chore(deps): bump mxschmitt/action-tmate from 3.23 to 3.24

Bumps [mxschmitt/action-tmate](https://github.com/mxschmitt/action-tmate) from 3.23 to 3.24.
- [Release notes](https://github.com/mxschmitt/action-tmate/releases)
- [Changelog](https://github.com/mxschmitt/action-tmate/blob/master/RELEASE.md)
- [Commits](https://github.com/mxschmitt/action-tmate/compare/v3.23...v3.24)

---
updated-dependencies:
- dependency-name: mxschmitt/action-tmate
  dependency-version: '3.24'
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/backend-matrix.yml

@@ -4974,12 +4974,6 @@ includeDarwin:
   - backend: "kitten-tts"
     tag-suffix: "-metal-darwin-arm64-kitten-tts"
     build-type: "mps"
-  - backend: "trl"
-    tag-suffix: "-metal-darwin-arm64-trl"
-    build-type: "mps"
-  - backend: "liquid-audio"
-    tag-suffix: "-metal-darwin-arm64-liquid-audio"
-    build-type: "mps"
   - backend: "piper"
     tag-suffix: "-metal-darwin-arm64-piper"
     build-type: "metal"
@@ -4996,10 +4990,6 @@ includeDarwin:
     tag-suffix: "-metal-darwin-arm64-sherpa-onnx"
     build-type: "metal"
     lang: "go"
-  - backend: "supertonic"
-    tag-suffix: "-metal-darwin-arm64-supertonic"
-    build-type: "metal"
-    lang: "go"
   - backend: "local-store"
     tag-suffix: "-metal-darwin-arm64-local-store"
     build-type: "metal"

.github/workflows/test.yml

@@ -71,7 +71,7 @@ jobs:
           if-no-files-found: ignore
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180
@@ -116,7 +116,7 @@ jobs:
           PATH="$PATH:$HOME/go/bin" BUILD_TYPE="GITHUB_CI_HAS_BROKEN_METAL" CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" make --jobs 4 --output-sync=target test
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180

.github/workflows/tests-aio.yml

@@ -79,7 +79,7 @@ jobs:
             PATH="$PATH:$HOME/go/bin" make backends/local-store backends/silero-vad backends/llama-cpp backends/whisper backends/piper backends/stablediffusion-ggml docker-build-e2e e2e-aio
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180

.github/workflows/tests-e2e.yml

@@ -57,7 +57,7 @@ jobs:
           PATH="$PATH:$HOME/go/bin" make build-mock-backend test-e2e
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180

.github/workflows/tests-pii-ner-e2e.yml

@@ -90,7 +90,7 @@ jobs:
         run: PATH="$PATH:$HOME/go/bin" make test-extra-backend-privacy-filter
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180

.github/workflows/tests-ui-e2e.yml

@@ -75,7 +75,7 @@ jobs:
           retention-days: 7
       - name: Setup tmate session if tests fail
         if: ${{ failure() }}
-        uses: mxschmitt/action-tmate@v3.23
+        uses: mxschmitt/action-tmate@v3.24
         with:
           detached: true
           connect-timeout-seconds: 180

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=d5507e33ae7ee2b7b41475f08044d3bde3b839ee
+IK_LLAMA_VERSION?=6c00e87ac84404af588ad2e65935bd6f079c696f
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=8be759e6f70d629638a7eb70db3824cbdcea370b
+LLAMA_VERSION?=7c082bc417bbe53210a83df4ba5b49e18ce6193c
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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

@@ -37,7 +37,6 @@
 #include "backend.pb.h"
 #include "backend.grpc.pb.h"
 #include "common.h"
-#include "arg.h"
 #include "chat-auto-parser.h"
 #include <getopt.h>
 #include <grpcpp/ext/proto_server_reflection_plugin.h>
@@ -593,10 +592,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
     params.checkpoint_min_step = 256;
 #endif
 
-    // Raw upstream llama-server flags collected from any option entry that
-    // starts with '-'. Applied once after the loop via common_params_parse.
-    std::vector<std::string> extra_argv;
-
      // decode options. Options are in form optname:optvale, or if booleans only optname.
     for (int i = 0; i < request->options_size(); i++) {
         std::string opt = request->options(i);
@@ -1085,31 +1080,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 } catch (...) {}
             }
 
-        // --- main model MoE on CPU (upstream --cpu-moe / --n-cpu-moe) ---
-        } else if (!strcmp(optname, "cpu_moe")) {
-            // Bool-style flag: keep all MoE expert weights on CPU.
-            const bool enable = (optval == NULL) ||
-                optval_str == "true" || optval_str == "1" || optval_str == "yes" ||
-                optval_str == "on" || optval_str == "enabled";
-            if (enable) {
-                params.tensor_buft_overrides.push_back(llm_ffn_exps_cpu_override());
-            }
-        } else if (!strcmp(optname, "n_cpu_moe")) {
-            if (optval != NULL) {
-                try {
-                    int n = std::stoi(optval_str);
-                    if (n < 0) n = 0;
-                    // Keep override-name storage alive for the lifetime of the
-                    // params struct (mirrors upstream arg.cpp's function-local static).
-                    static std::list<std::string> buft_overrides_main;
-                    for (int i = 0; i < n; ++i) {
-                        buft_overrides_main.push_back(llm_ffn_exps_block_regex(i));
-                        params.tensor_buft_overrides.push_back(
-                            {buft_overrides_main.back().c_str(), ggml_backend_cpu_buffer_type()});
-                    }
-                } catch (...) {}
-            }
-
         // --- draft model tensor buffer overrides (upstream --spec-draft-override-tensor) ---
         } else if (!strcmp(optname, "draft_override_tensor") || !strcmp(optname, "spec_draft_override_tensor")) {
             // Format: <tensor regex>=<buffer type>,<tensor regex>=<buffer type>,...
@@ -1141,30 +1111,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
                 else { cur.push_back(c); }
             }
             if (!cur.empty()) flush(cur);
-
-        // --- generic passthrough: any entry starting with '-' is a raw
-        //     upstream llama-server flag, forwarded verbatim to the parser. ---
-        } else if (optname[0] == '-') {
-            std::string flag = optname;
-            // These flags make upstream's parser exit() (printing usage /
-            // completion), which would kill the backend process. Skip them.
-            if (flag == "-h" || flag == "--help" || flag == "--usage" ||
-                flag == "--version" || flag == "--license" ||
-                flag == "--list-devices" || flag == "-cl" ||
-                flag == "--cache-list" ||
-                flag.rfind("--completion", 0) == 0) {
-                fprintf(stderr,
-                    "[llama-cpp] ignoring passthrough flag that would exit: %s\n",
-                    flag.c_str());
-            } else {
-                extra_argv.push_back(flag);
-                // Preserve the whole value after the first ':' so embedded
-                // colons (e.g. host:port) survive strtok's truncation of optval.
-                auto colon = opt.find(':');
-                if (colon != std::string::npos) {
-                    extra_argv.push_back(opt.substr(colon + 1));
-                }
-            }
         }
     }
 
@@ -1200,6 +1146,27 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
         }
     }
 
+    if (!params.kv_overrides.empty()) {
+        params.kv_overrides.emplace_back();
+        params.kv_overrides.back().key[0] = 0;
+    }
+
+    // tensor_buft_overrides sentinel termination (mirrors upstream common/arg.cpp).
+    // Real entries are pushed during option parsing; here we pad/terminate so the
+    // model loader sees back().pattern == nullptr (GGML_ASSERT at common.cpp:1543)
+    // and so llama_params_fit has the placeholder slots it requires.
+    {
+        const size_t ntbo = llama_max_tensor_buft_overrides();
+        while (params.tensor_buft_overrides.size() < ntbo) {
+            params.tensor_buft_overrides.push_back({nullptr, nullptr});
+        }
+    }
+    // Terminate the draft tensor_buft_overrides list with a sentinel, mirroring
+    // the main-model handling above.
+    if (!params.speculative.draft.tensor_buft_overrides.empty()) {
+        params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
+    }
+
     // TODO: Add yarn
 
     if (!request->tensorsplit().empty()) {
@@ -1292,69 +1259,6 @@ static void params_parse(server_context& /*ctx_server*/, const backend::ModelOpt
             params.sampling.grammar_triggers.push_back(std::move(trigger));
         }
     }
-
-    // Apply any raw upstream flags last so an explicit passthrough flag wins
-    // over the LocalAI-resolved field it maps to (e.g. --ctx-size beats
-    // context_size). This is the same parser llama-server itself uses.
-    if (!extra_argv.empty()) {
-        // common_params_parser_init resets a few fields for the SERVER example
-        // (n_parallel -> -1, use_color). Snapshot n_parallel so an unrelated
-        // passthrough flag can't silently clobber LocalAI's resolved value.
-        const int saved_n_parallel = params.n_parallel;
-
-        std::vector<char *> argv;
-        std::string prog = "llama-server";
-        argv.push_back(prog.data());
-        for (auto & a : extra_argv) {
-            argv.push_back(a.data());
-        }
-
-        // ctx_arg.params is a reference, so this overlays the given flags onto
-        // `params` in place. Returns false on a recoverable parse error (and
-        // self-restores params); may exit() on a hard error, exactly as
-        // passing the same bad flag to llama-server would.
-        if (!common_params_parse((int)argv.size(), argv.data(), params,
-                                 LLAMA_EXAMPLE_SERVER)) {
-            fprintf(stderr,
-                "[llama-cpp] failed to parse passthrough options; ignoring them\n");
-        }
-
-        // Restore n_parallel unless a passthrough flag explicitly set it
-        // (parser_init's reset sentinel for SERVER is -1).
-        if (params.n_parallel == -1) {
-            params.n_parallel = saved_n_parallel;
-        }
-    }
-
-    // Terminate/pad the override vectors only after BOTH the named-option loop
-    // and the generic passthrough (common_params_parse above) have pushed their
-    // real entries, so back() is the null sentinel the model loader asserts on.
-    // Running these before the passthrough let a passthrough flag (--cpu-moe,
-    // --override-tensor, --override-kv, ...) append a real entry after the
-    // sentinel: a GGML_ASSERT crash for tensor_buft_overrides, a silent drop for
-    // kv_overrides. Double-termination is harmless (the while is a no-op if the
-    // passthrough parse already padded; an extra trailing null is ignored).
-
-    if (!params.kv_overrides.empty()) {
-        params.kv_overrides.emplace_back();
-        params.kv_overrides.back().key[0] = 0;
-    }
-
-    // tensor_buft_overrides sentinel termination (mirrors upstream common/arg.cpp).
-    // Real entries are pushed during option parsing; here we pad/terminate so the
-    // model loader sees back().pattern == nullptr (GGML_ASSERT at common.cpp:1543)
-    // and so llama_params_fit has the placeholder slots it requires.
-    {
-        const size_t ntbo = llama_max_tensor_buft_overrides();
-        while (params.tensor_buft_overrides.size() < ntbo) {
-            params.tensor_buft_overrides.push_back({nullptr, nullptr});
-        }
-    }
-    // Terminate the draft tensor_buft_overrides list with a sentinel, mirroring
-    // the main-model handling above.
-    if (!params.speculative.draft.tensor_buft_overrides.empty()) {
-        params.speculative.draft.tensor_buft_overrides.push_back({nullptr, nullptr});
-    }
 }
 
 

backend/go/acestep-cpp/Makefile

@@ -117,8 +117,7 @@ libgoacestepcpp-custom: CMakeLists.txt cpp/goacestepcpp.cpp cpp/goacestepcpp.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goacestepcpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgoacestepcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgoacestepcpp.so ./$(SO_TARGET)
 
 test: acestep-cpp
 	@echo "Running acestep-cpp tests..."

backend/go/acestep-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -23,11 +22,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("ACESTEP_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgoacestepcpp-fallback.dylib"
-		} else {
-			libName = "./libgoacestepcpp-fallback.so"
-		}
+		libName = "./libgoacestepcpp-fallback.so"
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/acestep-cpp/package.sh

@@ -13,7 +13,6 @@ mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/acestep-cpp $CURDIR/package/
 cp -fv $CURDIR/libgoacestepcpp-*.so $CURDIR/package/
-cp -fv $CURDIR/libgoacestepcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/acestep-cpp/run.sh

@@ -12,19 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single library variant (Metal or Accelerate). The goacestepcpp
-	# target is built as a CMake MODULE, which emits a .dylib for a SHARED
-	# build but a .so for a MODULE build on Apple, so prefer .dylib and fall
-	# back to .so.
-	LIBRARY="$CURDIR/libgoacestepcpp-fallback.dylib"
-	if [ ! -e "$LIBRARY" ]; then
-		LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
-	fi
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
+LIBRARY="$CURDIR/libgoacestepcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoacestepcpp-avx.so ]; then
@@ -46,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgoacestepcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export ACESTEP_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/ced/Makefile

@@ -57,7 +57,6 @@ libced.so: sources/ced.cpp
 	cmake -B sources/ced.cpp/build-shared -S sources/ced.cpp $(CMAKE_ARGS)
 	cmake --build sources/ced.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/ced.cpp/build-shared/libced.so* ./ 2>/dev/null || true
-	cp -fv sources/ced.cpp/build-shared/libced.dylib ./ 2>/dev/null || true
 	cp -fv sources/ced.cpp/include/ced_capi.h ./
 
 ced-grpc: libced.so main.go goced.go

backend/go/ced/main.go

@@ -12,7 +12,6 @@ import (
 	"flag"
 	"fmt"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ type libFunc struct {
 func main() {
 	libName := os.Getenv("CED_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "libced.dylib"
-		} else {
-			libName = "libced.so"
-		}
+		libName = "libced.so"
 	}
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
 	if err != nil {

backend/go/ced/package.sh

@@ -15,12 +15,10 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/ced-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || true
-cp -avf "$CURDIR"/libced.dylib "$CURDIR/package/lib/" 2>/dev/null || true
-if ! ls "$CURDIR"/package/lib/libced.* >/dev/null 2>&1; then
-	echo "ERROR: libced shared library not found in $CURDIR, run 'make' first" >&2
+cp -avf "$CURDIR"/libced.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libced.so not found in $CURDIR, run 'make' first" >&2
 	exit 1
-fi
+}
 
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     echo "Detected x86_64 architecture, copying x86_64 libraries..."

backend/go/ced/run.sh

@@ -3,12 +3,7 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
-	export CED_LIBRARY="$CURDIR/lib/libced.dylib"
-else
-	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
-fi
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
 
 # If a self-contained ld.so was packaged, route through it so the packaged
 # libc / libstdc++ are used instead of the host's (matches the sibling backends).

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?=96b2a6ee31d30389fed8a7ef1a54239b75231ddc
+CRISPASR_VERSION?=7a8cb80907341c0204bd0488c1244764f4163883
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -75,8 +75,7 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgocrispasr-avx.so libgocrispasr-avx2.so libgocrispasr-avx512.so libgocrispasr-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgocrispasr-fallback.dylib
+	VARIANT_TARGETS = libgocrispasr-fallback.so
 endif
 
 crispasr: main.go gocrispasr.go $(VARIANT_TARGETS)
@@ -88,7 +87,7 @@ package: crispasr
 build: package
 
 clean: purge
-	rm -rf libgocrispasr*.so libgocrispasr*.dylib package sources/CrispASR crispasr
+	rm -rf libgocrispasr*.so package sources/CrispASR crispasr
 
 purge:
 	rm -rf build*
@@ -119,21 +118,13 @@ libgocrispasr-fallback.so: sources/CrispASR
 	SO_TARGET=libgocrispasr-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
 	rm -rfv build*
 
-# Build fallback variant as a dylib (Darwin)
-libgocrispasr-fallback.dylib: sources/CrispASR
-	$(MAKE) purge
-	$(info ${GREEN}I crispasr build info:fallback (dylib)${RESET})
-	SO_TARGET=libgocrispasr-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgocrispasr-custom
-	rm -rfv build*
-
 libgocrispasr-custom: CMakeLists.txt cpp/crispasr_shim.cpp cpp/crispasr_shim.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgocrispasr.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgocrispasr.so ./$(SO_TARGET)
 
 test: crispasr
 	CGO_ENABLED=0 $(GOCMD) test -v ./...

backend/go/crispasr/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("CRISPASR_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgocrispasr-fallback.dylib"
-		} else {
-			libName = "./libgocrispasr-fallback.so"
-		}
+		libName = "./libgocrispasr-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/crispasr/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/crispasr $CURDIR/package/
-cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgocrispasr-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgocrispasr-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/crispasr/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgocrispasr-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgocrispasr-fallback.so"
+LIBRARY="$CURDIR/libgocrispasr-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgocrispasr-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgocrispasr-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export CRISPASR_LIBRARY=$LIBRARY
 
 # Point piper's espeak-ng phonemizer at the bundled voice data. The variable

backend/go/depth-anything-cpp/Makefile

@@ -77,7 +77,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libdepthanythingcpp-avx.so libdepthanythingcpp-avx2.so libdepthanythingcpp-avx512.so libdepthanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libdepthanythingcpp-fallback.dylib
+	VARIANT_TARGETS = libdepthanythingcpp-fallback.so
 endif
 
 depth-anything-cpp: main.go godepthanythingcpp.go $(VARIANT_TARGETS)
@@ -89,7 +89,7 @@ package: depth-anything-cpp
 build: package
 
 clean: purge
-	rm -rf libdepthanythingcpp*.so libdepthanythingcpp*.dylib depth-anything-cpp package sources
+	rm -rf libdepthanythingcpp*.so depth-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -116,19 +116,11 @@ libdepthanythingcpp-avx512.so: sources/depth-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-libdepthanythingcpp-fallback.dylib: sources/depth-anything.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
-	rm -rfv build-$@
-else
 libdepthanythingcpp-fallback.so: sources/depth-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I depth-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
 	rm -rfv build-$@
-endif
 
 libdepthanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -136,8 +128,7 @@ libdepthanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libdepthanything.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET)
 
 all: depth-anything-cpp package
 

backend/go/depth-anything-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libdepthanythingcpp-fallback.dylib"
-		} else {
-			libName = "./libdepthanythingcpp-fallback.so"
-		}
+		libName = "./libdepthanythingcpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/depth-anything-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libdepthanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/depth-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/depth-anything-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
+LIBRARY="$CURDIR/libdepthanythingcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libdepthanythingcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libdepthanythingcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export DEPTHANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/localvqe/Makefile

@@ -67,9 +67,8 @@ $(LIB_SENTINEL): sources/LocalVQE
 	# that the loader picks at runtime. We must build every target — the
 	# default `--target localvqe_shared` drops these. CMAKE_LIBRARY_OUTPUT_DIRECTORY
 	# routes all of them into build/bin; copy them out next to the binary.
-	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/bin/liblocalvqe.dylib . 2>/dev/null || cp -P build/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.dylib .
+	cp -P build/bin/liblocalvqe.so* . 2>/dev/null || cp -P build/liblocalvqe.so* .
 	cp -P build/bin/libggml*.so* . 2>/dev/null || true
-	cp -P build/bin/libggml*.dylib . 2>/dev/null || true
 	touch $(LIB_SENTINEL)
 
 liblocalvqe.so: $(LIB_SENTINEL)

backend/go/localvqe/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("LOCALVQE_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./liblocalvqe.dylib"
-		} else {
-			libName = "./liblocalvqe.so"
-		}
+		libName = "./liblocalvqe.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/localvqe/package.sh

@@ -15,9 +15,7 @@ cp -avf $CURDIR/localvqe $CURDIR/package/
 # liblocalvqe.so* (with SOVERSION symlinks) and the libggml-*.so runtime
 # variants — LocalVQE picks the matching CPU variant at load time.
 cp -P $CURDIR/liblocalvqe.so* $CURDIR/package/ 2>/dev/null || true
-cp -P $CURDIR/liblocalvqe.dylib $CURDIR/package/ 2>/dev/null || true
 cp -P $CURDIR/libggml*.so* $CURDIR/package/ 2>/dev/null || true
-cp -P $CURDIR/libggml*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/localvqe/run.sh

@@ -10,19 +10,8 @@ CURDIR=$(dirname "$(realpath $0)")
 # exec'ing the binary.
 cd "$CURDIR"
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: LocalVQE is built as a SHARED library, so dyld needs the .dylib +
-	# DYLD_LIBRARY_PATH. Prefer .dylib and fall back to .so just in case.
-	export DYLD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$DYLD_LIBRARY_PATH
-	LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.dylib
-	if [ ! -e "$LOCALVQE_LIBRARY" ]; then
-		LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
-	fi
-	export LOCALVQE_LIBRARY
-else
-	export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
-	export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
-fi
+export LD_LIBRARY_PATH=$CURDIR:$CURDIR/lib:$LD_LIBRARY_PATH
+export LOCALVQE_LIBRARY=$CURDIR/liblocalvqe.so
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

backend/go/locate-anything-cpp/Makefile

@@ -70,7 +70,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = liblocateanythingcpp-avx.so liblocateanythingcpp-avx2.so liblocateanythingcpp-avx512.so liblocateanythingcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = liblocateanythingcpp-fallback.dylib
+	VARIANT_TARGETS = liblocateanythingcpp-fallback.so
 endif
 
 locate-anything-cpp: main.go golocateanythingcpp.go $(VARIANT_TARGETS)
@@ -82,7 +82,7 @@ package: locate-anything-cpp
 build: package
 
 clean: purge
-	rm -rf liblocateanythingcpp*.so liblocateanythingcpp*.dylib locate-anything-cpp package sources
+	rm -rf liblocateanythingcpp*.so locate-anything-cpp package sources
 
 purge:
 	rm -rf build*
@@ -109,19 +109,11 @@ liblocateanythingcpp-avx512.so: sources/locate-anything.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-liblocateanythingcpp-fallback.dylib: sources/locate-anything.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
-	rm -rfv build-$@
-else
 liblocateanythingcpp-fallback.so: sources/locate-anything.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I locate-anything-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) liblocateanythingcpp-custom
 	rm -rfv build-$@
-endif
 
 liblocateanythingcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -129,8 +121,7 @@ liblocateanythingcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/liblocateanythingcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/liblocateanythingcpp.so ./$(SO_TARGET)
 
 all: locate-anything-cpp package
 

backend/go/locate-anything-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("LOCATEANYTHING_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./liblocateanythingcpp-fallback.dylib"
-		} else {
-			libName = "./liblocateanythingcpp-fallback.so"
-		}
+		libName = "./liblocateanythingcpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/locate-anything-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/liblocateanythingcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/liblocateanythingcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/locate-anything-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/locate-anything-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
+LIBRARY="$CURDIR/liblocateanythingcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/liblocateanythingcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/liblocateanythingcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export LOCATEANYTHING_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/omnivoice-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # omnivoice.cpp version
 OMNIVOICE_REPO?=https://github.com/ServeurpersoCom/omnivoice.cpp
-OMNIVOICE_VERSION?=0f37401bebe9b20c0160a888e592108fc1d17607
+OMNIVOICE_VERSION?=96d30169afd5e6bb3fd6a0e9be0eb505bfe81fcd
 SO_TARGET?=libgomnivoicecpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -65,8 +65,7 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgomnivoicecpp-avx.so libgomnivoicecpp-avx2.so libgomnivoicecpp-avx512.so libgomnivoicecpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgomnivoicecpp-fallback.dylib
+	VARIANT_TARGETS = libgomnivoicecpp-fallback.so
 endif
 
 omnivoice-cpp: main.go gomnivoicecpp.go $(VARIANT_TARGETS)
@@ -78,7 +77,7 @@ package: omnivoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgomnivoicecpp*.so libgomnivoicecpp*.dylib package sources/omnivoice.cpp omnivoice-cpp
+	rm -rf libgomnivoicecpp*.so package sources/omnivoice.cpp omnivoice-cpp
 
 purge:
 	rm -rf build*
@@ -107,20 +106,13 @@ libgomnivoicecpp-fallback.so: sources/omnivoice.cpp
 	SO_TARGET=libgomnivoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
 	rm -rf build-libgomnivoicecpp-fallback.so
 
-# Build fallback variant as a dylib (Darwin)
-libgomnivoicecpp-fallback.dylib: sources/omnivoice.cpp
-	$(info ${GREEN}I omnivoice-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgomnivoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgomnivoicecpp-custom
-	rm -rf build-libgomnivoicecpp-fallback.dylib
-
 libgomnivoicecpp-custom: CMakeLists.txt cpp/gomnivoicecpp.cpp cpp/gomnivoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target gomnivoicecpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgomnivoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgomnivoicecpp.so ./$(SO_TARGET)
 
 test: omnivoice-cpp
 	@echo "Running omnivoice-cpp tests..."

backend/go/omnivoice-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("OMNIVOICE_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgomnivoicecpp-fallback.dylib"
-		} else {
-			libName = "./libgomnivoicecpp-fallback.so"
-		}
+		libName = "./libgomnivoicecpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/omnivoice-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/omnivoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgomnivoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgomnivoicecpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/omnivoice-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
+LIBRARY="$CURDIR/libgomnivoicecpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgomnivoicecpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgomnivoicecpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export OMNIVOICE_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/parakeet-cpp/Makefile

@@ -1,6 +1,6 @@
 # parakeet-cpp backend Makefile.
 #
-# Upstream pin lives below as PARAKEET_VERSION?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
+# Upstream pin lives below as PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
 # (.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?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
+PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
 PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
 
 GOCMD?=go
@@ -74,7 +74,6 @@ libparakeet.so: sources/parakeet.cpp
 	cmake -B sources/parakeet.cpp/build-shared -S sources/parakeet.cpp $(CMAKE_ARGS)
 	cmake --build sources/parakeet.cpp/build-shared --config Release -j$(JOBS)
 	cp -fv sources/parakeet.cpp/build-shared/libparakeet.so* ./ 2>/dev/null || true
-	cp -fv sources/parakeet.cpp/build-shared/libparakeet.dylib ./ 2>/dev/null || true
 	cp -fv sources/parakeet.cpp/include/parakeet_capi.h ./
 
 parakeet-cpp-grpc: libparakeet.so main.go goparakeetcpp.go

backend/go/parakeet-cpp/main.go

@@ -2,17 +2,15 @@ package main
 
 // Started internally by LocalAI - one gRPC server per loaded model.
 //
-// Loads the parakeet shared library via purego and registers the flat
-// C-API entry points declared in parakeet_capi.h. The library name can be
-// overridden with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY /
-// VIBEVOICECPP_LIBRARY convention in the sibling backends); the default
-// looks next to this binary for libparakeet.so on Linux and
-// libparakeet.dylib on macOS.
+// Loads libparakeet.so via purego and registers the flat C-API entry
+// points declared in parakeet_capi.h. The library name can be overridden
+// with PARAKEET_LIBRARY (mirrors the WHISPER_LIBRARY / VIBEVOICECPP_LIBRARY
+// convention in the sibling backends); the default looks for the .so next
+// to this binary.
 import (
 	"flag"
 	"fmt"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -30,11 +28,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("PARAKEET_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "libparakeet.dylib"
-		} else {
-			libName = "libparakeet.so"
-		}
+		libName = "libparakeet.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/parakeet-cpp/package.sh

@@ -16,15 +16,12 @@ mkdir -p "$CURDIR/package/lib"
 cp -avf "$CURDIR/parakeet-cpp-grpc" "$CURDIR/package/"
 cp -avf "$CURDIR/run.sh" "$CURDIR/package/"
 
-# libparakeet shared lib + any soname symlinks. On Linux this is
-# libparakeet.so[.X.Y]; on macOS it is libparakeet.dylib. purego.Dlopen
-# resolves it via the *_LIBRARY_PATH that run.sh points at lib/.
-cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || true
-cp -avf "$CURDIR"/libparakeet.dylib "$CURDIR/package/lib/" 2>/dev/null || true
-if ! ls "$CURDIR"/package/lib/libparakeet.* >/dev/null 2>&1; then
-	echo "ERROR: libparakeet shared library not found in $CURDIR, run 'make' first" >&2
+# libparakeet.so + any soname symlinks (libparakeet.so.X[.Y]). purego.Dlopen
+# resolves it via LD_LIBRARY_PATH, which run.sh points at lib/.
+cp -avf "$CURDIR"/libparakeet.so* "$CURDIR/package/lib/" 2>/dev/null || {
+	echo "ERROR: libparakeet.so not found in $CURDIR, run 'make' first" >&2
 	exit 1
-fi
+}
 
 # Detect architecture and copy the core runtime libs libparakeet.so links
 # against, plus the matching dynamic loader as lib/ld.so.
@@ -51,7 +48,7 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 "$CURDIR/package/lib/librt.so.1"
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 "$CURDIR/package/lib/libpthread.so.0"
 elif [ "$(uname -s)" = "Darwin" ]; then
-    echo "Detected Darwin — system frameworks linked dynamically, no bundled libs needed"
+    echo "Detected Darwin"
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/parakeet-cpp/run.sh

@@ -3,17 +3,11 @@ set -e
 
 CURDIR=$(dirname "$(realpath "$0")")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${DYLD_LIBRARY_PATH:-}"
-	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.dylib"
-else
-	export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
-	export PARAKEET_LIBRARY="$CURDIR/lib/libparakeet.so"
-fi
+export LD_LIBRARY_PATH="$CURDIR/lib:$CURDIR:${LD_LIBRARY_PATH:-}"
 
 # If a self-contained ld.so was packaged, route through it so the
 # packaged libc / libstdc++ are used instead of the host's (matches the
-# whisper backend's runtime layout). Linux only.
+# whisper backend's runtime layout).
 if [ -f "$CURDIR/lib/ld.so" ]; then
 	echo "Using lib/ld.so"
 	exec "$CURDIR/lib/ld.so" "$CURDIR/parakeet-cpp-grpc" "$@"

backend/go/qwen3-tts-cpp/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # qwentts.cpp version
 QWEN3TTS_REPO?=https://github.com/ServeurpersoCom/qwentts.cpp
-QWEN3TTS_CPP_VERSION?=9dbe7ea26a01b30fccb117ae5e86807c1dc23d42
+QWEN3TTS_CPP_VERSION?=4536dcdce27c3764a93a06d6bf64026b124962f5
 SO_TARGET?=libgoqwen3ttscpp.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -65,8 +65,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgoqwen3ttscpp-avx.so libgoqwen3ttscpp-avx2.so libgoqwen3ttscpp-avx512.so libgoqwen3ttscpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.dylib
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = libgoqwen3ttscpp-fallback.so
 endif
 
 qwen3-tts-cpp: main.go goqwen3ttscpp.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: qwen3-tts-cpp
 build: package
 
 clean: purge
-	rm -rf libgoqwen3ttscpp*.so libgoqwen3ttscpp*.dylib package sources/qwentts.cpp qwen3-tts-cpp
+	rm -rf libgoqwen3ttscpp*.so package sources/qwentts.cpp qwen3-tts-cpp
 
 purge:
 	rm -rf build*
@@ -110,20 +110,13 @@ libgoqwen3ttscpp-fallback.so: sources/qwentts.cpp
 	SO_TARGET=libgoqwen3ttscpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
 	rm -rf build-libgoqwen3ttscpp-fallback.so
 
-# Build fallback variant as a dylib (Darwin)
-libgoqwen3ttscpp-fallback.dylib: sources/qwentts.cpp
-	$(info ${GREEN}I qwen3-tts-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgoqwen3ttscpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgoqwen3ttscpp-custom
-	rm -rf build-libgoqwen3ttscpp-fallback.dylib
-
 libgoqwen3ttscpp-custom: CMakeLists.txt cpp/goqwen3ttscpp.cpp cpp/goqwen3ttscpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target goqwen3ttscpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgoqwen3ttscpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgoqwen3ttscpp.so ./$(SO_TARGET)
 
 test: qwen3-tts-cpp
 	@echo "Running qwen3-tts-cpp tests..."

backend/go/qwen3-tts-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("QWEN3TTS_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgoqwen3ttscpp-fallback.dylib"
-		} else {
-			libName = "./libgoqwen3ttscpp-fallback.so"
-		}
+		libName = "./libgoqwen3ttscpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/qwen3-tts-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/qwen3-tts-cpp $CURDIR/package/
-cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgoqwen3ttscpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgoqwen3ttscpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/qwen3-tts-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
+LIBRARY="$CURDIR/libgoqwen3ttscpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgoqwen3ttscpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgoqwen3ttscpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export QWEN3TTS_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/rfdetr-cpp/Makefile

@@ -71,7 +71,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = librfdetrcpp-avx.so librfdetrcpp-avx2.so librfdetrcpp-avx512.so librfdetrcpp-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = librfdetrcpp-fallback.dylib
+	VARIANT_TARGETS = librfdetrcpp-fallback.so
 endif
 
 rfdetr-cpp: main.go gorfdetrcpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: rfdetr-cpp
 build: package
 
 clean: purge
-	rm -rf librfdetrcpp*.so librfdetrcpp*.dylib rfdetr-cpp package sources
+	rm -rf librfdetrcpp*.so rfdetr-cpp package sources
 
 purge:
 	rm -rf build*
@@ -110,19 +110,11 @@ librfdetrcpp-avx512.so: sources/rt-detr.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-librfdetrcpp-fallback.dylib: sources/rt-detr.cpp
-	rm -rfv build-$@
-	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
-	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
-	rm -rfv build-$@
-else
 librfdetrcpp-fallback.so: sources/rt-detr.cpp
 	rm -rfv build-$@
 	$(info ${GREEN}I rfdetr-cpp build info:fallback${RESET})
 	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) librfdetrcpp-custom
 	rm -rfv build-$@
-endif
 
 librfdetrcpp-custom: CMakeLists.txt
 	mkdir -p build-$(SO_TARGET) && \
@@ -130,8 +122,7 @@ librfdetrcpp-custom: CMakeLists.txt
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/librfdetrcpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/librfdetrcpp.so ./$(SO_TARGET)
 
 all: rfdetr-cpp package
 

backend/go/rfdetr-cpp/main.go

@@ -9,7 +9,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -28,11 +27,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("RFDETR_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./librfdetrcpp-fallback.dylib"
-		} else {
-			libName = "./librfdetrcpp-fallback.so"
-		}
+		libName = "./librfdetrcpp-fallback.so"
 	}
 
 	rfdetrLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/rfdetr-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/librfdetrcpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/librfdetrcpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/librfdetrcpp-*.so $CURDIR/package/
 cp -avf $CURDIR/rfdetr-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/rfdetr-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/librfdetrcpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
+LIBRARY="$CURDIR/librfdetrcpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/librfdetrcpp-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/librfdetrcpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export RFDETR_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sam3-cpp/Makefile

@@ -66,7 +66,7 @@ ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgosam3-avx.so libgosam3-avx2.so libgosam3-avx512.so libgosam3-fallback.so
 else
 	# On non-Linux (e.g., Darwin), build only fallback variant
-	VARIANT_TARGETS = libgosam3-fallback.dylib
+	VARIANT_TARGETS = libgosam3-fallback.so
 endif
 
 sam3-cpp: main.go gosam3.go $(VARIANT_TARGETS)
@@ -78,7 +78,7 @@ package: sam3-cpp
 build: package
 
 clean: purge
-	rm -rf libgosam3*.so libgosam3*.dylib sam3-cpp package sources
+	rm -rf libgosam3*.so sam3-cpp package sources
 
 purge:
 	rm -rf build*
@@ -105,19 +105,11 @@ libgosam3-avx512.so: sources/sam3.cpp
 endif
 
 # Build fallback variant (all platforms)
-ifeq ($(UNAME_S),Darwin)
-libgosam3-fallback.dylib: sources/sam3.cpp
-	$(MAKE) purge
-	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
-	SO_TARGET=libgosam3-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
-	rm -rfv build*
-else
 libgosam3-fallback.so: sources/sam3.cpp
 	$(MAKE) purge
 	$(info ${GREEN}I sam3-cpp build info:fallback${RESET})
 	SO_TARGET=libgosam3-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgosam3-custom
 	rm -rfv build*
-endif
 
 libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	mkdir -p build-$(SO_TARGET) && \
@@ -125,7 +117,6 @@ libgosam3-custom: CMakeLists.txt cpp/gosam3.cpp cpp/gosam3.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgosam3.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgosam3.so ./$(SO_TARGET)
 
 all: sam3-cpp package

backend/go/sam3-cpp/main.go

@@ -3,7 +3,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SAM3_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgosam3-fallback.dylib"
-		} else {
-			libName = "./libgosam3-fallback.so"
-		}
+		libName = "./libgosam3-fallback.so"
 	}
 
 	gosamLib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sam3-cpp/package.sh

@@ -10,8 +10,7 @@ REPO_ROOT="${CURDIR}/../../.."
 # Create lib directory
 mkdir -p $CURDIR/package/lib
 
-cp -fv $CURDIR/libgosam3-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgosam3-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -avf $CURDIR/libgosam3-*.so $CURDIR/package/
 cp -avf $CURDIR/sam3-cpp $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/sam3-cpp/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgosam3-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgosam3-fallback.so"
+LIBRARY="$CURDIR/libgosam3-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosam3-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgosam3-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SAM3_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/sherpa-onnx/backend.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"runtime"
 	"strconv"
 	"strings"
 	"sync"
@@ -239,19 +238,11 @@ func loadSherpaLibs() error {
 func loadSherpaLibsOnce() error {
 	shimLib := os.Getenv("SHERPA_SHIM_LIBRARY")
 	if shimLib == "" {
-		if runtime.GOOS == "darwin" {
-			shimLib = "libsherpa-shim.dylib"
-		} else {
-			shimLib = "libsherpa-shim.so"
-		}
+		shimLib = "libsherpa-shim.so"
 	}
 	capiLib := os.Getenv("SHERPA_ONNX_LIBRARY")
 	if capiLib == "" {
-		if runtime.GOOS == "darwin" {
-			capiLib = "libsherpa-onnx-c-api.dylib"
-		} else {
-			capiLib = "libsherpa-onnx-c-api.so"
-		}
+		capiLib = "libsherpa-onnx-c-api.so"
 	}
 
 	shim, err := purego.Dlopen(shimLib, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/sherpa-onnx/run.sh

@@ -3,13 +3,7 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
-if [ "$(uname)" = "Darwin" ]; then
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-	export SHERPA_SHIM_LIBRARY=$CURDIR/lib/libsherpa-shim.dylib
-	export SHERPA_ONNX_LIBRARY=$CURDIR/lib/libsherpa-onnx-c-api.dylib
-else
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
-fi
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 
 if [ -f $CURDIR/lib/ld.so ]; then
 	echo "Using lib/ld.so"

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?=8caa3f908ae6d4a4bef531e73b9a969f266a3d1f
+STABLEDIFFUSION_GGML_VERSION?=b12098f5d09fc83da36e65c784f7bdb16a5a5ebf
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 
@@ -131,7 +131,6 @@ libgosd-custom: CMakeLists.txt cpp/gosd.cpp cpp/gosd.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgosd.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgosd.so ./$(SO_TARGET)
 
 all: stablediffusion-ggml package

backend/go/stablediffusion-ggml/main.go

@@ -3,7 +3,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("SD_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgosd-fallback.dylib"
-		} else {
-			libName = "./libgosd-fallback.so"
-		}
+		libName = "./libgosd-fallback.so"
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/stablediffusion-ggml/package.sh

@@ -12,7 +12,6 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/libgosd-*.so $CURDIR/package/
-cp -fv $CURDIR/libgosd-*.dylib $CURDIR/package/ 2>/dev/null || true
 cp -avf $CURDIR/stablediffusion-ggml $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 

backend/go/stablediffusion-ggml/run.sh

@@ -12,18 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single library variant (Metal or Accelerate). The gosd target is
-	# built as a CMake MODULE, which emits a .dylib for a SHARED build but a
-	# .so for a MODULE build on Apple, so prefer .dylib and fall back to .so.
-	LIBRARY="$CURDIR/libgosd-fallback.dylib"
-	if [ ! -e "$LIBRARY" ]; then
-		LIBRARY="$CURDIR/libgosd-fallback.so"
-	fi
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgosd-fallback.so"
+LIBRARY="$CURDIR/libgosd-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgosd-avx.so ]; then
@@ -45,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgosd-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export SD_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/go/supertonic/helper.go

@@ -16,7 +16,6 @@ import (
 	"os"
 	"path/filepath"
 	"regexp"
-	"runtime"
 	"strings"
 	"time"
 	"unicode"
@@ -944,13 +943,7 @@ func InitializeONNXRuntime() error {
 			}
 		}
 		if libPath == "" {
-			// LocalAI: default to the platform-native shared library
-			// extension when nothing else is found (dyld vs ld.so).
-			if runtime.GOOS == "darwin" {
-				libPath = "/usr/local/lib/libonnxruntime.dylib"
-			} else {
-				libPath = "/usr/local/lib/libonnxruntime.so"
-			}
+			libPath = "/usr/local/lib/libonnxruntime.so"
 		}
 	}
 	ort.SetSharedLibraryPath(libPath)

backend/go/supertonic/package.sh

@@ -32,10 +32,6 @@ elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
     cp -arfLv /lib/aarch64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
     cp -arfLv /lib/aarch64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
     cp -arfLv /lib/aarch64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
-elif [ $(uname -s) = "Darwin" ]; then
-    # macOS: dyld resolves the bundled .dylib via DYLD_LIBRARY_PATH (set in
-    # run.sh); there is no ld.so loader nor glibc to bundle.
-    echo "Detected Darwin"
 else
     echo "Error: Could not detect architecture"
     exit 1

backend/go/supertonic/run.sh

@@ -3,19 +3,12 @@ set -ex
 
 CURDIR=$(dirname "$(realpath $0)")
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS uses dyld: there is no ld.so loader, and the search path env
-	# var is DYLD_LIBRARY_PATH. ONNX Runtime ships as a .dylib here.
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.dylib
-else
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
-	export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export ONNXRUNTIME_LIB_PATH=$CURDIR/lib/libonnxruntime.so
 
-	if [ -f $CURDIR/lib/ld.so ]; then
-		echo "Using lib/ld.so"
-		exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
-	fi
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	exec $CURDIR/lib/ld.so $CURDIR/supertonic "$@"
 fi
 
 exec $CURDIR/supertonic "$@"

backend/go/vibevoice-cpp/Makefile

@@ -70,8 +70,8 @@ UNAME_S := $(shell uname -s)
 ifeq ($(UNAME_S),Linux)
 	VARIANT_TARGETS = libgovibevoicecpp-avx.so libgovibevoicecpp-avx2.so libgovibevoicecpp-avx512.so libgovibevoicecpp-fallback.so
 else
-	# On non-Linux (e.g., Darwin), build only fallback variant (as a dylib)
-	VARIANT_TARGETS = libgovibevoicecpp-fallback.dylib
+	# On non-Linux (e.g., Darwin), build only fallback variant
+	VARIANT_TARGETS = libgovibevoicecpp-fallback.so
 endif
 
 vibevoice-cpp: main.go govibevoicecpp.go $(VARIANT_TARGETS)
@@ -83,7 +83,7 @@ package: vibevoice-cpp
 build: package
 
 clean: purge
-	rm -rf libgovibevoicecpp*.so libgovibevoicecpp*.dylib package sources/vibevoice.cpp vibevoice-cpp
+	rm -rf libgovibevoicecpp*.so package sources/vibevoice.cpp vibevoice-cpp
 
 purge:
 	rm -rf build*
@@ -119,21 +119,13 @@ libgovibevoicecpp-fallback.so: sources/vibevoice.cpp
 	SO_TARGET=libgovibevoicecpp-fallback.so CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
 	rm -rfv build*
 
-# Build fallback variant as a dylib (Darwin)
-libgovibevoicecpp-fallback.dylib: sources/vibevoice.cpp
-	$(MAKE) purge
-	$(info ${GREEN}I vibevoice-cpp build info:fallback (dylib)${RESET})
-	SO_TARGET=libgovibevoicecpp-fallback.dylib CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libgovibevoicecpp-custom
-	rm -rfv build*
-
 libgovibevoicecpp-custom: CMakeLists.txt cpp/govibevoicecpp.cpp cpp/govibevoicecpp.h
 	mkdir -p build-$(SO_TARGET) && \
 	cd build-$(SO_TARGET) && \
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) --target govibevoicecpp && \
 	cd .. && \
-	(mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET) 2>/dev/null || \
-	 mv build-$(SO_TARGET)/libgovibevoicecpp.dylib ./$(SO_TARGET) 2>/dev/null)
+	mv build-$(SO_TARGET)/libgovibevoicecpp.so ./$(SO_TARGET)
 
 test: vibevoice-cpp
 	@echo "Running vibevoice-cpp tests..."

backend/go/vibevoice-cpp/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -22,11 +21,7 @@ type LibFuncs struct {
 func main() {
 	libName := os.Getenv("VIBEVOICECPP_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgovibevoicecpp-fallback.dylib"
-		} else {
-			libName = "./libgovibevoicecpp-fallback.so"
-		}
+		libName = "./libgovibevoicecpp-fallback.so"
 	}
 
 	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/vibevoice-cpp/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/vibevoice-cpp $CURDIR/package/
-cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgovibevoicecpp-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgovibevoicecpp-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/vibevoice-cpp/run.sh

@@ -11,13 +11,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgovibevoicecpp-fallback.so"
+LIBRARY="$CURDIR/libgovibevoicecpp-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgovibevoicecpp-avx.so ]; then
@@ -38,10 +34,9 @@ else
 			LIBRARY="$CURDIR/libgovibevoicecpp-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export VIBEVOICECPP_LIBRARY=$LIBRARY
 
 if [ -f $CURDIR/lib/ld.so ]; then

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?=43d78af5be58f41d6ffbc227d608f104577741ea
+WHISPER_CPP_VERSION?=5ed76e9a079962f1c85cfce44edd325c27ef1f97
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF
@@ -117,7 +117,6 @@ libgowhisper-custom: CMakeLists.txt cpp/gowhisper.cpp cpp/gowhisper.h
 	cmake .. $(CMAKE_ARGS) && \
 	cmake --build . --config Release -j$(JOBS) && \
 	cd .. && \
-	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET) 2>/dev/null || \
-		mv build-$(SO_TARGET)/libgowhisper.dylib ./$(SO_TARGET:.so=.dylib)
+	mv build-$(SO_TARGET)/libgowhisper.so ./$(SO_TARGET)
 
 all: whisper package

backend/go/whisper/main.go

@@ -4,7 +4,6 @@ package main
 import (
 	"flag"
 	"os"
-	"runtime"
 
 	"github.com/ebitengine/purego"
 	grpc "github.com/mudler/LocalAI/pkg/grpc"
@@ -23,11 +22,7 @@ func main() {
 	// Get library name from environment variable, default to fallback
 	libName := os.Getenv("WHISPER_LIBRARY")
 	if libName == "" {
-		if runtime.GOOS == "darwin" {
-			libName = "./libgowhisper-fallback.dylib"
-		} else {
-			libName = "./libgowhisper-fallback.so"
-		}
+		libName = "./libgowhisper-fallback.so"
 	}
 
 	gosd, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)

backend/go/whisper/package.sh

@@ -12,8 +12,7 @@ REPO_ROOT="${CURDIR}/../../.."
 mkdir -p $CURDIR/package/lib
 
 cp -avf $CURDIR/whisper $CURDIR/package/
-cp -fv $CURDIR/libgowhisper-*.so $CURDIR/package/ 2>/dev/null || true
-cp -fv $CURDIR/libgowhisper-*.dylib $CURDIR/package/ 2>/dev/null || true
+cp -fv $CURDIR/libgowhisper-*.so $CURDIR/package/
 cp -fv $CURDIR/run.sh $CURDIR/package/
 
 # Detect architecture and copy appropriate libraries

backend/go/whisper/run.sh

@@ -12,13 +12,9 @@ if [ "$(uname)" != "Darwin" ]; then
 	grep -e "flags" /proc/cpuinfo | head -1
 fi
 
-if [ "$(uname)" = "Darwin" ]; then
-	# macOS: single dylib variant (Metal or Accelerate)
-	LIBRARY="$CURDIR/libgowhisper-fallback.dylib"
-	export DYLD_LIBRARY_PATH=$CURDIR/lib:$DYLD_LIBRARY_PATH
-else
-	LIBRARY="$CURDIR/libgowhisper-fallback.so"
+LIBRARY="$CURDIR/libgowhisper-fallback.so"
 
+if [ "$(uname)" != "Darwin" ]; then
 	if grep -q -e "\savx\s" /proc/cpuinfo ; then
 		echo "CPU:    AVX    found OK"
 		if [ -e $CURDIR/libgowhisper-avx.so ]; then
@@ -40,10 +36,9 @@ else
 			LIBRARY="$CURDIR/libgowhisper-avx512.so"
 		fi
 	fi
-
-	export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 fi
 
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
 export WHISPER_LIBRARY=$LIBRARY
 
