fix(python-backends): parse tool-call arguments for chat templates and split implicit reasoning blocks

Two bugs broke OpenAI-style tool calling on the MLX backend (and any
Python backend sharing backend/python/common), reproduced end-to-end on
LocalAI v4.5.5 with the metal-mlx backend and
mlx-community/Qwen3.5-2B-MLX-8bit.

messages_to_dicts left each tool call's function.arguments as the raw
OpenAI-wire JSON string. HuggingFace chat templates (e.g. Qwen3.5)
iterate arguments as a mapping (.items()), so any request whose history
contained a prior assistant tool_calls message failed with HTTP 500
"Generation failed: Can only get item pairs from a mapping." — breaking
every agent loop on its second turn. Decode the string back into a dict
so the template sees a mapping.

split_reasoning returned ("", text) whenever the opening think tag was
absent. Models like Qwen3.5 open the assistant turn already inside
thinking, so the generated text carries only the closing </think>; the
whole chain-of-thought leaked into content. When the opener is missing
but the closer is present, treat everything before the closer as
reasoning.

Adds platform-independent unit tests under backend/python/common
(stdlib-only, no MLX/venv required, following parent_watch_test.py).

Assisted-by: Claude Code:claude-opus-4-8

Dockerfile

@@ -171,6 +171,17 @@ RUN if [ "${BUILD_TYPE}" = "hipblas" ]; then \
     ln -s /opt/rocm-**/lib/llvm/lib/libomp.so /usr/lib/libomp.so \
     ; fi
 
+# ROCm's bundled libdrm_amdgpu is built with a hardcoded fallback lookup path
+# for the ASIC ID table (/opt/amdgpu/share/libdrm/amdgpu.ids), which only exists
+# if AMD's full amdgpu graphics/DKMS stack is installed. This compute-only image
+# doesn't have it, so hipblas/rocBLAS log "No such file or directory" on every
+# model load and can fail to identify the GPU. Point it at the equivalent file
+# Ubuntu's libdrm-common package already ships.
+RUN if [ "${BUILD_TYPE}" = "hipblas" ] && [ -f /usr/share/libdrm/amdgpu.ids ] && [ ! -e /opt/amdgpu/share/libdrm/amdgpu.ids ]; then \
+    mkdir -p /opt/amdgpu/share/libdrm && \
+    ln -s /usr/share/libdrm/amdgpu.ids /opt/amdgpu/share/libdrm/amdgpu.ids \
+    ; fi
+
 RUN expr "${BUILD_TYPE}" = intel && echo "intel" > /run/localai/capability || echo "not intel"
 
 # Cuda

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=f74a6fb87b315b2c3154166e075360e15021a61d
+IK_LLAMA_VERSION?=87fc8701ff4da81a7d2a91ec0695f95eb3066a47
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

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/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=6f4f53f2b7da54fcdbbecaaa734337c337ad6176
+LLAMA_VERSION?=fdb1db877c526ec90f668eca1b858da5dba85560
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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/privacy-filter/Makefile

@@ -8,7 +8,7 @@
 # Local development: point at a working checkout instead of cloning, e.g.
 #   make PRIVACY_FILTER_SRC=$HOME/c/privacy-filter.cpp grpc-server
 
-PRIVACY_FILTER_VERSION?=595f59630c69d361b5196f2aba2c71c873d0c13c
+PRIVACY_FILTER_VERSION?=735a6c28607ee82afc3a670383f41b55266a3b9a
 PRIVACY_FILTER_REPO?=https://github.com/localai-org/privacy-filter.cpp
 PRIVACY_FILTER_SRC?=
 

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/go/cloud-proxy/provider_anthropic.go

@@ -142,19 +142,12 @@ func buildAnthropicRequest(opts *pb.PredictOptions, cfg *proxyConfig, stream boo
 	if req.MaxTokens <= 0 {
 		req.MaxTokens = anthropicDefaultMaxTokens
 	}
-	// Newer Anthropic models 400 when both temperature and top_p are
-	// set ("`temperature` and `top_p` cannot both be specified for
-	// this model. Please use only one.") even though their docs only
-	// "recommend" picking one. The OpenAI-compatible chat UI almost
-	// always sends both with default values, so prefer temperature
-	// and drop top_p when both are present.
-	if t := opts.GetTemperature(); t != 0 {
-		v := float64(t)
-		req.Temperature = &v
-	} else if t := opts.GetTopP(); t != 0 {
-		v := float64(t)
-		req.TopP = &v
-	}
+	// Do not forward temperature/top_p. Newer Anthropic reasoning models reject
+	// requests that carry temperature ("`temperature` is deprecated for this
+	// model"), and the OpenAI-compatible clients typically send only the
+	// server-side DEFAULT sampling values rather than user intent — dropping
+	// them loses nothing and lets the upstream apply its own defaults.
+	_ = opts
 
 	req.Tools = convertOpenAITools(opts.GetTools())
 	req.ToolChoice = convertOpenAIToolChoice(opts.GetToolChoice())

backend/go/cloud-proxy/provider_anthropic_test.go

@@ -3,7 +3,6 @@ package main
 import (
 	"encoding/json"
 	"io"
-	"math"
 	"net/http"
 	"net/http/httptest"
 	"strings"
@@ -75,15 +74,16 @@ func TestPredict_Anthropic_BasicMessages(t *testing.T) {
 	g.Expect(captured.Messages).To(HaveLen(1))
 	g.Expect(captured.Messages[0].Role).To(Equal("user"))
 	g.Expect(captured.MaxTokens).To(Equal(int32(32)))
-	g.Expect(captured.Temperature).NotTo(BeNil())
-	g.Expect(*captured.Temperature).To(Equal(0.5))
-	// Anthropic 400s when both temperature and top_p are set; the
-	// translator must prefer temperature and drop top_p.
+	// Newer Anthropic reasoning models reject requests carrying temperature
+	// ("`temperature` is deprecated for this model"); clients typically send
+	// only default sampling values, so the translator forwards neither.
+	g.Expect(captured.Temperature).To(BeNil())
 	g.Expect(captured.TopP).To(BeNil())
 	g.Expect(captured.Stream).To(BeFalse())
 }
 
-// When only top_p is set, it should be forwarded.
+// Sampling parameters are not forwarded at all — the upstream applies its
+// own defaults (newest models reject explicit temperature/top_p).
 func TestPredict_Anthropic_TopPOnly(t *testing.T) {
 	g := NewWithT(t)
 	srv, captured := fakeAnthropicUpstream(t, func(_ anthropicRequest) (int, string, string) {
@@ -99,11 +99,7 @@ func TestPredict_Anthropic_TopPOnly(t *testing.T) {
 	})
 	g.Expect(err).NotTo(HaveOccurred())
 	g.Expect(captured.Temperature).To(BeNil())
-	// PredictOptions.TopP is float32 on the wire; the translator widens
-	// to float64 so 0.9 round-trips as 0.8999999761581421… — compare
-	// with a small tolerance rather than exact equality.
-	g.Expect(captured.TopP).NotTo(BeNil())
-	g.Expect(math.Abs(*captured.TopP - 0.9)).To(BeNumerically("<=", 1e-6))
+	g.Expect(captured.TopP).To(BeNil())
 }
 
 func TestPredict_Anthropic_DefaultsMaxTokens(t *testing.T) {

backend/go/cloud-proxy/provider_openai.go

@@ -30,7 +30,7 @@ type openAIRequest struct {
 	Stream           bool            `json:"stream,omitempty"`
 	Temperature      *float64        `json:"temperature,omitempty"`
 	TopP             *float64        `json:"top_p,omitempty"`
-	MaxTokens        *int32          `json:"max_tokens,omitempty"`
+	MaxTokens        *int32          `json:"max_completion_tokens,omitempty"` // newer OpenAI models reject max_tokens ("use max_completion_tokens instead")
 	Stop             []string        `json:"stop,omitempty"`
 	FrequencyPenalty *float64        `json:"frequency_penalty,omitempty"`
 	PresencePenalty  *float64        `json:"presence_penalty,omitempty"`
@@ -107,14 +107,10 @@ func buildOpenAIRequest(opts *pb.PredictOptions, cfg *proxyConfig, stream bool)
 		Tools:      parseRawJSON(opts.GetTools()),
 		ToolChoice: parseRawJSON(opts.GetToolChoice()),
 	}
-	if t := opts.GetTemperature(); t != 0 {
-		v := float64(t)
-		req.Temperature = &v
-	}
-	if t := opts.GetTopP(); t != 0 {
-		v := float64(t)
-		req.TopP = &v
-	}
+	// Do not forward temperature/top_p. Newer OpenAI reasoning models reject
+	// temperature as deprecated, and clients typically send only default
+	// sampling values rather than user intent — let the upstream apply its
+	// own defaults.
 	if n := opts.GetTokens(); n > 0 {
 		req.MaxTokens = &n
 	}

backend/go/cloud-proxy/provider_openai_test.go

@@ -74,8 +74,9 @@ func TestPredict_OpenAI_BasicChat(t *testing.T) {
 	g.Expect(captured.Messages).To(HaveLen(2))
 	g.Expect(captured.Messages[0].Role).To(Equal("system"))
 	g.Expect(captured.Messages[1].Role).To(Equal("user"))
-	g.Expect(captured.Temperature).NotTo(BeNil())
-	g.Expect(*captured.Temperature).To(Equal(0.5))
+	// Sampling parameters are not forwarded (newest models reject explicit
+	// temperature); token limit is serialized as max_completion_tokens.
+	g.Expect(captured.Temperature).To(BeNil())
 	g.Expect(captured.MaxTokens).NotTo(BeNil())
 	g.Expect(*captured.MaxTokens).To(Equal(int32(32)))
 	g.Expect(captured.Stream).To(BeFalse())

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=3b93758f9725d400eca82976f895e4cec3f31260
+CRISPASR_VERSION?=9a26976a8c8cf5af0afcdd04463cf8ba91e96a54
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/parakeet-cpp/Makefile

@@ -1,6 +1,6 @@
 # parakeet-cpp backend Makefile.
 #
-# Upstream pin lives below as PARAKEET_VERSION?=f469a57270a1cc4554acb15febf60e56619673b9
+# Upstream pin lives below as PARAKEET_VERSION?=e8acc6172a94e20a952cf1843decace5d771a94b
 # (.github/bump_deps.sh) can find and update it - matches the
 # whisper.cpp / ds4 / vibevoice-cpp convention.
 #
@@ -15,7 +15,7 @@
 # That's what the L0 smoke test uses. The default target below does the
 # proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
 
-PARAKEET_VERSION?=f469a57270a1cc4554acb15febf60e56619673b9
+PARAKEET_VERSION?=e8acc6172a94e20a952cf1843decace5d771a94b
 PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
 
 GOCMD?=go

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=3b6c9ca97cfcda8e68e719e6670d06379fcbe943
+STABLEDIFFUSION_GGML_VERSION?=2574f5936571645f784b77623e1f09bad97d948a
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/stablediffusion-ggml/cpp/gosd.cpp

