valknar/llmx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore: use anyhow::Result for all app-server integration tests (#5836)

Browse Source 
There's a lot of visual noise in app-server's integration tests due to
the number of `.expect("<some_msg>")` lines which are largely redundant
/ not very useful. Clean them up by using `anyhow::Result` + `?`
consistently.

Replaces the existing pattern of:
```
    let codex_home = TempDir::new().expect("create temp dir");
    create_config_toml(codex_home.path()).expect("write config.toml");

    let mut mcp = McpProcess::new(codex_home.path())
        .await
        .expect("spawn mcp process");
    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
        .await
        .expect("initialize timeout")
        .expect("initialize request");
```

With:
```
    let codex_home = TempDir::new()?;
    create_config_toml(codex_home.path())?;

    let mut mcp = McpProcess::new(codex_home.path()).await?;
    timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
```
This commit is contained in:
Owen Lin
2025-10-28 08:10:23 -07:00
committed by GitHub
parent be4bdfec93
commit 266419217e
13 changed files with 414 additions and 765 deletions
Download Patch File Download Diff File Expand all files Collapse all files

254
codex-rs/app-server/tests/suite/codex_message_processor_flow.rs
View File

@@ -1,5 +1,4 @@
use std::path::Path;
use anyhow::Result;
use app_test_support::McpProcess;
use app_test_support::create_final_assistant_message_sse_response;
use app_test_support::create_mock_chat_completions_server;
@@ -32,26 +31,27 @@ use codex_protocol::protocol::Event;
use codex_protocol::protocol::EventMsg;
use pretty_assertions::assert_eq;
use std::env;
use std::path::Path;
use tempfile::TempDir;
use tokio::time::timeout;
const DEFAULT_READ_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(10);
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn test_codex_jsonrpc_conversation_flow() {
async fn test_codex_jsonrpc_conversation_flow() -> Result<()> {
if 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;
return Ok(());
}
let tmp = TempDir::new().expect("tmp dir");
let tmp = TempDir::new()?;
// Temporary Codex home with config pointing at the mock server.
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home).expect("create codex home dir");
std::fs::create_dir(&codex_home)?;
let working_directory = tmp.path().join("workdir");
std::fs::create_dir(&working_directory).expect("create working directory");
std::fs::create_dir(&working_directory)?;
// Create a mock model server that immediately ends each turn.
// Two turns are expected: initial session configure + one user message.
@@ -61,20 +61,15 @@ async fn test_codex_jsonrpc_conversation_flow() {
Some(&working_directory),
Some(5000),
"call1234",
)
.expect("create shell sse response"),
create_final_assistant_message_sse_response("Enjoy your new git repo!")
.expect("create final assistant message"),
)?,
create_final_assistant_message_sse_response("Enjoy your new git repo!")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri()).expect("write config");
create_config_toml(&codex_home, &server.uri())?;
// Start MCP server and initialize.
let mut mcp = McpProcess::new(&codex_home).await.expect("spawn mcp");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init error");
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// 1) newConversation
let new_conv_id = mcp
@@ -82,17 +77,13 @@ async fn test_codex_jsonrpc_conversation_flow() {
cwd: Some(working_directory.to_string_lossy().into_owned()),
..Default::default()
})
.await
.expect("send newConversation");
.await?;
let new_conv_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
)
.await
.expect("newConversation timeout")
.expect("newConversation resp");
let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)
.expect("deserialize newConversation response");
.await??;
let new_conv_resp = to_response::<NewConversationResponse>(new_conv_resp)?;
let NewConversationResponse {
conversation_id,
model,
@@ -107,18 +98,14 @@ async fn test_codex_jsonrpc_conversation_flow() {
conversation_id,
experimental_raw_events: false,
})
.await
.expect("send addConversationListener");
.await?;
let add_listener_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
)
.await
.expect("addConversationListener timeout")
.expect("addConversationListener resp");
.await??;
let AddConversationSubscriptionResponse { subscription_id } =
to_response::<AddConversationSubscriptionResponse>(add_listener_resp)
.expect("deserialize addConversationListener response");
to_response::<AddConversationSubscriptionResponse>(add_listener_resp)?;
// 3) sendUserMessage (should trigger notifications; we only validate an OK response)
let send_user_id = mcp
@@ -128,17 +115,13 @@ async fn test_codex_jsonrpc_conversation_flow() {
text: "text".to_string(),
}],
})
.await
.expect("send sendUserMessage");
.await?;
let send_user_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
)
.await
.expect("sendUserMessage timeout")
.expect("sendUserMessage resp");
let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)
.expect("deserialize sendUserMessage response");
.await??;
let SendUserMessageResponse {} = to_response::<SendUserMessageResponse>(send_user_resp)?;
// Verify the task_finished notification is received.
// Note this also ensures that the final request to the server was made.
@@ -146,9 +129,7 @@ async fn test_codex_jsonrpc_conversation_flow() {
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_finished_notification timeout")
