Clean vLLM process groups after parent exit

src/aituner/worker.py

@@ -401,27 +401,37 @@ def _wait_for_server_or_exit(
     raise HttpClientError(f"Timed out waiting for {base_url}{healthcheck_path}: {last_error}")
 
 
+def _process_group_exists(pgid: int) -> bool:
+    try:
+        os.killpg(pgid, 0)
+        return True
+    except ProcessLookupError:
+        return False
+
+
 def _terminate_process_tree(process: subprocess.Popen[str], *, timeout_s: float = 30.0) -> None:
-    if process.poll() is not None:
-        return
     try:
         pgid = os.getpgid(process.pid)
     except ProcessLookupError:
-        return
+        # Children can keep the session/process group alive after the vLLM API
+        # server exits.  In that case the group id is still the original pid
+        # because the process was launched with start_new_session=True.
+        pgid = process.pid
     try:
         os.killpg(pgid, signal.SIGTERM)
     except ProcessLookupError:
         return
     deadline = time.monotonic() + timeout_s
     while time.monotonic() < deadline:
-        if process.poll() is not None:
+        if not _process_group_exists(pgid):
             return
         time.sleep(0.1)
     try:
         os.killpg(pgid, signal.SIGKILL)
     except ProcessLookupError:
         return
-    process.wait(timeout=timeout_s)
+    if process.poll() is None:
+        process.wait(timeout=timeout_s)
 
 
 def run_trial(trial_spec_path: Path) -> dict[str, Any]: