fix(process): extend parent-death backstop to C++ and Python backends

The Go parent-death watcher (pkg/grpc/parentwatch.go, commit 772b435d5)
only protects backends that route through pkg/grpc. C++ and Python
backends don't, so the originally-reported case — the llama.cpp gRPC
worker surviving a non-graceful LocalAI death — was still uncovered.

Extend the same best-effort backstop to both languages, reusing the
exact mechanism and semantics:

- capture getppid() at startup, skip if already orphaned (<=1)
- a background thread polls getppid() and self-exits on reparenting
  (getppid() != orig || == 1), portable across Linux/macOS, no-op on
  Windows
- same env vars: LOCALAI_BACKEND_PARENT_WATCH (default on; falsy
  false/0/no/off disable) and LOCALAI_BACKEND_PARENT_WATCH_INTERVAL
  (default 2s; accepts Go-style durations like 500ms/2s/1m)

C++: implemented in backend/cpp/llama-cpp (the reported, most-used C++
backend) as a dependency-free header parent_watch.h, wired into
grpc-server.cpp's main() and copied at build time via prepare.sh. C++
backends have no shared server scaffolding, so other C++ backends
(ds4, ik-llama-cpp, privacy-filter, ...) are not yet covered and would
each need the same one-line include+call as follow-ups.

Python: implemented once in the shared common/parent_watch.py and armed
from common/grpc_auth.py's get_auth_interceptors() — the single helper
every one of the 35 Python backends invokes while building its gRPC
server — so all Python backends (and future ones) are covered with no
per-backend edits and no duplicated implementation.

Tests (real process-tree reparent detection, mirroring the Go test):
- backend/cpp/llama-cpp/parent_watch_test.cpp (via run-unit-tests.sh)
- backend/python/common/parent_watch_test.py (python -m unittest)

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

backend/cpp/llama-cpp/CMakeLists.txt

@@ -101,4 +101,13 @@ if(LLAMA_GRPC_BUILD_TESTS)
     target_link_libraries(message_content_test PRIVATE ${_LLAMA_COMMON_TARGET})
     target_compile_features(message_content_test PRIVATE cxx_std_17)
     add_test(NAME message_content_test COMMAND message_content_test)
+
+    # Parent-death watcher test (parent_watch.h) — standard library only, but
+    # needs a threading runtime for std::thread.
+    find_package(Threads REQUIRED)
+    add_executable(parent_watch_test parent_watch_test.cpp parent_watch.h)
+    target_include_directories(parent_watch_test PRIVATE ${CMAKE_CURRENT_SOURCE_DIR})
+    target_link_libraries(parent_watch_test PRIVATE Threads::Threads)
+    target_compile_features(parent_watch_test PRIVATE cxx_std_17)
+    add_test(NAME parent_watch_test COMMAND parent_watch_test)
 endif()

backend/cpp/llama-cpp/grpc-server.cpp

@@ -75,6 +75,8 @@
 #include <windows.h>
 #endif
 
+#include "parent_watch.h" // best-effort parent-death backstop (see header)
+
 
 using grpc::Server;
 using grpc::ServerBuilder;
@@ -3442,6 +3444,10 @@ int main(int argc, char** argv) {
     }
   }
 
+    // Best-effort backstop: self-terminate if the LocalAI process that spawned
+    // us dies without cleaning us up (see parent_watch.h).
+    llama_grpc::start_parent_death_watcher();
+
     server_context ctx_server;
     BackendServiceImpl service(ctx_server);
 