@@ -798,6 +798,7 @@ void sd_img_gen_params_set_seed(sd_img_gen_params_t *params, int64_t seed) {
 int gen_image(sd_img_gen_params_t *p, int steps, char *dst, float cfg_scale, char *src_image, float strength, char *mask_image, char* ref_images[], int ref_images_count) {
 
     sd_image_t* results;
+    int num_results_out = 0;
 
     std::vector<int> skip_layers = {7, 8, 9};
 
@@ -994,10 +995,14 @@ int gen_image(sd_img_gen_params_t *p, int steps, char *dst, float cfg_scale, cha
             sd_ctx_params_to_str(&ctx_params),
             sd_img_gen_params_to_str(p));
 
-    results = generate_image(sd_c, p);
+    bool gen_ok = generate_image(sd_c, p, &results, &num_results_out);
 
     std::free(p);
 
+    if (!gen_ok || num_results_out == 0) {
+        results = NULL;
+    }
+
     if (results == NULL) {
         fprintf (stderr, "NO results\n");
         if (input_image_buffer) free(input_image_buffer);

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=0ae02cdb2c7317b50991367c165736ce42ed96ac
+WHISPER_CPP_VERSION?=6fc7c33b4c3a2cec83e4b65abd5e96a890480375
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

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/mlx_utils.py

@@ -20,7 +20,15 @@ def split_reasoning(text, think_start, think_end):
     Returns ``(reasoning_content, remaining_text)``. When ``think_start`` is
     empty or not found, returns ``("", text)`` unchanged.
     """
-    if not think_start or not text or think_start not in text:
+    if not think_start or not text:
+        return "", text
+    if think_start not in text:
+        # Models like Qwen3.5 open assistant turns already INSIDE thinking, so
+        # the generated text carries only the closing tag. Everything before it
+        # is reasoning that would otherwise leak into the content.
+        if think_end and think_end in text:
+            head, _, tail = text.partition(think_end)
+            return head.strip(), tail.strip()
         return "", text
     pattern = re.compile(
         re.escape(think_start) + r"(.*?)" + re.escape(think_end or ""),

backend/python/common/mlx_utils_test.py

@@ -0,0 +1,75 @@
+"""Unit tests for the mlx/mlx-vlm shared helpers (mlx_utils.py).
+
+Run standalone (Python standard library only, no backend venv needed):
+    python3 -m unittest mlx_utils_test
+
+These mirror the server-less helper tests in backend/python/mlx/test.py
+(TestSharedHelpers), but live here so they run on any platform: the mlx
+test module imports grpc/backend_pb2 at import time and needs the MLX venv,
+whereas mlx_utils only needs the standard library.
+"""
+
+import types
+import unittest
+
+from mlx_utils import parse_tool_calls, split_reasoning
+
+
+class TestSplitReasoning(unittest.TestCase):
+    def test_both_tags(self):
+        r, c = split_reasoning(
+            "<think>step 1\nstep 2</think>The answer is 42.", "<think>", "</think>"
+        )
+        self.assertEqual(r, "step 1\nstep 2")
+        self.assertEqual(c, "The answer is 42.")
+
+    def test_implicit_opener_only_closing_tag(self):
+        # Qwen3.5 opens the assistant turn already inside thinking, so the
+        # output carries only the closing tag; everything before it is reasoning.
+        r, c = split_reasoning(
+            "The user is asking about the weather.\n</think>\n\nThe weather in Rome is sunny.",
+            "<think>",
+            "</think>",
+        )
+        self.assertEqual(r, "The user is asking about the weather.")
+        self.assertEqual(c, "The weather in Rome is sunny.")
+
+    def test_no_tags_at_all(self):
+        r, c = split_reasoning("just text", "<think>", "</think>")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "just text")
+
+    def test_empty_think_end_and_no_opener_match(self):
+        # No think_end to anchor on, and the opener is absent → return unchanged.
+        r, c = split_reasoning("no opener here", "<think>", "")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "no opener here")
+
+    def test_empty_text(self):
+        r, c = split_reasoning("", "<think>", "</think>")
+        self.assertEqual(r, "")
+        self.assertEqual(c, "")
+
+
+class TestParseToolCalls(unittest.TestCase):
+    def test_with_shim(self):
+        tm = types.SimpleNamespace(
+            tool_call_start="<tool_call>",
+            tool_call_end="</tool_call>",
+            parse_tool_call=lambda body, tools: {
+                "name": "get_weather",
+                "arguments": {"location": body.strip()},
+            },
+        )
+        calls, remaining = parse_tool_calls(
+            "Sure: <tool_call>Paris</tool_call>", tm, tools=None
+        )
+        self.assertEqual(len(calls), 1)
+        self.assertEqual(calls[0]["name"], "get_weather")
+        self.assertEqual(calls[0]["arguments"], '{"location": "Paris"}')
+        self.assertEqual(calls[0]["index"], 0)
+        self.assertNotIn("<tool_call>", remaining)
+
+
+if __name__ == "__main__":
+    unittest.main()

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()

backend/python/common/python_utils.py

@@ -58,7 +58,18 @@ def messages_to_dicts(proto_messages):
             d["reasoning_content"] = msg.reasoning_content
         if msg.tool_calls:
             try:
-                d["tool_calls"] = json.loads(msg.tool_calls)
+                tool_calls = json.loads(msg.tool_calls)
+                # Chat templates (e.g. Qwen) iterate function.arguments as a
+                # mapping, but the OpenAI wire format carries it as a JSON
+                # string — decode it back so the template's .items() works.
+                for tc in tool_calls:
+                    fn = tc.get("function") if isinstance(tc, dict) else None
+                    if isinstance(fn, dict) and isinstance(fn.get("arguments"), str):
+                        try:
+                            fn["arguments"] = json.loads(fn["arguments"])
+                        except json.JSONDecodeError:
+                            pass
+                d["tool_calls"] = tool_calls
             except json.JSONDecodeError:
                 pass
         result.append(d)

backend/python/common/python_utils_test.py

@@ -0,0 +1,122 @@
+"""Unit tests for the shared python backend helpers (python_utils.py).
+
+Run standalone (Python standard library only, no backend venv needed):
+    python3 -m unittest python_utils_test
+
+These mirror the server-less helper tests in backend/python/mlx/test.py
+(TestSharedHelpers), but live here so they run on any platform: the mlx
+test module imports grpc/backend_pb2 at import time and needs the MLX venv,
+whereas python_utils has no third-party dependency. Proto Message objects
+are faked with types.SimpleNamespace (real proto fields default to "").
+"""
+
+import json
+import types
+import unittest
+
+from python_utils import messages_to_dicts, parse_options
+
+
+def _msg(**fields):
+    """Fake a proto Message: every unset field is the empty string, as protobuf."""
+    defaults = {
+        "role": "",
+        "content": "",
+        "name": "",
+        "tool_call_id": "",
+        "reasoning_content": "",
+        "tool_calls": "",
+    }
+    defaults.update(fields)
+    return types.SimpleNamespace(**defaults)
+
+
+class TestParseOptions(unittest.TestCase):
+    def test_type_inference(self):
+        opts = parse_options(
+            ["temperature:0.7", "max_tokens:128", "trust:true", "name:hello", "no_colon_skipped"]
+        )
+        self.assertEqual(opts["temperature"], 0.7)
+        self.assertEqual(opts["max_tokens"], 128)
+        self.assertIs(opts["trust"], True)
+        self.assertEqual(opts["name"], "hello")
+        self.assertNotIn("no_colon_skipped", opts)
+
+
+class TestMessagesToDicts(unittest.TestCase):
+    def test_basic_fields(self):
+        out = messages_to_dicts(
+            [
+                _msg(role="user", content="hi"),
+                _msg(role="tool", content="42", tool_call_id="call_1", name="f"),
+            ]
+        )
+        self.assertEqual(out[0], {"role": "user", "content": "hi"})
+        self.assertEqual(out[1]["tool_call_id"], "call_1")
+        self.assertEqual(out[1]["name"], "f")
+
+    def test_tool_call_arguments_string_decoded_to_mapping(self):
+        # OpenAI wire format ships function.arguments as a JSON *string*; chat
+        # templates iterate it as a mapping, so it must come back as a dict.
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [
+                            {
+                                "id": "call_1",
+                                "type": "function",
+                                "function": {
+                                    "name": "get_weather",
+                                    "arguments": '{"location": "Rome"}',
+                                },
+                            }
+                        ]
+                    ),
+                )
+            ]
+        )
+        args = out[0]["tool_calls"][0]["function"]["arguments"]
+        self.assertEqual(args, {"location": "Rome"})
+        self.assertEqual(dict(args.items()), {"location": "Rome"})
+
+    def test_tool_call_arguments_already_mapping_is_idempotent(self):
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [{"function": {"name": "f", "arguments": {"a": 1}}}]
+                    ),
+                )
+            ]
+        )
+        self.assertEqual(out[0]["tool_calls"][0]["function"]["arguments"], {"a": 1})
+
+    def test_tool_call_arguments_invalid_json_left_as_string(self):
+        out = messages_to_dicts(
+            [
+                _msg(
+                    role="assistant",
+                    tool_calls=json.dumps(
+                        [{"function": {"name": "f", "arguments": "not-json"}}]
+                    ),
+                )
+            ]
+        )
+        self.assertEqual(out[0]["tool_calls"][0]["function"]["arguments"], "not-json")
+
+    def test_tool_call_without_function_key(self):
+        out = messages_to_dicts(
+            [_msg(role="assistant", tool_calls=json.dumps([{"id": "call_1"}]))]
+        )
+        self.assertEqual(out[0]["tool_calls"], [{"id": "call_1"}])
+
+    def test_tool_calls_invalid_json_dropped(self):
+        out = messages_to_dicts([_msg(role="assistant", tool_calls="{not json")])
+        self.assertNotIn("tool_calls", out[0])
+
+
+if __name__ == "__main__":
+    unittest.main()

backend/python/vllm/backend.py

@@ -748,7 +748,12 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
         # When (A) native streaming ran cleanly, per-delta yields above already
         # delivered everything — do NOT extract again on the full text or we'd
         # duplicate content/tool_calls into the final chunk.
-        if has_tool_parser and not (native_streaming and not native_streaming_error):
+        # NOTE: `native_streaming` is a capability flag ("streaming parser is
+        # available"), not a state flag ("streaming actually ran"). For
+        # non-streaming requests it is still True but the per-delta loop was
+        # never entered, so we MUST still run extract_tool_calls here. Hence
+        # the explicit `streaming and …` guard on both branches.
+        if has_tool_parser and not (streaming and native_streaming and not native_streaming_error):
             try:
                 tp = tp_instance
                 if tp is None:
@@ -770,7 +775,7 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
                         ))
             except Exception as e:
                 print(f"Tool parser error: {e}", file=sys.stderr)
-        elif native_streaming and not native_streaming_error:
+        elif streaming and native_streaming and not native_streaming_error:
             # Per-delta path already emitted content + tool_calls; the final
             # chat_delta should carry only metadata (token counts, logprobs).
             content = ""

backend/python/vllm/install.sh

@@ -35,6 +35,21 @@ if [ "x${BUILD_PROFILE}" == "xcpu" ]; then
     EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
 fi
 
+# AMD ROCm: vLLM ships prebuilt ROCm wheels, but on a DEDICATED index
+# (https://wheels.vllm.ai/rocm/), NOT PyPI, and ONLY for CPython 3.12. On any
+# other Python the installer silently falls back to the CUDA-only PyPI wheel,
+# which is unusable on an AMD GPU (import fails, so the backend never finds the
+# vllm module). Force Python 3.12 before the venv is created (matches the
+# intel/l4t13 cp312 bump); the hipblas branch below pulls vllm from the ROCm
+# wheel index. unsafe-best-match lets uv consult that index and PyPI together.
+# https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html?device=rocm
+if [ "x${BUILD_TYPE}" == "xhipblas" ]; then
+    PYTHON_VERSION="3.12"
+    PYTHON_PATCH="12"
+    PY_STANDALONE_TAG="20251120"
+    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-best-match"
+fi
+
 # cublas13 pulls the vLLM wheel from a per-tag cu130 index (PyPI's vllm wheel
 # is built against CUDA 12 and won't load on cu130). uv's default per-package
 # first-match strategy would still pick the PyPI wheel, so allow it to consult
@@ -104,7 +119,7 @@ if [ "$(uname -s)" = "Darwin" ]; then
     # can rewrite it. Darwin therefore follows vllm-metal and can lag the Linux
     # vllm pin (requirements-cublas13-after.txt, bumped independently against
     # vllm/vllm) until vllm-metal supports a newer vLLM.
-    VLLM_METAL_VERSION="v0.3.0.dev20260628073537"
+    VLLM_METAL_VERSION="v0.3.0.dev20260701212152"
 
     # The coupled vLLM source version is whatever this vllm-metal release builds
     # against -- it declares it in its own installer as `vllm_v=`. Derive it from
@@ -194,6 +209,22 @@ elif [ "x${BUILD_TYPE}" == "xintel" ]; then
         export CMAKE_PREFIX_PATH="$(python -c 'import site; print(site.getsitepackages()[0])'):${CMAKE_PREFIX_PATH:-}"
         VLLM_TARGET_DEVICE=xpu uv pip install ${EXTRA_PIP_INSTALL_FLAGS:-} --no-deps .
     popd
+# AMD ROCm: install vllm from its dedicated ROCm wheel index instead of the
+# CUDA-only PyPI wheel. installRequirements brings the base ROCm
+# torch/transformers (requirements-hipblas.txt), then we pull vllm (plus the
+# matching ROCm torch, via --upgrade) from wheels.vllm.ai/rocm. This is the
+# method upstream prescribes for AMD; the Python-3.12 pin is set above.
+# There is intentionally no requirements-hipblas-after.txt: a bare `vllm`
+# there would resolve to the CUDA wheel, and installRequirements never loads
+# a ${BUILD_TYPE}-after file for hipblas anyway (BUILD_TYPE == BUILD_PROFILE).
+# https://docs.vllm.ai/en/latest/getting_started/installation/gpu.html?device=rocm
+elif [ "x${BUILD_TYPE}" == "xhipblas" ]; then
+    installRequirements
+
+    # --upgrade reconciles the base ROCm torch to whatever the vllm ROCm wheel
+    # pins; --extra-index-url adds the ROCm wheel repository on top of PyPI.
+    uv pip install ${EXTRA_PIP_INSTALL_FLAGS:-} \
+        --extra-index-url https://wheels.vllm.ai/rocm/ --upgrade vllm
 # FROM_SOURCE=true on a CPU build skips the prebuilt vllm wheel in
 # requirements-cpu-after.txt and compiles vllm locally against the host's
 # actual CPU. Not used by default because it takes ~30-40 minutes, but

backend/python/vllm/requirements-cublas13-after.txt

@@ -3,8 +3,8 @@
 # on a cu130 host. Pull the cu130-flavoured wheel from vLLM's per-tag index
 # instead — the cublas13 case in install.sh adds --index-strategy=unsafe-best-match
 # so uv consults this index alongside PyPI.
---extra-index-url https://wheels.vllm.ai/0.23.0/cu130
+--extra-index-url https://wheels.vllm.ai/0.24.0/cu130
 # VERSION COUPLING: darwin/Apple-Silicon builds use vllm-metal (see install.sh),
 # which pins this exact vLLM version. Bumping vllm here means coordinating with a
 # vllm-metal release that supports the new version, or macOS/Metal builds break.
-vllm==0.23.0
+vllm==0.24.0

backend/python/vllm/requirements-hipblas-after.txt

@@ -1 +0,0 @@
-vllm

backend/rust/kokoros/src/service.rs

@@ -351,6 +351,16 @@ impl Backend for KokorosService {
         Err(Status::unimplemented("Not supported"))
     }
 
+    type AudioTranscriptionLiveStream =
+        ReceiverStream<Result<backend::TranscriptLiveResponse, Status>>;
+
+    async fn audio_transcription_live(
+        &self,
+        _: Request<tonic::Streaming<backend::TranscriptLiveRequest>>,
+    ) -> Result<Response<Self::AudioTranscriptionLiveStream>, Status> {
+        Err(Status::unimplemented("Not supported"))
+    }
+
     async fn diarize(
         &self,
         _: Request<backend::DiarizeRequest>,

cmd/launcher/internal/launcher.go

@@ -207,12 +207,20 @@ func (l *Launcher) StartLocalAI() error {
 	}
 
 	// Build command arguments
+	dataPath := l.GetDataPath()
 	args := []string{
 		"run",
 		"--models-path", l.config.ModelsPath,
 		"--backends-path", l.config.BackendsPath,
 		"--address", l.config.Address,
 		"--log-level", l.config.LogLevel,
+		// Keep persistent data and dynamic config under the launcher's data
+		// directory (~/.localai) rather than letting the server resolve them
+		// to ${basepath}/{data,configuration}. ${basepath} expands to the
+		// launcher process's CWD (often the user's home root), which puts
+		// ~/data and ~/configuration outside ~/.localai. See #10610.
+		"--data-path", filepath.Join(dataPath, "data"),
+		"--localai-config-dir", filepath.Join(dataPath, "configuration"),
 	}
 
 	l.localaiCmd = exec.CommandContext(l.ctx, binaryPath, args...)

core/application/distributed.go

@@ -356,6 +356,12 @@ func initDistributed(cfg *config.ApplicationConfig, authDB *gorm.DB, configLoade
 		PrefixConfig:     prefixCfg,
 		Pressure:         pressure,
 		SharedModels:     cfg.Distributed.SharedModels,
+		// Cap how long a cold load may hold the per-model advisory lock: the
+		// configured backend.install deadline plus a margin for file staging and
+		// the remote LoadModel. Derived from the install timeout so raising it
+		// (for slow links pulling multi-GB images) widens the ceiling too,
+		// instead of letting the static default cut a legitimately slow load.
+		ModelLoadCeiling: cfg.Distributed.BackendInstallTimeoutOrDefault() + 10*time.Minute,
 	})
 
 	// Wire staging-progress broadcasting so file-staging shows up on every

core/application/startup.go

@@ -369,7 +369,7 @@ func New(opts ...config.AppOption) (*Application, error) {
 	}
 
 	for _, backend := range options.ExternalBackends {
-		if err := galleryop.InstallExternalBackend(options.Context, options.BackendGalleries, options.SystemState, application.ModelLoader(), nil, backend, "", "", options.RequireBackendIntegrity); err != nil {
+		if err := galleryop.InstallExternalBackend(options.Context, options.BackendGalleries, options.SystemState, application.ModelLoader(), nil, backend, "", "", false, options.RequireBackendIntegrity); err != nil {
 			xlog.Error("error installing external backend", "error", err)
 		}
 	}

core/cli/backends.go

@@ -127,7 +127,7 @@ func (bi *BackendsInstall) Run(ctx *cliContext.Context) error {
 	}
 
 	modelLoader := model.NewModelLoader(systemState)
-	err = galleryop.InstallExternalBackend(context.Background(), galleries, systemState, modelLoader, progressCallback, bi.BackendArgs, bi.Name, bi.Alias, bi.RequireBackendIntegrity)
+	err = galleryop.InstallExternalBackend(context.Background(), galleries, systemState, modelLoader, progressCallback, bi.BackendArgs, bi.Name, bi.Alias, false, bi.RequireBackendIntegrity)
 	if err != nil {
 		return err
 	}

core/http/endpoints/localai/backend.go

@@ -65,6 +65,10 @@ type BackendEndpointService struct {
 
 type GalleryBackend struct {
 	ID string `json:"id"`
+	// Force reinstalls the backend even when it is already installed and
+	// runnable. Off by default so apply stays idempotent for supervising
+	// apps that ensure their backend on every boot.
+	Force bool `json:"force"`
 }
 
 func CreateBackendEndpointService(galleries []config.Gallery, systemState *system.SystemState, backendApplier *galleryop.GalleryService, upgradeChecker UpgradeInfoProvider) BackendEndpointService {
@@ -103,7 +107,9 @@ func (mgs *BackendEndpointService) GetAllStatusEndpoint() echo.HandlerFunc {
 	}
 }
 
-// ApplyBackendEndpoint installs a new backend to a LocalAI instance
+// ApplyBackendEndpoint installs a new backend to a LocalAI instance. The op is
+// idempotent: an already-installed, runnable backend is left alone unless the
+// request sets "force": true (explicit reinstall).
 // @Summary Install backends to LocalAI.
 // @Tags backends
 // @Param request body GalleryBackend true "query params"
@@ -137,6 +143,7 @@ func (mgs *BackendEndpointService) ApplyBackendEndpoint(systemState *system.Syst
 			ID:                 uuid.String(),
 			GalleryElementName: input.ID,
 			Galleries:          mgs.galleries,
+			Force:              input.Force,
 		}
 
 		return c.JSON(200, schema.BackendResponse{ID: uuid.String(), StatusURL: fmt.Sprintf("%sbackends/jobs/%s", middleware.BaseURL(c), uuid.String())})

core/http/endpoints/localai/backend_apply_test.go

@@ -0,0 +1,87 @@
+package localai_test
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"os"
+	"strings"
+
+	"github.com/labstack/echo/v4"
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/gallery"
+	. "github.com/mudler/LocalAI/core/http/endpoints/localai"
+	"github.com/mudler/LocalAI/core/services/galleryop"
+	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/mudler/LocalAI/pkg/system"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+// POST /backends/apply must be idempotent by default: supervising apps call it
+// on every boot to ensure a backend exists, and forcing a reinstall there
+// re-downloads the whole artifact each time. Reinstall stays available behind
+// the explicit force flag.
+var _ = Describe("POST /backends/apply force plumbing", func() {
+	var (
+		app     *echo.Echo
+		gs      *galleryop.GalleryService
+		tmpDir  string
+		received chan galleryop.ManagementOp[gallery.GalleryBackend, any]
+	)
+
+	BeforeEach(func() {
+		app = echo.New()
+
+		var err error
+		tmpDir, err = os.MkdirTemp("", "backends-apply-test-*")
+		Expect(err).NotTo(HaveOccurred())
+
+		systemState, err := system.GetSystemState(system.WithBackendPath(tmpDir))
+		Expect(err).NotTo(HaveOccurred())
+		appConfig := &config.ApplicationConfig{SystemState: systemState}
+
+		// The service is deliberately not started: the test reads the op off
+		// the (unbuffered) channel itself.
+		gs = galleryop.NewGalleryService(appConfig, model.NewModelLoader(systemState))
+		svc := CreateBackendEndpointService(nil, systemState, gs, nil)
+		app.POST("/backends/apply", svc.ApplyBackendEndpoint(systemState))
+
+		received = make(chan galleryop.ManagementOp[gallery.GalleryBackend, any], 1)
+		go func() {
+			op := <-gs.BackendGalleryChannel
+			received <- op
+		}()
+	})
+
+	AfterEach(func() {
+		Expect(os.RemoveAll(tmpDir)).To(Succeed())
+	})
+
+	apply := func(body string) *httptest.ResponseRecorder {
+		req := httptest.NewRequest(http.MethodPost, "/backends/apply", strings.NewReader(body))
+		req.Header.Set(echo.HeaderContentType, echo.MIMEApplicationJSON)
+		rec := httptest.NewRecorder()
+		app.ServeHTTP(rec, req)
+		return rec
+	}
+
+	It("enqueues a non-forced op by default", func() {
+		rec := apply(`{"id":"llama-cpp"}`)
+		Expect(rec.Code).To(Equal(http.StatusOK))
+
+		var op galleryop.ManagementOp[gallery.GalleryBackend, any]
+		Eventually(received).Should(Receive(&op))
+		Expect(op.GalleryElementName).To(Equal("llama-cpp"))
+		Expect(op.Force).To(BeFalse())
+	})
+
+	It("enqueues a forced op when the request sets force", func() {
+		rec := apply(`{"id":"llama-cpp","force":true}`)
+		Expect(rec.Code).To(Equal(http.StatusOK))
+
+		var op galleryop.ManagementOp[gallery.GalleryBackend, any]
+		Eventually(received).Should(Receive(&op))
+		Expect(op.GalleryElementName).To(Equal("llama-cpp"))
+		Expect(op.Force).To(BeTrue())
+	})
+})

core/http/react-ui/e2e/forking-chat.spec.js

@@ -0,0 +1,133 @@
+import { test, expect } from './coverage-fixtures.js'
+
+// Seeds two-message chat into localStorage so we don't need a live model.
+async function seedChat(page, history) {
+  await page.addInitScript((h) => {
+    const chat = {
+      id: 'seed1', name: 'Seeded Chat', model: 'test-model',
+      history: h, systemPrompt: '', mcpMode: false, mcpServers: [],
+      clientMCPServers: [], temperature: null, topP: null, topK: null,
+      tokenUsage: { prompt: 0, completion: 0, total: 0 },
+      contextSize: null, createdAt: Date.now(), updatedAt: Date.now(),
+    }
+    localStorage.setItem('localai_chats_data', JSON.stringify({
+      chats: [chat], activeChatId: 'seed1', lastSaved: Date.now(),
+    }))
+  }, history)
+}
+
+async function mockModels(page) {
+  await page.route('**/api/models/capabilities', (route) => route.fulfill({
+    contentType: 'application/json',
+    body: JSON.stringify({ data: [{ id: 'test-model', capabilities: ['FLAG_CHAT'] }] }),
+  }))
+  await page.route('**/api/operations', (route) => route.fulfill({
+    contentType: 'application/json', body: JSON.stringify({ operations: [] }),
+  }))
+}
+
+const TWO_TURNS = [
+  { role: 'user', content: 'first question' },
+  { role: 'assistant', content: 'first answer' },
+  { role: 'user', content: 'second question' },
+  { role: 'assistant', content: 'second answer' },
+]
+
+test('duplicate creates an independent copy and switches to it', async ({ page }) => {
+  await mockModels(page)
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  // Open the chats menu (Ctrl/Cmd+K) and duplicate the seeded chat.
+  // Wait for the menu trigger to mount so its global keydown listener is armed
+  // before we dispatch the shortcut.
+  await page.getByTitle('Conversations (Ctrl/Cmd+K)').waitFor()
+  await page.keyboard.press('Control+k')
+  await page.getByTitle('Duplicate chat').first().click()
+
+  // A new active chat named "Seeded Chat (fork)" with the same 4 messages.
+  await expect(page.locator('.chat-header-title')).toHaveText('Seeded Chat (fork)')
+  await expect(page.locator('.chat-message-user')).toHaveCount(2)
+  await expect(page.locator('.chat-message-assistant')).toHaveCount(2)
+})
+
+async function mockCompletion(page, replyText) {
+  await page.route('**/v1/chat/completions', (route) => {
+    const sse =
+      `data: ${JSON.stringify({ choices: [{ delta: { content: replyText } }] })}\n\n` +
+      `data: ${JSON.stringify({ choices: [{ delta: {}, finish_reason: 'stop' }], usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 } })}\n\n` +
+      `data: [DONE]\n\n`
+    route.fulfill({ status: 200, contentType: 'text/event-stream', body: sse })
+  })
+}
+
+test('retry regenerates the first answer and drops the later turn', async ({ page }) => {
+  await mockModels(page)
+  // Capture the outbound request body so we can assert the model receives the
+  // truncated history (not the stale downstream turns).
+  let sentMessages = null
+  await page.route('**/v1/chat/completions', (route) => {
+    sentMessages = route.request().postDataJSON()?.messages || []
+    const sse =
+      `data: ${JSON.stringify({ choices: [{ delta: { content: 'REGENERATED first answer' } }] })}\n\n` +
+      `data: ${JSON.stringify({ choices: [{ delta: {}, finish_reason: 'stop' }], usage: { prompt_tokens: 1, completion_tokens: 1, total_tokens: 2 } })}\n\n` +
+      `data: [DONE]\n\n`
+    route.fulfill({ status: 200, contentType: 'text/event-stream', body: sse })
+  })
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  // Hover the FIRST assistant message and click its retry button.
+  const firstAssistant = page.locator('.chat-message-assistant').first()
+  await firstAssistant.hover()
+  await firstAssistant.getByTitle('Regenerate').click()
+
+  // History is truncated to the first user turn, then the new answer streams in;
+  // the second Q/A turn is gone.
+  await expect(page.locator('.chat-message-assistant')).toContainText(['REGENERATED first answer'])
+  await expect(page.locator('.chat-message-user')).toHaveCount(1)
+  await expect(page.locator('.chat-message-assistant')).toHaveCount(1)
+
+  // The OUTBOUND payload must also be truncated: the resent user turn is present,
+  // but the downstream turn and the stale first answer must be gone.
+  const contents = (sentMessages || []).map(m =>
+    typeof m.content === 'string' ? m.content : JSON.stringify(m.content)
+  )
+  expect(contents.join('\n')).toContain('first question')
+  expect(contents.join('\n')).not.toContain('second question')
+  expect(contents.join('\n')).not.toContain('first answer')
+})
+
+test('copy chat puts the whole conversation on the clipboard', async ({ page, context }) => {
+  await context.grantPermissions(['clipboard-read', 'clipboard-write'])
+  await mockModels(page)
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  // Wait for the menu trigger to mount so its global keydown listener is armed
+  // before we dispatch the shortcut (same mount-race guard as the duplicate test).
+  await page.getByTitle('Conversations (Ctrl/Cmd+K)').waitFor()
+  await page.keyboard.press('Control+k')
+  await page.getByTitle('Copy chat').first().click()
+
+  const clip = await page.evaluate(() => navigator.clipboard.readText())
+  expect(clip).toContain('# Seeded Chat')
+  expect(clip).toContain('first answer')
+  expect(clip).toContain('second answer')
+})
+
+test('branch from the first answer forks history up to that point', async ({ page }) => {
+  await mockModels(page)
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  const firstAssistant = page.locator('.chat-message-assistant').first()
+  await firstAssistant.hover()
+  await firstAssistant.getByTitle('Branch from here').click()
+
+  // New active chat "Seeded Chat (fork)" contains only the first Q/A turn.
+  await expect(page.locator('.chat-header-title')).toHaveText('Seeded Chat (fork)')
+  await expect(page.locator('.chat-message-user')).toHaveCount(1)
+  await expect(page.locator('.chat-message-assistant')).toHaveCount(1)
+  await expect(page.locator('.chat-message-assistant')).toContainText(['first answer'])
+})

core/http/react-ui/public/locales/en/chat.json

@@ -72,6 +72,7 @@
   "actions": {
     "copy": "Copy",
     "regenerate": "Regenerate",
+    "branch": "Branch from here",
     "jumpToLatest": "Jump to latest"
   },
   "streaming": {
@@ -100,7 +101,9 @@
   "toasts": {
     "selectModel": "Please select a model",
     "copied": "Copied to clipboard",
-    "copyFailed": "Could not copy to clipboard"
+    "copyFailed": "Could not copy to clipboard",
+    "chatCopied": "Chat copied to clipboard",
+    "forked": "Created a new chat"
   },
   "menu": {
     "trigger": "Chats",
@@ -110,6 +113,8 @@
     "noMatch": "No conversations match your search",
     "noConversations": "No conversations yet",
     "rename": "Rename",
+    "duplicate": "Duplicate chat",
+    "copyChat": "Copy chat",
     "exportMarkdown": "Export as Markdown",
     "deleteChat": "Delete chat",
     "newChat": "New chat",

core/http/react-ui/src/components/ChatsMenu.jsx

@@ -24,6 +24,8 @@ const ChatsMenu = forwardRef(function ChatsMenu({
   onDeleteAll,
   onRename,
   onExport,
+  onCopyChat,
+  onDuplicate,
 }, ref) {
   const { t } = useTranslation('chat')
   const [open, setOpen] = useState(false)
@@ -230,6 +232,24 @@ const ChatsMenu = forwardRef(function ChatsMenu({
                   >
                     <i className="fas fa-pen" />
                   </button>
+                  {onDuplicate && (
+                    <button
+                      type="button"
+                      onClick={(e) => { e.stopPropagation(); onDuplicate(chat); setOpen(false) }}
+                      title={t('menu.duplicate')}
+                    >
+                      <i className="fas fa-clone" />
+                    </button>
+                  )}
+                  {(chat.history?.length || 0) > 0 && onCopyChat && (
+                    <button
+                      type="button"
+                      onClick={(e) => { e.stopPropagation(); onCopyChat(chat) }}
+                      title={t('menu.copyChat')}
+                    >
+                      <i className="fas fa-clipboard" />
+                    </button>
+                  )}
                   {(chat.history?.length || 0) > 0 && onExport && (
                     <button
                       type="button"

core/http/react-ui/src/hooks/useChat.js

@@ -141,6 +141,24 @@ export function useChat(initialModel = '') {
     return chat
   }, [])
 