 # If there is a lib/ld.so, use it

backend/index.yaml

@@ -1284,7 +1284,6 @@
     nvidia-cuda-13: "cuda13-liquid-audio"
     nvidia-cuda-12: "cuda12-liquid-audio"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-liquid-audio"
-    metal: "metal-liquid-audio"
   icon: https://cdn-avatars.huggingface.co/v1/production/uploads/61b8e2ba285851687028d395/7_6D7rWrLxp2hb6OHSV1p.png
 - &qwen-tts
   urls:
@@ -1570,7 +1569,6 @@
     - TTS
   capabilities:
     default: "cpu-supertonic"
-    metal: "metal-supertonic"
 - !!merge <<: *neutts
   name: "neutts-development"
   capabilities:
@@ -4614,7 +4612,6 @@
     nvidia-cuda-13: "cuda13-liquid-audio-development"
     nvidia-cuda-12: "cuda12-liquid-audio-development"
     nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-liquid-audio-development"
-    metal: "metal-liquid-audio-development"
 - !!merge <<: *liquid-audio
   name: "cpu-liquid-audio"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-liquid-audio"
@@ -4625,16 +4622,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-liquid-audio"
   mirrors:
     - localai/localai-backends:master-cpu-liquid-audio
-- !!merge <<: *liquid-audio
-  name: "metal-liquid-audio"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-liquid-audio"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-liquid-audio
-- !!merge <<: *liquid-audio
-  name: "metal-liquid-audio-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-liquid-audio"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-liquid-audio
 - !!merge <<: *liquid-audio
   name: "cuda12-liquid-audio"
   uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-liquid-audio"
@@ -5295,7 +5282,6 @@
     nvidia: "cuda12-trl"
     nvidia-cuda-12: "cuda12-trl"
     nvidia-cuda-13: "cuda13-trl"
-    metal: "metal-trl"
 ## TRL backend images
 - !!merge <<: *trl
   name: "cpu-trl"
@@ -5327,16 +5313,6 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-trl"
   mirrors:
     - localai/localai-backends:master-gpu-nvidia-cuda-13-trl
-- !!merge <<: *trl
-  name: "metal-trl"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-trl"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-trl
-- !!merge <<: *trl
-  name: "metal-trl-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-trl"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-trl
 ## llama.cpp quantization backend
 - &llama-cpp-quantization
   name: "llama-cpp-quantization"
@@ -5508,7 +5484,6 @@
   name: "supertonic-development"
   capabilities:
     default: "cpu-supertonic-development"
-    metal: "metal-supertonic-development"
 - !!merge <<: *supertonic
   name: "cpu-supertonic"
   uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-supertonic"
@@ -5519,13 +5494,3 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-cpu-supertonic"
   mirrors:
     - localai/localai-backends:master-cpu-supertonic
-- !!merge <<: *supertonic
-  name: "metal-supertonic"
-  uri: "quay.io/go-skynet/local-ai-backends:latest-metal-darwin-arm64-supertonic"
-  mirrors:
-    - localai/localai-backends:latest-metal-darwin-arm64-supertonic
-- !!merge <<: *supertonic
-  name: "metal-supertonic-development"
-  uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-supertonic"
-  mirrors:
-    - localai/localai-backends:master-metal-darwin-arm64-supertonic

backend/python/liquid-audio/install.sh

@@ -14,11 +14,5 @@ else
 fi
 
 # liquid-audio's torch wheels are large; allow upgrades to satisfy transitive pins
-EXTRA_PIP_INSTALL_FLAGS+=" --upgrade"
-# --index-strategy is a uv-only flag. The darwin/MPS build installs with pip
-# (USE_PIP=true in scripts/build/python-darwin.sh), which rejects it. Only add
-# it on the uv path; Linux/CUDA resolution is unchanged.
-if [ "x${USE_PIP:-}" != "xtrue" ]; then
-    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-first-match"
-fi
+EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
 installRequirements

backend/python/liquid-audio/requirements-mps.txt

@@ -1,4 +1,3 @@
-# MPS (Apple Silicon / Metal) build profile - installed by the darwin CI job.
 torch>=2.8.0
 torchaudio>=2.8.0
 torchcodec>=0.9.1

backend/python/trl/install.sh

@@ -8,13 +8,7 @@ else
     source $backend_dir/../common/libbackend.sh
 fi
 
-EXTRA_PIP_INSTALL_FLAGS+=" --upgrade"
-# --index-strategy is a uv-only flag. The darwin/MPS build installs with pip
-# (USE_PIP=true in scripts/build/python-darwin.sh), which rejects it. Only add
-# it when uv is the installer, keeping the Linux/CUDA resolution unchanged.
-if [ "x${USE_PIP:-}" != "xtrue" ]; then
-    EXTRA_PIP_INSTALL_FLAGS+=" --index-strategy=unsafe-first-match"
-fi
+EXTRA_PIP_INSTALL_FLAGS+=" --upgrade --index-strategy=unsafe-first-match"
 installRequirements
 
 # Fetch convert_hf_to_gguf.py and gguf package from the same llama.cpp version

backend/python/trl/requirements-mps.txt

@@ -1,12 +0,0 @@
-torch==2.10.0
-trl
-peft
-datasets>=3.0.0
-transformers>=4.56.2
-accelerate>=1.4.0
-huggingface-hub>=1.3.0
-sentencepiece
-# Note: bitsandbytes is intentionally omitted on MPS. It is only used by the
-# CUDA (cublas) variants for 8-bit/4-bit quantization and has poor support on
-# Apple Silicon. torch here uses the plain PyPI wheels, which ship MPS support
-# on macOS arm64.

core/application/config_file_watcher.go

@@ -215,7 +215,6 @@ func readRuntimeSettingsJson(startupAppConfig config.ApplicationConfig) fileHand
 		envBackendGalleries := slices.Equal(appConfig.BackendGalleries, startupAppConfig.BackendGalleries)
 		envAutoloadGalleries := appConfig.AutoloadGalleries == startupAppConfig.AutoloadGalleries
 		envAutoloadBackendGalleries := appConfig.AutoloadBackendGalleries == startupAppConfig.AutoloadBackendGalleries
-		envPIIDefaultDetectors := slices.Equal(appConfig.PIIDefaultDetectors, startupAppConfig.PIIDefaultDetectors)
 		envAgentJobRetentionDays := appConfig.AgentJobRetentionDays == startupAppConfig.AgentJobRetentionDays
 		envForceEvictionWhenBusy := appConfig.ForceEvictionWhenBusy == startupAppConfig.ForceEvictionWhenBusy
 		envLRUEvictionMaxRetries := appConfig.LRUEvictionMaxRetries == startupAppConfig.LRUEvictionMaxRetries
@@ -336,15 +335,6 @@ func readRuntimeSettingsJson(startupAppConfig config.ApplicationConfig) fileHand
 			if settings.AutoloadBackendGalleries != nil && !envAutoloadBackendGalleries {
 				appConfig.AutoloadBackendGalleries = *settings.AutoloadBackendGalleries
 			}
-			if settings.PIIDefaultDetectors != nil && !envPIIDefaultDetectors {
-				// Request-side default redaction reads this live via
-				// ResolvePIIPolicy, so a file edit takes effect on the next chat
-				// request. The MITM listener resolves its per-host detector map
-				// once at start, so a raw file edit reaches cloud-proxy traffic
-				// only after a restart or a POST /api/settings (which rebuilds
-				// the listener) — the admin UI uses the latter.
-				appConfig.PIIDefaultDetectors = append([]string(nil), (*settings.PIIDefaultDetectors)...)
-			}
 			if settings.AutoUpgradeBackends != nil {
 				appConfig.AutoUpgradeBackends = *settings.AutoUpgradeBackends
 			}

core/application/runtime_settings_branding_test.go

@@ -109,52 +109,6 @@ var _ = Describe("loadRuntimeSettingsFromFile", func() {
 		})
 	})
 
-	// Instance-wide default PII detectors. The file is the only source (no
-	// env var), and the loader runs immediately before startMITMIfConfigured,
-	// so a regression here means the cloud-proxy MITM listener resolves an
-	// empty detector set at boot and forwards intercepted traffic unredacted —
-	// even though pii_default_detectors is on disk and the MITM model has PII
-	// enabled. It also breaks request-side default redaction the same way.
-	Describe("PII default detectors", func() {
-		It("loads pii_default_detectors from the file", func() {
-			cfg := &config.ApplicationConfig{DynamicConfigsDir: seedSettings(`{"pii_default_detectors": ["privacy-filter-nemotron", "secret-filter"]}`)}
-			loadRuntimeSettingsFromFile(cfg)
-			Expect(cfg.PIIDefaultDetectors).To(Equal([]string{"privacy-filter-nemotron", "secret-filter"}))
-		})
-
-		It("does not override an env/CLI-set value (LOCALAI_PII_DEFAULT_DETECTORS)", func() {
-			cfg := &config.ApplicationConfig{
-				DynamicConfigsDir:   seedSettings(`{"pii_default_detectors": ["from-file"]}`),
-				PIIDefaultDetectors: []string{"from-env"}, // simulate WithPIIDefaultDetectors(env)
-			}
-			loadRuntimeSettingsFromFile(cfg)
-			Expect(cfg.PIIDefaultDetectors).To(Equal([]string{"from-env"}), "env var must win over the persisted file value")
-		})
-	})
-
-	// The live file watcher applies pii_default_detectors on a runtime change
-	// the same way it handles galleries/threads/etc.: env-set values (current
-	// == startup snapshot) are left alone, otherwise the file value is applied
-	// to the live config so request-side default redaction picks it up without
-	// a restart.
-	Describe("file watcher: pii_default_detectors", func() {
-		It("applies a changed file value to the live config", func() {
-			startup := config.ApplicationConfig{} // no env baseline
-			live := &config.ApplicationConfig{PIIDefaultDetectors: []string{"old"}}
-			handler := readRuntimeSettingsJson(startup)
-			Expect(handler([]byte(`{"pii_default_detectors":["new-a","new-b"]}`), live)).To(Succeed())
-			Expect(live.PIIDefaultDetectors).To(Equal([]string{"new-a", "new-b"}))
-		})
-
-		It("leaves an env-controlled value untouched", func() {
-			startup := config.ApplicationConfig{PIIDefaultDetectors: []string{"from-env"}}
-			live := &config.ApplicationConfig{PIIDefaultDetectors: []string{"from-env"}}
-			handler := readRuntimeSettingsJson(startup)
-			Expect(handler([]byte(`{"pii_default_detectors":["from-file"]}`), live)).To(Succeed())
-			Expect(live.PIIDefaultDetectors).To(Equal([]string{"from-env"}), "env-controlled detectors must not be overwritten by the file")
-		})
-	})
-
 	// The Agent Pool block has a mix of zero and non-zero defaults
 	// (Enabled=true, EmbeddingModel="granite-...", MaxChunkingSize=400,
 	// VectorEngine="chromem", AgentHubURL="https://agenthub.localai.io").

core/application/startup.go

@@ -750,20 +750,6 @@ func loadRuntimeSettingsFromFile(options *config.ApplicationConfig) {
 		options.MITMListen = *settings.MITMListen
 	}
 
-	// Instance-wide default PII detectors. LOCALAI_PII_DEFAULT_DETECTORS (via
-	// WithPIIDefaultDetectors) wins when set; otherwise the file is the source
-	// — apply it only when the env/CLI left the value empty, mirroring the
-	// "env > file" precedence used for the other fields. This must land before
-	// startMITMIfConfigured (called right after this loader): the cloud-proxy
-	// listener resolves each intercept host's detectors once at start via
-	// ResolvePIIPolicy, and a MITM model that names no detectors of its own
-	// falls back to these defaults. Without it the listener (and request-side
-	// default redaction) starts with an empty detector set and forwards
-	// traffic unredacted even though pii_default_detectors is on disk.
-	if settings.PIIDefaultDetectors != nil && len(options.PIIDefaultDetectors) == 0 {
-		options.PIIDefaultDetectors = append([]string(nil), (*settings.PIIDefaultDetectors)...)
-	}
-
 	// Backend upgrade flags
 	if settings.AutoUpgradeBackends != nil {
 		if !options.AutoUpgradeBackends {

core/cli/run.go

@@ -140,7 +140,7 @@ type RunCMD struct {
 	OIDCIssuer           string `env:"LOCALAI_OIDC_ISSUER" help:"OIDC issuer URL for auto-discovery" group:"auth"`
 	OIDCClientID         string `env:"LOCALAI_OIDC_CLIENT_ID" help:"OIDC Client ID (auto-enables auth)" group:"auth"`
 	OIDCClientSecret     string `env:"LOCALAI_OIDC_CLIENT_SECRET" help:"OIDC Client Secret" group:"auth"`
-	ExternalBaseURL      string `env:"LOCALAI_BASE_URL" help:"External base URL of this instance (e.g. https://localhost:8080). Used for OAuth callbacks and self-referential links (generated images/videos, job status). When unset, derived from X-Forwarded-Proto/Host or Forwarded headers." group:"api"`
+	AuthBaseURL          string `env:"LOCALAI_BASE_URL" help:"Base URL for OAuth callbacks (e.g. http://localhost:8080)" group:"auth"`
 	AuthAdminEmail       string `env:"LOCALAI_ADMIN_EMAIL" help:"Email address to auto-promote to admin role" group:"auth"`
 	AuthRegistrationMode string `env:"LOCALAI_REGISTRATION_MODE" default:"open" help:"Registration mode: 'open' (default), 'approval', or 'invite' (invite code required)" group:"auth"`
 	DisableLocalAuth     bool   `env:"LOCALAI_DISABLE_LOCAL_AUTH" default:"false" help:"Disable local email/password registration and login (use with OAuth/OIDC-only setups)" group:"auth"`
@@ -181,8 +181,6 @@ type RunCMD struct {
 	// Cloud-proxy MITM listener (off by default).
 	MITMListen string `env:"LOCALAI_MITM_LISTEN" help:"Address (host:port) for the cloudproxy MITM listener. Empty = disabled. Clients set HTTPS_PROXY=http://<this>:<port>. Intercept hosts are declared per-model via the model YAML mitm.hosts: block; create one from the Add Model UI." group:"middleware"`
 	MITMCADir  string `env:"LOCALAI_MITM_CA_DIR" type:"path" help:"Directory holding the MITM proxy CA cert + key. Defaults to <data-path>/mitm-ca." group:"middleware"`
-
-	PIIDefaultDetectors []string `env:"LOCALAI_PII_DEFAULT_DETECTORS" help:"Instance-wide default PII/secret detector model names applied to any PII-enabled model (chiefly cloud-proxy / MITM models) that names no pii.detectors of its own. Comma-separated, e.g. privacy-filter-nemotron,secret-filter. Takes precedence over the value persisted via the Middleware UI." group:"middleware"`
 }
 
 func (r *RunCMD) Run(ctx *cliContext.Context) error {
@@ -245,7 +243,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithAPIAddress(r.Address),
 		config.WithMITMListen(r.MITMListen),
 		config.WithMITMCADir(r.MITMCADir),
-		config.WithPIIDefaultDetectors(r.PIIDefaultDetectors),
 		config.WithAgentJobRetentionDays(r.AgentJobRetentionDays),
 		config.WithLlamaCPPTunnelCallback(func(tunnels []string) {
 			tunnelEnvVar := strings.Join(tunnels, ",")
@@ -503,6 +500,9 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 			opts = append(opts, config.WithAuthOIDCClientID(r.OIDCClientID))
 			opts = append(opts, config.WithAuthOIDCClientSecret(r.OIDCClientSecret))
 		}
+		if r.AuthBaseURL != "" {
+			opts = append(opts, config.WithAuthBaseURL(r.AuthBaseURL))
+		}
 		if r.AuthAdminEmail != "" {
 			opts = append(opts, config.WithAuthAdminEmail(r.AuthAdminEmail))
 		}
@@ -520,12 +520,6 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		}
 	}
 
-	// Applied unconditionally: the external base URL governs all self-referential
-	// links (not just OAuth callbacks), so it must take effect even when auth is off.
-	if r.ExternalBaseURL != "" {
-		opts = append(opts, config.WithExternalBaseURL(r.ExternalBaseURL))
-	}
-
 	if idleWatchDog || busyWatchDog {
 		opts = append(opts, config.EnableWatchDog)
 		if idleWatchDog {

core/config/application_config.go

@@ -49,13 +49,6 @@ type ApplicationConfig struct {
 	P2PNetworkID                  string
 	Federated                     bool
 
-	// ExternalBaseURL is the externally visible base URL of this instance
-	// (scheme+host[:port]), set via LOCALAI_BASE_URL. When non-empty it is
-	// authoritative for every self-referential URL LocalAI emits (OAuth
-	// callbacks, generated image/video links, async job StatusURLs),
-	// overriding proxy-header detection. Empty = derive from request headers.
-	ExternalBaseURL string
-
 	// DisableStats turns off per-request token tracking. By default the
 	// routing module's billing recorder runs in every mode (including
 	// no-auth single-user) so dashboards and `/api/usage` are immediately
@@ -203,6 +196,7 @@ type AuthConfig struct {
 	OIDCIssuer          string // OIDC issuer URL for auto-discovery (e.g. https://accounts.google.com)
 	OIDCClientID        string
 	OIDCClientSecret    string
+	BaseURL             string // for OAuth callback URLs (e.g. "http://localhost:8080")
 	AdminEmail          string // auto-promote to admin on login
 	RegistrationMode    string // "open", "approval" (default when empty), "invite"
 	DisableLocalAuth    bool   // disable local email/password registration and login
@@ -718,18 +712,6 @@ func WithMITMCADir(dir string) AppOption {
 	}
 }
 
-// WithPIIDefaultDetectors sets the instance-wide default PII/secret detector
-// model names applied to any PII-enabled model (chiefly cloud-proxy / MITM
-// models) that names no pii.detectors of its own. CLI/env:
-// LOCALAI_PII_DEFAULT_DETECTORS. Empty leaves the value to
-// runtime_settings.json / the Middleware UI; a non-empty value takes
-// precedence over the file (env > file).
-func WithPIIDefaultDetectors(detectors []string) AppOption {
-	return func(o *ApplicationConfig) {
-		o.PIIDefaultDetectors = detectors
-	}
-}
-
 func WithDynamicConfigDir(dynamicConfigsDir string) AppOption {
 	return func(o *ApplicationConfig) {
 		o.DynamicConfigsDir = dynamicConfigsDir
@@ -956,9 +938,9 @@ func WithAuthGitHubClientSecret(clientSecret string) AppOption {
 	}
 }
 
-func WithExternalBaseURL(url string) AppOption {
+func WithAuthBaseURL(baseURL string) AppOption {
 	return func(o *ApplicationConfig) {
-		o.ExternalBaseURL = url
+		o.Auth.BaseURL = baseURL
 	}
 }
 

core/config/hardware_defaults.go

@@ -2,7 +2,6 @@ package config
 
 import (
 	"fmt"
-	"os"
 	"strconv"
 	"strings"
 