backend/cpp/llama-cpp/parent_watch.h

@@ -0,0 +1,179 @@
+// Parent-death watcher (best-effort backstop) for the llama.cpp gRPC backend.
+//
+// LocalAI spawns this backend as a child process and, on a clean shutdown,
+// tears it down itself (SIGTERM -> grace -> SIGKILL). That graceful path only
+// runs when LocalAI receives a catchable signal and lives long enough to run
+// its handlers. If LocalAI is SIGKILLed (e.g. a supervising process's grace
+// period elapses first), that teardown never runs and this backend would be
+// reparented to init and linger, holding VRAM and its listen port.
+//
+// The watcher here is a best-effort backstop for exactly that case: it does
+// NOT replace the graceful teardown, it only covers the "parent vanished
+// without cleaning up" path. It detects reparenting: when the process that
+// spawned this backend dies, the kernel reparents us to the nearest sub-reaper
+// or to init (PID 1), so getppid() stops matching the value captured at
+// startup. This getppid() approach is portable across Linux/macOS (unlike the
+// Linux-only PR_SET_PDEATHSIG), which is why it is used here, mirroring the Go
+// backends' pkg/grpc/parentwatch.go. It is disabled on Windows, which has no
+// equivalent orphan-reparenting semantics.
+//
+// This header is intentionally dependency-free (C++ standard library only) so
+// it can be exercised by a standalone unit test (parent_watch_test.cpp) without
+// building the full llama.cpp + gRPC backend.
+#ifndef LLAMA_GRPC_PARENT_WATCH_H
+#define LLAMA_GRPC_PARENT_WATCH_H
+
+#include <algorithm>
+#include <cctype>
+#include <chrono>
+#include <cstdio>
+#include <cstdlib>
+#include <functional>
+#include <string>
+#include <thread>
+
+#if !defined(_WIN32)
+#include <unistd.h> // getppid(2), _exit(2)
+#endif
+
+namespace llama_grpc {
+
+// Env var names are shared verbatim with the Go and Python backends for
+// consistency across languages.
+inline const char *kEnvParentWatch()         { return "LOCALAI_BACKEND_PARENT_WATCH"; }
+inline const char *kEnvParentWatchInterval() { return "LOCALAI_BACKEND_PARENT_WATCH_INTERVAL"; }
+
+// Default poll interval in milliseconds. Matches the Go side's 2 * time.Second.
+inline long parent_watch_default_interval_ms() { return 2000; }
+
+namespace detail {
+inline std::string trim_lower(const std::string &in, bool lower) {
+    size_t a = in.find_first_not_of(" \t\r\n");
+    size_t b = in.find_last_not_of(" \t\r\n");
+    if (a == std::string::npos) {
+        return "";
+    }
+    std::string s = in.substr(a, b - a + 1);
+    if (lower) {
+        std::transform(s.begin(), s.end(), s.begin(),
+                       [](unsigned char c) { return std::tolower(c); });
+    }
+    return s;
+}
+} // namespace detail
+
+// parent_watch_enabled reports whether the watcher should run. Enabled by
+// default; a falsey value ("false"/"0"/"no"/"off", case-insensitive) disables
+// it, matching the Go implementation's exact semantics.
+inline bool parent_watch_enabled() {
+#if defined(_WIN32)
+    return false;
+#else
+    const char *v = std::getenv(kEnvParentWatch());
+    if (v == nullptr || v[0] == '\0') {
+        return true;
+    }
+    const std::string s = detail::trim_lower(v, true);
+    return !(s == "false" || s == "0" || s == "no" || s == "off");
+#endif
+}
+
+// parent_watch_interval_ms returns the poll interval in milliseconds. Accepts
+// Go-style duration strings ("500ms", "2s", "1m") for cross-language parity, or
+// a bare number interpreted as seconds. Defaults to
+// parent_watch_default_interval_ms().
+inline long parent_watch_interval_ms() {
+    const long def = parent_watch_default_interval_ms();
+    const char *v = std::getenv(kEnvParentWatchInterval());
+    if (v == nullptr || v[0] == '\0') {
+        return def;
+    }
+    const std::string s = detail::trim_lower(v, false);
+    if (s.empty()) {
+        return def;
+    }
+    size_t i = 0;
+    while (i < s.size() && (std::isdigit((unsigned char)s[i]) || s[i] == '.')) {
+        i++;
+    }
+    if (i == 0) {
+        return def;
+    }
+    double num = 0.0;
+    try {
+        num = std::stod(s.substr(0, i));
+    } catch (...) {
+        return def;
+    }
+    const std::string unit = s.substr(i);
+    long ms;
+    if (unit == "ms") {
+        ms = (long)num;
+    } else if (unit == "s" || unit.empty()) {
+        ms = (long)(num * 1000.0);
+    } else if (unit == "m") {
+        ms = (long)(num * 60000.0);
+    } else {
+        return def; // unrecognized unit
+    }
+    return ms > 0 ? ms : def;
+}
+
+#if !defined(_WIN32)
+// parent_died reports whether this process has been reparented away from the
+// parent it had when the watcher started. Reparenting is the standard POSIX
+// signal that the original parent (here, the LocalAI process that spawned this
+// backend) has exited: the orphan is handed to the nearest sub-reaper or to
+// init (PID 1), so getppid() no longer matches the value captured at startup.
+inline bool parent_died(pid_t orig_ppid) {
+    const pid_t ppid = getppid();
+    return ppid != orig_ppid || ppid == 1;
+}
+
+// watch_parent_death polls until parent_died reports the original parent is
+// gone, then invokes on_death. It blocks, so run it on its own thread.
+inline void watch_parent_death(pid_t orig_ppid, long interval_ms,
+                               const std::function<void()> &on_death) {
+    for (;;) {
+        std::this_thread::sleep_for(std::chrono::milliseconds(interval_ms));
+        if (parent_died(orig_ppid)) {
+            on_death();
+            return;
+        }
+    }
+}
+#endif
+
+// start_parent_death_watcher installs the best-effort safety net described in
+// the file header on the calling backend process. It is a no-op when disabled,
+// on Windows, or when the process is already orphaned at startup
+// (getppid() <= 1). This is a backstop alongside — never a replacement for —
+// LocalAI's graceful teardown.
+inline void start_parent_death_watcher() {
+#if !defined(_WIN32)
+    if (!parent_watch_enabled()) {
+        return;
+    }
+    const pid_t orig_ppid = getppid();
+    // A parent of 1 (or less) at startup means we were already orphaned (or
+    // launched directly under init) — there is no original parent to watch for.
+    if (orig_ppid <= 1) {
+        return;
+    }
+    const long interval_ms = parent_watch_interval_ms();
+    std::thread([orig_ppid, interval_ms]() {
+        watch_parent_death(orig_ppid, interval_ms, [orig_ppid]() {
+            fprintf(stderr,
+                    "backend parent process (pid %d) exited without stopping "
+                    "this backend; self-terminating to avoid orphaning\n",
+                    (int)orig_ppid);
+            fflush(stderr);
+            _exit(1);
+        });
+    }).detach();
+#endif
+}
+
+} // namespace llama_grpc
+
+#endif // LLAMA_GRPC_PARENT_WATCH_H