+  const forkChat = useCallback((chatId, uptoIndex) => {
+    const src = chats.find(c => c.id === chatId)
+    if (!src) return null
+    const end = typeof uptoIndex === 'number' ? uptoIndex : src.history.length
+    const forked = {
+      ...src,
+      id: generateId(),
+      name: `${src.name} (fork)`,
+      history: structuredClone(src.history.slice(0, end)),
+      tokenUsage: { prompt: 0, completion: 0, total: 0 },
+      createdAt: Date.now(),
+      updatedAt: Date.now(),
+    }
+    setChats(prev => [forked, ...prev])
+    setActiveChatId(forked.id)
+    return forked
+  }, [chats])
+
   const switchChat = useCallback((chatId) => {
     setActiveChatId(chatId)
     setStreamingContent('')
@@ -260,8 +278,12 @@ export function useChat(initialModel = '') {
     if (chat?.systemPrompt) {
       messages.push({ role: 'system', content: chat.systemPrompt })
     }
-    // Filter out thinking/reasoning/tool_call/tool_result messages
-    const historyForApi = (chat?.history || []).filter(m =>
+    // Filter out thinking/reasoning/tool_call/tool_result messages.
+    // options.baseHistory lets callers (e.g. mid-conversation retry) pass the
+    // intended truncated history synchronously; the closure `chat` still holds
+    // the stale pre-truncation state because setChats only schedules an update.
+    const baseHistory = options.baseHistory || chat?.history || []
+    const historyForApi = baseHistory.filter(m =>
       m.role !== 'thinking' && m.role !== 'reasoning' && m.role !== 'tool_call' && m.role !== 'tool_result'
     )
     messages.push(...historyForApi, { role: 'user', content: messageContent })
@@ -793,6 +815,7 @@ export function useChat(initialModel = '') {
     tokensPerSecond,
     maxTokensPerSecond,
     addChat,
+    forkChat,
     switchChat,
     deleteChat,
     deleteAllChats,

core/http/react-ui/src/pages/Chat.jsx

@@ -33,7 +33,7 @@ function getLastMessagePreview(chat) {
   return ''
 }
 
-function exportChatAsMarkdown(chat) {
+function serializeChatAsMarkdown(chat) {
   let md = `# ${chat.name}\n\n`
   md += `Model: ${chat.model || 'Unknown'}\n`
   md += `Date: ${new Date(chat.createdAt).toLocaleString()}\n\n---\n\n`
@@ -47,7 +47,11 @@ function exportChatAsMarkdown(chat) {
       md += `<details><summary>Thinking</summary>\n\n${msg.content}\n\n</details>\n\n`
     }
   }
-  const blob = new Blob([md], { type: 'text/markdown' })
+  return md
+}
+
+function downloadChatAsMarkdown(chat) {
+  const blob = new Blob([serializeChatAsMarkdown(chat)], { type: 'text/markdown' })
   const url = URL.createObjectURL(blob)
   const a = document.createElement('a')
   a.href = url
@@ -294,7 +298,7 @@ export default function Chat() {
   const {
     chats, activeChat, activeChatId, isStreaming, streamingChatId, streamingContent,
     streamingReasoning, streamingToolCalls, tokensPerSecond, maxTokensPerSecond,
-    addChat, switchChat, deleteChat, deleteAllChats, renameChat, updateChatSettings,
+    addChat, forkChat, switchChat, deleteChat, deleteAllChats, renameChat, updateChatSettings,
     sendMessage, stopGeneration, clearHistory, getContextUsagePercent, addMessage,
   } = useChat(urlModel || '')
 
@@ -795,34 +799,27 @@ export default function Chat() {
     await sendMessage(msg, files, mcpOptions)
   }, [input, files, activeChat, sendMessage, addToast, getToolsForLLM, isClientTool, executeTool, hasAppUI, getAppResource, getToolDefinition])
 
-  const handleRegenerate = useCallback(async () => {
+  const handleRegenerate = useCallback(async (targetIndex) => {
     if (!activeChat || isStreaming) return
     const history = activeChat.history
-    let lastUserMsg = null
-    let lastUserFiles = null
-    for (let i = history.length - 1; i >= 0; i--) {
-      if (history[i].role === 'user') {
-        lastUserMsg = typeof history[i].content === 'string' ? history[i].content : history[i].content?.[0]?.text || ''
-        lastUserFiles = history[i].files || []
-        break
-      }
+    const end = typeof targetIndex === 'number' ? targetIndex : history.length
+    // Nearest user message at or before the target answer.
+    let userIdx = -1
+    for (let i = Math.min(end, history.length) - 1; i >= 0; i--) {
+      if (history[i].role === 'user') { userIdx = i; break }
     }
-    if (!lastUserMsg) return
-
-    // Remove everything after and including the last user message
-    const newHistory = []
-    let foundLastUser = false
-    for (let i = history.length - 1; i >= 0; i--) {
-      if (!foundLastUser && history[i].role === 'user') {
-        foundLastUser = true
-        continue
-      }
-      if (foundLastUser) {
-        newHistory.unshift(history[i])
-      }
-    }
-    updateChatSettings(activeChat.id, { history: newHistory })
-    await sendMessage(lastUserMsg, lastUserFiles)
+    if (userIdx === -1) return
+    const userMsg = typeof history[userIdx].content === 'string'
+      ? history[userIdx].content
+      : history[userIdx].content?.[0]?.text || ''
+    const userFiles = history[userIdx].files || []
+    // Drop the user turn and everything after it; sendMessage re-appends it.
+    // Thread the truncated history through explicitly: updateChatSettings only
+    // schedules a state update, so sendMessage's closure would otherwise read
+    // the stale pre-truncation history for the outbound API payload.
+    const baseHistory = history.slice(0, userIdx)
+    updateChatSettings(activeChat.id, { history: baseHistory })
+    await sendMessage(userMsg, userFiles, { baseHistory })
   }, [activeChat, isStreaming, sendMessage, updateChatSettings])
 
   const handleKeyDown = (e) => {
@@ -852,6 +849,11 @@ export default function Chat() {
     }
   }
 
+  const copyChatAsMarkdown = async (chat) => {
+    const ok = await copyToClipboard(serializeChatAsMarkdown(chat))
+    addToast(ok ? t('toasts.chatCopied') : t('toasts.copyFailed'), ok ? 'success' : 'error', ok ? 2000 : 3000)
+  }
+
   const contextPercent = getContextUsagePercent()
 
   // Recent chats for the empty state — exclude the current chat and any
@@ -892,7 +894,9 @@ export default function Chat() {
             onDelete={deleteChat}
             onDeleteAll={promptDeleteAll}
             onRename={renameChat}
-            onExport={(chat) => exportChatAsMarkdown(chat)}
+            onExport={(chat) => downloadChatAsMarkdown(chat)}
+            onCopyChat={(chat) => copyChatAsMarkdown(chat)}
+            onDuplicate={(chat) => { if (forkChat(chat.id)) addToast(t('toasts.forked'), 'success', 2000) }}
           />
           {activeChat.localaiAssistant && (
             <span
@@ -1184,11 +1188,19 @@ export default function Chat() {
                       <button onClick={() => copyMessage(msg.content)} title={t('actions.copy')}>
                         <i className="fas fa-copy" />
                       </button>
-                      {msg.role === 'assistant' && i === activeChat.history.length - 1 && !isStreaming && (
-                        <button onClick={handleRegenerate} title={t('actions.regenerate')}>
+                      {msg.role === 'assistant' && !isStreaming && (
+                        <button onClick={() => handleRegenerate(i)} title={t('actions.regenerate')}>
                           <i className="fas fa-rotate" />
                         </button>
                       )}
+                      {msg.role === 'assistant' && !isStreaming && (
+                        <button
+                          onClick={() => { forkChat(activeChat.id, i + 1); addToast(t('toasts.forked'), 'success', 2000) }}
+                          title={t('actions.branch')}
+                        >
+                          <i className="fas fa-code-branch" />
+                        </button>
+                      )}
                     </div>
                   </div>
                 </div>

core/http/routes/ui_api.go

@@ -1243,6 +1243,9 @@ func RegisterUIAPIRoutes(app *echo.Echo, cl *config.ModelConfigLoader, ml *model
 			Galleries:          appConfig.BackendGalleries,
 			Context:            ctx,
 			CancelFunc:         cancelFunc,
+			// The React UI's "Reinstall backend" action reuses this route, so
+			// the op must force even when the backend is already installed.
+			Force: true,
 		}
 		// Store cancellation function immediately so queued operations can be cancelled
 		galleryService.StoreCancellation(uid, cancelFunc)

core/services/advisorylock/advisorylock.go

@@ -6,10 +6,39 @@ import (
 	"hash/fnv"
 	"strings"
 	"sync"
+	"time"
 
 	"gorm.io/gorm"
 )
 
+// advisoryLockWaitBackstop bounds, server-side, how long we will wait to
+// acquire a blocking advisory lock when the caller's context carries no
+// deadline (e.g. a startup schema migration using context.Background()). It
+// only exists so such a caller cannot hang forever behind a holder whose
+// session never releases the lock; it is far longer than any legitimate
+// guarded section. A var (not const) so tests can shrink it.
+var advisoryLockWaitBackstop = 30 * time.Minute
+
+// advisoryLockTimeoutMargin is added to a context's remaining budget when
+// deriving the server-side lock_timeout, so the Go context's own (cleaner)
+// cancellation fires first and the server bound is only ever a backstop.
+const advisoryLockTimeoutMargin = 30 * time.Second
+
+// advisoryLockWaitBudget returns the server-side lock_timeout to use for a
+// blocking acquire: the caller context's remaining time plus a margin (so the
+// Go context still governs), or the backstop when the context has no deadline.
+// Never returns zero - "wait forever" must not be possible.
+func advisoryLockWaitBudget(ctx context.Context) time.Duration {
+	if dl, ok := ctx.Deadline(); ok {
+		budget := time.Until(dl) + advisoryLockTimeoutMargin
+		if budget < time.Second {
+			budget = time.Second
+		}
+		return budget
+	}
+	return advisoryLockWaitBackstop
+}
+
 // localLocks holds one buffered channel (capacity 1) per lock key, used as an
 // in-process mutex for non-PostgreSQL dialects (SQLite). A SQLite auth DB is
 // effectively single-process, so serializing guarded sections within this
@@ -130,6 +159,27 @@ func WithLockCtx(ctx context.Context, db *gorm.DB, key int64, fn func() error) e
 	}
 	defer conn.Close()
 
