fix: disable PR_SET_PDEATHSIG (kernel binds it to parent thread, not process)

PR_SET_PDEATHSIG is bound to the *thread* that forked the child, not to the
parent process (man 2 prctl: "the 'parent' in this case is considered to be
the thread that created this process").

rkllama_server runs Flask with threaded=True, so Process.start() for a worker
is executed from a short-lived request-handler thread. As soon as the request
finishes and its thread exits, the kernel delivers SIGTERM to the worker, the
inherited shutdown handler cascades into stop_all() / sys.exit(0), and the
worker dies after serving a single request. The next /api/embed hits the
dying worker, waits the 30s stop_worker timeout, and returns 500.

Turn _set_parent_death_signal() into a documented no-op. Orphan-worker
protection continues to work via _kill_orphaned_workers() at startup.

Fixes #117.

Co-Authored-By: Claude <noreply@anthropic.com>

Author: iiiokojiadbi

src/rkllama/api/worker.py

@@ -31,17 +31,12 @@
 
 
 def _set_parent_death_signal():
-    """On Linux, ask the kernel to SIGTERM us if our parent dies.
-
-    Safe no-op on other platforms.
+    """No-op: PR_SET_PDEATHSIG is bound to the forking *thread*, not the
+    process (see ``man 2 prctl``). Flask runs with ``threaded=True``, so
+    enabling it kills the worker as soon as its request-thread exits
+    (issue #117). Orphan cleanup is handled by ``_kill_orphaned_workers``.
     """
-    if sys.platform != "linux":
-        return
-    try:
-        libc = ctypes.CDLL("libc.so.6", use_errno=True)
-        libc.prctl(PR_SET_PDEATHSIG, signal.SIGTERM, 0, 0, 0)
-    except Exception as exc:
-        logger.warning("Could not set parent-death signal: %s", exc)
+    return
 
 
 def _kill_orphaned_workers():