backend/cpp/llama-cpp/parent_watch_test.cpp

@@ -0,0 +1,197 @@
+// Unit tests for the parent-death watcher (parent_watch.h).
+//
+// Build & run standalone (C++ standard library only, no nlohmann/json needed):
+//   g++ -std=c++17 -pthread parent_watch_test.cpp -o t && ./t
+//
+// The core test (TestDetectsReparent) builds a genuine two-level process tree
+// (test -> middle -> grandchild), lets the middle process die, and asserts the
+// grandchild's watch_parent_death detects the reparenting and self-terminates —
+// mirroring the Go test in pkg/grpc/parentwatch_test.go, but with fork(2).
+//
+// On Windows this file compiles to a no-op success (the watcher is unsupported
+// there), matching parent_watch.h's platform gating.
+
+#include <cstdio>
+#include <cstdlib>
+#include <string>
+
+#include "parent_watch.h"
+
+static int failures = 0;
+
+static void check(bool ok, const std::string &name) {
+    if (!ok) {
+        failures++;
+        fprintf(stderr, "FAIL: %s\n", name.c_str());
+    } else {
+        fprintf(stderr, "ok:   %s\n", name.c_str());
+    }
+}
+
+// Env-parsing tests are platform-independent and always run.
+static void test_env_parsing() {
+    using namespace llama_grpc;
+
+    // Interval: default when unset.
+    unsetenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL");
+    check(parent_watch_interval_ms() == 2000, "interval default 2000ms");
+
+    setenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL", "500ms", 1);
+    check(parent_watch_interval_ms() == 500, "interval 500ms");
+
+    setenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL", "2s", 1);
+    check(parent_watch_interval_ms() == 2000, "interval 2s");
+
+    setenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL", "1m", 1);
+    check(parent_watch_interval_ms() == 60000, "interval 1m");
+
+    setenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL", "3", 1); // bare number -> seconds
+    check(parent_watch_interval_ms() == 3000, "interval bare 3 -> 3000ms");
+
+    setenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL", "garbage", 1);
+    check(parent_watch_interval_ms() == 2000, "interval garbage -> default");
+    unsetenv("LOCALAI_BACKEND_PARENT_WATCH_INTERVAL");
+
+#if !defined(_WIN32)
+    // Enabled semantics (POSIX only; always false on Windows).
+    unsetenv("LOCALAI_BACKEND_PARENT_WATCH");
+    check(parent_watch_enabled(), "enabled by default");
+
+    for (const char *falsey : {"false", "0", "no", "off", "OFF", " False "}) {
+        setenv("LOCALAI_BACKEND_PARENT_WATCH", falsey, 1);
+        check(!parent_watch_enabled(), std::string("disabled by '") + falsey + "'");
+    }
+    setenv("LOCALAI_BACKEND_PARENT_WATCH", "true", 1);
+    check(parent_watch_enabled(), "enabled by 'true'");
+    setenv("LOCALAI_BACKEND_PARENT_WATCH", "1", 1);
+    check(parent_watch_enabled(), "enabled by '1'");
+    unsetenv("LOCALAI_BACKEND_PARENT_WATCH");
+#endif
+}
+
+#if !defined(_WIN32)
+
+#include <atomic>
+#include <ctime>
+#include <sys/stat.h>
+#include <sys/wait.h>
+#include <unistd.h>
+
+static bool file_exists(const std::string &p) {
+    struct stat st;
+    return ::stat(p.c_str(), &st) == 0;
+}
+
+static bool wait_for_file(const std::string &p, int timeout_ms) {
+    int waited = 0;
+    while (waited < timeout_ms) {
+        if (file_exists(p)) {
+            return true;
+        }
+        usleep(20 * 1000);
+        waited += 20;
+    }
+    return false;
+}
+
+static void write_file(const std::string &p, const std::string &content) {
+    FILE *f = fopen(p.c_str(), "w");
+    if (f) {
+        fwrite(content.data(), 1, content.size(), f);
+        fclose(f);
+    }
+}
+
+// Builds test -> middle -> grandchild via fork(2). The grandchild arms the REAL
+// watch_parent_death against middle; middle exits, orphaning the grandchild;
+// the watcher must detect the reparenting and self-terminate.
+static void test_detects_reparent() {
+    char tmpl[] = "/tmp/parentwatch_test_XXXXXX";
+    char *dir = mkdtemp(tmpl);
+    if (dir == nullptr) {
+        check(false, "mkdtemp");
+        return;
+    }
+    const std::string ready_file = std::string(dir) + "/ready";
+    const std::string exited_file = std::string(dir) + "/exited";
+
+    pid_t middle = fork();
+    if (middle < 0) {
+        check(false, "fork middle");
+        return;
+    }
+
+    if (middle == 0) {
+        // ---- middle process ----
+        pid_t grandchild = fork();
+        if (grandchild < 0) {
+            _exit(4);
+        }
+        if (grandchild == 0) {
+            // ---- grandchild process ----
+            pid_t orig_ppid = getppid(); // == middle
+            std::thread([&]() {
+                llama_grpc::watch_parent_death(orig_ppid, 50 /*ms*/, [&]() {
+                    write_file(exited_file, "1");
+                    _exit(7);
+                });
+            }).detach();
+
+            // Safety valve: never linger if something goes wrong.
+            std::thread([]() {
+                usleep(30 * 1000 * 1000);
+                _exit(2);
+            }).detach();
+
+            // Signal readiness only after the watcher captured orig_ppid.
+            write_file(ready_file, std::to_string(getpid()));
+            for (;;) {
+                pause();
+            }
+        }
+        // middle: wait until grandchild is ready, then exit to orphan it.
+        if (!wait_for_file(ready_file, 10000)) {
+            _exit(5);
+        }
+        _exit(0);
+    }
+
+    // ---- test (top) process ----
+    int status = 0;
+    waitpid(middle, &status, 0); // reap middle only; grandchild is orphaned
+
+    check(file_exists(ready_file), "grandchild signaled readiness");
+
+    bool detected = wait_for_file(exited_file, 10000);
+    check(detected, "watcher detected parent death and self-terminated");
+
+    // Best-effort cleanup: kill the grandchild if it somehow survived.
+    if (file_exists(ready_file)) {
+        FILE *f = fopen(ready_file.c_str(), "r");
+        if (f) {
+            int pid = 0;
+            if (fscanf(f, "%d", &pid) == 1 && pid > 1) {
+                kill(pid, SIGKILL);
+            }
+            fclose(f);
+        }
+    }
+    unlink(ready_file.c_str());
+    unlink(exited_file.c_str());
+    rmdir(dir);
+}
+
+#endif // !_WIN32
+
+int main() {
+    test_env_parsing();
+#if !defined(_WIN32)
+    test_detects_reparent();
+#endif
+    if (failures == 0) {
+        fprintf(stderr, "\nAll parent_watch tests passed.\n");
+        return 0;
+    }
+    fprintf(stderr, "\n%d parent_watch test(s) failed.\n", failures);
+    return 1;
+}