+	// Override any deployment-wide lock_timeout on this dedicated connection.
+	// Operators commonly set a short global lock_timeout (on the role or
+	// database) to bound ordinary row-lock waits. Applied to the blocking
+	// pg_advisory_lock below, it aborts the wait with SQLSTATE 55P03 and turns
+	// LocalAI's intentional cross-replica "wait your turn, then re-check"
+	// coordination into a hard error for the caller (e.g. a chat request that
+	// just wanted to reuse a model another replica is loading).
+	//
+	// We do NOT disable it outright (lock_timeout = 0 would wait forever, which
+	// is unsafe for the schema-migration callers that pass context.Background()).
+	// Instead we set a bound derived from the caller's context: its remaining
+	// budget plus a margin so the Go context's cancellation wins with a clean
+	// error, or a finite backstop when the context has no deadline.
+	waitBudget := advisoryLockWaitBudget(ctx)
+	if _, err := conn.ExecContext(ctx,
+		fmt.Sprintf("SET lock_timeout = %d", waitBudget.Milliseconds())); err != nil {
+		return fmt.Errorf("advisorylock: setting lock_timeout: %w", err)
+	}
+	// Restore the session default before this pooled connection is reused.
+	defer func() { _, _ = conn.ExecContext(context.Background(), "RESET lock_timeout") }()
+
 	if _, err := conn.ExecContext(ctx, "SELECT pg_advisory_lock($1)", key); err != nil {
 		return fmt.Errorf("advisorylock: acquiring lock %d: %w", key, err)
 	}

core/services/advisorylock/advisorylock_test.go

@@ -158,6 +158,87 @@ var _ = Describe("AdvisoryLock", func() {
 			Expect(err).To(HaveOccurred())
 		})
 
+		It("waits out a short server-side lock_timeout instead of failing with 55P03", func() {
+			const lockKey int64 = 703
+
+			// Reproduce the production deployment that triggered this: a short
+			// global lock_timeout set on the database. Without the fix, a waiter
+			// blocked on pg_advisory_lock() is aborted by the server after this
+			// window and surfaces SQLSTATE 55P03 ("canceling statement due to
+			// lock timeout") to the caller instead of waiting for its turn.
+			Expect(db.Exec("ALTER DATABASE testdb SET lock_timeout = '300ms'").Error).ToNot(HaveOccurred())
+			sqlDB, err := db.DB()
+			Expect(err).ToNot(HaveOccurred())
+			// Drop pooled connections so subsequent ones reconnect and inherit
+			// the new database-level lock_timeout default.
+			sqlDB.SetMaxIdleConns(0)
+
+			holding := make(chan struct{})
+			released := make(chan struct{})
+			go func() {
+				defer GinkgoRecover()
+				herr := WithLockCtx(context.Background(), db, lockKey, func() error {
+					close(holding)
+					// Hold well past the 300ms server lock_timeout.
+					time.Sleep(1 * time.Second)
+					return nil
+				})
+				Expect(herr).ToNot(HaveOccurred())
+				close(released)
+			}()
+
+			<-holding // ensure the holder owns the lock before we contend
+
+			ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+			defer cancel()
+			executed := false
+			start := time.Now()
+			werr := WithLockCtx(ctx, db, lockKey, func() error {
+				executed = true
+				return nil
+			})
+			Expect(werr).ToNot(HaveOccurred(),
+				"waiter should wait out the in-progress hold, not fail with lock_timeout (55P03)")
+			Expect(executed).To(BeTrue())
+			Expect(time.Since(start)).To(BeNumerically(">=", 400*time.Millisecond),
+				"waiter should have actually waited for the holder to release")
+			<-released
+		})
+
+		It("bounds a deadline-less waiter with the backstop instead of waiting forever", func() {
+			const lockKey int64 = 704
+
+			// A caller with no context deadline (e.g. startup schema migration
+			// passing context.Background()) must not hang forever if the holder
+			// never releases. Shrink the backstop so the test is fast.
+			origBackstop := advisoryLockWaitBackstop
+			advisoryLockWaitBackstop = 500 * time.Millisecond
+			DeferCleanup(func() { advisoryLockWaitBackstop = origBackstop })
+
+			holding := make(chan struct{})
+			release := make(chan struct{})
+			go func() {
+				defer GinkgoRecover()
+				_ = WithLockCtx(context.Background(), db, lockKey, func() error {
+					close(holding)
+					<-release // hold until the test releases us
+					return nil
+				})
+			}()
+			defer close(release)
+
+			<-holding
+
+			start := time.Now()
+			err := WithLockCtx(context.Background(), db, lockKey, func() error {
+				Fail("waiter should not have acquired the still-held lock")
+				return nil
+			})
+			Expect(err).To(HaveOccurred(), "deadline-less waiter should give up at the backstop, not hang")
+			Expect(time.Since(start)).To(BeNumerically("<", 5*time.Second),
+				"backstop must cap the wait well under the test timeout")
+		})
+
 		It("serializes concurrent WithLockCtx on same key", func() {
 			const lockKey int64 = 702
 

core/services/galleryop/backend_force_test.go

@@ -0,0 +1,114 @@
+package galleryop_test
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/gallery"
+	"github.com/mudler/LocalAI/core/services/galleryop"
+	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/mudler/LocalAI/pkg/system"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+	"gopkg.in/yaml.v3"
+)
+
+// The install op must be idempotent unless Force is set: API clients call
+// POST /backends/apply on every boot to make sure the backend exists, and an
+// unconditional force here re-downloads the whole backend artifact each time.
+// Reinstall is an explicit, opted-in action.
+var _ = Describe("LocalBackendManager force semantics", func() {
+	var (
+		backendsDir string
+		srcDir      string
+		mgr         *galleryop.LocalBackendManager
+		systemState *system.SystemState
+		ml          *model.ModelLoader
+	)
+
+	const installedRunSh = "#!/bin/sh\necho installed\n"
+	const galleryRunSh = "#!/bin/sh\necho from-gallery\n"
+
+	installedRunShPath := func() string {
+		return filepath.Join(backendsDir, "test-backend", "run.sh")
+	}
+
+	BeforeEach(func() {
+		var err error
+		backendsDir, err = os.MkdirTemp("", "force-backends-*")
+		Expect(err).NotTo(HaveOccurred())
+		srcDir, err = os.MkdirTemp("", "force-src-*")
+		Expect(err).NotTo(HaveOccurred())
+
+		// The gallery serves test-backend from a plain directory (offline).
+		// The gallery yaml itself must live under the backends path: file://
+		// galleries outside the trusted root are rejected by the downloader.
+		Expect(os.WriteFile(filepath.Join(srcDir, "run.sh"), []byte(galleryRunSh), 0o755)).To(Succeed())
+		entries := []map[string]any{{"name": "test-backend", "uri": srcDir}}
+		data, err := yaml.Marshal(entries)
+		Expect(err).NotTo(HaveOccurred())
+		galleryYAML := filepath.Join(backendsDir, "gallery.yaml")
+		Expect(os.WriteFile(galleryYAML, data, 0o644)).To(Succeed())
+
+		// test-backend is already installed, with content that differs from
+		// the gallery's so a reinstall is observable.
+		Expect(os.MkdirAll(filepath.Join(backendsDir, "test-backend"), 0o755)).To(Succeed())
+		Expect(os.WriteFile(installedRunShPath(), []byte(installedRunSh), 0o755)).To(Succeed())
+
+		systemState, err = system.GetSystemState(system.WithBackendPath(backendsDir))
+		Expect(err).NotTo(HaveOccurred())
+		appConfig := &config.ApplicationConfig{
+			SystemState:      systemState,
+			BackendGalleries: []config.Gallery{{Name: "test", URL: "file://" + galleryYAML}},
+		}
+		ml = model.NewModelLoader(systemState)
+		mgr = galleryop.NewLocalBackendManager(appConfig, ml)
+	})
+
+	AfterEach(func() {
+		Expect(os.RemoveAll(backendsDir)).To(Succeed())
+		Expect(os.RemoveAll(srcDir)).To(Succeed())
+	})
+
+	It("skips an already-installed backend when Force is not set", func() {
+		op := &galleryop.ManagementOp[gallery.GalleryBackend, any]{
+			ID:                 "op-1",
+			GalleryElementName: "test-backend",
+		}
+		Expect(mgr.InstallBackend(context.Background(), op, nil)).To(Succeed())
+
+		content, err := os.ReadFile(installedRunShPath())
+		Expect(err).NotTo(HaveOccurred())
+		Expect(string(content)).To(Equal(installedRunSh), "install without Force must not overwrite an installed backend")
+	})
+
+	It("reinstalls an already-installed backend when Force is set", func() {
+		op := &galleryop.ManagementOp[gallery.GalleryBackend, any]{
+			ID:                 "op-2",
+			GalleryElementName: "test-backend",
+			Force:              true,
+		}
+		Expect(mgr.InstallBackend(context.Background(), op, nil)).To(Succeed())
+
+		content, err := os.ReadFile(installedRunShPath())
+		Expect(err).NotTo(HaveOccurred())
+		Expect(string(content)).To(Equal(galleryRunSh), "install with Force must overwrite the installed backend")
+	})
+
+	// The LOCALAI_EXTERNAL_BACKENDS boot loop goes through
+	// InstallExternalBackend's gallery-name path on EVERY startup; it must not
+	// force, or each boot re-downloads every listed backend.
+	It("skips an already-installed backend on the non-forced external gallery-name path", func() {
+		err := galleryop.InstallExternalBackend(context.Background(),
+			[]config.Gallery{{Name: "test", URL: "file://" + filepath.Join(backendsDir, "gallery.yaml")}},
+			systemState, ml, nil, "test-backend", "", "", false, false)
+		Expect(err).NotTo(HaveOccurred())
+
+		content, err := os.ReadFile(installedRunShPath())
+		Expect(err).NotTo(HaveOccurred())
+		Expect(string(content)).To(Equal(installedRunSh), "non-forced external install must not overwrite an installed backend")
+	})
+})

core/services/galleryop/backends.go

@@ -144,7 +144,12 @@ func (g *GalleryService) backendHandler(op *ManagementOp[gallery.GalleryBackend,
 // InstallExternalBackend installs a backend from an external source (OCI image, URL, or path).
 // This method contains the logic to detect the input type and call the appropriate installation function.
 // It can be used by both CLI and Web UI for installing backends from external sources.
-func InstallExternalBackend(ctx context.Context, galleries []config.Gallery, systemState *system.SystemState, modelLoader *model.ModelLoader, downloadStatus func(string, string, string, float64), backend, name, alias string, requireIntegrity bool) error {
+//
+// force applies only to the gallery-name fallback: a URI install (dir/OCI/file)
+// always writes, but a bare gallery name is an "ensure installed" — the
+// LOCALAI_EXTERNAL_BACKENDS boot loop runs it on every start and must not
+// re-download an installed, runnable backend.
+func InstallExternalBackend(ctx context.Context, galleries []config.Gallery, systemState *system.SystemState, modelLoader *model.ModelLoader, downloadStatus func(string, string, string, float64), backend, name, alias string, force, requireIntegrity bool) error {
 	uri := downloader.URI(backend)
 	switch {
 	case uri.LooksLikeDir():
@@ -202,7 +207,7 @@ func InstallExternalBackend(ctx context.Context, galleries []config.Gallery, sys
 		if name != "" || alias != "" {
 			return fmt.Errorf("specifying a name or alias is not supported for gallery backends")
 		}
-		err := gallery.InstallBackendFromGallery(ctx, galleries, systemState, modelLoader, backend, downloadStatus, true, requireIntegrity)
+		err := gallery.InstallBackendFromGallery(ctx, galleries, systemState, modelLoader, backend, downloadStatus, force, requireIntegrity)
 		if err != nil {
 			return fmt.Errorf("error installing backend %s: %w", backend, err)
 		}

