Avoid hang when tool's process spawns grandchild that shares stderr/stdout (#6575)

We've received many reports of codex hanging when calling certain tools.
[Here](https://github.com/openai/codex/issues/3204) is one example. This
is likely a major cause. The problem occurs when
`consume_truncated_output` waits for `stdout` and `stderr` to be closed
once the child process terminates. This normally works fine, but it
doesn't handle the case where the child has spawned grandchild processes
that inherits `stdout` and `stderr`.

The fix was originally written by @md-oai in [this
PR](https://github.com/openai/codex/pull/1852), which has gone stale.
I've copied the original fix (which looks sound to me) and added an
integration test to prevent future regressions.
This commit is contained in:
Eric Traut
2025-11-12 22:08:12 -06:00
committed by GitHub
Unverified
parent ad7eaa80f9
commit 73ed30d7e5
2 changed files with 146 additions and 2 deletions
+46 -2
View File
@@ -532,8 +532,52 @@ async fn consume_truncated_output(
}
};
let stdout = stdout_handle.await??;
let stderr = stderr_handle.await??;
// Wait for the stdout/stderr collection tasks but guard against them
// hanging forever. In the normal case, both pipes are closed once the child
// terminates so the tasks exit quickly. However, if the child process
// spawned grandchildren that inherited its stdout/stderr file descriptors
// those pipes may stay open after we `kill` the direct child on timeout.
// That would cause the `read_capped` tasks to block on `read()`
// indefinitely, effectively hanging the whole agent.
const IO_DRAIN_TIMEOUT_MS: u64 = 2_000; // 2 s should be plenty for local pipes
// We need mutable bindings so we can `abort()` them on timeout.
use tokio::task::JoinHandle;
async fn await_with_timeout(
handle: &mut JoinHandle<std::io::Result<StreamOutput<Vec<u8>>>>,
timeout: Duration,
) -> std::io::Result<StreamOutput<Vec<u8>>> {
match tokio::time::timeout(timeout, &mut *handle).await {
Ok(join_res) => match join_res {
Ok(io_res) => io_res,
Err(join_err) => Err(std::io::Error::other(join_err)),
},
Err(_elapsed) => {
// Timeout: abort the task to avoid hanging on open pipes.
handle.abort();
Ok(StreamOutput {
text: Vec::new(),
truncated_after_lines: None,
})
}
}
}
let mut stdout_handle = stdout_handle;
let mut stderr_handle = stderr_handle;
let stdout = await_with_timeout(
&mut stdout_handle,
Duration::from_millis(IO_DRAIN_TIMEOUT_MS),
)
.await?;
let stderr = await_with_timeout(
&mut stderr_handle,
Duration::from_millis(IO_DRAIN_TIMEOUT_MS),
)
.await?;
drop(agg_tx);