backend/cpp/llama-cpp/prepare.sh

@@ -22,6 +22,10 @@ cp -r grpc-server.cpp llama.cpp/tools/grpc-server/
 # unit test (compiled only when -DLLAMA_GRPC_BUILD_TESTS=ON).
 cp -r message_content.h llama.cpp/tools/grpc-server/
 cp -r message_content_test.cpp llama.cpp/tools/grpc-server/
+# Parent-death watcher (included by grpc-server.cpp) and its standalone unit
+# test (run via backend/cpp/run-unit-tests.sh; also buildable under ctest).
+cp -r parent_watch.h llama.cpp/tools/grpc-server/
+cp -r parent_watch_test.cpp llama.cpp/tools/grpc-server/
 cp -rfv llama.cpp/vendor/nlohmann/json.hpp llama.cpp/tools/grpc-server/
 cp -rfv llama.cpp/vendor/cpp-httplib/httplib.h llama.cpp/tools/grpc-server/
 

backend/cpp/run-unit-tests.sh

@@ -54,7 +54,7 @@ for test_src in "${tests[@]}"; do
     name="$(basename "$test_src" .cpp)"
     bin="$(mktemp -d)/$name"
     echo "==> $test_src"
-    if ! "$CXX" -std=c++17 -Wall -Wextra \
+    if ! "$CXX" -std=c++17 -Wall -Wextra -pthread \
         -I"$JSON_INC" -I"$(dirname "$test_src")" \
         "$test_src" -o "$bin"; then
         echo "COMPILE FAILED: $test_src" >&2

backend/python/common/grpc_auth.py

@@ -11,6 +11,8 @@ import os
 
 import grpc
 
+from parent_watch import start_parent_death_watcher
+
 
 class _AbortHandler(grpc.RpcMethodHandler):
     """A method handler that immediately aborts with UNAUTHENTICATED."""
@@ -70,6 +72,13 @@ def get_auth_interceptors(*, aio: bool = False):
 
     Returns an empty list when LOCALAI_GRPC_AUTH_TOKEN is not set.
     """
+    # Arm the best-effort parent-death backstop here: this is the single helper
+    # every LocalAI Python backend invokes exactly once while building its gRPC
+    # server (mirroring how the Go watcher arms in pkg/grpc's shared serve path).
+    # start_parent_death_watcher() is idempotent and a no-op when disabled or on
+    # unsupported platforms — see parent_watch.py.
+    start_parent_death_watcher()
+
     token = os.environ.get("LOCALAI_GRPC_AUTH_TOKEN", "")
     if not token:
         return []