@@ -10,19 +9,6 @@ import (
 	"github.com/mudler/xlog"
 )
 
-// HardwareDefaultsDisabled reports whether hardware auto-tuning is turned off via
-// LOCALAI_DISABLE_HARDWARE_DEFAULTS=true (mirrors LOCALAI_DISABLE_GUESSING). When
-// set, ApplyHardwareDefaults and the distributed router's node tuning are
-// skipped entirely, so the backend runs llama.cpp's stock batch/parallel
-// behavior — an escape hatch for users who want predictable, un-tuned defaults.
-func HardwareDefaultsDisabled() bool {
-	// Read directly like the sibling LOCALAI_DISABLE_GUESSING toggle in
-	// hooks_llamacpp.go: these config-layer heuristic switches run deep in the
-	// defaults pipeline with no ApplicationConfig in scope to plumb through.
-	//nolint:forbidigo // config-layer heuristic toggle, mirrors LOCALAI_DISABLE_GUESSING
-	return os.Getenv("LOCALAI_DISABLE_HARDWARE_DEFAULTS") == "true"
-}
-
 // Hardware-driven model-config defaults.
 //
 // This sits alongside the other config overriders (ApplyInferenceDefaults for
@@ -68,35 +54,8 @@ func (g GPU) IsNVIDIABlackwell() bool {
 	return maj >= 12
 }
 
-// Compute-buffer headroom guard for the raised physical batch.
-//
-// Raising n_ubatch grows the CUDA *compute buffer* (the scratch for the forward
-// graph), which is allocated PER DEVICE — it does not benefit from a second GPU
-// the way weights or KV (which are split across devices) do. The buffer scales
-// ~linearly with n_ubatch * n_ctx, so a large context turns the GB10-tuned
-// ub2048 into multi-GiB of extra scratch that must fit on a SINGLE card. On a
-// 16 GiB consumer Blackwell with a 200k context that overflows (issue #10485),
-// even though the GB10 it was measured on (128 GiB unified memory) had room.
-//
-// These constants size a conservative guard: only raise the batch when the
-// extra scratch fits the per-device VRAM ceiling.
-const (
-	// computeBufferBytesPerCell approximates the CUDA compute-buffer cost of one
-	// (n_ubatch * n_ctx) cell. Derived from an observed allocation (ub2048 *
-	// ctx204800 ~= 4.5 GiB => ~11 B/cell) and rounded up to 16 for margin, since
-	// the real cost also grows with model width (heads / embedding dim) which we
-	// don't know at config time.
-	computeBufferBytesPerCell = 16
-	// blackwellBatchHeadroomDivisor caps the extra compute buffer from raising the
-	// physical batch at VRAM/divisor. /4 keeps the bulk of a device for weights +
-	// KV, which already dominate VRAM use.
-	blackwellBatchHeadroomDivisor = 4
-)
-
 // PhysicalBatch returns the canonical physical batch (n_batch/n_ubatch) for the
-// given hardware class, ignoring context/VRAM headroom. Use
-// PhysicalBatchForContext when a model context and per-device VRAM are known
-// (the load paths) so the raised batch can't overflow a single device.
+// given hardware, used when the model config leaves batch unset.
 func PhysicalBatch(g GPU) int {
 	if g.IsNVIDIABlackwell() {
 		return BlackwellPhysicalBatch
@@ -104,51 +63,6 @@ func PhysicalBatch(g GPU) int {
 	return DefaultPhysicalBatch
 }
 
-// PhysicalBatchForContext is PhysicalBatch gated on per-device VRAM headroom for
-// the given context: it only raises the batch above the conservative default
-// when the extra compute buffer (which is allocated on a single device and grows
-// with n_ubatch * n_ctx) fits within blackwellBatchHeadroomDivisor of the GPU's
-// VRAM. g.VRAM must be the PER-DEVICE ceiling (the smallest device on a
-// multi-GPU host), not the summed total — the compute buffer can't be split.
-//
-// VRAM 0 (unknown) stays conservative rather than risk a per-device OOM; the
-// GB10 / unified-memory path reports system RAM, so it still clears the guard.
-func PhysicalBatchForContext(g GPU, ctx int) int {
-	if !g.IsNVIDIABlackwell() {
-		return DefaultPhysicalBatch
-	}
-	if g.VRAM == 0 {
-		return DefaultPhysicalBatch
-	}
-	if largeContextForDevice(g, ctx) {
-		return DefaultPhysicalBatch
-	}
-	return BlackwellPhysicalBatch
-}
-
-// largeContextForDevice reports whether the given context is large relative to
-// the per-device VRAM ceiling — the shared "tight single-model fit" signal that
-// suppresses BOTH throughput-oriented defaults (the Blackwell batch boost and
-// the concurrency slot count). It sizes the extra compute-buffer scratch a
-// raised batch would need at this context (which grows ~n_ubatch * n_ctx and
-// is allocated per device) and asks whether it overflows a fraction of the
-// device VRAM; when it does, the device has no headroom to spend on throughput
-// and the conservative defaults must hold (issue #10485).
-//
-// g.VRAM must be the PER-DEVICE ceiling (the smallest device on a multi-GPU
-// host). VRAM 0 (unknown) is treated as not-large so detection gaps don't
-// silently disable the defaults.
-func largeContextForDevice(g GPU, ctx int) bool {
-	if g.VRAM == 0 {
-		return false
-	}
-	if ctx <= 0 {
-		ctx = DefaultContextSize
-	}
-	extra := uint64(ctx) * uint64(BlackwellPhysicalBatch-DefaultPhysicalBatch) * computeBufferBytesPerCell
-	return extra > g.VRAM/blackwellBatchHeadroomDivisor
-}
-
 // IsManagedPhysicalBatch reports whether n is a value PhysicalBatch assigns.
 // Callers that re-tune a value chosen by an upstream host (the distributed
 // router correcting the frontend's guess) use this to avoid clobbering an
@@ -185,50 +99,17 @@ func DefaultParallelSlots(g GPU) int {
 	}
 }
 
-// ParallelSlotsForContext is DefaultParallelSlots gated on per-device VRAM
-// headroom for the given context. A large context already claims most of a
-// single device's VRAM (the KV cache plus the per-slot compute/checkpoint
-// scratch that scales with n_seq_max), so defaulting multiple slots there
-// pushes a tight single-model fit into per-device CUDA OOM (issue #10485): the
-// model loads but the final allocation (e.g. an MTP draft context's KV cache)
-// overflows the tighter card by a few hundred MiB. Returns 1 (no concurrency)
-// in that tight regime, otherwise the VRAM-scaled DefaultParallelSlots.
-//
-// g.VRAM must be the PER-DEVICE ceiling (smallest device on a multi-GPU host).
-// It shares largeContextForDevice with the batch boost so both throughput
-// defaults are suppressed together; the GB10 / unified-memory path reports
-// system RAM and so keeps full concurrency even at large contexts.
-func ParallelSlotsForContext(g GPU, ctx int) int {
-	slots := DefaultParallelSlots(g)
-	if slots <= 1 || g.VRAM == 0 {
-		return slots
-	}
-	if largeContextForDevice(g, ctx) {
-		return 1
-	}
-	return slots
-}
-
-// EnsureParallelOptionForContext appends a VRAM-scaled "parallel:N" backend
-// option when the model doesn't already set one and the GPU warrants (and has
-// headroom for) concurrency at this context. Returns the possibly-extended
-// options. Shared by the single-host config path (ApplyHardwareDefaults) and
-// the distributed router (per selected node).
-func EnsureParallelOptionForContext(opts []string, gpu GPU, ctx int) []string {
-	if slots := ParallelSlotsForContext(gpu, ctx); slots > 1 && !hasParallelOption(opts) {
+// EnsureParallelOption appends a VRAM-scaled "parallel:N" backend option when the
+// model doesn't already set one (and the GPU warrants concurrency). Returns the
+// possibly-extended options. Shared by the single-host config path
+// (ApplyHardwareDefaults) and the distributed router (per selected node).
+func EnsureParallelOption(opts []string, gpu GPU) []string {
+	if slots := DefaultParallelSlots(gpu); slots > 1 && !hasParallelOption(opts) {
 		return append(opts, fmt.Sprintf("parallel:%d", slots))
 	}
 	return opts
 }
 
-// EnsureParallelOption is EnsureParallelOptionForContext with no known context
-// (defaults to DefaultContextSize, which clears the headroom gate on any device
-// large enough to warrant concurrency). Kept for callers without a model
-// context.
-func EnsureParallelOption(opts []string, gpu GPU) []string {
-	return EnsureParallelOptionForContext(opts, gpu, 0)
-}
-
 // hasParallelOption reports whether the model already sets parallel/n_parallel
 // so we never override an explicit value (helper shared with serving_defaults.go).
 func hasParallelOption(opts []string) bool {
@@ -241,12 +122,7 @@ func hasParallelOption(opts []string) bool {
 // deterministic device — detection does a live nvidia-smi call.
 var localGPU = func() GPU {
 	vendor, _ := xsysinfo.DetectGPUVendor()
-	// Use the SMALLEST device's VRAM, not the summed total: the parallel-slot
-	// tier and the batch headroom guard both reason about what fits on a single
-	// card, and per-device compute buffers can't be split across GPUs. Summing
-	// two 16 GiB cards into "32 GiB" is what over-provisioned multi-GPU hosts
-	// into OOM (issue #10485).
-	vram, _ := xsysinfo.MinPerGPUVRAM()
+	vram, _ := xsysinfo.TotalAvailableVRAM()
 	return GPU{
 		Vendor:            vendor,
 		ComputeCapability: xsysinfo.NVIDIAComputeCapability(),
@@ -258,36 +134,25 @@ var localGPU = func() GPU {
 // and were left unset by the user. Currently: a larger physical batch on
 // Blackwell. Explicit config always wins (we only touch zero values).
 func ApplyHardwareDefaults(cfg *ModelConfig, gpu GPU) {
-	if cfg == nil || HardwareDefaultsDisabled() {
+	if cfg == nil {
 		return
 	}
-	// Raise the physical batch on Blackwell only when the resulting compute
-	// buffer fits the per-device VRAM at THIS model's context. Leaving Batch at 0
-	// (rather than writing the default 512) preserves the downstream single-pass
-	// sizing in core/backend.EffectiveBatchSize for embedding/score/rerank.
-	ctx := DefaultContextSize
-	if cfg.ContextSize != nil {
-		ctx = *cfg.ContextSize
-	}
-	if cfg.Batch == 0 {
-		if PhysicalBatchForContext(gpu, ctx) == BlackwellPhysicalBatch {
-			cfg.Batch = BlackwellPhysicalBatch
-			xlog.Debug("[hardware_defaults] Blackwell GPU: defaulting physical batch",
-				"batch", cfg.Batch, "compute_cap", gpu.ComputeCapability, "context", ctx, "vram_gib", gpu.VRAM>>30)
-		}
+	if cfg.Batch == 0 && gpu.IsNVIDIABlackwell() {
+		cfg.Batch = BlackwellPhysicalBatch
+		xlog.Debug("[hardware_defaults] Blackwell GPU: defaulting physical batch",
+			"batch", cfg.Batch, "compute_cap", gpu.ComputeCapability)
 	}
 
 	// Enable concurrent serving by default on a capable GPU: without this the
 	// llama.cpp backend runs n_parallel=1 and serializes multi-user requests
 	// (continuous batching stays off). Unified KV means the slots share the
-	// context budget, but a context large enough to fill a single device leaves
-	// no room for the per-slot scratch, so the slot count is gated on per-device
-	// headroom too (issue #10485). Explicit parallel/n_parallel always wins.
+	// context budget, so this is concurrency without extra KV memory. Explicit
+	// parallel/n_parallel in the model options always wins.
 	if before := len(cfg.Options); true {
-		cfg.Options = EnsureParallelOptionForContext(cfg.Options, gpu, ctx)
+		cfg.Options = EnsureParallelOption(cfg.Options, gpu)
 		if len(cfg.Options) > before {
 			xlog.Debug("[hardware_defaults] defaulting parallel slots for concurrent serving",
-				"option", cfg.Options[len(cfg.Options)-1], "context", ctx, "vram_gib", gpu.VRAM>>30)
+				"option", cfg.Options[len(cfg.Options)-1], "vram_gib", gpu.VRAM>>30)
 		}
 	}
 }

core/config/hardware_defaults_internal_test.go

@@ -9,37 +9,26 @@ import (
 // GPU. The detection seam (localGPU) is injected so the path is deterministic
 // without a real GPU.
 var _ = Describe("SetDefaults hardware defaults (single-instance)", func() {
-	const gib = uint64(1) << 30
-
 	var orig func() GPU
 	BeforeEach(func() { orig = localGPU })
 	AfterEach(func() { localGPU = orig })
 
-	It("sets the physical batch on a local Blackwell GPU with headroom", func() {
-		localGPU = func() GPU { return GPU{ComputeCapability: "12.1", VRAM: 119 * gib} }
+	It("sets the physical batch on a local Blackwell GPU", func() {
+		localGPU = func() GPU { return GPU{ComputeCapability: "12.1"} }
 		cfg := &ModelConfig{}
 		cfg.SetDefaults()
 		Expect(cfg.Batch).To(Equal(BlackwellPhysicalBatch))
 	})
 
-	It("leaves batch unset when a large context would overflow the device", func() {
-		// Regression guard for issue #10485: 16 GiB consumer Blackwell + ~200k ctx.
-		localGPU = func() GPU { return GPU{ComputeCapability: "12.0", VRAM: 16 * gib} }
-		ctx := 204800
-		cfg := &ModelConfig{LLMConfig: LLMConfig{ContextSize: &ctx}}
-		cfg.SetDefaults()
-		Expect(cfg.Batch).To(Equal(0))
-	})
-
 	It("leaves batch unset on a non-Blackwell local GPU", func() {
-		localGPU = func() GPU { return GPU{ComputeCapability: "8.9", VRAM: 119 * gib} }
+		localGPU = func() GPU { return GPU{ComputeCapability: "8.9"} }
 		cfg := &ModelConfig{}
 		cfg.SetDefaults()
 		Expect(cfg.Batch).To(Equal(0))
 	})
 
 	It("never overrides an explicit batch", func() {
-		localGPU = func() GPU { return GPU{ComputeCapability: "12.1", VRAM: 119 * gib} }
+		localGPU = func() GPU { return GPU{ComputeCapability: "12.1"} }
 		cfg := &ModelConfig{}
 		cfg.Batch = 1024
 		cfg.SetDefaults()

core/config/hardware_defaults_test.go

@@ -7,8 +7,6 @@ import (
 )
 
 var _ = Describe("Hardware-driven config defaults", func() {
-	const gib = uint64(1) << 30
-
 	DescribeTable("GPU.IsNVIDIABlackwell (sm_12x consumer family)",
 		func(cc string, want bool) {
 			Expect(GPU{ComputeCapability: cc}.IsNVIDIABlackwell()).To(Equal(want))
@@ -37,70 +35,30 @@ var _ = Describe("Hardware-driven config defaults", func() {
 		})
 	})
 
-	Describe("PhysicalBatchForContext (per-device VRAM headroom)", func() {
-		It("raises the batch when the compute buffer fits the device", func() {
-			// 16 GiB Blackwell with a small context: the extra scratch is tiny.
-			Expect(PhysicalBatchForContext(GPU{ComputeCapability: "12.0", VRAM: 16 * gib}, 8192)).
-				To(Equal(BlackwellPhysicalBatch))
-		})
-		It("keeps the default batch when a large context would overflow one device", func() {
-			// The issue #10485 case: 16 GiB consumer Blackwell, ~200k context.
-			Expect(PhysicalBatchForContext(GPU{ComputeCapability: "12.0", VRAM: 16 * gib}, 204800)).
-				To(Equal(DefaultPhysicalBatch))
-		})
-		It("still raises the batch on a large unified-memory device (GB10)", func() {
-			// GB10 reports system RAM (~119 GiB) as its single device's VRAM.
-			Expect(PhysicalBatchForContext(GPU{ComputeCapability: "12.1", VRAM: 119 * gib}, 204800)).
-				To(Equal(BlackwellPhysicalBatch))
-		})
-		It("stays conservative when VRAM is unknown", func() {
-			Expect(PhysicalBatchForContext(GPU{ComputeCapability: "12.1"}, 8192)).
-				To(Equal(DefaultPhysicalBatch))
-		})
-		It("never raises the batch on non-Blackwell", func() {
-			Expect(PhysicalBatchForContext(GPU{ComputeCapability: "9.0", VRAM: 80 * gib}, 8192)).
-				To(Equal(DefaultPhysicalBatch))
-		})
-	})
-
 	Describe("ApplyHardwareDefaults", func() {
-		It("raises an unset batch to 2048 on Blackwell with headroom", func() {
+		It("raises an unset batch to 2048 on Blackwell", func() {
 			cfg := &ModelConfig{}
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1", VRAM: 119 * gib})
+			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1"})
 			Expect(cfg.Batch).To(Equal(BlackwellPhysicalBatch))
 		})
-		It("leaves batch unset when a large context would overflow one device", func() {
-			// Regression guard for issue #10485: 16 GiB card + ~200k context.
-			ctx := 204800
-			cfg := &ModelConfig{LLMConfig: LLMConfig{ContextSize: &ctx}}
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.0", VRAM: 16 * gib})
-			Expect(cfg.Batch).To(Equal(0))
-		})
 		It("leaves batch unset on non-Blackwell", func() {
 			cfg := &ModelConfig{}
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "9.0", VRAM: 119 * gib})
+			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "9.0"})
 			Expect(cfg.Batch).To(Equal(0))
 		})
 		It("never overrides an explicit batch", func() {
 			cfg := &ModelConfig{}
 			cfg.Batch = 1024
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1", VRAM: 119 * gib})
+			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1"})
 			Expect(cfg.Batch).To(Equal(1024))
 		})
 		It("no-ops on nil", func() {
 			Expect(func() { ApplyHardwareDefaults(nil, GPU{ComputeCapability: "12.1"}) }).ToNot(Panic())
 		})
-
-		It("applies nothing when hardware defaults are disabled via env", func() {
-			GinkgoT().Setenv("LOCALAI_DISABLE_HARDWARE_DEFAULTS", "true")
-			Expect(HardwareDefaultsDisabled()).To(BeTrue())
-			cfg := &ModelConfig{}
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1", VRAM: 119 * gib})
-			Expect(cfg.Batch).To(Equal(0))
-			Expect(cfg.Options).To(BeEmpty())
-		})
 	})
 
