fix(depth): pin depth-anything.cpp to e0b6814 (ABI 3 dense C-API)

The Depth RPC handler calls da_capi_depth_dense / da_capi_points (C-API ABI 3);
pin the native build to the commit that exports them.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/backend-matrix.yml

@@ -716,6 +716,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "8"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-12-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "12"
     cuda-minor-version: "8"
@@ -1582,6 +1595,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-nvidia-cuda-13-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -1621,6 +1647,19 @@ include:
     backend: "locate-anything-cpp"
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
+  - build-type: 'cublas'
+    cuda-major-version: "13"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-cuda-13-arm64-depth-anything-cpp'
+    base-image: "ubuntu:24.04"
+    ubuntu-version: '2404'
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
   - build-type: 'cublas'
     cuda-major-version: "13"
     cuda-minor-version: "0"
@@ -2898,6 +2937,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2911,6 +2963,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f32'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f32-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f16'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2924,6 +2989,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'sycl_f16'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-intel-sycl-f16-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "intel/oneapi-basekit:2025.3.0-0-devel-ubuntu24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2938,6 +3016,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-depth-anything-cpp'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'vulkan'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -2952,6 +3044,20 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  - build-type: 'vulkan'
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-gpu-vulkan-depth-anything-cpp'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
   - build-type: 'sycl_f32'
     cuda-major-version: ""
     cuda-minor-version: ""
@@ -3058,6 +3164,19 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2204'
+  - build-type: 'cublas'
+    cuda-major-version: "12"
+    cuda-minor-version: "0"
+    platforms: 'linux/arm64'
+    skip-drivers: 'false'
+    tag-latest: 'auto'
+    tag-suffix: '-nvidia-l4t-arm64-depth-anything-cpp'
+    base-image: "nvcr.io/nvidia/l4t-jetpack:r36.4.0"
+    runs-on: 'ubuntu-24.04-arm'
+    backend: "depth-anything-cpp"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2204'
   # whisper
   - build-type: ''
     cuda-major-version: ""
@@ -4490,6 +4609,36 @@ include:
     dockerfile: "./backend/Dockerfile.golang"
     context: "./"
     ubuntu-version: '2404'
+  # supertonic CPU (amd64)
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/amd64'
+    platform-tag: 'amd64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-supertonic'
+    runs-on: 'ubuntu-latest'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "supertonic"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
+  # supertonic CPU (arm64)
+  - build-type: ''
+    cuda-major-version: ""
+    cuda-minor-version: ""
+    platforms: 'linux/arm64'
+    platform-tag: 'arm64'
+    tag-latest: 'auto'
+    tag-suffix: '-cpu-supertonic'
+    runs-on: 'ubuntu-24.04-arm'
+    base-image: "ubuntu:24.04"
+    skip-drivers: 'false'
+    backend: "supertonic"
+    dockerfile: "./backend/Dockerfile.golang"
+    context: "./"
+    ubuntu-version: '2404'
 
 # Darwin matrix (consumed by backend-jobs-darwin).
 includeDarwin:

.github/workflows/secscan.yaml

@@ -21,7 +21,10 @@ jobs:
         uses: securego/gosec@v2.27.1
         with:
           # we let the report trigger content trigger a failure using the GitHub Security features.
-          args: '-no-fail -fmt sarif -out results.sarif ./...'
+          # backend/go/supertonic is excluded: it vendors upstream supertone-inc/supertonic
+          # (helper.go), whose findings (G304 model-file loads, G404 math/rand for flow-matching
+          # noise, G104 unhandled errors) are inherent to that upstream code, not ours to rewrite.
+          args: '-no-fail -exclude-dir=backend/go/supertonic -fmt sarif -out results.sarif ./...'
       - name: Upload SARIF file
         if: ${{ github.actor != 'dependabot[bot]' }}
         uses: github/codeql-action/upload-sarif@v4

.golangci.yml

@@ -74,6 +74,8 @@ linters:
     paths:
       # Upstream whisper.cpp source tree fetched by the whisper backend Makefile.
       - 'backend/go/whisper/sources'
+      # Vendored upstream supertonic pipeline (supertone-inc/supertonic go/helper.go).
+      - 'backend/go/supertonic/helper.go'
       - 'docs/'
     rules:
       # CLI entry points: kong's `env:"..."` tag is the legitimate env→struct

Makefile

@@ -1,5 +1,5 @@
 # Disable parallel execution for backend builds
-.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio
+.NOTPARALLEL: backends/diffusers backends/llama-cpp backends/turboquant backends/outetts backends/piper backends/stablediffusion-ggml backends/whisper backends/crispasr backends/parakeet-cpp backends/faster-whisper backends/silero-vad backends/local-store backends/huggingface backends/rfdetr backends/rfdetr-cpp backends/insightface backends/speaker-recognition backends/kitten-tts backends/kokoro backends/chatterbox backends/llama-cpp-darwin backends/neutts build-darwin-python-backend build-darwin-go-backend backends/mlx backends/diffuser-darwin backends/mlx-vlm backends/mlx-audio backends/mlx-distributed backends/stablediffusion-ggml-darwin backends/vllm backends/vllm-omni backends/sglang backends/moonshine backends/pocket-tts backends/qwen-tts backends/faster-qwen3-tts backends/qwen-asr backends/nemo backends/voxcpm backends/whisperx backends/ace-step backends/acestep-cpp backends/fish-speech backends/voxtral backends/opus backends/trl backends/llama-cpp-quantization backends/kokoros backends/sam3-cpp backends/qwen3-tts-cpp backends/omnivoice-cpp backends/vibevoice-cpp backends/localvqe backends/tinygrad backends/sherpa-onnx backends/ds4 backends/ds4-darwin backends/liquid-audio backends/supertonic
 
 GOCMD=go
 GOTEST=$(GOCMD) test
@@ -595,6 +595,7 @@ test-extra: prepare-test-extra
 	$(MAKE) -C backend/rust/kokoros test
 	$(MAKE) -C backend/go/rfdetr-cpp test
 	$(MAKE) -C backend/go/locate-anything-cpp test
+	$(MAKE) -C backend/go/supertonic test
 
 ##
 ## End-to-end gRPC tests that exercise a built backend container image.
@@ -1181,6 +1182,7 @@ BACKEND_VIBEVOICE_CPP = vibevoice-cpp|golang|.|false|true
 BACKEND_LOCALVQE = localvqe|golang|.|false|true
 BACKEND_OPUS = opus|golang|.|false|true
 BACKEND_SHERPA_ONNX = sherpa-onnx|golang|.|false|true
+BACKEND_SUPERTONIC = supertonic|golang|.|false|true
 
 # Python backends with root context
 BACKEND_RERANKERS = rerankers|python|.|false|true
@@ -1308,12 +1310,13 @@ $(eval $(call generate-docker-build-target,$(BACKEND_KOKOROS)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SAM3_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_RFDETR_CPP)))
 $(eval $(call generate-docker-build-target,$(BACKEND_SHERPA_ONNX)))
+$(eval $(call generate-docker-build-target,$(BACKEND_SUPERTONIC)))
 
 # Pattern rule for docker-save targets
 docker-save-%: backend-images
 	docker save local-ai-backend:$* -o backend-images/$*.tar
 
-docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-omnivoice-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy
+docker-build-backends: docker-build-llama-cpp docker-build-ik-llama-cpp docker-build-turboquant docker-build-ds4 docker-build-rerankers docker-build-vllm docker-build-vllm-omni docker-build-sglang docker-build-transformers docker-build-outetts docker-build-diffusers docker-build-kokoro docker-build-faster-whisper docker-build-crispasr docker-build-coqui docker-build-chatterbox docker-build-vibevoice docker-build-liquid-audio docker-build-moonshine docker-build-pocket-tts docker-build-qwen-tts docker-build-fish-speech docker-build-faster-qwen3-tts docker-build-qwen-asr docker-build-nemo docker-build-voxcpm docker-build-whisperx docker-build-ace-step docker-build-acestep-cpp docker-build-voxtral docker-build-mlx-distributed docker-build-trl docker-build-llama-cpp-quantization docker-build-tinygrad docker-build-kokoros docker-build-sam3-cpp docker-build-rfdetr-cpp docker-build-qwen3-tts-cpp docker-build-omnivoice-cpp docker-build-vibevoice-cpp docker-build-localvqe docker-build-insightface docker-build-speaker-recognition docker-build-sherpa-onnx docker-build-cloud-proxy docker-build-supertonic
 
 ########################################################
 ### Mock Backend for E2E Tests

backend/backend.proto

@@ -24,6 +24,7 @@ service Backend {
   rpc TokenizeString(PredictOptions) returns (TokenizationResponse) {}
   rpc Status(HealthMessage) returns (StatusResponse) {}
   rpc Detect(DetectOptions) returns (DetectResponse) {}
+  rpc Depth(DepthRequest) returns (DepthResponse) {}
   rpc FaceVerify(FaceVerifyRequest) returns (FaceVerifyResponse) {}
   rpc FaceAnalyze(FaceAnalyzeRequest) returns (FaceAnalyzeResponse) {}
   rpc VoiceVerify(VoiceVerifyRequest) returns (VoiceVerifyResponse) {}
@@ -670,6 +671,35 @@ message DetectResponse {
   repeated Detection Detections = 1;
 }
 
+// --- Depth estimation messages (Depth Anything 3) ---
+
+message DepthRequest {
+  string src = 1;                  // input image (filesystem path or base64-encoded payload)
+  string dst = 2;                  // optional output directory for exports (glb/colmap)
+  bool include_depth = 3;          // return the per-pixel metric depth map
+  bool include_confidence = 4;     // return the per-pixel confidence map (DualDPT)
+  bool include_pose = 5;           // return camera extrinsics/intrinsics (DualDPT)
+  bool include_sky = 6;            // return the per-pixel sky map (mono models)
+  bool include_points = 7;         // back-project to a 3D point cloud (DualDPT)
+  float points_conf_thresh = 8;    // keep points with confidence >= this threshold
+  repeated string exports = 9;     // requested exports: "glb", "colmap"
+}
+
+message DepthResponse {
+  int32 width = 1;                 // processed depth-map width
+  int32 height = 2;                // processed depth-map height
+  repeated float depth = 3;        // width*height row-major metric depth
+  repeated float confidence = 4;   // width*height row-major confidence (DualDPT)
+  repeated float sky = 5;          // width*height row-major sky map (mono)
+  repeated float extrinsics = 6;   // 12 floats, 3x4 row-major (world-to-camera)
+  repeated float intrinsics = 7;   // 9 floats, 3x3 row-major
+  int32 num_points = 8;            // number of 3D points
+  repeated float points = 9;       // num_points*3 xyz, world space
+  bytes point_colors = 10;         // num_points*3 uint8 rgb
+  repeated string export_paths = 11; // paths written for the requested exports
+  bool is_metric = 12;             // depth is in metric units
+}
+
 // --- Face recognition messages ---
 
 message FacialArea {

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=e6f8112f3ba126eed3ff5b30cdd08085414a7516
+IK_LLAMA_VERSION?=5f917a64b391b7d31839845153a473a65f630458
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=4c6595503fe45d5a39f88d194e270f64c7424677
+LLAMA_VERSION?=4988f6e866057afd130c1515ecef0c9bab9a15f8
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

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

@@ -0,0 +1,7 @@
+sources/
+build*/
+package/
+libdepthanythingcpp*.so
+depth-anything-cpp
+test-models/
+test-data/

backend/go/depth-anything-cpp/CMakeLists.txt

@@ -0,0 +1,28 @@
+cmake_minimum_required(VERSION 3.18)
+project(libdepthanythingcpp LANGUAGES C CXX)
+
+set(CMAKE_POSITION_INDEPENDENT_CODE ON)
+set(CMAKE_CXX_STANDARD 17)
+set(CMAKE_CXX_STANDARD_REQUIRED ON)
+
+# Static-link ggml into the depth-anything shared library so the resulting .so
+# has no runtime dependency on an external libggml — only on
+# libc/libstdc++/libgomp, which the LocalAI package step bundles into the
+# docker image.
+set(BUILD_SHARED_LIBS OFF CACHE BOOL "Build static libraries" FORCE)
+
+# depth-anything.cpp build switches: skip CLI/tests, but build libdepthanything
+# itself as a SHARED library (DA_SHARED) while ggml stays static
+# (BUILD_SHARED_LIBS OFF above). The da_capi_* C ABI is compiled into
+# src/da_capi.cpp and re-exported by that shared library, so no extra MODULE
+# wrapper is needed (unlike locate-anything.cpp).
+set(DA_BUILD_CLI OFF CACHE BOOL "Disable depth-anything CLI" FORCE)
+set(DA_BUILD_TESTS OFF CACHE BOOL "Disable depth-anything tests" FORCE)
+set(DA_SHARED ON CACHE BOOL "Build libdepthanything as a shared lib" FORCE)
+
+add_subdirectory(./sources/depth-anything.cpp)
+
+# Emit libdepthanything.so into the top-level build dir so the Makefile can
+# rename it to the per-variant libdepthanythingcpp-<variant>.so.
+set_target_properties(depthanything PROPERTIES
+    LIBRARY_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR})

backend/go/depth-anything-cpp/Makefile

@@ -0,0 +1,136 @@
+CMAKE_ARGS?=
+BUILD_TYPE?=
+NATIVE?=false
+
+GOCMD?=go
+GO_TAGS?=
+JOBS?=$(shell nproc --ignore=1)
+
+# depth-anything.cpp. Pin to a specific commit for a stable build; a squash
+# merge upstream can orphan a branch, so the native version is pinned by SHA.
+DEPTHANYTHING_REPO?=https://github.com/mudler/depth-anything.cpp.git
+DEPTHANYTHING_VERSION?=e0b6814d2f58261216da69d63326f1f2d75d4435
+
+ifeq ($(NATIVE),false)
+	CMAKE_ARGS+=-DGGML_NATIVE=OFF
+endif
+
+# Forward LocalAI's BUILD_TYPE to the matching ggml backend switch. depth-anything.cpp
+# force-sets GGML_CUDA/GGML_VULKAN/GGML_METAL from its own DA_GGML_* options, so
+# those must be toggled via the DA_GGML_* names (a bare -DGGML_CUDA=ON would be
+# overridden); the remaining ggml switches pass straight through.
+ifeq ($(BUILD_TYPE),cublas)
+	CMAKE_ARGS+=-DGGML_CUDA=ON -DDA_GGML_CUDA=ON
+else ifeq ($(BUILD_TYPE),openblas)
+	CMAKE_ARGS+=-DGGML_BLAS=ON -DGGML_BLAS_VENDOR=OpenBLAS
+else ifeq ($(BUILD_TYPE),clblas)
+	CMAKE_ARGS+=-DGGML_CLBLAST=ON
+else ifeq ($(BUILD_TYPE),hipblas)
+	ROCM_HOME ?= /opt/rocm
+	ROCM_PATH ?= /opt/rocm
+	export CXX=$(ROCM_HOME)/llvm/bin/clang++
+	export CC=$(ROCM_HOME)/llvm/bin/clang
+	AMDGPU_TARGETS?=gfx908,gfx90a,gfx942,gfx950,gfx1030,gfx1100,gfx1101,gfx1102,gfx1200,gfx1201
+	CMAKE_ARGS+=-DGGML_HIPBLAS=ON -DAMDGPU_TARGETS=$(AMDGPU_TARGETS)
+else ifeq ($(BUILD_TYPE),vulkan)
+	CMAKE_ARGS+=-DGGML_VULKAN=ON -DDA_GGML_VULKAN=ON
+else ifeq ($(OS),Darwin)
+	ifneq ($(BUILD_TYPE),metal)
+		CMAKE_ARGS+=-DGGML_METAL=OFF
+	else
+		CMAKE_ARGS+=-DGGML_METAL=ON
+		CMAKE_ARGS+=-DGGML_METAL_EMBED_LIBRARY=ON
+		CMAKE_ARGS+=-DDA_GGML_METAL=ON
+	endif
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f16)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx \
+		-DGGML_SYCL_F16=ON
+endif
+
+ifeq ($(BUILD_TYPE),sycl_f32)
+	CMAKE_ARGS+=-DGGML_SYCL=ON \
+		-DCMAKE_C_COMPILER=icx \
+		-DCMAKE_CXX_COMPILER=icpx
+endif
+
+sources/depth-anything.cpp:
+	mkdir -p sources && \
+	git clone --recursive $(DEPTHANYTHING_REPO) sources/depth-anything.cpp && \
+	cd sources/depth-anything.cpp && \
+	git checkout $(DEPTHANYTHING_VERSION) && \
+	git submodule update --init --recursive --depth 1 --single-branch
+
+# Detect OS
+UNAME_S := $(shell uname -s)
+
+# Only build CPU variants on Linux
+ifeq ($(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.so
+endif
+
+depth-anything-cpp: main.go godepthanythingcpp.go $(VARIANT_TARGETS)
+	CGO_ENABLED=0 $(GOCMD) build -tags "$(GO_TAGS)" -o depth-anything-cpp ./
+
+package: depth-anything-cpp
+	bash package.sh
+
+build: package
+
+clean: purge
+	rm -rf libdepthanythingcpp*.so depth-anything-cpp package sources
+
+purge:
+	rm -rf build*
+
+# Build all variants (Linux only)
+ifeq ($(UNAME_S),Linux)
+libdepthanythingcpp-avx.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-avx2.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx2${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=off -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-avx512.so: sources/depth-anything.cpp
+	rm -rfv build-$@
+	$(info ${GREEN}I depth-anything-cpp build info:avx512${RESET})
+	SO_TARGET=$@ CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=on -DGGML_AVX2=on -DGGML_AVX512=on -DGGML_FMA=on -DGGML_F16C=on -DGGML_BMI2=on" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+endif
+
+# Build fallback variant (all platforms)
+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" $(MAKE) libdepthanythingcpp-custom
+	rm -rfv build-$@
+
+libdepthanythingcpp-custom: CMakeLists.txt
+	mkdir -p build-$(SO_TARGET) && \
+	cd build-$(SO_TARGET) && \
+	cmake .. $(CMAKE_ARGS) && \
+	cmake --build . --config Release -j$(JOBS) && \
+	cd .. && \
+	mv build-$(SO_TARGET)/libdepthanything.so ./$(SO_TARGET)
+
+all: depth-anything-cpp package
+
+# `test` is invoked by the top-level Makefile's `test-extra` target. It builds
+# the backend binary + the fallback shared library (needed for dlopen at
+# runtime), then runs test.sh which downloads a small GGUF + a test image and
+# exercises the gRPC Load/Predict wire path via the Go smoke test in
+# main_test.go.
+test: depth-anything-cpp libdepthanythingcpp-fallback.so
+	bash test.sh