backend/python/common/parent_watch.py

@@ -0,0 +1,149 @@
+"""Parent-death watcher (best-effort backstop) for LocalAI Python backends.
+
+LocalAI spawns each backend as a child process and, on a clean shutdown, tears
+it down itself (SIGTERM -> grace -> SIGKILL). That graceful path only runs when
+LocalAI receives a catchable signal and lives long enough to run its handlers.
+If LocalAI is SIGKILLed (e.g. a supervising process's grace period elapses
+first), that teardown never runs and this backend would be reparented to init
+and linger, holding GPU/VRAM and its listen port.
+
+The watcher here is a best-effort backstop for exactly that case: it does NOT
+replace the graceful teardown, it only covers the "parent vanished without
+cleaning up" path. It detects reparenting: when the process that spawned this
+backend dies, the kernel reparents us to the nearest sub-reaper or to init
+(PID 1), so os.getppid() stops matching the value captured at startup. This
+getppid() approach is portable across Linux/macOS (unlike the Linux-only
+PR_SET_PDEATHSIG), which is why it is used here, mirroring the Go backends'
+pkg/grpc/parentwatch.go and the C++ backends' parent_watch.h. It is disabled on
+Windows, which has no equivalent orphan-reparenting semantics.
+
+Env vars (shared verbatim across the Go, C++ and Python backends):
+  LOCALAI_BACKEND_PARENT_WATCH           enabled by default; a falsey value
+                                         ("false"/"0"/"no"/"off", case-insensitive)
+                                         disables it.
+  LOCALAI_BACKEND_PARENT_WATCH_INTERVAL  poll interval as a Go-style duration
+                                         string ("500ms", "2s", "1m") or a bare
+                                         number of seconds. Defaults to 2s.
+"""
+
+import os
+import sys
+import threading
+
+ENV_PARENT_WATCH = "LOCALAI_BACKEND_PARENT_WATCH"
+ENV_PARENT_WATCH_INTERVAL = "LOCALAI_BACKEND_PARENT_WATCH_INTERVAL"
+
+_DEFAULT_INTERVAL_SECONDS = 2.0
+
+# Guard so repeated calls (e.g. get_auth_interceptors invoked more than once)
+# only ever arm a single watcher thread per process.
+_started = False
+_started_lock = threading.Lock()
+
+
+def _enabled():
+    """Report whether the watcher should run in this process."""
+    # Windows does not reparent orphans to a well-known init PID, so the
+    # getppid() heuristic used here doesn't apply there.
+    if os.name == "nt" or sys.platform.startswith("win"):
+        return False
+    val = os.environ.get(ENV_PARENT_WATCH, "").strip().lower()
+    if val in ("false", "0", "no", "off"):
+        return False
+    return True
+
+
+def _interval_seconds():
+    """Return the configured poll interval in seconds, or the default.
+
+    Accepts Go-style duration strings ("500ms", "2s", "1m") for cross-language
+    parity, or a bare number interpreted as seconds.
+    """
+    raw = os.environ.get(ENV_PARENT_WATCH_INTERVAL, "").strip()
+    if not raw:
+        return _DEFAULT_INTERVAL_SECONDS
+    # Split numeric prefix from unit suffix.
+    i = 0
+    while i < len(raw) and (raw[i].isdigit() or raw[i] == "." or (i == 0 and raw[i] in "+-")):
+        i += 1
+    if i == 0:
+        return _DEFAULT_INTERVAL_SECONDS
+    try:
+        num = float(raw[:i])
+    except ValueError:
+        return _DEFAULT_INTERVAL_SECONDS
+    unit = raw[i:].lower()
+    if unit == "ms":
+        seconds = num / 1000.0
+    elif unit in ("s", ""):
+        seconds = num
+    elif unit == "m":
+        seconds = num * 60.0
+    else:
+        return _DEFAULT_INTERVAL_SECONDS
+    return seconds if seconds > 0 else _DEFAULT_INTERVAL_SECONDS
+
+
+def _parent_died(orig_ppid):
+    """Report whether this process has been reparented away from orig_ppid.
+
+    Reparenting is the standard POSIX signal that the original parent (here, the
+    LocalAI process that spawned this backend) has exited: the orphan is handed
+    to the nearest sub-reaper or to init (PID 1), so os.getppid() no longer
+    matches the value captured at startup.
+    """
+    ppid = os.getppid()
+    return ppid != orig_ppid or ppid == 1
+
+
+def _watch(orig_ppid, interval, on_death):
+    """Poll until _parent_died reports the original parent is gone, then call
+    on_death. Blocks, so run it on its own (daemon) thread."""
+    import time
+
+    while True:
+        time.sleep(interval)
+        if _parent_died(orig_ppid):
+            on_death()
+            return
+
+
+def start_parent_death_watcher():
+    """Install the best-effort safety net described in this module's docstring.
+
+    No-op when disabled, on Windows, when already orphaned at startup
+    (os.getppid() <= 1), or if already started. This is a backstop alongside —
+    never a replacement for — LocalAI's graceful teardown.
+    """
+    global _started
+    if not _enabled():
+        return
+    with _started_lock:
+        if _started:
+            return
+        orig_ppid = os.getppid()
+        # A parent of 1 (or less) at startup means we were already orphaned (or
+        # launched directly under init) — there is no original parent to watch.
+        if orig_ppid <= 1:
+            return
+        interval = _interval_seconds()
+
+        def on_death():
+            print(
+                "backend parent process (pid {}) exited without stopping this "
+                "backend; self-terminating to avoid orphaning".format(orig_ppid),
+                file=sys.stderr,
+                flush=True,
+            )
+            # Immediate, non-cleanup exit: this is a shutdown safety net and the
+            # normal graceful path is already gone.
+            os._exit(1)
+
+        thread = threading.Thread(
+            target=_watch,
+            args=(orig_ppid, interval, on_death),
+            name="parent-death-watcher",
+            daemon=True,
+        )
+        thread.start()
+        _started = True

