[codex-rs] Improve linux sandbox timeouts (#662)

* Fixes flaking rust unit test
* Adds explicit sandbox exec timeout handling

codex-rs/core/src/exec.rs

@@ -1,4 +1,6 @@
 use std::io;
+#[cfg(target_family = "unix")]
+use std::os::unix::process::ExitStatusExt;
 use std::path::PathBuf;
 use std::process::ExitStatus;
 use std::process::Stdio;
@@ -18,17 +20,18 @@ use crate::error::Result;
 use crate::error::SandboxErr;
 use crate::protocol::SandboxPolicy;
 
-/// Maximum we send for each stream, which is either:
-/// - 10KiB OR
-/// - 256 lines
+// Maximum we send for each stream, which is either:
+// - 10KiB OR
+// - 256 lines
 const MAX_STREAM_OUTPUT: usize = 10 * 1024;
 const MAX_STREAM_OUTPUT_LINES: usize = 256;
 
 const DEFAULT_TIMEOUT_MS: u64 = 10_000;
 
-/// Hardcode this since it does not seem worth including the libc craate just
-/// for this.
+// Hardcode these since it does not seem worth including the libc crate just
+// for these.
 const SIGKILL_CODE: i32 = 9;
+const TIMEOUT_CODE: i32 = 64;
 
 const MACOS_SEATBELT_READONLY_POLICY: &str = include_str!("seatbelt_readonly_policy.sbpl");
 
@@ -113,10 +116,20 @@ pub async fn process_exec_tool_call(
     let duration = start.elapsed();
     match raw_output_result {
         Ok(raw_output) => {
-            let exit_code = raw_output.exit_status.code().unwrap_or(-1);
             let stdout = String::from_utf8_lossy(&raw_output.stdout).to_string();
             let stderr = String::from_utf8_lossy(&raw_output.stderr).to_string();
 
+            #[cfg(target_family = "unix")]
+            match raw_output.exit_status.signal() {
+                Some(TIMEOUT_CODE) => return Err(CodexErr::Sandbox(SandboxErr::Timeout)),
+                Some(signal) => {
+                    return Err(CodexErr::Sandbox(SandboxErr::Signal(signal)));
+                }
+                None => {}
+            }
+
+            let exit_code = raw_output.exit_status.code().unwrap_or(-1);
+
             // NOTE(ragona): This is much less restrictive than the previous check. If we exec
             // a command, and it returns anything other than success, we assume that it may have
             // been a sandboxing error and allow the user to retry. (The user of course may choose
@@ -244,7 +257,7 @@ pub async fn exec(
                     // timeout
                     child.start_kill()?;
                     // Debatable whether `child.wait().await` should be called here.
-                    synthetic_exit_status(128 + SIGKILL_CODE)
+                    synthetic_exit_status(128 + TIMEOUT_CODE)
                 }
             }
         }