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

@@ -0,0 +1,509 @@
+package main
+
+// godepthanythingcpp.go - gRPC handlers (Load, Predict, GenerateImage) for the
+// depth-anything-cpp backend, wrapping the Depth Anything 3 ggml C-API
+// (libdepthanythingcpp-<variant>.so) via purego.
+//
+// Embeds base.SingleThread to default the unimplemented RPCs to "not supported"
+// and to serialize calls — the C side shares a ggml graph allocator and is NOT
+// reentrant, so all inference must run one-at-a-time.
+//
+// Depth has no native OpenAI endpoint, so the model is exposed two ways:
+//
+//   - GenerateImage(src, dst): run depth on the src image and write a
+//     min-max-normalised grayscale depth PNG to dst.
+//   - Predict(images[0]): run depth+pose and return a JSON blob with the depth
+//     dimensions, depth stats and the camera extrinsics (3x4) / intrinsics (3x3).
+
+import (
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"image"
+	"image/png"
+	"math"
+	"os"
+	"path/filepath"
+	"unsafe"
+
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// C-API function pointers, registered in main.go via purego. The da_capi_*
+// symbols live inside libdepthanything (src/da_capi.cpp) and are re-exported by
+// the DA_SHARED build.
+var (
+	// da_capi_load(const char* gguf_path, int n_threads) -> da_ctx* (0 = fail)
+	CapiLoad func(gguf string, nThreads int32) uintptr
+	// da_capi_free(da_ctx* ctx) — safe on a 0 handle.
+	CapiFree func(handle uintptr)
+	// da_capi_last_error(da_ctx* ctx) -> const char* (owned by ctx, "" if none).
+	// purego marshals the returned C string into a Go string (a copy), so we
+	// never free it.
+	CapiLastError func(handle uintptr) string
+	// da_capi_depth_path(ctx, image_path, out_h*, out_w*) -> float* depth map
+	// (row-major H*W); nil on error. Caller frees via da_capi_free_floats.
+	CapiDepthPath func(handle uintptr, imagePath string, outH *int32, outW *int32) *float32
+	// da_capi_free_floats(float* p)
+	CapiFreeFloats func(p *float32)
+	// da_capi_pose_path(ctx, image_path, out_ext[12], out_intr[9]) -> 0 ok, -1 err
+	CapiPosePath func(handle uintptr, imagePath string, outExt *float32, outIntr *float32) int32
+	// da_capi_depth_dense(ctx, image_path, out_h*, out_w*, out_depth**, out_conf**,
+	//   out_sky**, out_ext[12], out_intr[9], out_is_metric*) -> 0 ok, -1 err.
+	// Each non-NULL out_depth/out_conf/out_sky receives a malloc'd float[H*W] (free
+	// via da_capi_free_floats); buffers the model doesn't produce are set NULL.
+	CapiDepthDense func(handle uintptr, imagePath string,
+		outH, outW *int32,
+		outDepth, outConf, outSky **float32,
+		outExt, outIntr *float32,
+		outIsMetric *int32) int32
+	// da_capi_points(ctx, image_path, conf_thresh, out_n*, out_xyz**, out_rgb**) ->
+	//   0 ok, -1 err. *out_xyz = malloc'd float[3*N] (free via da_capi_free_floats),
+	//   *out_rgb = malloc'd uint8[3*N] (free via da_capi_free_bytes).
+	CapiPoints func(handle uintptr, imagePath string, confThresh float32,
+		outN *int32, outXyz **float32, outRgb **byte) int32
+	// da_capi_free_bytes(unsigned char* p)
+	CapiFreeBytes func(p *byte)
+	// da_capi_export_glb(ctx, image_path, out_glb) -> 0 ok, -1 err
+	CapiExportGlb func(handle uintptr, imagePath string, outGlb string) int32
+	// da_capi_export_colmap(ctx, image_path, out_dir, binary) -> 0 ok, -1 err
+	CapiExportColmap func(handle uintptr, imagePath string, outDir string, binary int32) int32
+)
+
+type DepthAnythingCpp struct {
+	base.SingleThread
+	handle uintptr
+}
+
+// Load loads the GGUF model at opts.ModelFile (joined with opts.ModelPath if
+// relative) and stores the da_ctx handle for later inference calls.
+func (r *DepthAnythingCpp) Load(opts *pb.ModelOptions) error {
+	modelFile := opts.ModelFile
+	if modelFile == "" {
+		modelFile = opts.Model
+	}
+	if modelFile == "" {
+		return fmt.Errorf("depth-anything-cpp: ModelFile is empty")
+	}
+
+	var modelPath string
+	if filepath.IsAbs(modelFile) {
+		modelPath = modelFile
+	} else {
+		modelPath = filepath.Join(opts.ModelPath, modelFile)
+	}
+
+	if _, err := os.Stat(modelPath); err != nil {
+		return fmt.Errorf("depth-anything-cpp: model file not found: %s: %w", modelPath, err)
+	}
+
+	threads := opts.Threads
+	if threads <= 0 {
+		threads = 4
+	}
+
+	// Release previous model if any (re-Load).
+	if r.handle != 0 {
+		CapiFree(r.handle)
+		r.handle = 0
+	}
+
+	h := CapiLoad(modelPath, threads)
+	if h == 0 {
+		// da_capi_last_error needs a ctx; on a failed load we have none (it
+		// returns "" for a null ctx), so the text is best-effort.
+		if msg := CapiLastError(0); msg != "" {
+			return fmt.Errorf("depth-anything-cpp: da_capi_load failed for %s: %s", modelPath, msg)
+		}
+		return fmt.Errorf("depth-anything-cpp: da_capi_load failed for %s", modelPath)
+	}
+	r.handle = h
+	return nil
+}
+
+// depthResult is the JSON payload returned by Predict.
+type depthResult struct {
+	DepthW     int         `json:"depth_w"`
+	DepthH     int         `json:"depth_h"`
+	DepthMin   float32     `json:"depth_min"`
+	DepthMax   float32     `json:"depth_max"`
+	Extrinsics [12]float32 `json:"extrinsics"` // 3x4 row-major
+	Intrinsics [9]float32  `json:"intrinsics"` // 3x3 row-major
+}
+
+// Predict runs depth+pose on the first supplied image and returns depth
+// statistics + camera pose as a JSON string. LocalAI wraps the string into the
+// Reply.Message of the gRPC response. The image in Images[0] may be a
+// filesystem path or a base64-encoded payload.
+func (r *DepthAnythingCpp) Predict(opts *pb.PredictOptions) (string, error) {
+	imgs := opts.GetImages()
+	if len(imgs) == 0 {
+		return "", fmt.Errorf("depth-anything-cpp: Predict requires an image in Images[]")
+	}
+
+	imgPath, cleanup, err := materializeImage(imgs[0])
+	if err != nil {
+		return "", fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	depth, h, w, ext, intr, err := r.runDepthPose(imgPath)
+	if err != nil {
+		return "", err
+	}
+
+	dmin, dmax := minMax(depth)
+	payload, err := json.Marshal(depthResult{
+		DepthW: w, DepthH: h,
+		DepthMin: dmin, DepthMax: dmax,
+		Extrinsics: ext, Intrinsics: intr,
+	})
+	if err != nil {
+		return "", fmt.Errorf("depth-anything-cpp: marshal: %w", err)
+	}
+	return string(payload), nil
+}
+
+// GenerateImage runs depth on req.Src and writes a normalised grayscale depth
+// PNG to req.Dst.
+func (r *DepthAnythingCpp) GenerateImage(req *pb.GenerateImageRequest) error {
+	if req.GetSrc() == "" {
+		return fmt.Errorf("depth-anything-cpp: GenerateImage requires src")
+	}
+	if req.GetDst() == "" {
+		return fmt.Errorf("depth-anything-cpp: GenerateImage requires dst")
+	}
+
+	imgPath, cleanup, err := materializeImage(req.GetSrc())
+	if err != nil {
+		return fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	depth, h, w, _, _, err := r.runDepthPose(imgPath)
+	if err != nil {
+		return err
+	}
+	return writeDepthPNG(req.GetDst(), depth, h, w)
+}
+
+// Depth is the typed Depth RPC. It runs the Depth Anything 3 pipeline on the
+// request's src image and fills a DepthResponse honoring the include_* flags and
+// exports: per-pixel metric depth + confidence (DualDPT) or depth + sky (mono),
+// camera extrinsics/intrinsics, an optional back-projected 3D point cloud and
+// glb/COLMAP exports. The src may be a filesystem path or a base64 payload.
+func (r *DepthAnythingCpp) Depth(in *pb.DepthRequest) (pb.DepthResponse, error) {
+	// Accumulate into locals and return a single composite literal at the end:
+	// returning a named pb.DepthResponse value would copy its embedded mutex
+	// (go vet copylocks).
+	if r.handle == 0 {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: model not loaded")
+	}
+	if in.GetSrc() == "" {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: Depth requires src")
+	}
+
+	imgPath, cleanup, err := materializeImage(in.GetSrc())
+	if err != nil {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: %w", err)
+	}
+	defer cleanup()
+
+	// Dense per-pixel output + pose. Pass buffer pointers only for the
+	// requested maps so the native side can skip unrequested work; ext/intr
+	// must always point at 12/9 floats per the C ABI.
+	var (
+		h, w, isMetric      int32
+		depthPtr, confPtr   *float32
+		skyPtr              *float32
+		ext                 [12]float32
+		intr                [9]float32
+		pDepth, pConf, pSky **float32
+	)
+	if in.GetIncludeDepth() {
+		pDepth = &depthPtr
+	}
+	if in.GetIncludeConfidence() {
+		pConf = &confPtr
+	}
+	if in.GetIncludeSky() {
+		pSky = &skyPtr
+	}
+
+	rc := CapiDepthDense(r.handle, imgPath, &h, &w, pDepth, pConf, pSky, &ext[0], &intr[0], &isMetric)
+	if rc != 0 {
+		return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: da_capi_depth_dense failed (rc=%d): %s", rc, r.lastError())
+	}
+
+	n := int(h) * int(w)
+	var (
+		depth, conf, sky      []float32
+		extrinsics, intrinsic []float32
+		numPoints             int32
+		points                []float32
+		pointColors           []byte
+		exportPaths           []string
+	)
+
+	if depthPtr != nil {
+		depth = copyFloats(depthPtr, n)
+		CapiFreeFloats(depthPtr)
+	}
+	if confPtr != nil {
+		conf = copyFloats(confPtr, n)
+		CapiFreeFloats(confPtr)
+	}
+	if skyPtr != nil {
+		sky = copyFloats(skyPtr, n)
+		CapiFreeFloats(skyPtr)
+	}
+	if in.GetIncludePose() {
+		extrinsics = append([]float32(nil), ext[:]...)
+		intrinsic = append([]float32(nil), intr[:]...)
+	}
+
+	// 3D point cloud (DualDPT / pose-capable models only).
+	if in.GetIncludePoints() {
+		var (
+			np     int32
+			xyzPtr *float32
+			rgbPtr *byte
+		)
+		if rc := CapiPoints(r.handle, imgPath, in.GetPointsConfThresh(), &np, &xyzPtr, &rgbPtr); rc != 0 {
+			return pb.DepthResponse{}, fmt.Errorf("depth-anything-cpp: da_capi_points failed (rc=%d): %s", rc, r.lastError())
+		}
+		numPoints = np
+		if xyzPtr != nil {
+			points = copyFloats(xyzPtr, int(np)*3)
+			CapiFreeFloats(xyzPtr)
+		}
+		if rgbPtr != nil {
+			pointColors = copyBytes(rgbPtr, int(np)*3)
+			CapiFreeBytes(rgbPtr)
+		}
+	}
+
+	// Exports (glb / colmap). They are written under in.Dst (a directory); a
+	// temp dir is used when Dst is empty.
+	if len(in.GetExports()) > 0 {
+		exportPaths, err = r.runExports(imgPath, in.GetDst(), in.GetExports())
+		if err != nil {
+			return pb.DepthResponse{}, err
+		}
+	}
+
+	return pb.DepthResponse{
+		Width:       w,
+		Height:      h,
+		Depth:       depth,
+		Confidence:  conf,
+		Sky:         sky,
+		Extrinsics:  extrinsics,
+		Intrinsics:  intrinsic,
+		NumPoints:   numPoints,
+		Points:      points,
+		PointColors: pointColors,
+		ExportPaths: exportPaths,
+		IsMetric:    isMetric != 0,
+	}, nil
+}
+
+// runExports writes the requested exports for imgPath into dstDir and returns
+// the written paths. Supported exports: "glb", "colmap".
+func (r *DepthAnythingCpp) runExports(imgPath, dstDir string, exports []string) ([]string, error) {
+	if dstDir == "" {
+		tmp, err := os.MkdirTemp("", "depth-anything-export-*")
+		if err != nil {
+			return nil, fmt.Errorf("depth-anything-cpp: mkdir export dir: %w", err)
+		}
+		dstDir = tmp
+	} else if err := os.MkdirAll(dstDir, 0o755); err != nil {
+		return nil, fmt.Errorf("depth-anything-cpp: mkdir %s: %w", dstDir, err)
+	}
+
+	var paths []string
+	for _, exp := range exports {
+		switch exp {
+		case "glb":
+			out := filepath.Join(dstDir, "pointcloud.glb")
+			if rc := CapiExportGlb(r.handle, imgPath, out); rc != 0 {
+				return nil, fmt.Errorf("depth-anything-cpp: da_capi_export_glb failed (rc=%d): %s", rc, r.lastError())
+			}
+			paths = append(paths, out)
+		case "colmap":
+			out := filepath.Join(dstDir, "colmap")
+			if err := os.MkdirAll(out, 0o755); err != nil {
+				return nil, fmt.Errorf("depth-anything-cpp: mkdir %s: %w", out, err)
+			}
+			if rc := CapiExportColmap(r.handle, imgPath, out, 1); rc != 0 {
+				return nil, fmt.Errorf("depth-anything-cpp: da_capi_export_colmap failed (rc=%d): %s", rc, r.lastError())
+			}
+			paths = append(paths, out)
+		default:
+			return nil, fmt.Errorf("depth-anything-cpp: unknown export %q (want glb|colmap)", exp)
+		}
+	}
+	return paths, nil
+}
+
+// copyFloats copies n float32 values from a C heap pointer into a fresh Go
+// slice so the C buffer can be freed afterwards.
+func copyFloats(p *float32, n int) []float32 {
+	if p == nil || n <= 0 {
+		return nil
+	}
+	src := unsafe.Slice(p, n)
+	out := make([]float32, n)
+	copy(out, src)
+	return out
+}
+
+// copyBytes copies n bytes from a C heap pointer into a fresh Go slice.
+func copyBytes(p *byte, n int) []byte {
+	if p == nil || n <= 0 {
+		return nil
+	}
+	src := unsafe.Slice(p, n)
+	out := make([]byte, n)
+	copy(out, src)
+	return out
+}
+
+// runDepthPose runs depth estimation then pose recovery on an image file. It
+// returns the row-major depth map (length h*w), its dimensions, the 3x4
+// extrinsics (12 floats) and 3x3 intrinsics (9 floats).
+func (r *DepthAnythingCpp) runDepthPose(imagePath string) (depth []float32, h, w int, ext [12]float32, intr [9]float32, err error) {
+	if r.handle == 0 {
+		err = fmt.Errorf("depth-anything-cpp: model not loaded")
+		return
+	}
+
+	var ch, cw int32
+	ptr := CapiDepthPath(r.handle, imagePath, &ch, &cw)
+	if ptr == nil {
+		err = fmt.Errorf("depth-anything-cpp: da_capi_depth_path failed: %s", r.lastError())
+		return
+	}
+	h, w = int(ch), int(cw)
+	n := h * w
+	if n > 0 {
+		src := unsafe.Slice(ptr, n)
+		depth = make([]float32, n)
+		copy(depth, src)
+	}
+	CapiFreeFloats(ptr)
+
+	if rc := CapiPosePath(r.handle, imagePath, &ext[0], &intr[0]); rc != 0 {
+		err = fmt.Errorf("depth-anything-cpp: da_capi_pose_path failed (rc=%d): %s", rc, r.lastError())
+		return
+	}
+	return
+}
+
+// lastError returns the context's last error string, or "" if none.
+func (r *DepthAnythingCpp) lastError() string {
+	if CapiLastError == nil || r.handle == 0 {
+		return ""
+	}
+	return CapiLastError(r.handle)
+}
+
+// materializeImage returns a filesystem path for an image argument that may be
+// either an existing path or a base64-encoded payload. When the input is
+// base64 it is decoded into a temp file; cleanup removes it (no-op for a path).
+func materializeImage(arg string) (path string, cleanup func(), err error) {
+	cleanup = func() {}
+	if _, statErr := os.Stat(arg); statErr == nil {
+		return arg, cleanup, nil
+	}
+	// Strip an optional data URL prefix (data:image/...;base64,<payload>).
+	b64 := arg
+	if i := indexComma(b64); i >= 0 && hasDataPrefix(b64) {
+		b64 = b64[i+1:]
+	}
+	data, decErr := base64.StdEncoding.DecodeString(b64)
+	if decErr != nil {
+		return "", cleanup, fmt.Errorf("image is neither an existing path nor valid base64: %v", decErr)
+	}
+	f, tErr := os.CreateTemp("", "depth-anything-*.img")
+	if tErr != nil {
+		return "", cleanup, tErr
+	}
+	if _, wErr := f.Write(data); wErr != nil {
+		_ = f.Close()
+		_ = os.Remove(f.Name())
+		return "", cleanup, wErr
+	}
+	_ = f.Close()
+	name := f.Name()
+	return name, func() { _ = os.Remove(name) }, nil
+}
+
+func hasDataPrefix(s string) bool {
+	return len(s) >= 5 && s[:5] == "data:"
+}
+
+func indexComma(s string) int {
+	for i := 0; i < len(s); i++ {
+		if s[i] == ',' {
+			return i
+		}
+	}
+	return -1
+}
+
+// writeDepthPNG min-max normalises a depth map and writes it as an 8-bit
+// grayscale PNG. Near = bright (255), far = dark (0), matching the usual
+// depth-map convention for inverse-depth-like outputs.
+func writeDepthPNG(dst string, depth []float32, h, w int) error {
+	if h <= 0 || w <= 0 || len(depth) < h*w {
+		return fmt.Errorf("depth-anything-cpp: writeDepthPNG: bad dims h=%d w=%d len=%d", h, w, len(depth))
+	}
+	dmin, dmax := minMax(depth)
+	span := dmax - dmin
+	if span <= 0 || math.IsNaN(float64(span)) {
+		span = 1
+	}
+	img := image.NewGray(image.Rect(0, 0, w, h))
+	for y := 0; y < h; y++ {
+		for x := 0; x < w; x++ {
+			v := depth[y*w+x]
+			n := (v - dmin) / span // 0..1
+			if math.IsNaN(float64(n)) {
+				n = 0
+			}
+			if n < 0 {
+				n = 0
+			} else if n > 1 {
+				n = 1
+			}
+			img.Pix[y*img.Stride+x] = uint8(n * 255)
+		}
+	}
+	f, err := os.Create(dst)
+	if err != nil {
+		return err
+	}
+	defer func() { _ = f.Close() }()
+	return png.Encode(f, img)
+}
+
+func minMax(v []float32) (mn, mx float32) {
+	if len(v) == 0 {
+		return 0, 0
+	}
+	mn, mx = v[0], v[0]
+	for _, x := range v {
+		if math.IsNaN(float64(x)) || math.IsInf(float64(x), 0) {
+			continue
+		}
+		if x < mn {
+			mn = x
+		}
+		if x > mx {
+			mx = x
+		}
+	}
+	return mn, mx
+}

