From 5ce18bf472bc6905f7678452c3fe3667692b9957 Mon Sep 17 00:00:00 2001
From: "Aaron D. Lee" <himself@adlee.work>
Date: Sat, 4 Jul 2026 20:35:11 -0400
Subject: [PATCH] slice-5: readyz timeout covers send; fix test thread leak

Task 5 review fixes: the 250ms readiness bound now wraps the whole
Stats round trip (a wedged thread can stall the send, not just the
reply), and the readyz integration test tears down its MediaThread
like the sibling test does.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_012QndwfhjyTiZcUYp87dwW8
Signed-off-by: Aaron D. Lee <himself@adlee.work>
---
 crates/rutster/src/routes.rs            | 22 ++++++++++++++++------
 crates/rutster/tests/api_integration.rs |  5 ++++-
 2 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/crates/rutster/src/routes.rs b/crates/rutster/src/routes.rs
index d90bd6e..3f02131 100644
--- a/crates/rutster/src/routes.rs
+++ b/crates/rutster/src/routes.rs
@@ -17,7 +17,6 @@ use axum::{Json, Router};
 use serde::{Deserialize, Serialize};
 use uuid::Uuid;
 
-use crate::media_thread::MediaCmd;
 use crate::session_map::AppState;
 
 #[derive(Serialize)]
@@ -168,11 +167,22 @@ pub async fn healthz() -> Response {
 /// the zombie-node failure from the 2026-07-04 review).
 pub async fn readyz(State(state): State<AppState>) -> Response {
     let (reply, rx) = tokio::sync::oneshot::channel();
-    if state.cmd_tx.send(MediaCmd::Stats { reply }).await.is_err() {
-        return (StatusCode::SERVICE_UNAVAILABLE, "media thread unresponsive").into_response();
-    }
-    let stats = match tokio::time::timeout(std::time::Duration::from_millis(250), rx).await {
-        Ok(Ok(s)) => s,
+    // One timeout bounds the WHOLE round trip — send AND reply. A wedged
+    // media thread can stall the send (full command channel), not just
+    // the reply, and the probe's 250ms promise must hold in that case too.
+    let stats = match tokio::time::timeout(std::time::Duration::from_millis(250), async {
+        state
+            .cmd_tx
+            .send(crate::media_thread::MediaCmd::Stats { reply })
+            .await
+            .ok()?;
+        rx.await.ok()
+    })
+    .await
+    {
+        Ok(Some(s)) => s,
+        // Elapsed timeout, send failure (thread gone), or dropped reply —
+        // all mean the media thread cannot vouch for itself right now.
         _ => {
             return (StatusCode::SERVICE_UNAVAILABLE, "media thread unresponsive").into_response();
         }
diff --git a/crates/rutster/tests/api_integration.rs b/crates/rutster/tests/api_integration.rs
index af4f7b5..0c2cc9e 100644
--- a/crates/rutster/tests/api_integration.rs
+++ b/crates/rutster/tests/api_integration.rs
@@ -107,7 +107,7 @@ async fn get_root_serves_html() {
 #[tokio::test]
 async fn readyz_200_with_stats_json_when_thread_alive() {
     let state = rutster::session_map::AppState::default();
-    let (state, _thread) = state
+    let (state, media_thread) = state
         .spawn_media_thread(tokio::runtime::Handle::current())
         .expect("spawn");
     let app = rutster::routes::router(state);
@@ -127,4 +127,7 @@ async fn readyz_200_with_stats_json_when_thread_alive() {
     let v: serde_json::Value = serde_json::from_slice(&body).unwrap();
     assert_eq!(v["draining"], false);
     assert!(v["max_sessions"].as_u64().unwrap() > 0);
+    tokio::task::spawn_blocking(move || media_thread.shutdown())
+        .await
+        .unwrap();
 }