core/services/galleryop/backends_test.go

@@ -70,6 +70,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				"test-backend", // gallery name
 				"custom-name",  // name should not be allowed
 				"",
+				false, // force
 				false,
 			)
 			Expect(err).To(HaveOccurred())
@@ -86,6 +87,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				"non-existent-backend",
 				"",
 				"",
+				false, // force
 				false,
 			)
 			Expect(err).To(HaveOccurred())
@@ -103,6 +105,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				"oci://quay.io/mudler/tests:localai-backend-test",
 				"", // name is required for OCI images
 				"",
+				false, // force
 				false,
 			)
 			Expect(err).To(HaveOccurred())
@@ -136,6 +139,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				testBackendPath,
 				"", // name should be inferred as "source-backend"
 				"",
+				false, // force
 				false,
 			)
 			// The function should at least attempt to install with the inferred name
@@ -155,6 +159,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				testBackendPath,
 				"custom-backend-name",
 				"",
+				false, // force
 				false,
 			)
 			// The function should use the provided name
@@ -173,6 +178,7 @@ var _ = Describe("InstallExternalBackend", func() {
 				testBackendPath,
 				"custom-backend-name",
 				"custom-alias",
+				false, // force
 				false,
 			)
 			// The function should accept alias for directory paths

core/services/galleryop/managers_local.go

@@ -110,10 +110,13 @@ func (b *LocalBackendManager) CheckUpgrades(ctx context.Context) (map[string]gal
 func (b *LocalBackendManager) InstallBackend(ctx context.Context, op *ManagementOp[gallery.GalleryBackend, any], progressCb ProgressCallback) error {
 	if op.ExternalURI != "" {
 		return InstallExternalBackend(ctx, b.backendGalleries, b.systemState, b.modelLoader,
-			progressCb, op.ExternalURI, op.ExternalName, op.ExternalAlias, b.requireBackendIntegrity)
+			progressCb, op.ExternalURI, op.ExternalName, op.ExternalAlias, op.Force, b.requireBackendIntegrity)
 	}
+	// op.Force distinguishes an explicit reinstall from an idempotent
+	// "make sure it's installed" op; the latter must not re-download an
+	// already-runnable backend (supervisors apply on every boot).
 	return gallery.InstallBackendFromGallery(ctx, b.backendGalleries, b.systemState,
-		b.modelLoader, op.GalleryElementName, progressCb, true, b.requireBackendIntegrity)
+		b.modelLoader, op.GalleryElementName, progressCb, op.Force, b.requireBackendIntegrity)
 }
 
 func (b *LocalBackendManager) IsDistributed() bool { return false }

core/services/galleryop/operation.go

@@ -45,6 +45,13 @@ type ManagementOp[T any, E any] struct {
 
 	// Upgrade is true if this is an upgrade operation (not a fresh install)
 	Upgrade bool
+
+	// Force reinstalls a backend even when it is already installed and
+	// runnable. Without it a backend install op is idempotent — API clients
+	// that ensure a backend exists on every boot must not trigger a full
+	// artifact re-download each time. The UI's explicit "Reinstall backend"
+	// action sets it.
+	Force bool
 }
 
 type OpStatus struct {

core/services/nodes/router.go

@@ -68,6 +68,13 @@ type SmartRouterOptions struct {
 	// the absolute model paths untouched so the worker loads them directly from
 	// the shared volume (#10556). See config.DistributedConfig.SharedModels.
 	SharedModels bool
+	// ModelLoadCeiling is the hard upper bound on how long a single cold-load
+	// attempt (node selection -> backend install -> file staging -> LoadModel)
+	// may run while holding the per-model advisory lock. It backstops every
+	// sub-step's own timeout so a wedged worker can never pin the lock - and
+	// every other replica's request for that model - indefinitely. Zero selects
+	// defaultModelLoadCeiling.
+	ModelLoadCeiling time.Duration
 }
 
 // SmartRouter routes inference requests to the best available backend node.
@@ -101,8 +108,18 @@ type SmartRouter struct {
 	// sharedModels skips file staging when all nodes mount the same models
 	// directory at the same path (see SmartRouterOptions.SharedModels).
 	sharedModels bool
+	// modelLoadCeiling bounds how long a cold load may hold the per-model
+	// advisory lock (see SmartRouterOptions.ModelLoadCeiling).
+	modelLoadCeiling time.Duration
 }
 
+// defaultModelLoadCeiling is the fallback hold ceiling for a cold model load.
+// It must comfortably exceed the slowest legitimate load - a multi-GB backend
+// install (DefaultBackendInstallTimeout, 15m) plus staging and the remote
+// LoadModel (5m) - so it never cuts a real load short; it only ever fires when
+// a step is genuinely wedged (e.g. a worker that died mid-install).
+const defaultModelLoadCeiling = 25 * time.Minute
+
 // probeCacheTTL is how long a successful gRPC HealthCheck on a backend is
 // trusted before the next request re-probes. Matches healthCheckTTL in
 // pkg/model/model.go so the single-process and distributed paths share a
@@ -117,6 +134,10 @@ func NewSmartRouter(registry ModelRouter, opts SmartRouterOptions) *SmartRouter
 	if factory == nil {
 		factory = &tokenClientFactory{token: opts.AuthToken}
 	}
+	ceiling := opts.ModelLoadCeiling
+	if ceiling <= 0 {
+		ceiling = defaultModelLoadCeiling
+	}
 	return &SmartRouter{
 		registry:         registry,
 		unloader:         opts.Unloader,
@@ -131,6 +152,7 @@ func NewSmartRouter(registry ModelRouter, opts SmartRouterOptions) *SmartRouter
 		prefixConfig:     opts.PrefixConfig,
 		pressure:         opts.Pressure,
 		sharedModels:     opts.SharedModels,
+		modelLoadCeiling: ceiling,
 	}
 }
 
@@ -383,11 +405,19 @@ func (r *SmartRouter) Route(ctx context.Context, modelID, modelName, backendType
 	// the request context. If staging were bound to it, the multi-GB upload
 	// aborts with "context canceled" mid-transfer and large models can never
 	// finish staging (the model-load outage). WithoutCancel keeps the request's
-	// values (prefix chain, etc.) but drops its cancellation/deadline. Each
-	// long step still has its own bound (the file stager's resume budget,
-	// LoadModel's 5m timeout), and the per-model advisory lock below de-dupes
-	// concurrent loaders across replicas.
-	loadCtx := context.WithoutCancel(ctx)
+	// values (prefix chain, etc.) but drops its cancellation/deadline.
+	//
+	// Detaching from the caller is necessary, but it must not be unbounded: the
+	// load runs while holding the per-model advisory lock, and a worker that
+	// dies mid-install (its backend.install never replies) would otherwise pin
+	// that lock (and every other replica's request for the same model) until
+	// the NATS install deadline alone expires. Re-impose a single hard ceiling
+	// over the whole sequence so the lock is always released in bounded time,
+	// even if a sub-step wedges. Each long step still has its own (tighter)
+	// bound; this only backstops them. The per-model advisory lock below
+	// de-dupes concurrent loaders across replicas.
+	loadCtx, cancelLoad := context.WithTimeout(context.WithoutCancel(ctx), r.modelLoadCeiling)
+	defer cancelLoad()
 	loadModel := func(ctx context.Context) (*RouteResult, error) {
 		// Re-check after acquiring lock — another request may have loaded it
 		node, nm, err := r.registry.FindAndLockNodeWithModel(ctx, trackingKey, candidateNodeIDs, pref)
@@ -916,7 +946,14 @@ func (r *SmartRouter) installBackendOnNode(ctx context.Context, node *BackendNod
 	}
 
 	key := fmt.Sprintf("%s|%s|%s|%d", node.ID, backendType, modelID, replicaIndex)
-	v, err, _ := r.installFlight.Do(key, func() (any, error) {
+	// DoChan rather than Do so this wait honors ctx cancellation. InstallBackend
+	// blocks for its full NATS deadline (15m by default) when a worker accepts
+	// the request but never replies (e.g. it died mid-install). Without ctx
+	// awareness the caller (holding the per-model advisory lock) would sit there
+	// the whole time; here a cancelled ctx (typically the model-load ceiling)
+	// frees the caller promptly. The shared install keeps running in the
+	// background and still coalesces other callers via singleflight.
+	resCh := r.installFlight.DoChan(key, func() (any, error) {
 		reply, err := r.unloader.InstallBackend(node.ID, backendType, modelID, r.galleriesJSON, "", "", "", replicaIndex, "", nil)
 		if err != nil {
 			return "", err
@@ -931,10 +968,15 @@ func (r *SmartRouter) installBackendOnNode(ctx context.Context, node *BackendNod
 		}
 		return addr, nil
 	})
-	if err != nil {
-		return "", err
+	select {
+	case <-ctx.Done():
+		return "", ctx.Err()
+	case res := <-resCh:
+		if res.Err != nil {
+			return "", res.Err
+		}
+		return res.Val.(string), nil
 	}
-	return v.(string), nil
 }
 
 func (r *SmartRouter) buildClientForAddr(node *BackendNode, addr string, parallel bool) grpc.Backend {

core/services/nodes/router_test.go

@@ -493,6 +493,44 @@ var _ = Describe("SmartRouter", func() {
 				Expect(result.Node.ID).To(Equal("n3"))
 			})
 		})
+
+		Context("worker wedges mid-install (dead node holding the lock)", func() {
+			It("aborts the load at the ModelLoadCeiling instead of blocking forever", func() {
+				// Simulate the production incident: the chosen worker accepts the
+				// backend.install but never replies (it died), so InstallBackend
+				// would otherwise block for its full NATS deadline (15m by
+				// default) while pinning the per-model advisory lock. Route must
+				// give up at the ceiling so the lock is released promptly.
+				reg.findAndLockErr = errors.New("not found")
+				reg.findIdleNode = &BackendNode{ID: "n4", Name: "dead-node", Address: "10.0.0.4:50051"}
+
+				block := make(chan struct{})
+				defer close(block) // let the background install goroutine drain at test end
+				unloader.installHook = func() { <-block }
+
+				router := NewSmartRouter(reg, SmartRouterOptions{
+					Unloader:         unloader,
+					ClientFactory:    factory,
+					ModelLoadCeiling: 200 * time.Millisecond,
+				})
+
+				done := make(chan error, 1)
+				start := time.Now()
+				go func() {
+					defer GinkgoRecover()
+					_, err := router.Route(context.Background(), "wedged-model",
+						"models/wedged.gguf", "llama-cpp",
+						&pb.ModelOptions{Model: "models/wedged.gguf"}, false)
+					done <- err
+				}()
+
+				var routeErr error
+				Eventually(done, 5*time.Second).Should(Receive(&routeErr),
+					"Route must not block on a wedged install past the ceiling")
+				Expect(routeErr).To(HaveOccurred())
+				Expect(time.Since(start)).To(BeNumerically("<", 5*time.Second))
+			})
+		})
 	})
 