.expect("task_finished_notification resp");
.await??;
let serde_json::Value::Object(map) = task_finished_notification
.params
.expect("notification should have params")
@@ -166,33 +147,31 @@ async fn test_codex_jsonrpc_conversation_flow() {
.send_remove_conversation_listener_request(RemoveConversationListenerParams {
subscription_id,
})
.await
.expect("send removeConversationListener");
.await?;
let remove_listener_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(remove_listener_id)),
)
.await
.expect("removeConversationListener timeout")
.expect("removeConversationListener resp");
let RemoveConversationSubscriptionResponse {} =
to_response(remove_listener_resp).expect("deserialize removeConversationListener response");
.await??;
let RemoveConversationSubscriptionResponse {} = to_response(remove_listener_resp)?;
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn test_send_user_turn_changes_approval_policy_behavior() {
async fn test_send_user_turn_changes_approval_policy_behavior() -> Result<()> {
if 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;
return Ok(());
}
let tmp = TempDir::new().expect("tmp dir");
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home).expect("create codex home dir");
std::fs::create_dir(&codex_home)?;
let working_directory = tmp.path().join("workdir");
std::fs::create_dir(&working_directory).expect("create working directory");
std::fs::create_dir(&working_directory)?;
// Mock server will request a python shell call for the first and second turn, then finish.
let responses = vec![
@@ -205,10 +184,8 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
Some(&working_directory),
Some(5000),
"call1",
)
.expect("create first shell sse response"),
create_final_assistant_message_sse_response("done 1")
.expect("create final assistant message 1"),
)?,
create_final_assistant_message_sse_response("done 1")?,
create_shell_sse_response(
vec![
"python3".to_string(),
@@ -218,20 +195,15 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
Some(&working_directory),
Some(5000),
"call2",
)
.expect("create second shell sse response"),
create_final_assistant_message_sse_response("done 2")
.expect("create final assistant message 2"),
)?,
create_final_assistant_message_sse_response("done 2")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri()).expect("write config");
create_config_toml(&codex_home, &server.uri())?;
// Start MCP server and initialize.
let mut mcp = McpProcess::new(&codex_home).await.expect("spawn mcp");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init error");
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
// 1) Start conversation with approval_policy=untrusted
let new_conv_id = mcp
@@ -239,19 +211,15 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
cwd: Some(working_directory.to_string_lossy().into_owned()),
..Default::default()
})
.await
.expect("send newConversation");
.await?;
let new_conv_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
)
.await
.expect("newConversation timeout")
.expect("newConversation resp");
.await??;
let NewConversationResponse {
conversation_id, ..
} = to_response::<NewConversationResponse>(new_conv_resp)
.expect("deserialize newConversation response");
} = to_response::<NewConversationResponse>(new_conv_resp)?;
// 2) addConversationListener
let add_listener_id = mcp
@@ -259,19 +227,14 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
conversation_id,
experimental_raw_events: false,
})
.await
.expect("send addConversationListener");
let _: AddConversationSubscriptionResponse =
to_response::<AddConversationSubscriptionResponse>(
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
)
.await
.expect("addConversationListener timeout")
.expect("addConversationListener resp"),
.await?;
let _: AddConversationSubscriptionResponse = to_response::<AddConversationSubscriptionResponse>(
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
)
.expect("deserialize addConversationListener response");
.await??,
)?;
// 3) sendUserMessage triggers a shell call; approval policy is Untrusted so we should get an elicitation
let send_user_id = mcp
@@ -281,27 +244,21 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
text: "run python".to_string(),
}],
})
.await
.expect("send sendUserMessage");
.await?;
let _send_user_resp: SendUserMessageResponse = to_response::<SendUserMessageResponse>(
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(send_user_id)),
)
.await
.expect("sendUserMessage timeout")
.expect("sendUserMessage resp"),
)
.expect("deserialize sendUserMessage response");
.await??,
)?;
// Expect an ExecCommandApproval request (elicitation)
let request = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_request_message(),
)
.await
.expect("waiting for exec approval request timeout")
.expect("exec approval request");
.await??;
let ServerRequest::ExecCommandApproval { request_id, params } = request else {
panic!("expected ExecCommandApproval request, got: {request:?}");
};
@@ -330,17 +287,14 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
request_id,
serde_json::json!({ "decision": codex_core::protocol::ReviewDecision::Approved }),
)
.await
.expect("send approval response");
.await?;
// Wait for first TaskComplete
let _ = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 1 timeout")
.expect("task_complete 1 notification");
.await??;
// 4) sendUserTurn with approval_policy=never should run without elicitation
let send_turn_id = mcp
@@ -356,19 +310,15 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
.expect("send sendUserTurn");
