Add a baseline test for resume initial messages (#5466)

This commit is contained in:
pakrym-oai
2025-10-21 11:45:01 -07:00
committed by GitHub
parent 26f314904a
commit 5cd8803998
3 changed files with 118 additions and 21 deletions

View File

@@ -6,7 +6,6 @@ use codex_core::CodexAuth;
use codex_core::CodexConversation;
use codex_core::ConversationManager;
use codex_core::ModelProviderInfo;
use codex_core::NewConversation;
use codex_core::built_in_model_providers;
use codex_core::config::Config;
use codex_core::protocol::SessionConfiguredEvent;
@@ -30,14 +29,59 @@ impl TestCodexBuilder {
}
pub async fn build(&mut self, server: &wiremock::MockServer) -> anyhow::Result<TestCodex> {
// Build config pointing to the mock server and spawn Codex.
let home = Arc::new(TempDir::new()?);
self.build_with_home(server, home, None).await
}
pub async fn resume(
&mut self,
server: &wiremock::MockServer,
home: Arc<TempDir>,
rollout_path: PathBuf,
) -> anyhow::Result<TestCodex> {
self.build_with_home(server, home, Some(rollout_path)).await
}
async fn build_with_home(
&mut self,
server: &wiremock::MockServer,
home: Arc<TempDir>,
resume_from: Option<PathBuf>,
) -> anyhow::Result<TestCodex> {
let (config, cwd) = self.prepare_config(server, &home).await?;
let conversation_manager = ConversationManager::with_auth(CodexAuth::from_api_key("dummy"));
let new_conversation = match resume_from {
Some(path) => {
let auth_manager = codex_core::AuthManager::from_auth_for_testing(
CodexAuth::from_api_key("dummy"),
);
conversation_manager
.resume_conversation_from_rollout(config, path, auth_manager)
.await?
}
None => conversation_manager.new_conversation(config).await?,
};
Ok(TestCodex {
home,
cwd,
codex: new_conversation.conversation,
session_configured: new_conversation.session_configured,
})
}
async fn prepare_config(
&mut self,
server: &wiremock::MockServer,
home: &TempDir,
) -> anyhow::Result<(Config, Arc<TempDir>)> {
let model_provider = ModelProviderInfo {
base_url: Some(format!("{}/v1", server.uri())),
..built_in_model_providers()["openai"].clone()
};
let home = TempDir::new()?;
let cwd = TempDir::new()?;
let mut config = load_default_config_for_test(&home);
let cwd = Arc::new(TempDir::new()?);
let mut config = load_default_config_for_test(home);
config.cwd = cwd.path().to_path_buf();
config.model_provider = model_provider;
config.codex_linux_sandbox_exe = Some(PathBuf::from(
@@ -48,29 +92,17 @@ impl TestCodexBuilder {
let mut mutators = vec![];
swap(&mut self.config_mutators, &mut mutators);
for mutator in mutators {
mutator(&mut config)
mutator(&mut config);
}
let conversation_manager = ConversationManager::with_auth(CodexAuth::from_api_key("dummy"));
let NewConversation {
conversation,
session_configured,
..
} = conversation_manager.new_conversation(config).await?;
Ok(TestCodex {
home,
cwd,
codex: conversation,
session_configured,
})
Ok((config, cwd))
}
}
pub struct TestCodex {
pub home: TempDir,
pub cwd: TempDir,
pub home: Arc<TempDir>,
pub cwd: Arc<TempDir>,
pub codex: Arc<CodexConversation>,
pub session_configured: SessionConfiguredEvent,
}

View File

@@ -20,6 +20,7 @@ mod model_tools;
mod otel;
mod prompt_caching;
mod read_file;
mod resume;
mod review;
mod rmcp_client;
mod rollout_list_find;

View File

@@ -0,0 +1,64 @@
use anyhow::Result;
use codex_core::protocol::EventMsg;
use codex_core::protocol::Op;
use codex_protocol::user_input::UserInput;
use core_test_support::responses::ev_assistant_message;
use core_test_support::responses::ev_completed;
use core_test_support::responses::ev_response_created;
use core_test_support::responses::mount_sse_once_match;
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::test_codex;
use core_test_support::wait_for_event;
use std::sync::Arc;
use wiremock::matchers::any;
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn resume_includes_initial_messages_from_rollout_events() -> Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let mut builder = test_codex();
let initial = builder.build(&server).await?;
let codex = Arc::clone(&initial.codex);
let home = initial.home.clone();
let rollout_path = initial.session_configured.rollout_path.clone();
let initial_sse = sse(vec![
ev_response_created("resp-initial"),
ev_assistant_message("msg-1", "Completed first turn"),
ev_completed("resp-initial"),
]);
mount_sse_once_match(&server, any(), initial_sse).await;
codex
.submit(Op::UserInput {
items: vec![UserInput::Text {
text: "Record some messages".into(),
}],
})
.await?;
wait_for_event(&codex, |event| matches!(event, EventMsg::TaskComplete(_))).await;
let resumed = builder.resume(&server, home, rollout_path).await?;
let initial_messages = resumed
.session_configured
.initial_messages
.expect("expected initial messages to be present for resumed session");
match initial_messages.as_slice() {
[
EventMsg::UserMessage(first_user),
EventMsg::TokenCount(_),
EventMsg::AgentMessage(assistant_message),
EventMsg::TokenCount(_),
] => {
assert_eq!(first_user.message, "Record some messages");
assert_eq!(assistant_message.message, "Completed first turn");
}
other => panic!("unexpected initial messages after resume: {other:#?}"),
}
Ok(())
}