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

@@ -0,0 +1,61 @@
+package main
+
+// main.go - entry point for the depth-anything-cpp gRPC backend.
+//
+// Dlopens libdepthanythingcpp-<variant>.so via purego at the path in
+// DEPTHANYTHING_LIBRARY (set by run.sh based on /proc/cpuinfo), registers the
+// da_capi_* C ABI symbols, then starts the gRPC server.
+
+import (
+	"flag"
+	"os"
+
+	"github.com/ebitengine/purego"
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+)
+
+var (
+	addr = flag.String("addr", "localhost:50051", "the address to connect to")
+)
+
+type LibFuncs struct {
+	FuncPtr any
+	Name    string
+}
+
+func main() {
+	// Get library name from environment variable, default to fallback
+	libName := os.Getenv("DEPTHANYTHING_LIBRARY")
+	if libName == "" {
+		libName = "./libdepthanythingcpp-fallback.so"
+	}
+
+	lib, err := purego.Dlopen(libName, purego.RTLD_NOW|purego.RTLD_GLOBAL)
+	if err != nil {
+		panic(err)
+	}
+
+	libFuncs := []LibFuncs{
+		{&CapiLoad, "da_capi_load"},
+		{&CapiFree, "da_capi_free"},
+		{&CapiLastError, "da_capi_last_error"},
+		{&CapiDepthPath, "da_capi_depth_path"},
+		{&CapiFreeFloats, "da_capi_free_floats"},
+		{&CapiPosePath, "da_capi_pose_path"},
+		{&CapiDepthDense, "da_capi_depth_dense"},
+		{&CapiPoints, "da_capi_points"},
+		{&CapiFreeBytes, "da_capi_free_bytes"},
+		{&CapiExportGlb, "da_capi_export_glb"},
+		{&CapiExportColmap, "da_capi_export_colmap"},
+	}
+
+	for _, lf := range libFuncs {
+		purego.RegisterLibFunc(lf.FuncPtr, lib, lf.Name)
+	}
+
+	flag.Parse()
+
+	if err := grpc.StartServer(*addr, &DepthAnythingCpp{}); err != nil {
+		panic(err)
+	}
+}

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

@@ -0,0 +1,167 @@
+package main
+
+// main_test.go - end-to-end smoke test for the depth-anything-cpp gRPC backend.
+//
+// Spawns the compiled depth-anything-cpp binary on a free local port, dials it
+// via gRPC, and exercises LoadModel + Predict against the test fixtures
+// downloaded by test.sh: the small (vits) f32 GGUF of Depth Anything 3 and a
+// real photo. Asserts that Predict returns a JSON payload with a positive
+// depth-map width/height.
+//
+// The spec Skip()s cleanly if its fixtures (the model, the test image, the
+// built binary, or the fallback .so) are missing, so the test target stays
+// usable on a fresh checkout / on CI runners where the model hasn't been
+// downloaded.
+
+import (
+	"context"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"testing"
+	"time"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+)
+
+func TestDepth(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "depth-anything-cpp backend smoke suite")
+}
+
+// freePort grabs an ephemeral TCP port and immediately releases it so the
+// spawned backend can bind to it. There is a tiny TOCTOU window here but in
+// practice it's adequate for a smoke test on a quiet runner.
+func freePort() int {
+	l, err := net.Listen("tcp", "127.0.0.1:0")
+	Expect(err).ToNot(HaveOccurred(), "freePort listen")
+	port := l.Addr().(*net.TCPAddr).Port
+	Expect(l.Close()).To(Succeed())
+	return port
+}
+
+// startBackend spawns the depth-anything-cpp binary on the given port and waits
+// until it accepts TCP connections (up to 10s). It mirrors how main.go resolves
+// the purego library: the DEPTHANYTHING_LIBRARY env var points the dlopen at the
+// freshly built fallback .so. The returned cleanup func kills the process.
+func startBackend(port int) func() {
+	binary, err := filepath.Abs("./depth-anything-cpp")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(binary); err != nil {
+		Skip(fmt.Sprintf("backend binary not built: %s (run `make depth-anything-cpp` first)", binary))
+	}
+
+	libPath, err := filepath.Abs("./libdepthanythingcpp-fallback.so")
+	Expect(err).ToNot(HaveOccurred())
+	if _, err := os.Stat(libPath); err != nil {
+		Skip(fmt.Sprintf("fallback library not built: %s (run `make libdepthanythingcpp-fallback.so` first)", libPath))
+	}
+
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	cmd := exec.Command(binary, "--addr", addr)
+	cmd.Env = append(os.Environ(), "DEPTHANYTHING_LIBRARY="+libPath)
+	cmd.Stdout = os.Stderr
+	cmd.Stderr = os.Stderr
+	Expect(cmd.Start()).To(Succeed())
+
+	cleanup := func() {
+		if cmd.Process != nil {
+			_ = cmd.Process.Kill()
+			_, _ = cmd.Process.Wait()
+		}
+	}
+
+	deadline := time.Now().Add(10 * time.Second)
+	for time.Now().Before(deadline) {
+		c, err := net.DialTimeout("tcp", addr, 200*time.Millisecond)
+		if err == nil {
+			_ = c.Close()
+			return cleanup
+		}
+		time.Sleep(200 * time.Millisecond)
+	}
+
+	cleanup()
+	Fail(fmt.Sprintf("backend did not become ready on %s within 10s", addr))
+	return func() {}
+}
+
+// loadTestImage reads the test image downloaded by test.sh and returns its
+// base64-encoded content (one of the wire formats accepted by Predict).
+func loadTestImage() string {
+	imgPath, err := filepath.Abs("test-data/test.jpg")
+	Expect(err).ToNot(HaveOccurred())
+	imgBytes, err := os.ReadFile(imgPath)
+	if err != nil {
+		Skip(fmt.Sprintf("test image not present: %s (run test.sh first)", imgPath))
+	}
+	return base64.StdEncoding.EncodeToString(imgBytes)
+}
+
+// dialBackend opens a gRPC client connection to the spawned backend.
+func dialBackend(port int) (pb.BackendClient, func()) {
+	addr := fmt.Sprintf("127.0.0.1:%d", port)
+	conn, err := grpc.NewClient(addr, grpc.WithTransportCredentials(insecure.NewCredentials()))
+	Expect(err).ToNot(HaveOccurred())
+	return pb.NewBackendClient(conn), func() { _ = conn.Close() }
+}
+
+// modelPathOrSkip resolves the model file under ./test-models/ and Skip()s the
+// current spec if it's missing (not present on a fresh checkout / on CI runners
+// without the download).
+func modelPathOrSkip(name string) string {
+	modelDir, err := filepath.Abs("test-models")
+	Expect(err).ToNot(HaveOccurred())
+	modelPath := filepath.Join(modelDir, name)
+	if _, err := os.Stat(modelPath); err != nil {
+		Skip(fmt.Sprintf("model not present: %s (run test.sh first)", modelPath))
+	}
+	return modelPath
+}
+
+var _ = Describe("depth-anything-cpp backend", func() {
+	It("runs depth+pose against a known-good image", func() {
+		modelPath := modelPathOrSkip("depth-anything-small-f32.gguf")
+		imgB64 := loadTestImage()
+
+		port := freePort()
+		cleanup := startBackend(port)
+		defer cleanup()
+
+		client, closeConn := dialBackend(port)
+		defer closeConn()
+
+		ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute)
+		defer cancel()
+
+		loadResp, err := client.LoadModel(ctx, &pb.ModelOptions{
+			Model:     "depth-anything-small-f32.gguf",
+			ModelFile: modelPath,
+			Threads:   4,
+		})
+		Expect(err).ToNot(HaveOccurred(), "LoadModel")
+		Expect(loadResp.GetSuccess()).To(BeTrue(), "LoadModel reported failure: %s", loadResp.GetMessage())
+
+		// Predict runs depth+pose and returns the JSON depthResult in Reply.Message.
+		reply, err := client.Predict(ctx, &pb.PredictOptions{
+			Images: []string{imgB64},
+		})
+		Expect(err).ToNot(HaveOccurred(), "Predict")
+
+		var res depthResult
+		Expect(json.Unmarshal(reply.GetMessage(), &res)).To(Succeed(), "Predict returned non-JSON: %q", string(reply.GetMessage()))
+		Expect(res.DepthW).To(BeNumerically(">", 0), "depth width should be positive")
+		Expect(res.DepthH).To(BeNumerically(">", 0), "depth height should be positive")
+
+		_, _ = fmt.Fprintf(GinkgoWriter, "depth OK: %dx%d min=%.3f max=%.3f\n",
+			res.DepthW, res.DepthH, res.DepthMin, res.DepthMax)
+	})
+})

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

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+# Script to copy the appropriate libraries based on architecture
+
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+# Create lib directory
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/libdepthanythingcpp-*.so $CURDIR/package/
+cp -avf $CURDIR/depth-anything-cpp $CURDIR/package/
+cp -fv $CURDIR/run.sh $CURDIR/package/
+
+# Detect architecture and copy appropriate libraries
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    # x86_64 architecture
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    # ARM64 architecture
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    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 [ $(uname -s) = "Darwin" ]; then
+    echo "Detected Darwin"
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+# Package GPU libraries based on BUILD_TYPE
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

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

@@ -0,0 +1,52 @@
+#!/bin/bash
+set -ex
+
+# Get the absolute current dir where the script is located
+CURDIR=$(dirname "$(realpath $0)")
+
+cd /
+
+echo "CPU info:"
+if [ "$(uname)" != "Darwin" ]; then
+	grep -e "model\sname" /proc/cpuinfo | head -1
+	grep -e "flags" /proc/cpuinfo | head -1
+fi
+
+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 $CURDIR/libdepthanythingcpp-avx.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx.so"
+		fi
+	fi
+
+	if grep -q -e "\savx2\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX2   found OK"
+		if [ -e $CURDIR/libdepthanythingcpp-avx2.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx2.so"
+		fi
+	fi
+
+	# Check avx 512
+	if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
+		echo "CPU:    AVX512F found OK"
+		if [ -e $CURDIR/libdepthanythingcpp-avx512.so ]; then
+			LIBRARY="$CURDIR/libdepthanythingcpp-avx512.so"
+		fi
+	fi
+fi
+
+export LD_LIBRARY_PATH=$CURDIR/lib:$LD_LIBRARY_PATH
+export DEPTHANYTHING_LIBRARY=$LIBRARY
+
+# If there is a lib/ld.so, use it
+if [ -f $CURDIR/lib/ld.so ]; then
+	echo "Using lib/ld.so"
+	echo "Using library: $LIBRARY"
+	exec $CURDIR/lib/ld.so $CURDIR/depth-anything-cpp "$@"
+fi
+
+echo "Using library: $LIBRARY"
+exec $CURDIR/depth-anything-cpp "$@"

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

@@ -0,0 +1,45 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+
+echo "Running depth-anything-cpp backend tests..."
+
+# Test model from the mudler/depth-anything.cpp-gguf HuggingFace repo. The small
+# (vits) f32 GGUF is the lightest backbone (~131 MB), so it keeps the download
+# cheap. It is resumed with `curl -C -` and skipped entirely if already present.
+DEPTHANYTHING_MODEL_DIR="${DEPTHANYTHING_MODEL_DIR:-$CURDIR/test-models}"
+
+DEPTHANYTHING_MODEL_FILE="${DEPTHANYTHING_MODEL_FILE:-depth-anything-small-f32.gguf}"
+DEPTHANYTHING_MODEL_URL="${DEPTHANYTHING_MODEL_URL:-https://huggingface.co/mudler/depth-anything.cpp-gguf/resolve/main/depth-anything-small-f32.gguf}"
+
+mkdir -p "$DEPTHANYTHING_MODEL_DIR"
+
+if [ ! -f "$DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE" ]; then
+    echo "Downloading depth-anything small f32 model (~131 MB)..."
+    # -C - resumes a partial download so an interrupted run doesn't restart from 0.
+    curl -L -C - -o "$DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE" "$DEPTHANYTHING_MODEL_URL" --progress-bar
+fi
+
+# Use a real photo (people + cars) from the upstream rf-detr.cpp repo (~46 KB).
+# Depth estimation needs real content; a synthetic image would be degenerate.
+TEST_IMAGE_DIR="$CURDIR/test-data"
+TEST_IMAGE_FILE="$TEST_IMAGE_DIR/test.jpg"
+TEST_IMAGE_URL="${TEST_IMAGE_URL:-https://raw.githubusercontent.com/mudler/rf-detr.cpp/main/tests/fixtures/ci/test_image.jpg}"
+
+mkdir -p "$TEST_IMAGE_DIR"
+if [ ! -f "$TEST_IMAGE_FILE" ]; then
+    echo "Downloading test image..."
+    curl -L -o "$TEST_IMAGE_FILE" "$TEST_IMAGE_URL" --progress-bar
+fi
+
+echo "depth-anything-cpp test setup complete."
+echo "  model:      $DEPTHANYTHING_MODEL_DIR/$DEPTHANYTHING_MODEL_FILE"
+echo "  test image: $TEST_IMAGE_FILE"
+
+# Run the Go smoke test: spawns the backend binary on a free port, calls
+# LoadModel + Predict via gRPC against the downloaded GGUF + image.
+echo ""
+echo "Running Go smoke test..."
+cd "$CURDIR"
+go test -v -timeout 30m ./...