.await?;
// Acknowledge sendUserTurn
let _send_turn_resp: SendUserTurnResponse = to_response::<SendUserTurnResponse>(
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(send_turn_id)),
)
.await
.expect("sendUserTurn timeout")
.expect("sendUserTurn resp"),
)
.expect("deserialize sendUserTurn response");
.await??,
)?;
// Ensure we do NOT receive an ExecCommandApproval request before the task completes.
// If any Request is seen while waiting for task_complete, the helper will error and the test fails.
@@ -376,31 +326,31 @@ async fn test_send_user_turn_changes_approval_policy_behavior() {
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 2 timeout")
.expect("task_complete 2 notification");
.await??;
Ok(())
}
// Helper: minimal config.toml pointing at mock provider.
#[tokio::test(flavor = "multi_thread", worker_threads = 4)]
async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() -> Result<()> {
if 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;
return Ok(());
}
let tmp = TempDir::new().expect("tmp dir");
let tmp = TempDir::new()?;
let codex_home = tmp.path().join("codex_home");
std::fs::create_dir(&codex_home).expect("create codex home dir");
std::fs::create_dir(&codex_home)?;
let workspace_root = tmp.path().join("workspace");
std::fs::create_dir(&workspace_root).expect("create workspace root");
std::fs::create_dir(&workspace_root)?;
let first_cwd = workspace_root.join("turn1");
let second_cwd = workspace_root.join("turn2");
std::fs::create_dir(&first_cwd).expect("create first cwd");
std::fs::create_dir(&second_cwd).expect("create second cwd");
std::fs::create_dir(&first_cwd)?;
std::fs::create_dir(&second_cwd)?;
let responses = vec![
create_shell_sse_response(
@@ -412,10 +362,8 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
None,
Some(5000),
"call-first",
)
.expect("create first shell response"),
create_final_assistant_message_sse_response("done first")
.expect("create first final assistant message"),
)?,
create_final_assistant_message_sse_response("done first")?,
create_shell_sse_response(
vec![
"bash".to_string(),
@@ -425,21 +373,14 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
None,
Some(5000),
"call-second",
)
.expect("create second shell response"),
create_final_assistant_message_sse_response("done second")
.expect("create second final assistant message"),
)?,
create_final_assistant_message_sse_response("done second")?,
];
let server = create_mock_chat_completions_server(responses).await;
create_config_toml(&codex_home, &server.uri()).expect("write config");
create_config_toml(&codex_home, &server.uri())?;
let mut mcp = McpProcess::new(&codex_home)
.await
.expect("spawn mcp process");
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize())
.await
.expect("init timeout")
.expect("init failed");
let mut mcp = McpProcess::new(&codex_home).await?;
timeout(DEFAULT_READ_TIMEOUT, mcp.initialize()).await??;
let new_conv_id = mcp
.send_new_conversation_request(NewConversationParams {
@@ -448,36 +389,29 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
sandbox: Some(SandboxMode::WorkspaceWrite),
..Default::default()
})
.await
.expect("send newConversation");
.await?;
let new_conv_resp: JSONRPCResponse = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(new_conv_id)),
)
.await
.expect("newConversation timeout")
.expect("newConversation resp");
.await??;
let NewConversationResponse {
conversation_id,
model,
..
} = to_response::<NewConversationResponse>(new_conv_resp)
.expect("deserialize newConversation response");
} = to_response::<NewConversationResponse>(new_conv_resp)?;
let add_listener_id = mcp
.send_add_conversation_listener_request(AddConversationListenerParams {
conversation_id,
experimental_raw_events: false,
})
.await
.expect("send addConversationListener");
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(add_listener_id)),
)
.await
.expect("addConversationListener timeout")
.expect("addConversationListener resp");
.await??;
let first_turn_id = mcp
.send_send_user_turn_request(SendUserTurnParams {
@@ -497,22 +431,17 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
.expect("send first sendUserTurn");
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(first_turn_id)),
)
.await
.expect("sendUserTurn 1 timeout")
.expect("sendUserTurn 1 resp");
.await??;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 1 timeout")
.expect("task_complete 1 notification");
.await??;
let second_turn_id = mcp
.send_send_user_turn_request(SendUserTurnParams {
@@ -527,23 +456,18 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
effort: Some(ReasoningEffort::Medium),
summary: ReasoningSummary::Auto,
})
.await
.expect("send second sendUserTurn");
.await?;
timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_response_message(RequestId::Integer(second_turn_id)),
)
.await
.expect("sendUserTurn 2 timeout")
.expect("sendUserTurn 2 resp");
.await??;
let exec_begin_notification = timeout(
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/exec_command_begin"),
)
.await
.expect("exec_command_begin timeout")
.expect("exec_command_begin notification");
.await??;
let params = exec_begin_notification
.params
.clone()
@@ -571,9 +495,9 @@ async fn test_send_user_turn_updates_sandbox_and_cwd_between_turns() {
DEFAULT_READ_TIMEOUT,
mcp.read_stream_until_notification_message("codex/event/task_complete"),
)
.await
.expect("task_complete 2 timeout")
.expect("task_complete 2 notification");
.await??;
Ok(())
}
fn create_config_toml(codex_home: &Path, server_uri: &str) -> std::io::Result<()> {