+	const gib = uint64(1) << 30
+
 	DescribeTable("DefaultParallelSlots (by VRAM)",
 		func(vramGiB uint64, want int) {
 			Expect(DefaultParallelSlots(GPU{VRAM: vramGiB * gib})).To(Equal(want))
@@ -114,46 +72,12 @@ var _ = Describe("Hardware-driven config defaults", func() {
 		Entry("unknown 0", uint64(0), 1),
 	)
 
-	Describe("ParallelSlotsForContext (per-device VRAM headroom)", func() {
-		It("keeps the VRAM-scaled slot count when the context fits the device", func() {
-			// 16 GiB card, small context: plenty of room for concurrency.
-			Expect(ParallelSlotsForContext(GPU{VRAM: 16 * gib}, 8192)).To(Equal(4))
-		})
-		It("drops to a single slot when a large context already fills the device", func() {
-			// Regression guard for issue #10485: 16 GiB consumer Blackwell, ~200k
-			// context. Even with unified KV, the per-slot compute/checkpoint
-			// scratch from 4 slots is the straw that overflows the tighter device.
-			Expect(ParallelSlotsForContext(GPU{VRAM: 16 * gib}, 204800)).To(Equal(1))
-		})
-		It("keeps concurrency on a large unified-memory device (GB10)", func() {
-			// GB10 reports system RAM (~119 GiB): a 200k context leaves headroom.
-			Expect(ParallelSlotsForContext(GPU{VRAM: 119 * gib}, 204800)).To(Equal(8))
-		})
-		It("keeps concurrency on a big datacenter card with a large context", func() {
-			// 80 GiB A100: 200k context is a small fraction, concurrency stays.
-			Expect(ParallelSlotsForContext(GPU{VRAM: 80 * gib}, 204800)).To(Equal(8))
-		})
-		It("stays a single slot on small/unknown VRAM regardless of context", func() {
-			Expect(ParallelSlotsForContext(GPU{VRAM: 2 * gib}, 8192)).To(Equal(1))
-			Expect(ParallelSlotsForContext(GPU{}, 8192)).To(Equal(1))
-		})
-	})
-
 	Describe("ApplyHardwareDefaults parallel slots", func() {
 		It("adds a VRAM-scaled parallel option on a capable GPU", func() {
 			cfg := &ModelConfig{}
 			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.1", VRAM: 119 * gib})
 			Expect(cfg.Options).To(ContainElement("parallel:8"))
 		})
-		It("adds no parallel option when a large context already fills one device", func() {
-			// Regression guard for issue #10485: 16 GiB card + ~200k context. The
-			// model barely fits; defaulting concurrency tips the tighter GPU into
-			// CUDA OOM during the final (MTP draft) KV allocation.
-			ctx := 204800
-			cfg := &ModelConfig{LLMConfig: LLMConfig{ContextSize: &ctx}}
-			ApplyHardwareDefaults(cfg, GPU{ComputeCapability: "12.0", VRAM: 16 * gib})
-			Expect(cfg.Options).ToNot(ContainElement(ContainSubstring("parallel")))
-		})
 		It("scales the slot count down with VRAM", func() {
 			cfg := &ModelConfig{}
 			ApplyHardwareDefaults(cfg, GPU{VRAM: 24 * gib})

core/config/model_config.go

@@ -1204,6 +1204,11 @@ func (cfg *ModelConfig) SetDefaults(opts ...ConfigLoaderOption) {
 	// This ensures gallery-installed and runtime-loaded models get optimal parameters.
 	ApplyInferenceDefaults(cfg, cfg.Name, cfg.Model)
 
+	// Apply hardware-driven defaults (e.g. a larger physical batch on Blackwell).
+	// Uses the local GPU here; in distributed mode the router re-applies the same
+	// heuristics for the selected node's GPU before loading. Explicit config wins.
+	ApplyHardwareDefaults(cfg, localGPU())
+
 	// Apply serving-policy defaults (device-independent): cross-request prefix
 	// caching. Propagates to distributed nodes via the model options.
 	ApplyServingDefaults(cfg)
@@ -1242,16 +1247,6 @@ func (cfg *ModelConfig) SetDefaults(opts ...ConfigLoaderOption) {
 		cfg.ContextSize = &ctx
 	}
 	runBackendHooks(cfg, lo.modelPath)
-
-	// Apply hardware-driven defaults (e.g. a larger physical batch on Blackwell)
-	// LAST, after the context size is fully resolved (explicit config, LoadOptions,
-	// then the GGUF guess inside runBackendHooks): the Blackwell batch guard sizes
-	// the per-device compute buffer against this model's context, so it must see
-	// the final value, not a pre-guess nil. Uses the local GPU here; in distributed
-	// mode the router re-applies the same heuristics for the selected node's GPU
-	// before loading. Explicit config always wins.
-	ApplyHardwareDefaults(cfg, localGPU())
-
 	cfg.syncKnownUsecasesFromString()
 }
 

core/config/runtime_settings_persist.go

@@ -5,7 +5,6 @@ import (
 	"errors"
 	"os"
 	"path/filepath"
-	"reflect"
 )
 
 // runtimeSettingsFile is the on-disk filename inside DynamicConfigsDir.
@@ -34,35 +33,6 @@ func (o *ApplicationConfig) ReadPersistedSettings() (RuntimeSettings, error) {
 	return settings, nil
 }
 
-// MergeNonNil overlays every set (non-nil) field of overlay onto the
-// receiver, leaving the receiver's value untouched wherever overlay left a
-// field unset. Every RuntimeSettings field is a pointer precisely so "set"
-// can be told apart from "absent" (see the type doc), which makes this a
-// faithful partial update: a caller that submits only the field it owns
-// changes exactly that field and never clobbers unrelated settings.
-//
-// This is the read-modify-write contract the persistence helpers exist for.
-// UpdateSettingsEndpoint reads the on-disk settings, merges the request body
-// on top, and writes the result — so a focused admin page that POSTs only its
-// own field (the Middleware page sends only mitm_listen; the detector table
-// only pii_default_detectors) no longer nulls every other setting.
-//
-// Reflection keeps the merge total over the struct: a field added to
-// RuntimeSettings later is merged automatically, so the persistence path can
-// never silently drop a new setting the way a hand-maintained field list
-// would. Non-pointer fields (none today) are skipped — they cannot express
-// "absent", so the receiver wins.
-func (s *RuntimeSettings) MergeNonNil(overlay RuntimeSettings) {
-	dst := reflect.ValueOf(s).Elem()
-	src := reflect.ValueOf(overlay)
-	for i := 0; i < src.NumField(); i++ {
-		f := src.Field(i)
-		if f.Kind() == reflect.Pointer && !f.IsNil() {
-			dst.Field(i).Set(f)
-		}
-	}
-}
-
 // WritePersistedSettings serialises the given RuntimeSettings to
 // runtime_settings.json with restricted permissions (it may carry API
 // keys and P2P tokens).

core/config/runtime_settings_persist_test.go

@@ -12,7 +12,6 @@ import (
 )
 
 func strPtr(s string) *string { return &s }
-func boolPtr(b bool) *bool     { return &b }
 
 var _ = Describe("RuntimeSettings persistence helpers", func() {
 	var (
@@ -52,47 +51,6 @@ var _ = Describe("RuntimeSettings persistence helpers", func() {
 		})
 	})
 
-	// MergeNonNil is the partial-update primitive UpdateSettingsEndpoint
-	// relies on: a focused admin page POSTs only the field it owns, and the
-	// handler reads the on-disk settings and overlays the request on top.
-	// Without it, the body would be written verbatim and every field the
-	// caller omitted would be nulled (the reported regression: changing
-	// mitm_listen wiped the galleries, api keys, watchdog config, etc.).
-	Describe("MergeNonNil partial update", func() {
-		It("overlays set fields and preserves unset ones", func() {
-			base := config.RuntimeSettings{
-				MITMListen:          strPtr(":9000"),
-				Galleries:           &[]config.Gallery{{Name: "g1", URL: "http://example/g1"}},
-				WatchdogIdleEnabled: boolPtr(true),
-				ApiKeys:             &[]string{"persisted-key"},
-				PIIDefaultDetectors: &[]string{"det-a"},
-			}
-
-			// Simulate the Middleware proxy tab: only mitm_listen is sent.
-			overlay := config.RuntimeSettings{MITMListen: strPtr(":8443")}
-			base.MergeNonNil(overlay)
-
-			Expect(base.MITMListen).ToNot(BeNil())
-			Expect(*base.MITMListen).To(Equal(":8443"), "set field should be overlaid")
-			// Everything the overlay left unset must survive untouched.
-			Expect(base.Galleries).ToNot(BeNil(), "galleries were clobbered")
-			Expect(*base.Galleries).To(HaveLen(1))
-			Expect(base.WatchdogIdleEnabled).ToNot(BeNil())
-			Expect(*base.WatchdogIdleEnabled).To(BeTrue())
-			Expect(base.ApiKeys).ToNot(BeNil(), "api_keys were clobbered")
-			Expect(*base.ApiKeys).To(Equal([]string{"persisted-key"}))
-			Expect(base.PIIDefaultDetectors).ToNot(BeNil(), "pii_default_detectors were clobbered")
-			Expect(*base.PIIDefaultDetectors).To(Equal([]string{"det-a"}))
-		})
-
-		It("lets an explicit empty slice clear a field", func() {
-			base := config.RuntimeSettings{PIIDefaultDetectors: &[]string{"det-a"}}
-			base.MergeNonNil(config.RuntimeSettings{PIIDefaultDetectors: &[]string{}})
-			Expect(base.PIIDefaultDetectors).ToNot(BeNil())
-			Expect(*base.PIIDefaultDetectors).To(BeEmpty(), "an explicit empty slice should clear, not preserve")
-		})
-	})
-
 	// MITM round trip pins the contract that loadRuntimeSettingsFromFile
 	// MITM listener address must survive a write/read round trip so the
 	// next process restart can bring the listener back up. (Intercept

core/http/app.go

@@ -149,18 +149,6 @@ func API(application *application.Application) (*echo.Echo, error) {
 	// Middleware - StripPathPrefix must be registered early as it uses Rewrite which runs before routing
 	e.Pre(httpMiddleware.StripPathPrefix())
 
-	// Stamp the configured external base URL into each request context so
-	// middleware.BaseURL can treat it as authoritative for self-referential
-	// links. Registered as Pre so it runs before routing and handlers.
-	if extBaseURL := application.ApplicationConfig().ExternalBaseURL; extBaseURL != "" {
-		e.Pre(func(next echo.HandlerFunc) echo.HandlerFunc {
-			return func(c echo.Context) error {
-				c.Set("_external_base_url", extBaseURL)
-				return next(c)
-			}
-		})
-	}
-
 	e.Pre(middleware.RemoveTrailingSlash())
 
 	if application.ApplicationConfig().MachineTag != "" {

core/http/endpoints/localai/agent_collections.go

@@ -70,7 +70,7 @@ func UploadToCollectionEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		file, err := c.FormFile("file")
 		if err != nil {
 			return c.JSON(http.StatusBadRequest, map[string]string{"error": "file required"})
@@ -116,7 +116,7 @@ func ListCollectionEntriesEndpoint(app *application.Application) echo.HandlerFun
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		entries, err := svc.ListCollectionEntriesForUser(userID, decodedParam(c, "name"))
+		entries, err := svc.ListCollectionEntriesForUser(userID, c.Param("name"))
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
@@ -139,7 +139,7 @@ func GetCollectionEntryContentEndpoint(app *application.Application) echo.Handle
 		if err != nil {
 			entry = entryParam
 		}
-		content, chunkCount, err := svc.GetCollectionEntryContentForUser(userID, decodedParam(c, "name"), entry)
+		content, chunkCount, err := svc.GetCollectionEntryContentForUser(userID, c.Param("name"), entry)
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
@@ -164,7 +164,7 @@ func SearchCollectionEndpoint(app *application.Application) echo.HandlerFunc {
 		if err := c.Bind(&payload); err != nil {
 			return c.JSON(http.StatusBadRequest, map[string]string{"error": err.Error()})
 		}
-		results, err := svc.SearchCollectionForUser(userID, decodedParam(c, "name"), payload.Query, payload.MaxResults)
+		results, err := svc.SearchCollectionForUser(userID, c.Param("name"), payload.Query, payload.MaxResults)
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
@@ -182,7 +182,7 @@ func ResetCollectionEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		if err := svc.ResetCollectionForUser(userID, decodedParam(c, "name")); err != nil {
+		if err := svc.ResetCollectionForUser(userID, c.Param("name")); err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
 			}
@@ -202,7 +202,7 @@ func DeleteCollectionEntryEndpoint(app *application.Application) echo.HandlerFun
 		if err := c.Bind(&payload); err != nil {
 			return c.JSON(http.StatusBadRequest, map[string]string{"error": err.Error()})
 		}
-		remaining, err := svc.DeleteCollectionEntryForUser(userID, decodedParam(c, "name"), payload.Entry)
+		remaining, err := svc.DeleteCollectionEntryForUser(userID, c.Param("name"), payload.Entry)
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
@@ -230,7 +230,7 @@ func AddCollectionSourceEndpoint(app *application.Application) echo.HandlerFunc
 		if payload.UpdateInterval < 1 {
 			payload.UpdateInterval = 60
 		}
-		if err := svc.AddCollectionSourceForUser(userID, decodedParam(c, "name"), payload.URL, payload.UpdateInterval); err != nil {
+		if err := svc.AddCollectionSourceForUser(userID, c.Param("name"), payload.URL, payload.UpdateInterval); err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
 			}
@@ -250,7 +250,7 @@ func RemoveCollectionSourceEndpoint(app *application.Application) echo.HandlerFu
 		if err := c.Bind(&payload); err != nil {
 			return c.JSON(http.StatusBadRequest, map[string]string{"error": err.Error()})
 		}
-		if err := svc.RemoveCollectionSourceForUser(userID, decodedParam(c, "name"), payload.URL); err != nil {
+		if err := svc.RemoveCollectionSourceForUser(userID, c.Param("name"), payload.URL); err != nil {
 			return c.JSON(http.StatusInternalServerError, map[string]string{"error": err.Error()})
 		}
 		return c.JSON(http.StatusOK, map[string]string{"status": "ok"})
@@ -267,7 +267,7 @@ func GetCollectionEntryRawFileEndpoint(app *application.Application) echo.Handle
 		if err != nil {
 			entry = entryParam
 		}
-		fpath, err := svc.GetCollectionEntryFilePathForUser(userID, decodedParam(c, "name"), entry)
+		fpath, err := svc.GetCollectionEntryFilePathForUser(userID, c.Param("name"), entry)
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
@@ -282,7 +282,7 @@ func ListCollectionSourcesEndpoint(app *application.Application) echo.HandlerFun
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		sources, err := svc.ListCollectionSourcesForUser(userID, decodedParam(c, "name"))
+		sources, err := svc.ListCollectionSourcesForUser(userID, c.Param("name"))
 		if err != nil {
 			if strings.Contains(err.Error(), "not found") {
 				return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})

core/http/endpoints/localai/agent_collections_param_test.go

@@ -1,49 +0,0 @@
-package localai
-
-import (
-	"net/http"
-	"net/http/httptest"
-
-	"github.com/labstack/echo/v4"
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-)
-
-// Regression for #10443: agent/collection names carry a "legacy-api-key:"
-// prefix, so the ':' is percent-encoded as %3A in the request path. Echo routes
-// such paths via URL.RawPath and stores the path-param value still escaped, so
-// handlers must URL-decode it before looking the collection up in the store -
-// otherwise the lookup sees "legacy-api-key%3ALiteraryResearch" and 404s.
-var _ = Describe("decodedParam", func() {
-	var e *echo.Echo
-
-	BeforeEach(func() {
-		e = echo.New()
-	})
-
-	// route runs a request through Echo's real router so the path param is
-	// populated exactly as it would be in production, then returns the decoded
-	// value the handler would observe.
-	route := func(rawPath string) string {
-		var got string
-		e.GET("/api/agents/collections/:name/upload", func(c echo.Context) error {
-			got = decodedParam(c, "name")
-			return c.NoContent(http.StatusOK)
-		})
-		req := httptest.NewRequest(http.MethodGet, rawPath, nil)
-		rec := httptest.NewRecorder()
-		e.ServeHTTP(rec, req)
-		Expect(rec.Code).To(Equal(http.StatusOK))
-		return got
-	}
-
-	It("decodes a percent-encoded colon in the collection name", func() {
-		got := route("/api/agents/collections/legacy-api-key%3ALiteraryResearch/upload")
-		Expect(got).To(Equal("legacy-api-key:LiteraryResearch"))
-	})
-
-	It("leaves an unencoded name untouched", func() {
-		got := route("/api/agents/collections/PlainCollection/upload")
-		Expect(got).To(Equal("PlainCollection"))
-	})
-})

core/http/endpoints/localai/agents.go

@@ -6,7 +6,6 @@ import (
 	"io"
 	"maps"
 	"net/http"
-	"net/url"
 	"os"
 	"path/filepath"
 	"slices"
@@ -34,22 +33,6 @@ func getUserID(c echo.Context) string {
 	return user.ID
 }
 