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?=19bdfe22d255d5b4dff39d449318b9bc5ea2317f
+STABLEDIFFUSION_GGML_VERSION?=276025e054555166ec419413c6748ca79986ee93
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/supertonic/.gitignore

@@ -0,0 +1,4 @@
+/supertonic
+/sources/
+/backend-assets/
+/package/

backend/go/supertonic/Makefile

@@ -0,0 +1,62 @@
+CURRENT_DIR=$(abspath ./)
+GOCMD=go
+
+ONNX_VERSION?=1.24.4
+ONNX_ARCH?=x64
+ONNX_OS?=linux
+
+ifneq (,$(findstring aarch64,$(shell uname -m)))
+	ONNX_ARCH=aarch64
+endif
+
+ifeq ($(OS),Darwin)
+	ONNX_OS=osx
+	ifneq (,$(findstring arm64,$(shell uname -m)))
+		ONNX_ARCH=arm64
+	else
+		ONNX_ARCH=x86_64
+	endif
+endif
+
+# CUDA 12 ships as -gpu, CUDA 13 as -gpu_cuda13 (underscore). CPU has no suffix.
+ifeq ($(BUILD_TYPE),cublas)
+	ONNX_PROVIDER=cuda
+	ifeq ($(CUDA_MAJOR_VERSION),13)
+		ONNX_VARIANT=-gpu_cuda13
+	else
+		ONNX_VARIANT=-gpu
+	endif
+else
+	ONNX_VARIANT=
+	ONNX_PROVIDER=cpu
+endif
+
+sources/onnxruntime:
+	mkdir -p sources/onnxruntime
+	curl -L https://github.com/microsoft/onnxruntime/releases/download/v$(ONNX_VERSION)/onnxruntime-$(ONNX_OS)-$(ONNX_ARCH)$(ONNX_VARIANT)-$(ONNX_VERSION).tgz \
+	  -o sources/onnxruntime/onnxruntime.tgz
+	cd sources/onnxruntime && tar -xf onnxruntime.tgz --strip-components=1 && rm onnxruntime.tgz
+
+backend-assets/lib: sources/onnxruntime
+	mkdir -p backend-assets/lib
+	cp -rfLv sources/onnxruntime/lib/* backend-assets/lib/
+
+supertonic: backend-assets/lib
+	CGO_ENABLED=1 $(GOCMD) build \
+	  -ldflags "$(LD_FLAGS) -X main.onnxProvider=$(ONNX_PROVIDER)" \
+	  -tags "$(GO_TAGS)" -o supertonic ./
+
+package:
+	bash package.sh
+
+build: supertonic package
+
+# Tests need only the Go toolchain (gcc); yalue dlopens onnxruntime at
+# runtime, so no tarball download is required to compile or run unit specs.
+test:
+	CGO_ENABLED=1 $(GOCMD) test -v -timeout 120s ./...
+
+clean:
+	rm -rf supertonic sources/ backend-assets/ package/
+
+.PHONY: build package clean test

backend/go/supertonic/backend.go

@@ -0,0 +1,307 @@
+package main
+
+import (
+	"bytes"
+	"encoding/binary"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"sync"
+
+	laudio "github.com/mudler/LocalAI/pkg/audio"
+	"github.com/mudler/LocalAI/pkg/grpc/base"
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// onnxProvider is set via -ldflags "-X main.onnxProvider=cuda" by the
+// CUDA build (later phase). Defaults to CPU.
+var onnxProvider = "cpu"
+
+// Per-model generation defaults, overridable via ModelOptions.Options:
+//
+//	supertonic.steps=<int>          denoising steps (quality), default 8
+//	supertonic.speed=<float>        speech rate, default 1.05
+//	supertonic.silence=<float>      inter-chunk silence seconds, default 0.3
+//	supertonic.default_voice=<name> voice-style used when request omits voice
+//	supertonic.default_lang=<lang>  language tag used when request omits it
+const (
+	optionSteps        = "supertonic.steps="
+	optionSpeed        = "supertonic.speed="
+	optionSilence      = "supertonic.silence="
+	optionDefaultVoice = "supertonic.default_voice="
+	optionDefaultLang  = "supertonic.default_lang="
+)
+
+type SupertonicBackend struct {
+	base.SingleThread
+
+	tts          *TextToSpeech
+	cfg          Config
+	modelDir     string
+	voicesDir    string
+	defaultVoice string
+	defaultLang  string
+	steps        int
+	speed        float32
+	silence      float32
+
+	styleMu sync.Mutex
+	styles  map[string]*Style // voice name -> loaded style cache
+}
+
+func (s *SupertonicBackend) Load(opts *pb.ModelOptions) error {
+	modelDir, err := resolveModelDir(opts.ModelFile)
+	if err != nil {
+		return err
+	}
+	s.modelDir = modelDir
+	s.voicesDir = resolveVoicesDir(modelDir)
+
+	cfg, err := LoadCfgs(modelDir)
+	if err != nil {
+		return fmt.Errorf("loading tts.json from %s: %w", modelDir, err)
+	}
+	s.cfg = cfg
+
+	// onnxProvider is "cpu" for the CPU build; the CUDA build sets it to
+	// "cuda" via -ldflags. Upstream LoadTextToSpeech still errors on GPU
+	// until the CUDA phase wires the execution provider.
+	tts, err := LoadTextToSpeech(modelDir, onnxProvider == "cuda", cfg)
+	if err != nil {
+		return fmt.Errorf("loading supertonic models from %s: %w", modelDir, err)
+	}
+	s.tts = tts
+
+	s.steps = int(findOptionInt(opts, optionSteps, 8))
+	s.speed = findOptionFloat(opts, optionSpeed, 1.05)
+	s.silence = findOptionFloat(opts, optionSilence, 0.3)
+	s.defaultVoice = findOptionValue(opts, optionDefaultVoice, "")
+	s.defaultLang = findOptionValue(opts, optionDefaultLang, "na")
+	s.styles = map[string]*Style{}
+	return nil
+}
+
+func (s *SupertonicBackend) TTS(req *pb.TTSRequest) error {
+	wav, sr, err := s.synthesize(req)
+	if err != nil {
+		return err
+	}
+	out := make([]float64, len(wav))
+	for i, v := range wav {
+		out[i] = float64(v)
+	}
+	if err := writeWavFile(req.Dst, out, sr); err != nil {
+		return fmt.Errorf("writing wav to %s: %w", req.Dst, err)
+	}
+	return nil
+}
+
+func (s *SupertonicBackend) TTSStream(req *pb.TTSRequest, results chan []byte) error {
+	defer close(results)
+
+	wav, sr, err := s.synthesize(req)
+	if err != nil {
+		return err
+	}
+
+	results <- streamingWAVHeader(uint32(sr))
+
+	const chunkSamples = 4096
+	for off := 0; off < len(wav); off += chunkSamples {
+		end := off + chunkSamples
+		if end > len(wav) {
+			end = len(wav)
+		}
+		results <- pcmFloatToInt16LE(wav[off:end])
+	}
+	return nil
+}
+
+// synthesize runs the full pipeline and returns the trimmed mono float32
+// PCM and its sample rate.
+func (s *SupertonicBackend) synthesize(req *pb.TTSRequest) ([]float32, int, error) {
+	if s.tts == nil {
+		return nil, 0, fmt.Errorf("supertonic model not loaded")
+	}
+	if strings.TrimSpace(req.Text) == "" {
+		return nil, 0, fmt.Errorf("empty text")
+	}
+
+	style, err := s.loadStyle(s.voiceName(req.Voice))
+	if err != nil {
+		return nil, 0, err
+	}
+
+	lang := s.resolveLang("")
+	if req.Language != nil {
+		lang = s.resolveLang(*req.Language)
+	}
+
+	wav, dur, err := s.tts.Call(req.Text, lang, style, s.steps, s.speed, s.silence)
+	if err != nil {
+		return nil, 0, err
+	}
+
+	sr := s.tts.SampleRate
+	// Call returns concatenated audio; trim to the reported duration.
+	wavLen := int(float32(sr) * dur)
+	if wavLen < 0 {
+		wavLen = 0
+	}
+	if wavLen > len(wav) {
+		wavLen = len(wav)
+	}
+	return wav[:wavLen], sr, nil
+}
+
+// voiceName picks the request voice, falling back to the model default.
+func (s *SupertonicBackend) voiceName(reqVoice string) string {
+	v := strings.TrimSpace(reqVoice)
+	if v == "" {
+		return s.defaultVoice
+	}
+	return v
+}
+
+// resolveLang validates against AvailableLangs, falling back to the model
+// default (then "na").
+func (s *SupertonicBackend) resolveLang(reqLang string) string {
+	l := strings.TrimSpace(reqLang)
+	if l != "" && isValidLang(l) {
+		return l
+	}
+	if s.defaultLang != "" && isValidLang(s.defaultLang) {
+		return s.defaultLang
+	}
+	return "na"
+}
+
+// loadStyle resolves and caches a voice-style. An empty name with no model
+// default is an error (supertonic requires a style embedding).
+func (s *SupertonicBackend) loadStyle(name string) (*Style, error) {
+	if name == "" {
+		return nil, fmt.Errorf("no voice specified and no supertonic.default_voice set")
+	}
+	s.styleMu.Lock()
+	defer s.styleMu.Unlock()
+	if st, ok := s.styles[name]; ok {
+		return st, nil
+	}
+	path := s.voiceStylePath(name)
+	st, err := LoadVoiceStyle([]string{path}, false)
+	if err != nil {
+		return nil, fmt.Errorf("loading voice style %q (%s): %w", name, path, err)
+	}
+	s.styles[name] = st
+	return st, nil
+}
+
+// voiceStylePath maps a voice name to a JSON path. Absolute paths are honored;
+// names containing a separator resolve under modelDir; bare names resolve under
+// the resolved voicesDir (see resolveVoicesDir).
+func (s *SupertonicBackend) voiceStylePath(name string) string {
+	if !strings.HasSuffix(name, ".json") {
+		name += ".json"
+	}
+	if filepath.IsAbs(name) {
+		return name
+	}
+	if strings.ContainsRune(name, filepath.Separator) {
+		return filepath.Join(s.modelDir, name)
+	}
+	return filepath.Join(s.voicesDir, name)
+}
+
+// resolveVoicesDir locates the voice_styles directory. The HF model layout
+// puts the ONNX files in an onnx/ subdir with voice_styles/ as its sibling,
+// so check modelDir/voice_styles first, then the parent's voice_styles.
+func resolveVoicesDir(modelDir string) string {
+	candidates := []string{
+		filepath.Join(modelDir, "voice_styles"),
+		filepath.Join(filepath.Dir(modelDir), "voice_styles"),
+	}
+	for _, c := range candidates {
+		if info, err := os.Stat(c); err == nil && info.IsDir() {
+			return c
+		}
+	}
+	return candidates[0]
+}
+
+// resolveModelDir accepts either a directory (used as-is) or a file (its
+// parent dir is used).
+func resolveModelDir(modelFile string) (string, error) {
+	if modelFile == "" {
+		return "", fmt.Errorf("empty model path")
+	}
+	info, err := os.Stat(modelFile)
+	if err != nil {
+		return "", fmt.Errorf("stat model path %s: %w", modelFile, err)
+	}
+	if info.IsDir() {
+		return modelFile, nil
+	}
+	return filepath.Dir(modelFile), nil
+}
+
+// ---- option helpers (mirrors backend/go/sherpa-onnx/backend.go) ----
+
+func findOptionValue(opts *pb.ModelOptions, prefix, def string) string {
+	for _, o := range opts.Options {
+		if strings.HasPrefix(o, prefix) {
+			return strings.TrimPrefix(o, prefix)
+		}
+	}
+	return def
+}
+
+func findOptionFloat(opts *pb.ModelOptions, prefix string, def float32) float32 {
+	raw := findOptionValue(opts, prefix, "")
+	if raw == "" {
+		return def
+	}
+	v, err := strconv.ParseFloat(raw, 32)
+	if err != nil {
+		return def
+	}
+	return float32(v)
+}
+
+func findOptionInt(opts *pb.ModelOptions, prefix string, def int32) int32 {
+	raw := findOptionValue(opts, prefix, "")
+	if raw == "" {
+		return def
+	}
+	v, err := strconv.ParseInt(raw, 10, 32)
+	if err != nil {
+		return def
+	}
+	return int32(v)
+}
+
+// ---- PCM helpers ----
+
+func pcmFloatToInt16LE(samples []float32) []byte {
+	buf := make([]byte, len(samples)*2)
+	for i, f := range samples {
+		v := int32(f * 32767)
+		if v > 32767 {
+			v = 32767
+		} else if v < -32768 {
+			v = -32768
+		}
+		binary.LittleEndian.PutUint16(buf[2*i:], uint16(int16(v)))
+	}
+	return buf
+}
+
+func streamingWAVHeader(sampleRate uint32) []byte {
+	const streamingSize = 0xFFFFFFFF
+	h := laudio.NewWAVHeaderWithRate(streamingSize, sampleRate)
+	h.ChunkSize = streamingSize
+	var buf bytes.Buffer
+	_ = h.Write(&buf)
+	return buf.Bytes()
+}

