Files
llmx/codex-rs/mcp-server/src/lib.rs
Michael Bolin d49d802b06 test: add integration test for MCP server (#1633)
This PR introduces a single integration test for `cargo mcp`, though it
also introduces a number of reusable components so that it should be
easier to introduce more integration tests going forward.

The new test is introduced in `codex-rs/mcp-server/tests/elicitation.rs`
and the reusable pieces are in `codex-rs/mcp-server/tests/common`.

The test itself verifies new functionality around elicitations
introduced in https://github.com/openai/codex/pull/1623 (and the fix
introduced in https://github.com/openai/codex/pull/1629) by doing the
following:

- starts a mock model provider with canned responses for
`/v1/chat/completions`
- starts the MCP server with a `config.toml` to use that model provider
(and `approval_policy = "untrusted"`)
- sends the `codex` tool call which causes the mock model provider to
request a shell call for `git init`
- the MCP server sends an elicitation to the client to approve the
request
- the client replies to the elicitation with `"approved"`
- the MCP server runs the command and re-samples the model, getting a
`"finish_reason": "stop"`
- in turn, the MCP server sends the final response to the original
`codex` tool call
- verifies that `git init` ran as expected

To test:

```
cargo test shell_command_approval_triggers_elicitation
```

In writing this test, I discovered that `ExecApprovalResponse` does not
conform to `ElicitResult`, so I added a TODO to fix that, since I think
that should be updated in a separate PR. As it stands, this PR does not
update any business logic, though it does make a number of members of
the `mcp-server` crate `pub` so they can be used in the test.

One additional learning from this PR is that
`std::process::Command::cargo_bin()` from the `assert_cmd` trait is only
available for `std::process::Command`, but we really want to use
`tokio::process::Command` so that everything is async and we can
leverage utilities like `tokio::time::timeout()`. The trick I came up
with was to use `cargo_bin()` to locate the program, and then to use
`std::process::Command::get_program()` when constructing the
`tokio::process::Command`.
2025-07-21 10:27:07 -07:00

123 lines
4.5 KiB
Rust
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
//! Prototype MCP server.
#![deny(clippy::print_stdout, clippy::print_stderr)]
use std::io::Result as IoResult;
use std::path::PathBuf;
use mcp_types::JSONRPCMessage;
use tokio::io::AsyncBufReadExt;
use tokio::io::AsyncWriteExt;
use tokio::io::BufReader;
use tokio::io::{self};
use tokio::sync::mpsc;
use tracing::debug;
use tracing::error;
use tracing::info;
mod codex_tool_config;
mod codex_tool_runner;
mod json_to_toml;
mod message_processor;
mod outgoing_message;
use crate::message_processor::MessageProcessor;
use crate::outgoing_message::OutgoingMessage;
use crate::outgoing_message::OutgoingMessageSender;
pub use crate::codex_tool_config::CodexToolCallParam;
pub use crate::codex_tool_runner::ExecApprovalElicitRequestParams;
pub use crate::codex_tool_runner::ExecApprovalResponse;
/// Size of the bounded channels used to communicate between tasks. The value
/// is a balance between throughput and memory usage 128 messages should be
/// plenty for an interactive CLI.
const CHANNEL_CAPACITY: usize = 128;
pub async fn run_main(codex_linux_sandbox_exe: Option<PathBuf>) -> IoResult<()> {
// Install a simple subscriber so `tracing` output is visible. Users can
// control the log level with `RUST_LOG`.
tracing_subscriber::fmt()
.with_writer(std::io::stderr)
.init();
// Set up channels.
let (incoming_tx, mut incoming_rx) = mpsc::channel::<JSONRPCMessage>(CHANNEL_CAPACITY);
let (outgoing_tx, mut outgoing_rx) = mpsc::channel::<OutgoingMessage>(CHANNEL_CAPACITY);
// Task: read from stdin, push to `incoming_tx`.
let stdin_reader_handle = tokio::spawn({
let incoming_tx = incoming_tx.clone();
async move {
let stdin = io::stdin();
let reader = BufReader::new(stdin);
let mut lines = reader.lines();
while let Some(line) = lines.next_line().await.unwrap_or_default() {
match serde_json::from_str::<JSONRPCMessage>(&line) {
Ok(msg) => {
if incoming_tx.send(msg).await.is_err() {
// Receiver gone nothing left to do.
break;
}
}
Err(e) => error!("Failed to deserialize JSONRPCMessage: {e}"),
}
}
debug!("stdin reader finished (EOF)");
}
});
// Task: process incoming messages.
let processor_handle = tokio::spawn({
let outgoing_message_sender = OutgoingMessageSender::new(outgoing_tx);
let mut processor = MessageProcessor::new(outgoing_message_sender, codex_linux_sandbox_exe);
async move {
while let Some(msg) = incoming_rx.recv().await {
match msg {
JSONRPCMessage::Request(r) => processor.process_request(r).await,
JSONRPCMessage::Response(r) => processor.process_response(r).await,
JSONRPCMessage::Notification(n) => processor.process_notification(n),
JSONRPCMessage::Error(e) => processor.process_error(e),
}
}
info!("processor task exited (channel closed)");
}
});
// Task: write outgoing messages to stdout.
let stdout_writer_handle = tokio::spawn(async move {
let mut stdout = io::stdout();
while let Some(outgoing_message) = outgoing_rx.recv().await {
let msg: JSONRPCMessage = outgoing_message.into();
match serde_json::to_string(&msg) {
Ok(json) => {
if let Err(e) = stdout.write_all(json.as_bytes()).await {
error!("Failed to write to stdout: {e}");
break;
}
if let Err(e) = stdout.write_all(b"\n").await {
error!("Failed to write newline to stdout: {e}");
break;
}
if let Err(e) = stdout.flush().await {
error!("Failed to flush stdout: {e}");
break;
}
}
Err(e) => error!("Failed to serialize JSONRPCMessage: {e}"),
}
}
info!("stdout writer exited (channel closed)");
});
// Wait for all tasks to finish. The typical exit path is the stdin reader
// hitting EOF which, once it drops `incoming_tx`, propagates shutdown to
// the processor and then to the stdout task.
let _ = tokio::join!(stdin_reader_handle, processor_handle, stdout_writer_handle);
Ok(())
}