backend/python/common/parent_watch_test.py

@@ -0,0 +1,150 @@
+"""Unit tests for the parent-death watcher (parent_watch.py).
+
+Run standalone (Python standard library only, no backend venv needed):
+    python3 -m unittest parent_watch_test
+
+The core test (test_detects_reparent) builds a genuine two-level process tree
+(test -> middle -> grandchild) with os.fork, lets the middle process die, and
+asserts the grandchild's parent_watch._watch detects the reparenting and
+self-terminates — mirroring the Go test in pkg/grpc/parentwatch_test.go and the
+C++ test in backend/cpp/llama-cpp/parent_watch_test.cpp.
+"""
+
+import os
+import sys
+import tempfile
+import threading
+import time
+import unittest
+
+import parent_watch
+
+
+class TestParentWatchEnvParsing(unittest.TestCase):
+    def setUp(self):
+        self._saved = {
+            k: os.environ.get(k)
+            for k in (parent_watch.ENV_PARENT_WATCH, parent_watch.ENV_PARENT_WATCH_INTERVAL)
+        }
+        for k in self._saved:
+            os.environ.pop(k, None)
+
+    def tearDown(self):
+        for k, v in self._saved.items():
+            if v is None:
+                os.environ.pop(k, None)
+            else:
+                os.environ[k] = v
+
+    def test_interval_default(self):
+        self.assertEqual(parent_watch._interval_seconds(), 2.0)
+
+    def test_interval_units(self):
+        cases = {"500ms": 0.5, "2s": 2.0, "1m": 60.0, "3": 3.0, "0.5s": 0.5}
+        for raw, expected in cases.items():
+            os.environ[parent_watch.ENV_PARENT_WATCH_INTERVAL] = raw
+            self.assertAlmostEqual(parent_watch._interval_seconds(), expected, msg=raw)
+
+    def test_interval_garbage_falls_back(self):
+        os.environ[parent_watch.ENV_PARENT_WATCH_INTERVAL] = "garbage"
+        self.assertEqual(parent_watch._interval_seconds(), 2.0)
+
+    @unittest.skipIf(os.name == "nt" or sys.platform.startswith("win"), "POSIX only")
+    def test_enabled_default(self):
+        self.assertTrue(parent_watch._enabled())
+
+    @unittest.skipIf(os.name == "nt" or sys.platform.startswith("win"), "POSIX only")
+    def test_disabled_by_falsey(self):
+        for val in ("false", "0", "no", "off", "OFF", " False "):
+            os.environ[parent_watch.ENV_PARENT_WATCH] = val
+            self.assertFalse(parent_watch._enabled(), msg=val)
+
+    @unittest.skipIf(os.name == "nt" or sys.platform.startswith("win"), "POSIX only")
+    def test_enabled_by_truthy(self):
+        for val in ("true", "1", "yes", "on"):
+            os.environ[parent_watch.ENV_PARENT_WATCH] = val
+            self.assertTrue(parent_watch._enabled(), msg=val)
+
+
+@unittest.skipIf(os.name == "nt" or sys.platform.startswith("win"), "fork/reparent is POSIX only")
+class TestParentWatchReparent(unittest.TestCase):
+    def _wait_for_file(self, path, timeout=10.0):
+        deadline = time.time() + timeout
+        while time.time() < deadline:
+            if os.path.exists(path):
+                return True
+            time.sleep(0.02)
+        return False
+
+    def test_detects_reparent(self):
+        tmpdir = tempfile.mkdtemp(prefix="parentwatch_test_")
+        ready_file = os.path.join(tmpdir, "ready")
+        exited_file = os.path.join(tmpdir, "exited")
+
+        middle = os.fork()
+        if middle == 0:
+            # ---- middle process ----
+            grandchild = os.fork()
+            if grandchild == 0:
+                # ---- grandchild process: arm the REAL watcher against middle ----
+                orig_ppid = os.getppid()
+
+                def on_death():
+                    with open(exited_file, "w") as f:
+                        f.write("1")
+                    os._exit(7)
+
+                threading.Thread(
+                    target=parent_watch._watch,
+                    args=(orig_ppid, 0.05, on_death),
+                    daemon=True,
+                ).start()
+
+                # Safety valve: never linger if something goes wrong.
+                def bail():
+                    time.sleep(30)
+                    os._exit(2)
+
+                threading.Thread(target=bail, daemon=True).start()
+
+                # Signal readiness only after the watcher captured orig_ppid.
+                with open(ready_file, "w") as f:
+                    f.write(str(os.getpid()))
+                while True:
+                    time.sleep(1)
+            else:
+                # middle: wait until grandchild is ready, then exit to orphan it.
+                if not self._wait_for_file(ready_file):
+                    os._exit(5)
+                os._exit(0)
+
+        # ---- test (top) process ----
+        os.waitpid(middle, 0)  # reap middle only; grandchild is orphaned
+
+        self.assertTrue(os.path.exists(ready_file), "grandchild never signaled readiness")
+        self.assertTrue(
+            self._wait_for_file(exited_file),
+            "watcher did not detect parent death within timeout",
+        )
+
+        # Best-effort cleanup: kill the grandchild if it somehow survived.
+        try:
+            with open(ready_file) as f:
+                pid = int(f.read().strip())
+            if pid > 1:
+                os.kill(pid, 9)
+        except (OSError, ValueError):
+            pass
+        for p in (ready_file, exited_file):
+            try:
+                os.remove(p)
+            except OSError:
+                pass
+        try:
+            os.rmdir(tmpdir)
+        except OSError:
+            pass
+
+
+if __name__ == "__main__":
+    unittest.main()