 	Describe("scheduleNewModel (mock-based, via Route)", func() {

core/services/worker/install.go

@@ -134,7 +134,7 @@ func (s *backendSupervisor) installBackend(req messaging.BackendInstallRequest,
 		if req.URI != "" {
 			xlog.Info("Installing backend from external URI", "backend", req.Backend, "uri", req.URI, "force", force)
 			if err := galleryop.InstallExternalBackend(
-				context.Background(), galleries, s.systemState, s.ml, downloadCb, req.URI, req.Name, req.Alias, s.cfg.RequireBackendIntegrity,
+				context.Background(), galleries, s.systemState, s.ml, downloadCb, req.URI, req.Name, req.Alias, force, s.cfg.RequireBackendIntegrity,
 			); err != nil {
 				return "", fmt.Errorf("installing backend from gallery: %w", err)
 			}
@@ -201,7 +201,7 @@ func (s *backendSupervisor) upgradeBackend(req messaging.BackendUpgradeRequest)
 	if req.URI != "" {
 		xlog.Info("Upgrading backend from external URI", "backend", req.Backend, "uri", req.URI)
 		if err := galleryop.InstallExternalBackend(
-			context.Background(), galleries, s.systemState, s.ml, downloadCb, req.URI, req.Name, req.Alias, s.cfg.RequireBackendIntegrity,
+			context.Background(), galleries, s.systemState, s.ml, downloadCb, req.URI, req.Name, req.Alias, true, s.cfg.RequireBackendIntegrity,
 		); err != nil {
 			return fmt.Errorf("upgrading backend from external URI: %w", err)
 		}

docs/data/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "v4.5.5"
+  "version": "v4.5.6"
 }

gallery/index.yaml

@@ -1,4 +1,61 @@
 ---
+- name: "ornith-1.0-9b-mtp"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/protoLabsAI/Ornith-1.0-9B-MTP-GGUF
+  description: |
+    [](https://deep-reinforce.com/ornith.html)
+
+    # Ornith-1.0-9B
+
+    Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
+
+    Highlights:
+
+      - **State-of-the-Art Coding Agents**: Available in 9B-Dense, 31B-Dense, 35B-MoE, and 397B-MoE (post-trained on top of Gemma 4 and Qwen 3.5), achieving state-of-the-art performance among open-source models of comparable size on coding benchmarks such as Terminal-Bench 2.1, SWE-Bench, NL2Repo and OpenClaw.
+      - **Self-Improving Training Framework**:  Ornith-1.0 employs RL to learn to generate not only solution rollouts, but also the scallfold that drive those rollouts. By jointly optimizing the scaffold and the resulting solution, the model  discovers better search trajectories and generates higher-quality solutions.
+      - **Licence**: MIT licensed, globally accessible, and free from regional limitations.
+
+    ## Ornith 1.0 9B
+
+    This model card documents **Ornith-1.0-9B**, the most lightweight member of the Ornith family, designed for efficient single-GPU deployment.
+
+    ### Benchmarks
+
+    Ornith-1.0-9B
+    Qwen3.5-9B
+    Qwen3.5-35B
+    Gemma4-12B
+    Gemma4-31B
+
+    Agentic Coding
+
+    ...
+  license: "mit"
+  tags:
+    - llm
+    - gguf
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    options:
+      - use_jinja:true
+      - spec_type:draft-mtp
+      - spec_n_max:6
+      - spec_p_min:0.75
+    parameters:
+      model: llama-cpp/models/ornith-9b-mtp-kl-Q4_K_M/ornith-9b-mtp-kl-Q4_K_M.gguf
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/models/ornith-9b-mtp-kl-Q4_K_M/ornith-9b-mtp-kl-Q4_K_M.gguf
+      sha256: 03de14e9849a02258b9ac9ec2830af39dd7ac48f1ca5492b35539d1838707bc8
+      uri: https://huggingface.co/protoLabsAI/Ornith-1.0-9B-MTP-GGUF/resolve/main/ornith-9b-mtp-kl-Q4_K_M.gguf
 - name: "qwen-agentworld-35b-a3b"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -1716,7 +1773,7 @@
       - use_jinja:true
     parameters:
       min_p: 0.15
-      model: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q4_K_M.gguf
+      model: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q8_0.gguf
       repeat_penalty: 1.05
       temperature: 0.1
       top_k: 50
@@ -1724,9 +1781,9 @@
     template:
       use_tokenizer_template: true
   files:
-    - filename: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q4_K_M.gguf
-      uri: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF/resolve/main/LFM2.5-8B-A1B-Q4_K_M.gguf
-      sha256: 4923ec14f06b968b74d663e5949867d2d9c3bf13a20b8be1a9f9af39989b2bb0
+    - filename: llama-cpp/models/LFM2.5-8B-A1B-GGUF/LFM2.5-8B-A1B-Q8_0.gguf
+      uri: https://huggingface.co/LiquidAI/LFM2.5-8B-A1B-GGUF/resolve/main/LFM2.5-8B-A1B-Q8_0.gguf
+      sha256: 33ab3b8ce6a964fb8ebac89360c9b3cf72c4fa418d5e4c0a94d46883124d5c02
 - name: "qwopus3.5-9b-coder-mtp"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls:
@@ -1758,8 +1815,8 @@
       use_tokenizer_template: true
   files:
     - filename: llama-cpp/models/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-Q4_K_M.gguf
-      sha256: f6fc5d193045796d9e1870cbc40f827fe55f53f70593c3f5c1968b82b9331991
       uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-Q4_K_M.gguf
+      sha256: 9ea3ecd122a5165b8b81655f29eaf09d71daf841503e4c4212bdfadb36ab3712
     - filename: llama-cpp/mmproj/Qwopus3.5-9B-Coder-MTP-GGUF/Qwopus3.5-9B-Coder-MTP-mmproj.gguf
       sha256: f48daca405a1c768a9514e392c3955dcc4a9d66a5cf64cf45e064092b5f20ee4
       uri: https://huggingface.co/Jackrong/Qwopus3.5-9B-Coder-MTP-GGUF/resolve/main/Qwopus3.5-9B-Coder-MTP-mmproj.gguf

pkg/grpc/grpcerrors/errors.go

@@ -58,6 +58,23 @@ func IsLiveTranscriptionUnsupported(err error) bool {
 	return strings.Contains(strings.ToLower(err.Error()), "unimplemented")
 }
 
+// IsUnimplemented reports whether err is a gRPC Unimplemented status — the
+// signal a backend gives for an RPC it does not implement. The generated
+// UnimplementedBackendServer stub returns exactly this for any RPC a backend
+// (e.g. a Python or external backend) has not overridden, so callers can treat
+// an optional RPC as a no-op rather than a failure. Prefers the typed status
+// code and falls back to the message for paths that lose the status (e.g. errors
+// wrapped across non-gRPC boundaries).
+func IsUnimplemented(err error) bool {
+	if err == nil {
+		return false
+	}
+	if status.Code(err) == codes.Unimplemented {
+		return true
+	}
+	return strings.Contains(strings.ToLower(err.Error()), "unimplemented")
+}
+
 // StreamTranscriptionUnsupported returns the canonical error a backend returns
 // when it (or the loaded model) cannot serve the server-streaming
 // AudioTranscriptionStream RPC. It carries codes.Unimplemented like the live

pkg/grpc/grpcerrors/errors_test.go

@@ -55,6 +55,18 @@ var _ = Describe("grpcerrors", func() {
 		Expect(grpcerrors.IsModelNotLoaded(err)).To(BeFalse())
 	})
 
+	DescribeTable("IsUnimplemented",
+		func(err error, want bool) {
+			Expect(grpcerrors.IsUnimplemented(err)).To(Equal(want))
+		},
+		Entry("nil", nil, false),
+		Entry("typed code", status.Error(codes.Unimplemented, "method Free not implemented"), true),
+		Entry("stale stub message (Unknown code)", errors.New("rpc error: code = Unimplemented desc = "), true),
+		Entry("unrelated error", errors.New("context deadline exceeded"), false),
+		Entry("unrelated grpc code", status.Error(codes.Unavailable, "connection refused"), false),
+		Entry("model not loaded is NOT unimplemented", grpcerrors.ModelNotLoaded("parakeet-cpp"), false),
+	)
+
 	It("StreamTranscriptionUnsupported carries Unimplemented and is not ModelNotLoaded", func() {
 		err := grpcerrors.StreamTranscriptionUnsupported("parakeet-cpp", "not a streaming model")
 		Expect(status.Code(err)).To(Equal(codes.Unimplemented))

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()

pkg/model/process.go

@@ -11,6 +11,7 @@ import (
 	"time"
 
 	"github.com/hpcloud/tail"
+	"github.com/mudler/LocalAI/pkg/grpc/grpcerrors"
 	"github.com/mudler/LocalAI/pkg/signals"
 	process "github.com/mudler/go-processmanager"
 	"github.com/mudler/xlog"
@@ -52,10 +53,21 @@ func (ml *ModelLoader) deleteProcess(s string) error {
 		hook(s)
 	}
 
-	// Free GPU resources before stopping the process to ensure VRAM is released
+	// Free GPU resources before stopping the process to ensure VRAM is released.
+	// Free is optional: backends that don't override it (the generated stub, many
+	// Python/external backends, or a federation proxy in distributed mode) return
+	// gRPC Unimplemented. That is expected, not a failure — VRAM is reclaimed when
+	// the process is stopped below, or by the remote unloader for remote backends —
+	// so don't surface it as an error.
 	xlog.Debug("Calling Free() to release GPU resources", "model", s)
 	if err := model.GRPC(false, ml.wd).Free(context.Background()); err != nil {
-		xlog.Warn("Error freeing GPU resources", "error", err, "model", s)
+		if grpcerrors.IsUnimplemented(err) {
+			xlog.Debug("Backend does not implement Free(); GPU release handled on process stop", "model", s)
+		} else {
+			// Now that the expected Unimplemented case is filtered out above, a
+			// remaining error is a genuine failure to release VRAM — surface it.
+			xlog.Error("Error freeing GPU resources", "error", err, "model", s)
+		}
 	}
 
 	process := model.Process()

swagger/docs.go

@@ -3605,6 +3605,10 @@ const docTemplate = `{
         "localai.GalleryBackend": {
             "type": "object",
             "properties": {
+                "force": {
+                    "description": "Force reinstalls the backend even when it is already installed and\nrunnable. Off by default so apply stays idempotent for supervising\napps that ensure their backend on every boot.",
+                    "type": "boolean"
+                },
                 "id": {
                     "type": "string"
                 }

swagger/swagger.json

@@ -3602,6 +3602,10 @@
         "localai.GalleryBackend": {
             "type": "object",
             "properties": {
+                "force": {
+                    "description": "Force reinstalls the backend even when it is already installed and\nrunnable. Off by default so apply stays idempotent for supervising\napps that ensure their backend on every boot.",
+                    "type": "boolean"
+                },
                 "id": {
                     "type": "string"
                 }

swagger/swagger.yaml

@@ -303,6 +303,12 @@ definitions:
     type: object
   localai.GalleryBackend:
     properties:
+      force:
+        description: |-
+          Force reinstalls the backend even when it is already installed and
+          runnable. Off by default so apply stays idempotent for supervising
+          apps that ensure their backend on every boot.
+        type: boolean
       id:
         type: string
     type: object