backend/go/supertonic/backend_test.go

@@ -0,0 +1,86 @@
+package main
+
+import (
+	"os"
+	"path/filepath"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+var _ = Describe("voiceStylePath", func() {
+	s := &SupertonicBackend{modelDir: "/models/st/onnx", voicesDir: "/models/st/voice_styles"}
+
+	It("resolves a bare name under the resolved voicesDir", func() {
+		Expect(s.voiceStylePath("M1")).To(Equal(filepath.Join("/models/st/voice_styles", "M1.json")))
+	})
+	It("keeps an explicit .json suffix", func() {
+		Expect(s.voiceStylePath("M1.json")).To(Equal(filepath.Join("/models/st/voice_styles", "M1.json")))
+	})
+	It("honors absolute paths", func() {
+		Expect(s.voiceStylePath("/abs/v.json")).To(Equal("/abs/v.json"))
+	})
+})
+
+var _ = Describe("resolveVoicesDir", func() {
+	It("prefers voice_styles under modelDir", func() {
+		dir := GinkgoT().TempDir()
+		Expect(os.MkdirAll(filepath.Join(dir, "voice_styles"), 0o755)).To(Succeed())
+		Expect(resolveVoicesDir(dir)).To(Equal(filepath.Join(dir, "voice_styles")))
+	})
+	It("falls back to the sibling voice_styles next to an onnx subdir", func() {
+		root := GinkgoT().TempDir()
+		Expect(os.MkdirAll(filepath.Join(root, "voice_styles"), 0o755)).To(Succeed())
+		Expect(os.MkdirAll(filepath.Join(root, "onnx"), 0o755)).To(Succeed())
+		Expect(resolveVoicesDir(filepath.Join(root, "onnx"))).To(Equal(filepath.Join(root, "voice_styles")))
+	})
+})
+
+var _ = Describe("resolveLang", func() {
+	It("accepts a valid request language", func() {
+		s := &SupertonicBackend{defaultLang: "na"}
+		Expect(s.resolveLang("ko")).To(Equal("ko"))
+	})
+	It("falls back to the model default for an invalid language", func() {
+		s := &SupertonicBackend{defaultLang: "en"}
+		Expect(s.resolveLang("zz")).To(Equal("en"))
+	})
+	It("falls back to na when nothing is valid", func() {
+		s := &SupertonicBackend{defaultLang: ""}
+		Expect(s.resolveLang("")).To(Equal("na"))
+	})
+})
+
+var _ = Describe("pcmFloatToInt16LE", func() {
+	It("clamps and encodes little-endian", func() {
+		out := pcmFloatToInt16LE([]float32{0, 1.0, -1.0, 2.0})
+		Expect(out).To(HaveLen(8))
+		Expect(out[0:2]).To(Equal([]byte{0x00, 0x00})) // 0
+		Expect(out[2:4]).To(Equal([]byte{0xff, 0x7f})) // 32767
+		Expect(out[6:8]).To(Equal([]byte{0xff, 0x7f})) // clamp 2.0 -> 32767
+	})
+})
+
+var _ = Describe("end-to-end synthesis", Ordered, func() {
+	var modelDir string
+	BeforeAll(func() {
+		modelDir = os.Getenv("SUPERTONIC_MODEL_PATH")
+		if modelDir == "" {
+			Skip("set SUPERTONIC_MODEL_PATH to a supertonic model dir to run")
+		}
+		Expect(InitializeONNXRuntime()).To(Succeed())
+	})
+
+	It("synthesizes a wav file", func() {
+		b := &SupertonicBackend{}
+		Expect(b.Load(&pb.ModelOptions{ModelFile: modelDir, Options: []string{"supertonic.default_voice=F1"}})).To(Succeed())
+		dst := filepath.Join(GinkgoT().TempDir(), "out.wav")
+		lang := "en"
+		Expect(b.TTS(&pb.TTSRequest{Text: "Hello from LocalAI.", Dst: dst, Language: &lang})).To(Succeed())
+		info, err := os.Stat(dst)
+		Expect(err).ToNot(HaveOccurred())
+		Expect(info.Size()).To(BeNumerically(">", 44)) // header + PCM
+	})
+})

backend/go/supertonic/main.go

@@ -0,0 +1,27 @@
+package main
+
+// Started internally by LocalAI; a server is allocated per model.
+
+import (
+	"flag"
+
+	grpc "github.com/mudler/LocalAI/pkg/grpc"
+	ort "github.com/yalue/onnxruntime_go"
+)
+
+var addr = flag.String("addr", "localhost:50051", "the address to connect to")
+
+func main() {
+	flag.Parse()
+
+	// InitializeONNXRuntime reads ONNXRUNTIME_LIB_PATH (set by run.sh) and
+	// dlopens libonnxruntime before any session is created in Load().
+	if err := InitializeONNXRuntime(); err != nil {
+		panic(err)
+	}
+	defer func() { _ = ort.DestroyEnvironment() }()
+
+	if err := grpc.StartServer(*addr, &SupertonicBackend{}); err != nil {
+		panic(err)
+	}
+}

backend/go/supertonic/main_suite_test.go

@@ -0,0 +1,13 @@
+package main
+
+import (
+	"testing"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+func TestSupertonic(t *testing.T) {
+	RegisterFailHandler(Fail)
+	RunSpecs(t, "Supertonic backend test suite")
+}

backend/go/supertonic/package.sh

@@ -0,0 +1,49 @@
+#!/bin/bash
+set -e
+
+CURDIR=$(dirname "$(realpath $0)")
+REPO_ROOT="${CURDIR}/../../.."
+
+mkdir -p $CURDIR/package/lib
+
+cp -avf $CURDIR/supertonic $CURDIR/package/
+cp -avf $CURDIR/run.sh $CURDIR/package/
+cp -rfLv $CURDIR/backend-assets/lib/* $CURDIR/package/lib/
+
+if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
+    echo "Detected x86_64 architecture, copying x86_64 libraries..."
+    cp -arfLv /lib64/ld-linux-x86-64.so.2 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/x86_64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/x86_64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libdl.so.2 $CURDIR/package/lib/libdl.so.2
+    cp -arfLv /lib/x86_64-linux-gnu/librt.so.1 $CURDIR/package/lib/librt.so.1
+    cp -arfLv /lib/x86_64-linux-gnu/libpthread.so.0 $CURDIR/package/lib/libpthread.so.0
+elif [ -f "/lib/ld-linux-aarch64.so.1" ]; then
+    echo "Detected ARM64 architecture, copying ARM64 libraries..."
+    cp -arfLv /lib/ld-linux-aarch64.so.1 $CURDIR/package/lib/ld.so
+    cp -arfLv /lib/aarch64-linux-gnu/libc.so.6 $CURDIR/package/lib/libc.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgcc_s.so.1 $CURDIR/package/lib/libgcc_s.so.1
+    cp -arfLv /lib/aarch64-linux-gnu/libstdc++.so.6 $CURDIR/package/lib/libstdc++.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libm.so.6 $CURDIR/package/lib/libm.so.6
+    cp -arfLv /lib/aarch64-linux-gnu/libgomp.so.1 $CURDIR/package/lib/libgomp.so.1
+    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 $CURDIR/package/lib/libpthread.so.0
+else
+    echo "Error: Could not detect architecture"
+    exit 1
+fi
+
+GPU_LIB_SCRIPT="${REPO_ROOT}/scripts/build/package-gpu-libs.sh"
+if [ -f "$GPU_LIB_SCRIPT" ]; then
+    echo "Packaging GPU libraries for BUILD_TYPE=${BUILD_TYPE:-cpu}..."
+    source "$GPU_LIB_SCRIPT" "$CURDIR/package/lib"
+    package_gpu_libs
+fi
+
+echo "Packaging completed successfully"
+ls -liah $CURDIR/package/
+ls -liah $CURDIR/package/lib/

backend/go/supertonic/run.sh

@@ -0,0 +1,14 @@
+#!/bin/bash
+set -ex
+
+CURDIR=$(dirname "$(realpath $0)")
+
+export LD_LIBRARY_PATH=$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
+
+exec $CURDIR/supertonic "$@"

backend/index.yaml

@@ -458,6 +458,126 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-locate-anything-cpp"
   mirrors:
     - localai/localai-backends:master-gpu-vulkan-locate-anything-cpp
+- &depthanything
+  name: "depth-anything"
+  alias: "depth-anything"
+  license: apache-2.0
+  description: |
+    Depth Anything 3 monocular metric depth + camera pose estimation in C/C++
+    using GGML. Loads pre-built GGUF weights and, given an image, returns a
+    dense depth map plus the recovered camera extrinsics (3x4) and intrinsics
+    (3x3). No Python at inference (purego, cgo-less).
+  urls:
+    - https://github.com/mudler/depth-anything.cpp
+    - https://huggingface.co/depth-anything/Depth-Anything-V3
+  tags:
+    - depth-estimation
+    - camera-pose
+    - depth-anything
+    - gpu
+    - cpu
+  capabilities:
+    default: "cpu-depth-anything-cpp"
+    nvidia: "cuda12-depth-anything-cpp"
+    nvidia-cuda-12: "cuda12-depth-anything-cpp"
+    nvidia-cuda-13: "cuda13-depth-anything-cpp"
+    nvidia-l4t: "nvidia-l4t-arm64-depth-anything-cpp"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-depth-anything-cpp"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-depth-anything-cpp"
+    intel: "intel-sycl-f32-depth-anything-cpp"
+    vulkan: "vulkan-depth-anything-cpp"
+- !!merge <<: *depthanything
+  name: "depth-anything-development"
+  capabilities:
+    default: "cpu-depth-anything-cpp-development"
+    nvidia: "cuda12-depth-anything-cpp-development"
+    nvidia-cuda-12: "cuda12-depth-anything-cpp-development"
+    nvidia-cuda-13: "cuda13-depth-anything-cpp-development"
+    nvidia-l4t: "nvidia-l4t-arm64-depth-anything-cpp-development"
+    nvidia-l4t-cuda-12: "nvidia-l4t-arm64-depth-anything-cpp-development"
+    nvidia-l4t-cuda-13: "cuda13-nvidia-l4t-arm64-depth-anything-cpp-development"
+    intel: "intel-sycl-f32-depth-anything-cpp-development"
+    vulkan: "vulkan-depth-anything-cpp-development"
+- !!merge <<: *depthanything
+  name: "cpu-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-cpu-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cpu-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-cpu-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda12-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-12-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda12-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-12-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-nvidia-cuda-13-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-nvidia-cuda-13-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "nvidia-l4t-arm64-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "nvidia-l4t-arm64-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-nvidia-l4t-arm64-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "cuda13-nvidia-l4t-arm64-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-nvidia-l4t-cuda-13-arm64-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f32-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f32-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f32-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f32-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f16-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-intel-sycl-f16-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "intel-sycl-f16-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-intel-sycl-f16-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "vulkan-depth-anything-cpp"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-gpu-vulkan-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:latest-gpu-vulkan-depth-anything-cpp
+- !!merge <<: *depthanything
+  name: "vulkan-depth-anything-cpp-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-gpu-vulkan-depth-anything-cpp"
+  mirrors:
+    - localai/localai-backends:master-gpu-vulkan-depth-anything-cpp
 - &vllm
   name: "vllm"
   license: apache-2.0
@@ -1368,6 +1488,20 @@
     nvidia: "cuda12-sherpa-onnx"
     nvidia-cuda-12: "cuda12-sherpa-onnx"
     metal: "metal-sherpa-onnx"
+- &supertonic
+  name: "supertonic"
+  alias: "supertonic"
+  urls:
+    - https://github.com/supertone-inc/supertonic
+  description: |
+    Supertonic backend: lightning-fast, on-device multilingual text-to-speech via ONNX Runtime.
+    Runs Supertone's flow-matching TTS model (Supertone/supertonic-3), 44.1kHz output, 31 languages,
+    multiple preset voice styles. No espeak-ng dependency.
+  tags:
+    - text-to-speech
+    - TTS
+  capabilities:
+    default: "cpu-supertonic"
 - !!merge <<: *neutts
   name: "neutts-development"
   capabilities:
@@ -5132,3 +5266,18 @@
   uri: "quay.io/go-skynet/local-ai-backends:master-metal-darwin-arm64-sherpa-onnx"
   mirrors:
     - localai/localai-backends:master-metal-darwin-arm64-sherpa-onnx
+## supertonic
+- !!merge <<: *supertonic
+  name: "supertonic-development"
+  capabilities:
+    default: "cpu-supertonic-development"
+- !!merge <<: *supertonic
+  name: "cpu-supertonic"
+  uri: "quay.io/go-skynet/local-ai-backends:latest-cpu-supertonic"
+  mirrors:
+    - localai/localai-backends:latest-cpu-supertonic
+- !!merge <<: *supertonic
+  name: "cpu-supertonic-development"
+  uri: "quay.io/go-skynet/local-ai-backends:master-cpu-supertonic"
+  mirrors:
+    - localai/localai-backends:master-cpu-supertonic