pkg/grpc/parentwatch.go

@@ -0,0 +1,105 @@
+package grpc
+
+import (
+	"log"
+	"os"
+	"runtime"
+	"strings"
+	"time"
+)
+
+// Backend worker processes (the per-model gRPC servers LocalAI spawns) are
+// deliberately placed in their own process group by the process manager so
+// LocalAI's graceful shutdown can signal the whole group. That graceful path
+// (SIGTERM -> grace -> SIGKILL, driven by pkg/signals + pkg/model) only runs
+// when LocalAI itself receives a catchable signal and lives long enough to run
+// its handlers. If LocalAI is SIGKILLed (e.g. a supervising process's
+// graceful-shutdown grace period elapses first), that teardown never runs and
+// this backend would be reparented to init and linger, holding VRAM and its
+// listen port.
+//
+// The watcher below is a best-effort backstop for exactly that case: it does
+// NOT replace the graceful teardown, it only covers the "parent vanished
+// without cleaning up" path. It works by detecting reparenting: when the
+// process that spawned this backend dies, the kernel reparents us to the
+// nearest sub-reaper or to init (PID 1), so getppid() stops matching the value
+// we captured at startup. This getppid() approach is portable across
+// Linux/macOS (unlike Linux-only PR_SET_PDEATHSIG), which is why it's used
+// here rather than a kernel parent-death signal.
+const (
+	// EnvBackendParentWatch toggles the parent-death watcher. It is enabled by
+	// default; set it to a falsey value ("false", "0", "no", "off") to disable
+	// (e.g. when running a backend standalone for debugging under a shell whose
+	// lifetime shouldn't govern the backend).
+	EnvBackendParentWatch = "LOCALAI_BACKEND_PARENT_WATCH"
+	// EnvBackendParentWatchInterval overrides the poll interval as a Go
+	// duration string (e.g. "500ms"). Defaults to defaultParentWatchInterval.
+	EnvBackendParentWatchInterval = "LOCALAI_BACKEND_PARENT_WATCH_INTERVAL"
+
+	defaultParentWatchInterval = 2 * time.Second
+)
+
+// parentWatchEnabled reports whether the watcher should run in this process.
+func parentWatchEnabled() bool {
+	switch strings.ToLower(strings.TrimSpace(os.Getenv(EnvBackendParentWatch))) {
+	case "false", "0", "no", "off":
+		return false
+	}
+	// Windows does not reparent orphans to a well-known init PID, so the
+	// getppid() heuristic used here doesn't apply there.
+	return runtime.GOOS != "windows"
+}
+
+// parentWatchInterval returns the configured poll interval, or the default.
+func parentWatchInterval() time.Duration {
+	if v := os.Getenv(EnvBackendParentWatchInterval); v != "" {
+		if d, err := time.ParseDuration(v); err == nil && d > 0 {
+			return d
+		}
+	}
+	return defaultParentWatchInterval
+}
+
+// parentDied reports whether this process has been reparented away from the
+// parent it had when the watcher started. Reparenting is the standard POSIX
+// signal that the original parent (here, the LocalAI process that spawned this
+// backend) has exited: the orphan is handed to the nearest sub-reaper or to
+// init (PID 1), so getppid() no longer matches the value captured at startup.
+func parentDied(origPPID int) bool {
+	ppid := os.Getppid()
+	return ppid != origPPID || ppid == 1
+}
+
+// watchParentDeath polls until parentDied reports the original parent is gone,
+// then invokes onDeath. It blocks, so run it in its own goroutine.
+func watchParentDeath(origPPID int, interval time.Duration, onDeath func()) {
+	ticker := time.NewTicker(interval)
+	defer ticker.Stop()
+	for range ticker.C {
+		if parentDied(origPPID) {
+			onDeath()
+			return
+		}
+	}
+}
+
+// startParentDeathWatcher installs the best-effort safety net described above
+// on the calling backend process. It is a no-op when disabled or on platforms
+// where the mechanism doesn't apply. This is a backstop alongside — never a
+// replacement for — LocalAI's graceful SIGTERM->grace->SIGKILL teardown.
+func startParentDeathWatcher() {
+	if !parentWatchEnabled() {
+		return
+	}
+	origPPID := os.Getppid()
+	// A parent of 1 at startup means we were already orphaned (or launched
+	// directly under init) — there's no original parent to watch for.
+	if origPPID <= 1 {
+		return
+	}
+	interval := parentWatchInterval()
+	go watchParentDeath(origPPID, interval, func() {
+		log.Printf("backend parent process (pid %d) exited without stopping this backend; self-terminating to avoid orphaning", origPPID)
+		os.Exit(1)
+	})
+}