-// decodedParam returns the named path parameter, URL-decoding it.
-//
-// Echo routes a request via URL.RawPath whenever the path contains
-// percent-encoded characters (e.g. %3A for ':'), and in that case stores the
-// matched path-param value raw/escaped. Agent and collection names carry a
-// "legacy-api-key:" prefix, so the ':' arrives as %3A and the raw param no
-// longer matches the stored name. Callers must unescape before lookups.
-// Falls back to the raw value if it isn't valid percent-encoding.
-func decodedParam(c echo.Context, name string) string {
-	raw := c.Param(name)
-	if decoded, err := url.PathUnescape(raw); err == nil {
-		return decoded
-	}
-	return raw
-}
-
 // isAdminUser returns true if the authenticated user has admin role.
 func isAdminUser(c echo.Context) bool {
 	user := auth.GetUser(c)
@@ -144,7 +127,7 @@ func GetAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 
 		statuses := svc.ListAgentsForUser(userID)
 		active, exists := statuses[name]
@@ -159,7 +142,7 @@ func UpdateAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		var cfg state.AgentConfig
 		if err := c.Bind(&cfg); err != nil {
 			return c.JSON(http.StatusBadRequest, map[string]string{"error": err.Error()})
@@ -178,7 +161,7 @@ func DeleteAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		if err := svc.DeleteAgentForUser(userID, name); err != nil {
 			return c.JSON(http.StatusInternalServerError, map[string]string{"error": err.Error()})
 		}
@@ -190,7 +173,7 @@ func GetAgentConfigEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		cfg := svc.GetAgentConfigForUser(userID, name)
 		if cfg == nil {
 			return c.JSON(http.StatusNotFound, map[string]string{"error": "Agent not found"})
@@ -203,7 +186,7 @@ func PauseAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		if err := svc.PauseAgentForUser(userID, decodedParam(c, "name")); err != nil {
+		if err := svc.PauseAgentForUser(userID, c.Param("name")); err != nil {
 			return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
 		}
 		return c.JSON(http.StatusOK, map[string]string{"status": "ok"})
@@ -214,7 +197,7 @@ func ResumeAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		if err := svc.ResumeAgentForUser(userID, decodedParam(c, "name")); err != nil {
+		if err := svc.ResumeAgentForUser(userID, c.Param("name")); err != nil {
 			return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
 		}
 		return c.JSON(http.StatusOK, map[string]string{"status": "ok"})
@@ -225,7 +208,7 @@ func GetAgentStatusEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 
 		history := svc.GetAgentStatusForUser(userID, name)
 		if history == nil {
@@ -258,7 +241,7 @@ func GetAgentObservablesEndpoint(app *application.Application) echo.HandlerFunc
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 
 		history, err := svc.GetAgentObservablesForUser(userID, name)
 		if err != nil {
@@ -278,7 +261,7 @@ func ClearAgentObservablesEndpoint(app *application.Application) echo.HandlerFun
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		if err := svc.ClearAgentObservablesForUser(userID, name); err != nil {
 			return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})
 		}
@@ -290,7 +273,7 @@ func ChatWithAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		var payload struct {
 			Message string `json:"message"`
 		}
@@ -319,7 +302,7 @@ func AgentSSEEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 
 		// Try local SSE manager first
 		manager := svc.GetSSEManagerForUser(userID, name)
@@ -351,7 +334,7 @@ func ExportAgentEndpoint(app *application.Application) echo.HandlerFunc {
 	return func(c echo.Context) error {
 		svc := app.AgentPoolService()
 		userID := effectiveUserID(c)
-		name := decodedParam(c, "name")
+		name := c.Param("name")
 		data, err := svc.ExportAgentForUser(userID, name)
 		if err != nil {
 			return c.JSON(http.StatusNotFound, map[string]string{"error": err.Error()})

core/http/endpoints/localai/settings.go

@@ -4,6 +4,8 @@ import (
 	"encoding/json"
 	"io"
 	"net/http"
+	"os"
+	"path/filepath"
 	"time"
 
 	"github.com/labstack/echo/v4"
@@ -108,18 +110,6 @@ func UpdateSettingsEndpoint(app *application.Application) echo.HandlerFunc {
 			})
 		}
 
-		// Read whatever is already persisted: it is both the source of truth
-		// for branding asset filenames (below) and the base we merge this
-		// request onto before writing. A read failure must not let a Save
-		// silently discard the existing settings — surface it instead.
-		persisted, err := appConfig.ReadPersistedSettings()
-		if err != nil {
-			return c.JSON(http.StatusInternalServerError, schema.SettingsResponse{
-				Success: false,
-				Error:   "Failed to read existing settings: " + err.Error(),
-			})
-		}
-
 		// Branding asset filenames are owned exclusively by
 		// /api/branding/asset/{kind} (upload/delete). The Settings page also
 		// round-trips them via GET /api/settings, but its local state is stale
@@ -128,9 +118,11 @@ func UpdateSettingsEndpoint(app *application.Application) echo.HandlerFunc {
 		// at page open. Replace whatever the body sent for these three fields
 		// with the values currently on disk so /api/settings can never
 		// regress them.
-		settings.LogoFile = persisted.LogoFile
-		settings.LogoHorizontalFile = persisted.LogoHorizontalFile
-		settings.FaviconFile = persisted.FaviconFile
+		if existing, err := appConfig.ReadPersistedSettings(); err == nil {
+			settings.LogoFile = existing.LogoFile
+			settings.LogoHorizontalFile = existing.LogoHorizontalFile
+			settings.FaviconFile = existing.FaviconFile
+		}
 
 		// The UI reads ApiKeys from GET /api/settings, which already returns the
 		// merged env+runtime list. When the user clicks Save, the same merged
@@ -153,17 +145,16 @@ func UpdateSettingsEndpoint(app *application.Application) echo.HandlerFunc {
 			settings.ApiKeys = &runtimeOnly
 		}
 
-		// Persist as a partial update: overlay only the fields this request set
-		// onto the settings already on disk. Focused admin pages POST just the
-		// keys they own (the Middleware proxy tab sends only mitm_listen; the
-		// detector table only pii_default_detectors), so writing the request
-		// body verbatim would null every unrelated setting (the no-omitempty
-		// api_keys / pii_default_detectors fields even round-trip as JSON
-		// null). The full Settings page still round-trips every field, so its
-		// Save is unchanged.
-		toPersist := persisted
-		toPersist.MergeNonNil(settings)
-		if err := appConfig.WritePersistedSettings(toPersist); err != nil {
+		settingsFile := filepath.Join(appConfig.DynamicConfigsDir, "runtime_settings.json")
+		settingsJSON, err := json.MarshalIndent(settings, "", "  ")
+		if err != nil {
+			return c.JSON(http.StatusInternalServerError, schema.SettingsResponse{
+				Success: false,
+				Error:   "Failed to marshal settings: " + err.Error(),
+			})
+		}
+
+		if err := os.WriteFile(settingsFile, settingsJSON, 0600); err != nil {
 			return c.JSON(http.StatusInternalServerError, schema.SettingsResponse{
 				Success: false,
 				Error:   "Failed to write settings file: " + err.Error(),
@@ -271,14 +262,7 @@ func UpdateSettingsEndpoint(app *application.Application) echo.HandlerFunc {
 			}
 		}
 
-		// Rebuild the MITM listener when its address OR the instance-wide
-		// default detectors change. The per-host detector map is resolved once
-		// at listener start (startMITMLocked → ResolvePIIPolicy), so a
-		// default-detector change is otherwise invisible to cloud-proxy traffic
-		// until the next restart — an admin toggling a default detector would
-		// see no redaction. RestartMITM is a no-op when the listener is
-		// disabled (empty address).
-		if settings.MITMListen != nil || settings.PIIDefaultDetectors != nil {
+		if settings.MITMListen != nil {
 			if err := app.RestartMITM(); err != nil {
 				xlog.Error("Failed to restart MITM proxy", "error", err)
 				return c.JSON(http.StatusInternalServerError, schema.SettingsResponse{

core/http/endpoints/localai/settings_test.go

@@ -52,10 +52,6 @@ var _ = Describe("Settings endpoints", func() {
 		// Settings are persisted here; set after construction since there's no
 		// dedicated AppOption for it.
 		app.ApplicationConfig().DynamicConfigsDir = tmp
-		// Contain the MITM CA inside tmp too. The partial-save spec flips
-		// mitm_listen, which starts the listener and writes a CA; without this
-		// it defaults to ./mitm-ca and litters the package source tree.
-		app.ApplicationConfig().MITMCADir = filepath.Join(tmp, "mitm-ca")
 
 		e = echo.New()
 		e.GET("/api/settings", GetSettingsEndpoint(app))
@@ -113,57 +109,6 @@ var _ = Describe("Settings endpoints", func() {
 		Expect(err).ToNot(HaveOccurred())
 	})
 
-	// Regression: a focused admin page (the Middleware proxy tab) POSTs only
-	// the one field it owns — mitm_listen. The old handler wrote the request
-	// body verbatim, so every other persisted setting was dropped (and
-	// api_keys / pii_default_detectors, which lack omitempty, were written as
-	// null). A partial POST must now merge onto what is already on disk.
-	It("preserves unrelated persisted settings when a partial POST sets only mitm_listen", func() {
-		// First save establishes a fuller settings file (as the full Settings
-		// page would): galleries, an API key, and the MITM listener. The
-		// listener restart binds a real socket, so use 127.0.0.1:0 for an
-		// ephemeral free port rather than a fixed one that may be in use.
-		rec := post(`{"mitm_listen":"127.0.0.1:0","galleries":[{"name":"g1","url":"http://example/g1"}],"api_keys":["k1"],"pii_default_detectors":["det-a"]}`)
-		Expect(rec.Code).To(Equal(http.StatusOK), rec.Body.String())
-
-		// The Middleware proxy tab then changes only the listen address — the
-		// exact partial body that nulled everything else before the fix.
-		rec = post(`{"mitm_listen":"127.0.0.1:0"}`)
-		Expect(rec.Code).To(Equal(http.StatusOK), rec.Body.String())
-
-		raw, err := os.ReadFile(filepath.Join(tmp, "runtime_settings.json"))
-		Expect(err).ToNot(HaveOccurred())
-		var ondisk config.RuntimeSettings
-		Expect(json.Unmarshal(raw, &ondisk)).To(Succeed())
-
-		Expect(ondisk.MITMListen).ToNot(BeNil())
-		Expect(*ondisk.MITMListen).To(Equal("127.0.0.1:0"), "the changed field should be saved")
-		Expect(ondisk.Galleries).ToNot(BeNil(), "galleries were clobbered by the partial save")
-		Expect(*ondisk.Galleries).To(HaveLen(1))
-		Expect(ondisk.ApiKeys).ToNot(BeNil(), "api_keys were nulled by the partial save")
-		Expect(*ondisk.ApiKeys).To(Equal([]string{"k1"}))
-		Expect(ondisk.PIIDefaultDetectors).ToNot(BeNil(), "pii_default_detectors were nulled by the partial save")
-		Expect(*ondisk.PIIDefaultDetectors).To(Equal([]string{"det-a"}))
-	})
-
-	// The MITM listener resolves its per-host PII detectors once at start
-	// (startMITMLocked → ResolvePIIPolicy), and the handler used to restart it
-	// only when mitm_listen changed. So an admin toggling a default detector
-	// (the Middleware detector table POSTs only pii_default_detectors) left
-	// cloud-proxy traffic unredacted until the next reboot. A
-	// pii_default_detectors change must now rebuild the listener.
-	It("rebuilds the MITM listener when only pii_default_detectors changes", func() {
-		rec := post(`{"mitm_listen":"127.0.0.1:0"}`)
-		Expect(rec.Code).To(Equal(http.StatusOK), rec.Body.String())
-		srv1 := app.MITMServer()
-		Expect(srv1).ToNot(BeNil(), "listener should be running after mitm_listen is set")
-
-		rec = post(`{"pii_default_detectors":["det-a"]}`)
-		Expect(rec.Code).To(Equal(http.StatusOK), rec.Body.String())
-		Expect(app.MITMServer()).ToNot(BeIdenticalTo(srv1),
-			"a default-detector change must restart the listener so it picks up the new detectors")
-	})
-
 	// Residual #9125: enabling the watchdog from a cold (off) state via the
 	// React master toggle must start the live watchdog immediately, without a
 	// restart. The toggle posts watchdog_idle_enabled/busy_enabled=true while

core/http/endpoints/openai/realtime_model.go

@@ -432,7 +432,7 @@ func loadSoundDetectionConfig(pipeline *config.Pipeline, cl *config.ModelConfigL
 	if pipeline.SoundDetection == "" {
 		return nil, nil
 	}
-	cfg, err := loadPipelineSubModel(cl, pipeline.SoundDetection, ml.ModelPath)
+	cfg, err := cl.LoadModelConfigFileByName(pipeline.SoundDetection, ml.ModelPath)
 	if err != nil {
 		return nil, fmt.Errorf("failed to load sound detection config: %w", err)
 	}
@@ -443,7 +443,7 @@ func loadSoundDetectionConfig(pipeline *config.Pipeline, cl *config.ModelConfigL
 }
 
 func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) (Model, *config.ModelConfig, error) {
-	cfgVAD, err := loadPipelineSubModel(cl, pipeline.VAD, ml.ModelPath)
+	cfgVAD, err := cl.LoadModelConfigFileByName(pipeline.VAD, ml.ModelPath)
 	if err != nil {
 
 		return nil, nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -453,7 +453,7 @@ func newTranscriptionOnlyModel(pipeline *config.Pipeline, cl *config.ModelConfig
 		return nil, nil, fmt.Errorf("failed to validate config: %w", err)
 	}
 
-	cfgSST, err := loadPipelineSubModel(cl, pipeline.Transcription, ml.ModelPath)
+	cfgSST, err := cl.LoadModelConfigFileByName(pipeline.Transcription, ml.ModelPath)
 	if err != nil {
 
 		return nil, nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -542,30 +542,11 @@ func buildRealtimeRoutingContext(a *application.Application, sessionID string) *
 	}
 }
 
-// loadPipelineSubModel loads a pipeline sub-model config by name and follows a
-// single alias hop, so a pipeline that references an alias (e.g. `llm: default`)
-// gets the alias target's full config (Backend, Model, ...) rather than the
-// alias stub with an empty Backend. Without this the alias survives unresolved
-// into model loading and fails downstream — notably in distributed mode with
-// "backend name is empty". Mirrors the top-level alias resolution in
-// core/http/middleware/request.go.
-func loadPipelineSubModel(cl *config.ModelConfigLoader, name, modelPath string) (*config.ModelConfig, error) {
-	cfg, err := cl.LoadModelConfigFileByName(name, modelPath)
-	if err != nil {
-		return nil, err
-	}
-	resolved, _, err := cl.ResolveAlias(cfg)
-	if err != nil {
-		return nil, err
-	}
-	return resolved, nil
-}
-
 // returns and loads either a wrapped model or a model that support audio-to-audio
 func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig, evaluator *templates.Evaluator, routing *RealtimeRoutingContext) (Model, error) {
 	xlog.Debug("Creating new model pipeline model", "pipeline", pipeline)
 
-	cfgVAD, err := loadPipelineSubModel(cl, pipeline.VAD, ml.ModelPath)
+	cfgVAD, err := cl.LoadModelConfigFileByName(pipeline.VAD, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -576,7 +557,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	}
 