backend/python/vllm/requirements.txt

@@ -1,4 +1,4 @@
-grpcio==1.81.0
+grpcio==1.81.1
 protobuf
 certifi
 setuptools

core/backend/depth.go

@@ -0,0 +1,66 @@
+package backend
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/trace"
+	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/LocalAI/pkg/model"
+)
+
+// Depth runs depth estimation (Depth Anything 3) on the supplied image and
+// returns the full DepthResponse: per-pixel metric depth + confidence + sky,
+// camera pose (extrinsics/intrinsics), an optional 3D point cloud and any
+// requested exports (glb/colmap). The include_* flags and exports mirror the
+// DepthRequest proto so callers can ask for less work.
+func Depth(
+	ctx context.Context,
+	in *proto.DepthRequest,
+	loader *model.ModelLoader,
+	appConfig *config.ApplicationConfig,
+	modelConfig config.ModelConfig,
+) (*proto.DepthResponse, error) {
+	opts := ModelOptions(modelConfig, appConfig)
+	depthModel, err := loader.Load(opts...)
+	if err != nil {
+		recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
+		return nil, err
+	}
+
+	if depthModel == nil {
+		return nil, fmt.Errorf("could not load depth model")
+	}
+
+	var startTime time.Time
+	if appConfig.EnableTracing {
+		trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
+		startTime = time.Now()
+	}
+
+	res, err := depthModel.Depth(ctx, in)
+
+	if appConfig.EnableTracing {
+		errStr := ""
+		if err != nil {
+			errStr = err.Error()
+		}
+
+		trace.RecordBackendTrace(trace.BackendTrace{
+			Timestamp: startTime,
+			Duration:  time.Since(startTime),
+			Type:      trace.BackendTraceDepth,
+			ModelName: modelConfig.Name,
+			Backend:   modelConfig.Backend,
+			Summary:   trace.TruncateString(in.GetSrc(), 200),
+			Error:     errStr,
+			Data: map[string]any{
+				"exports": in.GetExports(),
+			},
+		})
+	}
+
+	return res, err
+}

core/config/application_config.go

@@ -488,6 +488,16 @@ func (o *ApplicationConfig) GetEffectiveMaxActiveBackends() int {
 	return 0
 }
 
+// WatchdogShouldRun reports whether the live watchdog process should be
+// running for the current config. It mirrors the gating in
+// (*Application).startWatchdog so the /api/settings start/stop decision and
+// the startup path agree on a single source of truth: the watchdog runs when
+// idle/busy checks are enabled (WatchDog), when LRU eviction is active
+// (effective max active backends > 0), or when the memory reclaimer is on.
+func (o *ApplicationConfig) WatchdogShouldRun() bool {
+	return o.WatchDog || o.GetEffectiveMaxActiveBackends() > 0 || o.MemoryReclaimerEnabled
+}
+
 // WithForceEvictionWhenBusy sets whether to force eviction even when models have active API calls
 func WithForceEvictionWhenBusy(enabled bool) AppOption {
 	return func(o *ApplicationConfig) {
@@ -1198,18 +1208,22 @@ func (o *ApplicationConfig) ApplyRuntimeSettings(settings *RuntimeSettings) (req
 	}
 	if settings.WatchdogIdleEnabled != nil {
 		o.WatchDogIdle = *settings.WatchdogIdleEnabled
-		if o.WatchDogIdle {
-			o.WatchDog = true
-		}
 		requireRestart = true
 	}
 	if settings.WatchdogBusyEnabled != nil {
 		o.WatchDogBusy = *settings.WatchdogBusyEnabled
-		if o.WatchDogBusy {
-			o.WatchDog = true
-		}
 		requireRestart = true
 	}
+	// The React Settings "Enable Watchdog" master toggle manages only the
+	// idle/busy checks — watchdog_enabled is vestigial in that UI. Whenever
+	// either idle/busy field is present in the body, derive the run-state from
+	// idle||busy so a cold enable starts the watchdog and a full disable stops
+	// it, instead of trusting the stale watchdog_enabled the UI never updates.
+	// This mirrors the startup invariant in startup.go. An API client posting
+	// only watchdog_enabled (idle/busy absent) keeps its explicit value.
+	if settings.WatchdogIdleEnabled != nil || settings.WatchdogBusyEnabled != nil {
+		o.WatchDog = o.WatchDogIdle || o.WatchDogBusy
+	}
 	if settings.WatchdogIdleTimeout != nil {
 		if dur, err := time.ParseDuration(*settings.WatchdogIdleTimeout); err == nil {
 			o.WatchDogIdleTimeout = dur

core/config/application_config_test.go

@@ -223,6 +223,69 @@ var _ = Describe("ApplicationConfig RuntimeSettings Conversion", func() {
 			Expect(appConfig.WatchDogBusy).To(BeTrue())
 		})
 
+		// Residual #9125: the React Settings "Enable Watchdog" master toggle
+		// manages only watchdog_idle_enabled / watchdog_busy_enabled — it never
+		// touches the vestigial watchdog_enabled field. On a cold enable the
+		// body therefore carries watchdog_enabled=false alongside idle/busy=true.
+		// The derived run-state (WatchDog) must follow idle||busy so the live
+		// watchdog actually starts, not the stale watchdog_enabled=false.
+		It("should derive WatchDog from idle||busy on a cold enable even when watchdog_enabled=false", func() {
+			appConfig := &ApplicationConfig{WatchDog: false}
+
+			watchdogEnabled := false
+			watchdogIdle := true
+			watchdogBusy := true
+			rs := &RuntimeSettings{
+				WatchdogEnabled:     &watchdogEnabled,
+				WatchdogIdleEnabled: &watchdogIdle,
+				WatchdogBusyEnabled: &watchdogBusy,
+			}
+
+			appConfig.ApplyRuntimeSettings(rs)
+
+			Expect(appConfig.WatchDog).To(BeTrue())
+			Expect(appConfig.WatchdogShouldRun()).To(BeTrue())
+		})
+
+		// The disable direction: the master toggle off sends idle=false,
+		// busy=false, but watchdog_enabled may still be the stale true loaded
+		// before the change. WatchDog must follow idle||busy down to false so
+		// the live watchdog is stopped (it stays stopped unless LRU / memory
+		// reclaimer keep it alive, which is gated by WatchdogShouldRun).
+		It("should disable WatchDog when both idle and busy are turned off", func() {
+			appConfig := &ApplicationConfig{WatchDog: true, WatchDogIdle: true, WatchDogBusy: true}
+
+			watchdogEnabled := true
+			watchdogIdle := false
+			watchdogBusy := false
+			rs := &RuntimeSettings{
+				WatchdogEnabled:     &watchdogEnabled,
+				WatchdogIdleEnabled: &watchdogIdle,
+				WatchdogBusyEnabled: &watchdogBusy,
+			}
+
+			appConfig.ApplyRuntimeSettings(rs)
+
+			Expect(appConfig.WatchDog).To(BeFalse())
+			Expect(appConfig.WatchdogShouldRun()).To(BeFalse())
+		})
+
+		// Backward compatibility: an API client that posts only watchdog_enabled
+		// (idle/busy nil) keeps the explicit value — the idle/busy derivation
+		// only kicks in when those fields are actually present in the body.
+		It("should preserve explicit watchdog_enabled when idle/busy are absent", func() {
+			appConfig := &ApplicationConfig{WatchDog: false}
+
+			watchdogEnabled := true
+			rs := &RuntimeSettings{
+				WatchdogEnabled: &watchdogEnabled,
+			}
+
+			appConfig.ApplyRuntimeSettings(rs)
+
+			Expect(appConfig.WatchDog).To(BeTrue())
+		})
+
 		It("should handle MaxActiveBackends and update SingleBackend accordingly", func() {
 			appConfig := &ApplicationConfig{}
 

core/config/backend_capabilities.go

@@ -21,6 +21,7 @@ const (
 	UsecaseSoundGeneration = "sound_generation"
 	UsecaseRerank          = "rerank"
 	UsecaseDetection       = "detection"
+	UsecaseDepth           = "depth"
 	UsecaseVAD             = "vad"
 	UsecaseAudioTransform      = "audio_transform"
 	UsecaseDiarization         = "diarization"
@@ -44,6 +45,7 @@ const (
 	MethodSoundGeneration    GRPCMethod = "SoundGeneration"
 	MethodTokenizeString     GRPCMethod = "TokenizeString"
 	MethodDetect             GRPCMethod = "Detect"
+	MethodDepth              GRPCMethod = "Depth"
 	MethodRerank             GRPCMethod = "Rerank"
 	MethodVAD                GRPCMethod = "VAD"
 	MethodAudioTransform     GRPCMethod = "AudioTransform"
@@ -141,6 +143,11 @@ var UsecaseInfoMap = map[string]UsecaseInfo{
 		GRPCMethod:  MethodDetect,
 		Description: "Object detection via the Detect RPC with bounding boxes.",
 	},
+	UsecaseDepth: {
+		Flag:        FLAG_DEPTH,
+		GRPCMethod:  MethodDepth,
+		Description: "Per-pixel metric depth, camera pose and 3D point cloud via the Depth RPC (Depth Anything 3).",
+	},
 	UsecaseVAD: {
 		Flag:        FLAG_VAD,
 		GRPCMethod:  MethodVAD,
@@ -488,6 +495,13 @@ var BackendCapabilities = map[string]BackendCapability{
 		DefaultUsecases:  []string{UsecaseDetection},
 		Description:      "RF-DETR C++ object detection",
 	},
+	"depth-anything": {
+		GRPCMethods:      []GRPCMethod{MethodDepth, MethodPredict, MethodGenerateImage},
+		PossibleUsecases: []string{UsecaseDepth},
+		DefaultUsecases:  []string{UsecaseDepth},
+		AcceptsImages:    true,
+		Description:      "Depth Anything 3 C++ — per-pixel metric depth, camera pose and 3D point cloud",
+	},
 
 	// --- Face and speaker recognition backends ---
 	"insightface": {

core/config/meta/constants.go

@@ -64,6 +64,7 @@ var UsecaseOptions = []FieldOption{
 	{Value: "image", Label: "Image"},
 	{Value: "vision", Label: "Vision"},
 	{Value: "detection", Label: "Detection"},
+	{Value: "depth", Label: "Depth"},
 	{Value: "face_recognition", Label: "Face Recognition"},
 	{Value: "transcript", Label: "Transcript"},
 	{Value: "diarization", Label: "Diarization"},

core/config/meta/registry.go

@@ -434,6 +434,13 @@ func DefaultRegistry() map[string]FieldMetaOverride {
 			Component:   "json-editor",
 			Order:       78,
 		},
+		"pipeline.max_history_items": {
+			Section:     "pipeline",
+			Label:       "Max History Items",
+			Description: "Cap how many trailing conversation items are fed to the LLM each realtime turn (0 = unlimited, rely on the LLM's context window). Set it on a composed pipeline (VAD+STT+LLM+TTS) so a long-running session doesn't grow until the context fills. Unset uses the per-model-type default.",
+			Component:   "number",
+			Order:       79,
+		},
 
 		// --- Functions ---
 		"function.grammar.parallel_calls": {

core/config/model_config.go

@@ -510,6 +510,13 @@ type Pipeline struct {
 	// LLM model config. Unset leaves the LLM model config in charge.
 	DisableThinking *bool `yaml:"disable_thinking,omitempty" json:"disable_thinking,omitempty"`
 