pkg/grpc/parentwatch_test.go

@@ -0,0 +1,163 @@
+//go:build !windows
+
+package grpc
+
+import (
+	"os"
+	"os/exec"
+	"path/filepath"
+	"runtime"
+	"strconv"
+	"syscall"
+	"time"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// These env vars drive the helper roles this test binary re-executes itself as
+// (see the init() dispatcher). They are only set for the spawned child/
+// grandchild processes, never for the normal `go test` invocation.
+const (
+	envRole   = "LOCALAI_PARENTWATCH_TEST_ROLE"
+	envReady  = "LOCALAI_PARENTWATCH_TEST_READY"  // grandchild writes its PID here once the watcher is armed
+	envExited = "LOCALAI_PARENTWATCH_TEST_EXITED" // grandchild writes here when it detects reparenting
+)
+
+// init dispatches the helper roles when this test binary is re-executed with a
+// role set. It runs before the testing/Ginkgo machinery, and is a no-op during
+// a normal test run (role unset).
+func init() {
+	switch os.Getenv(envRole) {
+	case "middle":
+		runMiddleRole()
+	case "grandchild":
+		runGrandchildRole()
+	}
+}
+
+// childEnv returns the current environment with the parentwatch test role set
+// to the given value (replacing any inherited role), leaving the ready/exited
+// file paths inherited.
+func childEnv(role string) []string {
+	out := make([]string, 0, len(os.Environ())+1)
+	for _, kv := range os.Environ() {
+		if len(kv) > len(envRole) && kv[:len(envRole)+1] == envRole+"=" {
+			continue
+		}
+		out = append(out, kv)
+	}
+	return append(out, envRole+"="+role)
+}
+
+// runGrandchildRole arms the REAL watchParentDeath against its current parent
+// (the "middle" process), signals readiness, then blocks. When middle exits and
+// we are reparented, the watcher fires and we record it before exiting.
+func runGrandchildRole() {
+	exitedFile := os.Getenv(envExited)
+	readyFile := os.Getenv(envReady)
+
+	origPPID := os.Getppid()
+	go watchParentDeath(origPPID, 50*time.Millisecond, func() {
+		_ = os.WriteFile(exitedFile, []byte("1"), 0o644)
+		os.Exit(7)
+	})
+
+	// Safety valve: never linger if something goes wrong with the test.
+	go func() {
+		time.Sleep(30 * time.Second)
+		os.Exit(2)
+	}()
+
+	// Signal readiness only after the watcher captured origPPID, so middle
+	// won't exit before we've recorded it as our original parent.
+	_ = os.WriteFile(readyFile, []byte(strconv.Itoa(os.Getpid())), 0o644)
+
+	select {} // block until the watcher terminates us
+}
+
+// runMiddleRole spawns the grandchild (which arms the watcher against us),
+// waits until it is ready, then exits — orphaning the grandchild so it gets
+// reparented, which is what the watcher must detect.
+func runMiddleRole() {
+	readyFile := os.Getenv(envReady)
+
+	self, err := os.Executable()
+	if err != nil {
+		os.Exit(3)
+	}
+	cmd := exec.Command(self)
+	cmd.Env = childEnv("grandchild")
+	// Own process group, mirroring how real backends are spawned, and discard
+	// std streams so the grandchild doesn't keep any parent pipe open.
+	cmd.SysProcAttr = &syscall.SysProcAttr{Setpgid: true}
+	if err := cmd.Start(); err != nil {
+		os.Exit(4)
+	}
+
+	if !waitForFile(readyFile, 10*time.Second) {
+		os.Exit(5)
+	}
+	os.Exit(0) // orphan the grandchild
+}
+
+func waitForFile(path string, timeout time.Duration) bool {
+	deadline := time.Now().Add(timeout)
+	for time.Now().Before(deadline) {
+		if _, err := os.Stat(path); err == nil {
+			return true
+		}
+		time.Sleep(20 * time.Millisecond)
+	}
+	return false
+}
+
+// This spec builds a genuine two-level process tree (test -> middle ->
+// grandchild), lets the middle process die, and asserts the grandchild's
+// watchParentDeath detects the reparenting and self-terminates.
+var _ = Describe("watchParentDeath", func() {
+	It("detects reparenting and self-terminates the orphaned process", func() {
+		if runtime.GOOS == "windows" {
+			Skip("parent-death watcher is not supported on windows")
+		}
+
+		dir := GinkgoT().TempDir()
+		readyFile := filepath.Join(dir, "ready")
+		exitedFile := filepath.Join(dir, "exited")
+
+		self, err := os.Executable()
+		Expect(err).NotTo(HaveOccurred(), "cannot resolve test executable")
+
+		middle := exec.Command(self)
+		middle.Env = append(childEnv("middle"),
+			envReady+"="+readyFile,
+			envExited+"="+exitedFile,
+		)
+		// Discard the helpers' output; keep the test log clean.
+		middle.Stdout = nil
+		middle.Stderr = nil
+
+		Expect(middle.Start()).To(Succeed(), "failed to start middle helper")
+		// Wait only for the middle process; the grandchild is intentionally left
+		// orphaned. No pipes are shared, so this returns as soon as middle exits.
+		Expect(middle.Wait()).To(Succeed(), "middle helper exited with error")
+
+		// The grandchild must have armed the watcher (and thus captured middle as
+		// its parent) before middle exited.
+		_, err = os.Stat(readyFile)
+		Expect(err).NotTo(HaveOccurred(), "grandchild never signaled readiness")
+
+		// Best-effort cleanup in case the watcher somehow doesn't fire.
+		DeferCleanup(func() {
+			if b, err := os.ReadFile(readyFile); err == nil {
+				if pid, err := strconv.Atoi(string(b)); err == nil {
+					_ = syscall.Kill(pid, syscall.SIGKILL)
+				}
+			}
+		})
+
+		// Now that middle is gone, the grandchild has been reparented; the watcher
+		// must notice and write the exited marker.
+		Expect(waitForFile(exitedFile, 10*time.Second)).To(BeTrue(), "watcher did not detect parent death within timeout")
+	})
+})

pkg/grpc/server.go

@@ -939,6 +939,9 @@ func StartServer(address string, model AIModel) error {
 	s := grpc.NewServer(serverOpts()...)
 	pb.RegisterBackendServer(s, &server{llm: model})
 	log.Printf("gRPC Server listening at %v", lis.Addr())
+	// Safety net: self-terminate if the LocalAI process that spawned this
+	// backend dies without running its graceful teardown (see parentwatch.go).
+	startParentDeathWatcher()
 	if err := s.Serve(lis); err != nil {
 		return err
 	}
@@ -954,6 +957,9 @@ func RunServer(address string, model AIModel) (func() error, error) {
 	s := grpc.NewServer(serverOpts()...)
 	pb.RegisterBackendServer(s, &server{llm: model})
 	log.Printf("gRPC Server listening at %v", lis.Addr())
+	// Safety net: self-terminate if the LocalAI process that spawned this
+	// backend dies without running its graceful teardown (see parentwatch.go).
+	startParentDeathWatcher()
 	if err = s.Serve(lis); err != nil {
 		return func() error {
 			return lis.Close()