollout_text(path: &Path) -> anyhow::Result<String> {
for _ in 0..50 {
if path.exists()
&& let Ok(text) = std::fs::read_to_string(path)
&& !text.trim().is_empty()
{
return Ok(text);
}
tokio::time::sleep(Duration::from_millis(20)).await;
}
Ok(std::fs::read_to_string(path)?)
}
fn rollout_developer_texts(text: &str) -> Vec<String> {
let mut texts = Vec::new();
for line in text.lines() {
let trimmed = line.trim();
if trimmed.is_empty() {
continue;
}
let rollout: RolloutLine = match serde_json::from_str(trimmed) {
Ok(rollout) => rollout,
Err(_) => continue,
};
if let RolloutItem::ResponseItem(ResponseItem::Message { role, content, .. }) =
rollout.item
&& role == "developer"
{
for item in content {
if let ContentItem::InputText { text } = item {
texts.push(text);
}
}
}
}
texts
}
fn rollout_environment_texts(text: &str) -> Vec<String> {
let mut texts = Vec::new();
for line in text.lines() {
let trimmed = line.trim();
if trimmed.is_empty() {
continue;
}
let rollout: RolloutLine = match serde_json::from_str(trimmed) {
Ok(rollout) => rollout,
Err(_) => continue,
};
if let RolloutItem::ResponseItem(ResponseItem::Message { role, content, .. }) =
rollout.item
&& role == "user"
{
for item in content {
if let ContentItem::InputText { text } = item
&& text.starts_with(ENVIRONMENT_CONTEXT_OPEN_TAG)
{
texts.push(text);
}
}
}
}
texts
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn override_turn_context_records_permissions_update() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let mut builder = test_codex().with_config(|config| {
config.approval_policy = Constrained::allow_any(AskForApproval::OnRequest);
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: Some(AskForApproval::Never),
sandbox_policy: None,
model: None,
effort: None,
summary: None,
collaboration_mode: None,
personality: None,
})
.await?;
test.codex.submit(Op::Shutdown).await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
let rollout_path = test.codex.rollout_path();
let rollout_text = read_rollout_text(&rollout_path).await?;
let developer_texts = rollout_developer_texts(&rollout_text);
let approval_texts: Vec<&String> = developer_texts
.iter()
.filter(|text| text.contains("`approval_policy`"))
.collect();
assert!(
approval_texts
.iter()
.any(|text| text.contains("`approval_policy` is `never`")),
"expected updated approval policy instructions in rollout"
);
let unique: HashSet<&String> = approval_texts.iter().copied().collect();
assert_eq!(unique.len(), 2);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn override_turn_context_records_environment_update() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let test = test_codex().build(&server).await?;
let new_cwd = TempDir::new()?;
test.codex
.submit(Op::OverrideTurnContext {
cwd: Some(new_cwd.path().to_path_buf()),
approval_policy: None,
sandbox_policy: None,
model: None,
effort: None,
summary: None,
collaboration_mode: None,
personality: None,
})
.await?;
test.codex.submit(Op::Shutdown).await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
let rollout_path = test.codex.rollout_path();
let rollout_text = read_rollout_text(&rollout_path).await?;
let env_texts = rollout_environment_texts(&rollout_text);
let new_cwd_text = new_cwd.path().display().to_string();
assert!(
env_texts.iter().any(|text| text.contains(&new_cwd_text)),
"expected environment update with new cwd in rollout"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn override_turn_context_records_collaboration_update() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let test = test_codex().build(&server).await?;
let collab_text = "override collaboration instructions";
let collaboration_mode = collab_mode_with_instructions(Some(collab_text));
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
sandbox_policy: None,
model: None,
effort: None,
summary: None,
collaboration_mode: Some(collaboration_mode),
personality: None,
})
.await?;
test.codex.submit(Op::Shutdown).await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::ShutdownComplete)).await;
let rollout_path = test.codex.rollout_path();
let rollout_text = read_rollout_text(&rollout_path).await?;
let developer_texts = rollout_developer_texts(&rollout_text);
let collab_text = collab_xml(collab_text);
let collab_count = developer_texts
.iter()
.filter(|text| text.as_str() == collab_text.as_str())
.count();
assert_eq!(collab_count, 1);
Ok(())
}