 	// TODO: Do we always need a transcription model? It can be disabled. Note that any-to-any instruction following models don't transcribe as such, so if transcription is required it is a separate process
-	cfgSST, err := loadPipelineSubModel(cl, pipeline.Transcription, ml.ModelPath)
+	cfgSST, err := cl.LoadModelConfigFileByName(pipeline.Transcription, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -608,7 +589,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	xlog.Debug("Loading a wrapped model")
 
 	// Otherwise we want to return a wrapped model, which is a "virtual" model that re-uses other models to perform operations
-	cfgLLM, err := loadPipelineSubModel(cl, pipeline.LLM, ml.ModelPath)
+	cfgLLM, err := cl.LoadModelConfigFileByName(pipeline.LLM, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)
@@ -623,7 +604,7 @@ func newModel(pipeline *config.Pipeline, cl *config.ModelConfigLoader, ml *model
 	applyPipelineReasoning(cfgLLM, *pipeline)
 	applyPipelineThinking(cfgLLM, *pipeline)
 
-	cfgTTS, err := loadPipelineSubModel(cl, pipeline.TTS, ml.ModelPath)
+	cfgTTS, err := cl.LoadModelConfigFileByName(pipeline.TTS, ml.ModelPath)
 	if err != nil {
 
 		return nil, fmt.Errorf("failed to load backend config: %w", err)

core/http/endpoints/openai/realtime_model_alias_test.go

@@ -1,52 +0,0 @@
-package openai
-
-import (
-	"os"
-	"path/filepath"
-
-	. "github.com/onsi/ginkgo/v2"
-	. "github.com/onsi/gomega"
-
-	"github.com/mudler/LocalAI/core/config"
-)
-
-// loadPipelineSubModel must resolve a pipeline sub-model that references an
-// alias (e.g. `llm: default`) one hop to the alias target's full config — so
-// the effective backend is the target's backend, not the empty backend of the
-// alias stub. This mirrors the top-level alias resolution done in
-// core/http/middleware/request.go, which the realtime pipeline previously
-// skipped (failing in distributed mode with "backend name is empty").
-var _ = Describe("loadPipelineSubModel", func() {
-	It("resolves a sub-model alias one hop to the target's config", func() {
-		tmpDir := GinkgoT().TempDir()
-
-		// A real model config with a concrete backend.
-		realLLM := `name: real-llm
-backend: llama-cpp
-parameters:
-  model: real-llm.gguf
-`
-		Expect(os.WriteFile(filepath.Join(tmpDir, "real-llm.yaml"), []byte(realLLM), 0644)).To(Succeed())
-
-		// An alias pointing at the real model.
-		aliasCfg := `name: default
-alias: real-llm
-`
-		Expect(os.WriteFile(filepath.Join(tmpDir, "default.yaml"), []byte(aliasCfg), 0644)).To(Succeed())
-
-		cl := config.NewModelConfigLoader(tmpDir)
-		Expect(cl.LoadModelConfigsFromPath(tmpDir)).To(Succeed())
-
-		// Resolving the alias must follow the hop to the target's full config.
-		resolved, err := loadPipelineSubModel(cl, "default", tmpDir)
-		Expect(err).NotTo(HaveOccurred())
-		Expect(resolved.IsAlias()).To(BeFalse())
-		Expect(resolved.Backend).To(Equal("llama-cpp"))
-
-		// A non-alias name must load unchanged.
-		direct, err := loadPipelineSubModel(cl, "real-llm", tmpDir)
-		Expect(err).NotTo(HaveOccurred())
-		Expect(direct.Backend).To(Equal("llama-cpp"))
-		Expect(direct.Name).To(Equal("real-llm"))
-	})
-})

core/http/middleware/baseurl.go

@@ -55,70 +55,17 @@ func BasePathPrefix(c echo.Context) string {
 // The returned URL is guaranteed to end with `/`.
 // The method should be used in conjunction with the StripPathPrefix middleware.
 func BaseURL(c echo.Context) string {
-	// An explicit external base URL (LOCALAI_BASE_URL) is authoritative for
-	// the origin. The proxy-derived path prefix is still appended so a
-	// reverse-proxy mount point keeps working. Trailing slashes are
-	// normalized via BasePathPrefix, which always starts and ends with "/".
-	if ext, ok := c.Get("_external_base_url").(string); ok && ext != "" {
-		return strings.TrimRight(ext, "/") + BasePathPrefix(c)
-	}
-
-	fwdProto, fwdHost := parseForwarded(c.Request().Header.Get("Forwarded"))
-
 	scheme := "http"
-	switch {
-	case c.Request().TLS != nil:
+	if c.Request().Header.Get("X-Forwarded-Proto") == "https" {
 		scheme = "https"
-	case strings.EqualFold(firstToken(c.Request().Header.Get("X-Forwarded-Proto")), "https"):
-		scheme = "https"
-	case strings.EqualFold(fwdProto, "https"):
+	} else if c.Request().TLS != nil {
 		scheme = "https"
 	}
 
 	host := c.Request().Host
 	if forwardedHost := c.Request().Header.Get("X-Forwarded-Host"); forwardedHost != "" {
 		host = forwardedHost
-	} else if fwdHost != "" {
-		host = fwdHost
 	}
 
 	return scheme + "://" + host + BasePathPrefix(c)
 }
-
-// firstToken returns the first comma-separated token of v, trimmed of spaces.
-// Reverse-proxy chains can emit X-Forwarded-Proto as "https,http"; only the
-// first hop (closest to the client) is meaningful for scheme detection.
-func firstToken(v string) string {
-	if i := strings.IndexByte(v, ','); i >= 0 {
-		v = v[:i]
-	}
-	return strings.TrimSpace(v)
-}
-
-// parseForwarded extracts the proto and host directives from the first element
-// of an RFC 7239 Forwarded header (e.g. `for=x;proto=https;host=h, for=y`).
-// Values may be quoted. Returns empty strings when absent or malformed so the
-// caller can fall through to other signals.
-func parseForwarded(header string) (proto, host string) {
-	if header == "" {
-		return "", ""
-	}
-	// Only the first element (closest proxy to the client) matters here.
-	if i := strings.IndexByte(header, ','); i >= 0 {
-		header = header[:i]
-	}
-	for _, directive := range strings.Split(header, ";") {
-		key, value, ok := strings.Cut(strings.TrimSpace(directive), "=")
-		if !ok {
-			continue
-		}
-		value = strings.Trim(strings.TrimSpace(value), `"`)
-		switch strings.ToLower(strings.TrimSpace(key)) {
-		case "proto":
-			proto = value
-		case "host":
-			host = value
-		}
-	}
-	return proto, host
-}

core/http/middleware/baseurl_test.go

@@ -135,138 +135,4 @@ var _ = Describe("BaseURL", func() {
 			Entry("missing leading slash", "evil"),
 		)
 	})
-
-	Context("scheme detection hardening", func() {
-		It("treats comma-separated X-Forwarded-Proto as https when first token is https", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/x", func(c echo.Context) error {
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/x", nil)
-			req.Header.Set("X-Forwarded-Proto", "https,http")
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("https://example.com/"))
-		})
-
-		It("derives https from the RFC 7239 Forwarded proto directive", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/x", func(c echo.Context) error {
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/x", nil)
-			req.Header.Set("Forwarded", "for=192.0.2.1;proto=https;host=proxy.example")
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("https://proxy.example/"))
-		})
-
-		It("prefers X-Forwarded-Host over the Forwarded host directive", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/x", func(c echo.Context) error {
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/x", nil)
-			req.Header.Set("X-Forwarded-Host", "xfh.example")
-			req.Header.Set("Forwarded", "host=fwd.example;proto=https")
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("https://xfh.example/"))
-		})
-	})
-
-	Context("explicit external base URL override", func() {
-		It("uses the configured origin over conflicting forwarded headers", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/x", func(c echo.Context) error {
-				c.Set("_external_base_url", "https://192.168.0.13:34567")
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/x", nil)
-			req.Header.Set("X-Forwarded-Proto", "http")
-			req.Header.Set("X-Forwarded-Host", "internal:8080")
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("https://192.168.0.13:34567/"))
-		})
-
-		It("combines the configured origin with a detected path prefix", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/hello", func(c echo.Context) error {
-				c.Set("_original_path", "/localai/hello")
-				c.Set("_external_base_url", "https://ext.example")
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/hello", nil)
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("https://ext.example/localai/"))
-		})
-
-		It("ignores an empty override", func() {
-			app := echo.New()
-			actualURL := ""
-			app.GET("/x", func(c echo.Context) error {
-				c.Set("_external_base_url", "")
-				actualURL = BaseURL(c)
-				return nil
-			})
-			req := httptest.NewRequest("GET", "/x", nil)
-			rec := httptest.NewRecorder()
-			app.ServeHTTP(rec, req)
-			Expect(actualURL).To(Equal("http://example.com/"))
-		})
-	})
-
-	Context("parseForwarded helper", func() {
-		It("parses unquoted proto and host", func() {
-			proto, host := parseForwarded("for=192.0.2.1;proto=https;host=h.example")
-			Expect(proto).To(Equal("https"))
-			Expect(host).To(Equal("h.example"))
-		})
-
-		It("strips quotes around values", func() {
-			proto, host := parseForwarded(`proto="https";host="h.example"`)
-			Expect(proto).To(Equal("https"))
-			Expect(host).To(Equal("h.example"))
-		})
-
-		It("uses only the first element of a multi-element header", func() {
-			proto, host := parseForwarded("proto=https;host=first.example, proto=http;host=second.example")
-			Expect(proto).To(Equal("https"))
-			Expect(host).To(Equal("first.example"))
-		})
-
-		It("returns empty strings for an empty header", func() {
-			proto, host := parseForwarded("")
-			Expect(proto).To(BeEmpty())
-			Expect(host).To(BeEmpty())
-		})
-
-		It("skips directives without a value", func() {
-			proto, host := parseForwarded("proto;host=h.example")
-			Expect(proto).To(BeEmpty())
-			Expect(host).To(Equal("h.example"))
-		})
-	})
-
-	Context("firstToken helper", func() {
-		It("returns the whole trimmed string when there is no comma", func() {
-			Expect(firstToken("  https  ")).To(Equal("https"))
-		})
-
-		It("returns the first trimmed token when there is a comma", func() {
-			Expect(firstToken("https , http")).To(Equal("https"))
-		})
-	})
 })

core/http/react-ui/e2e/role-mode-adaptive.spec.js

@@ -0,0 +1,100 @@
+import { test, expect } from './coverage-fixtures.js'
+
+// These specs stub /api/features and /api/auth/status per cell. The test server
+// disables auth (isAdmin=true) and reports its own features, so we intercept
+// before navigation to simulate each role x mode cell.
+
+function stubFeatures(page, features) {
+  return page.route('**/api/features', route =>
+    route.fulfill({ contentType: 'application/json', body: JSON.stringify(features) }))
+}
+
+function stubNoP2P(page) {
+  // P2P token endpoint returns empty -> p2pEnabled=false.
+  return page.route('**/api/p2p/token', route =>
+    route.fulfill({ contentType: 'text/plain', body: '' }))
+}
+
+test.describe('Adaptive landing (HomeRoute)', () => {
+  test('admin + distributed redirects /app to Nodes', async ({ page }) => {
+    await stubFeatures(page, { distributed: true })
+    await stubNoP2P(page)
+    await page.goto('/app')
+    await expect(page).toHaveURL(/\/app\/nodes$/)
+    await expect(page.locator('.page-title').first()).toBeVisible({ timeout: 15_000 })
+  })
+
+  test('admin + single-node stays on Home', async ({ page }) => {
+    await stubFeatures(page, { distributed: false })
+    await stubNoP2P(page)
+    await page.goto('/app')
+    await expect(page).toHaveURL(/\/app$/)
+    await expect(page.locator('.home-greeting')).toBeVisible({ timeout: 15_000 })
+  })
+})
+
+test.describe('Adaptive sidebar', () => {
+  test('distributed pins the Cluster group with Nodes at the top', async ({ page }) => {
+    await stubFeatures(page, { distributed: true })
+    await stubNoP2P(page)
+    await page.goto('/app/chat') // any in-app page so the sidebar is mounted
+    const pinned = page.locator('.sidebar-nav .sidebar-section-items').first()
+    await expect(pinned.getByText('Nodes', { exact: false })).toBeVisible({ timeout: 15_000 })
+  })
+
+  test('single-node does not pin a Cluster group', async ({ page }) => {
+    await stubFeatures(page, { distributed: false })
+    await stubNoP2P(page)
+    await page.goto('/app/chat')
+    // Nodes is reachable only via the Operate rail, not pinned at the top.
+    await expect(page.locator('.sidebar-nav')).toBeVisible({ timeout: 15_000 })
+    await expect(page.locator('.sidebar-nav .sidebar-section-items').first()
+      .getByText('Nodes', { exact: false })).toHaveCount(0)
+  })
+})
+
+test.describe('Top navbar', () => {
+  test('admin sees the mode pill and settings cog', async ({ page }) => {
+    await stubFeatures(page, { distributed: true })
+    await stubNoP2P(page)
+    await page.goto('/app/chat')
+    await expect(page.locator('.top-navbar__mode')).toBeVisible({ timeout: 15_000 })
+    await expect(page.locator('.top-navbar__icon[aria-label]')).not.toHaveCount(0)
+  })
+
+  test('admin-via-chat jump shows when localai_assistant is enabled', async ({ page }) => {
+    await stubFeatures(page, { distributed: false, localai_assistant: true })
+    await stubNoP2P(page)
+    await page.goto('/app/chat')
+    await expect(page.locator('.top-navbar__assistant')).toBeVisible({ timeout: 15_000 })
+  })
+
+  test('admin-via-chat jump hidden when localai_assistant is off', async ({ page }) => {
+    await stubFeatures(page, { distributed: false, localai_assistant: false })
+    await stubNoP2P(page)
+    await page.goto('/app/chat')
+    await expect(page.locator('.top-navbar__assistant')).toHaveCount(0)
+  })
+})
+
+test.describe('Token usage meter', () => {
+  test('renders when admin usage has data', async ({ page }) => {
+    await stubFeatures(page, { distributed: false })
+    await stubNoP2P(page)
+    await page.route('**/api/auth/admin/usage**', route =>
+      route.fulfill({ contentType: 'application/json',
+        body: JSON.stringify({ buckets: [{ total_tokens: 1234 }] }) }))
+    await page.goto('/app/chat')
+    await expect(page.locator('.top-navbar__meter')).toBeVisible({ timeout: 15_000 })
+  })
+
+  test('hidden when admin usage is empty (graceful degrade)', async ({ page }) => {
+    await stubFeatures(page, { distributed: false })
+    await stubNoP2P(page)
+    await page.route('**/api/auth/admin/usage**', route =>
+      route.fulfill({ contentType: 'application/json', body: JSON.stringify({ buckets: [] }) }))
+    await page.goto('/app/chat')
+    await expect(page.locator('.top-navbar')).toBeVisible({ timeout: 15_000 })
+    await expect(page.locator('.top-navbar__meter')).toHaveCount(0)
+  })
+})

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

@@ -86,7 +86,6 @@
   "input": {
     "placeholder": "Message...",
     "attachFile": "Attach file",
-    "send": "Send message",
     "stopGenerating": "Stop generating",
     "canvasTitle": "Canvas — extract code blocks and media into a side panel for preview, copy, and download",
     "canvasLabel": "Canvas",

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

@@ -77,21 +77,6 @@
     "noModelsTitle": "No Models Available",
     "noModelsBody": "There are no models installed yet. Ask your administrator to set up models so you can start chatting."
   },
-  "starters": {
-    "title": "Recommended for your hardware",
-    "tier": {
-      "cpu": "CPU-only",
-      "gpu-small": "GPU",
-      "gpu-mid": "GPU",
-      "gpu-large": "GPU"
-    },
-    "cpuNote": "No GPU detected — these small models stay responsive on CPU.",
-    "gpuNote": "Picked to fit your available VRAM with room for context.",
-    "install": "Install",
-    "installing": "Installing",
-    "installStarted": "Installing {{model}}…",
-    "installFailed": "Install failed: {{message}}"
-  },
   "connect": {
     "title": "One endpoint, every API",
     "subtitle": "LocalAI serves its own full API — image & video generation, depth, object detection, reranking, audio, face & voice recognition, and realtime voice over WebRTC and WebSocket. On top of that, a drop-in compatibility layer lets any app built for OpenAI, Anthropic, Ollama or OpenAI Responses talk to it unchanged.",

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

@@ -2,16 +2,6 @@
   "title": "Install Models",
   "subtitle": "Browse and install AI models from the gallery",
   "models": "Models",
-  "recommended": {
-    "title": "Recommended for your hardware",
-    "cpuNote": "No GPU detected - small models that stay responsive on CPU.",
-    "gpuNote": "Sized to fit your available VRAM with room for context.",
-    "install": "Install",
-    "installing": "Installing",
-    "installStarted": "Installing {{model}}…",
-    "installFailed": "Install failed: {{message}}",
-    "dismiss": "Dismiss recommendations"
-  },
   "stats": {
     "available": "Available",
     "installed": "Installed"