+	// MaxHistoryItems caps how many trailing conversation items are fed to the
+	// LLM each realtime turn (0 = unlimited, rely on the LLM's context window).
+	// Unset (nil) uses the per-model-type default. Set it on a composed pipeline
+	// (VAD+STT+LLM+TTS) so a long-running session doesn't grow until the LLM's
+	// context fills.
+	MaxHistoryItems *int `yaml:"max_history_items,omitempty" json:"max_history_items,omitempty"`
+
 	// VoiceRecognition gates the pipeline behind speaker verification. Nil
 	// (block absent) means no gate, preserving existing behavior.
 	VoiceRecognition *PipelineVoiceRecognition `yaml:"voice_recognition,omitempty" json:"voice_recognition,omitempty"`
@@ -1284,6 +1291,10 @@ const (
 	// chat/completion/embeddings.
 	FLAG_SCORE ModelConfigUsecase = 0b10000000000000000000
 
+	// Marks a model as wired for the Depth gRPC primitive (per-pixel
+	// metric depth + camera pose + 3D point cloud via Depth Anything 3).
+	FLAG_DEPTH ModelConfigUsecase = 0b100000000000000000000
+
 	// Common Subsets
 	FLAG_LLM ModelConfigUsecase = FLAG_CHAT | FLAG_COMPLETION | FLAG_EDIT
 )
@@ -1341,6 +1352,7 @@ func GetAllModelConfigUsecases() map[string]ModelConfigUsecase {
 		"FLAG_DIARIZATION":         FLAG_DIARIZATION,
 		"FLAG_REALTIME_AUDIO":      FLAG_REALTIME_AUDIO,
 		"FLAG_SCORE":               FLAG_SCORE,
+		"FLAG_DEPTH":               FLAG_DEPTH,
 	}
 }
 
@@ -1484,6 +1496,13 @@ func (c *ModelConfig) GuessUsecases(u ModelConfigUsecase) bool {
 		}
 	}
 
+	if (u & FLAG_DEPTH) == FLAG_DEPTH {
+		depthBackends := []string{"depth-anything"}
+		if !slices.Contains(depthBackends, c.Backend) {
+			return false
+		}
+	}
+
 	if (u & FLAG_FACE_RECOGNITION) == FLAG_FACE_RECOGNITION {
 		faceBackends := []string{"insightface"}
 		if !slices.Contains(faceBackends, c.Backend) {

core/http/endpoints/localai/backend.go

@@ -38,6 +38,7 @@ var knownPrefOnlyBackends = []schema.KnownBackend{
 	{Name: "qwen3-tts-cpp", Modality: "tts", AutoDetect: false, Description: "Qwen3 TTS C++ (preference-only)"},
 	{Name: "omnivoice-cpp", Modality: "tts", AutoDetect: false, Description: "OmniVoice C++ TTS with voice cloning and voice design (preference-only)"},
 	{Name: "faster-qwen3-tts", Modality: "tts", AutoDetect: false, Description: "Faster Qwen3 TTS (preference-only)"},
+	{Name: "supertonic", Modality: "tts", AutoDetect: false, Description: "Supertonic multilingual ONNX TTS (preference-only)"},
 	// Detection
 	{Name: "sam3-cpp", Modality: "detection", AutoDetect: false, Description: "SAM3 C++ object detection (preference-only)"},
 	// Audio transform (audio-in / audio-out, optional reference signal)

core/http/endpoints/localai/backend_test.go

@@ -145,6 +145,7 @@ var _ = Describe("Backend Endpoints", func() {
 			expectPrefOnly("qwen-tts", "tts")
 			expectPrefOnly("qwen3-tts-cpp", "tts")
 			expectPrefOnly("faster-qwen3-tts", "tts")
+			expectPrefOnly("supertonic", "tts")
 			expectPrefOnly("sam3-cpp", "detection")
 		})
 

core/http/endpoints/localai/depth.go

@@ -0,0 +1,95 @@
+package localai
+
+import (
+	"encoding/base64"
+
+	"github.com/labstack/echo/v4"
+	"github.com/mudler/LocalAI/core/backend"
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/http/middleware"
+	"github.com/mudler/LocalAI/core/schema"
+	"github.com/mudler/LocalAI/pkg/grpc/proto"
+	"github.com/mudler/LocalAI/pkg/model"
+	"github.com/mudler/xlog"
+)
+
+// DepthEndpoint is the LocalAI Depth endpoint exposing the full Depth Anything 3
+// output (per-pixel metric depth + confidence + sky, camera pose, 3D point cloud
+// and optional glb/COLMAP exports).
+// @Summary Estimates per-pixel depth (and optionally pose/points) from an image.
+// @Tags depth
+// @Param request body schema.DepthRequest true "query params"
+// @Success 200 {object} schema.DepthResponse "Response"
+// @Router /v1/depth [post]
+func DepthEndpoint(cl *config.ModelConfigLoader, ml *model.ModelLoader, appConfig *config.ApplicationConfig) echo.HandlerFunc {
+	return func(c echo.Context) error {
+
+		input, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_LOCALAI_REQUEST).(*schema.DepthRequest)
+		if !ok || input.Model == "" {
+			return echo.ErrBadRequest
+		}
+
+		cfg, ok := c.Get(middleware.CONTEXT_LOCALS_KEY_MODEL_CONFIG).(*config.ModelConfig)
+		if !ok || cfg == nil {
+			return echo.ErrBadRequest
+		}
+
+		xlog.Debug("Depth", "image", input.Image, "backend", cfg.Backend)
+
+		image, err := decodeImageInput(input.Image)
+		if err != nil {
+			return err
+		}
+
+		// Default to returning everything the model can produce when the
+		// caller hasn't asked for any specific subset, so a bare request is
+		// still useful.
+		includeDepth := input.IncludeDepth
+		includeConfidence := input.IncludeConfidence
+		includePose := input.IncludePose
+		includeSky := input.IncludeSky
+		includePoints := input.IncludePoints
+		if !includeDepth && !includeConfidence && !includePose && !includeSky && !includePoints {
+			includeDepth = true
+			includeConfidence = true
+			includePose = true
+			includeSky = true
+		}
+
+		req := &proto.DepthRequest{
+			Src:               image,
+			Dst:               input.Dst,
+			IncludeDepth:      includeDepth,
+			IncludeConfidence: includeConfidence,
+			IncludePose:       includePose,
+			IncludeSky:        includeSky,
+			IncludePoints:     includePoints,
+			PointsConfThresh:  input.PointsConfThresh,
+			Exports:           input.Exports,
+		}
+
+		res, err := backend.Depth(c.Request().Context(), req, ml, appConfig, *cfg)
+		if err != nil {
+			return mapBackendError(err)
+		}
+
+		response := schema.DepthResponse{
+			Width:       res.GetWidth(),
+			Height:      res.GetHeight(),
+			Depth:       res.GetDepth(),
+			Confidence:  res.GetConfidence(),
+			Sky:         res.GetSky(),
+			Extrinsics:  res.GetExtrinsics(),
+			Intrinsics:  res.GetIntrinsics(),
+			NumPoints:   res.GetNumPoints(),
+			Points:      res.GetPoints(),
+			ExportPaths: res.GetExportPaths(),
+			IsMetric:    res.GetIsMetric(),
+		}
+		if len(res.GetPointColors()) > 0 {
+			response.PointColors = base64.StdEncoding.EncodeToString(res.GetPointColors())
+		}
+
+		return c.JSON(200, response)
+	}
+}

core/http/endpoints/localai/settings.go

@@ -221,9 +221,18 @@ func UpdateSettingsEndpoint(app *application.Application) echo.HandlerFunc {
 		// Check if agent job retention changed
 		agentJobChanged := settings.AgentJobRetentionDays != nil
 
-		// Restart watchdog if settings changed
+		// Restart watchdog if settings changed.
+		//
+		// The live start/stop decision derives from the post-apply config
+		// (WatchdogShouldRun) rather than the raw watchdog_enabled request
+		// field: the React master toggle only ever writes the idle/busy flags,
+		// so keying off watchdog_enabled left the live watchdog stopped on a
+		// cold enable until the next restart (#9125). WatchdogShouldRun mirrors
+		// the gating in startWatchdog, so a cold enable starts it immediately
+		// and a full disable (both checks off, no LRU / memory reclaimer) stops
+		// it.
 		if watchdogChanged {
-			if settings.WatchdogEnabled != nil && !*settings.WatchdogEnabled {
+			if !appConfig.WatchdogShouldRun() {
 				if err := app.StopWatchdog(); err != nil {
 					xlog.Error("Failed to stop watchdog", "error", err)
 					return c.JSON(http.StatusInternalServerError, schema.SettingsResponse{

core/http/endpoints/localai/settings_test.go

@@ -108,4 +108,20 @@ var _ = Describe("Settings endpoints", func() {
 		_, err := os.Stat(filepath.Join(tmp, "runtime_settings.json"))
 		Expect(err).ToNot(HaveOccurred())
 	})
+
+	// 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
+	// the vestigial watchdog_enabled stays false (it was loaded false). The
+	// old handler keyed its stop decision off that raw watchdog_enabled=false
+	// and called StopWatchdog(), so the watchdog never started until restart.
+	It("starts the live watchdog on a cold enable even when watchdog_enabled=false", func() {
+		Expect(app.ModelLoader().GetWatchDog()).To(BeNil(), "precondition: watchdog should be off")
+
+		rec := post(`{"watchdog_enabled":false,"watchdog_idle_enabled":true,"watchdog_busy_enabled":true,"watchdog_idle_timeout":"15m","watchdog_busy_timeout":"5m","watchdog_interval":"1s"}`)
+		Expect(rec.Code).To(Equal(http.StatusOK))
+
+		Expect(app.ModelLoader().GetWatchDog()).ToNot(BeNil(),
+			"watchdog should be running after a cold enable, without waiting for a restart")
+	})
 })

core/http/endpoints/openai/realtime.go

@@ -340,6 +340,17 @@ func defaultMaxHistoryItems(cfg *config.ModelConfig) int {
 	return 0
 }
 
+// resolveMaxHistoryItems honors an explicit pipeline.max_history_items when set,
+// otherwise falls back to the per-model-type default. This lets a composed
+// pipeline (VAD+STT+LLM+TTS) cap its history so a long-running session doesn't
+// grow until the LLM's context window fills.
+func resolveMaxHistoryItems(cfg *config.ModelConfig) int {
+	if cfg != nil && cfg.Pipeline.MaxHistoryItems != nil {
+		return *cfg.Pipeline.MaxHistoryItems
+	}
+	return defaultMaxHistoryItems(cfg)
+}
+
 // trimRealtimeItems returns the tail of items capped at maxItems (0 = no cap).
 // Walks backwards keeping function_call + function_call_output pairs together
 // so we never feed the LLM an orphaned tool result that references a call it
@@ -492,7 +503,7 @@ func runRealtimeSession(application *application.Application, t Transport, model
 		Conversations:    make(map[string]*Conversation),
 		InputSampleRate:  defaultRemoteSampleRate,
 		OutputSampleRate: defaultRemoteSampleRate,
-		MaxHistoryItems:  defaultMaxHistoryItems(cfg),
+		MaxHistoryItems:  resolveMaxHistoryItems(cfg),
 	}
 
 	// Create a default conversation

core/http/endpoints/openai/realtime_gate_test.go

@@ -107,6 +107,29 @@ var _ = Describe("defaultMaxHistoryItems", func() {
 	})
 })
 
+var _ = Describe("resolveMaxHistoryItems", func() {
+	ptr := func(i int) *int { return &i }
+
+	It("uses an explicit pipeline.max_history_items", func() {
+		cfg := &config.ModelConfig{Pipeline: config.Pipeline{LLM: "llama", MaxHistoryItems: ptr(10)}}
+		Expect(resolveMaxHistoryItems(cfg)).To(Equal(10))
+	})
+	It("honors an explicit 0 (unlimited) over the type default", func() {
+		cfg := &config.ModelConfig{
+			KnownUsecases: withUsecases(config.FLAG_REALTIME_AUDIO),
+			Pipeline:      config.Pipeline{MaxHistoryItems: ptr(0)},
+		}
+		Expect(resolveMaxHistoryItems(cfg)).To(Equal(0))
+	})
+	It("falls back to the type default when unset", func() {
+		cfg := &config.ModelConfig{KnownUsecases: withUsecases(config.FLAG_REALTIME_AUDIO)}
+		Expect(resolveMaxHistoryItems(cfg)).To(Equal(6))
+	})
+	It("tolerates nil", func() {
+		Expect(resolveMaxHistoryItems(nil)).To(Equal(0))
+	})
+})
+
 var _ = Describe("trimRealtimeItems", func() {
 	user := func(id string) *types.MessageItemUnion {
 		return &types.MessageItemUnion{User: &types.MessageItemUser{ID: id}}

core/http/react-ui/e2e/model-editor-back-nav.spec.js

@@ -44,7 +44,7 @@ test.describe('Model Editor — Back navigation', () => {
     await mockEditorEndpoints(page)
   })
 
-  test('Back returns to Manage with a "Back to Manage" caption', async ({ page }) => {
+  test('Back returns to Manage with a "Back to System" caption', async ({ page }) => {
     await page.goto('/app/manage')
     await expect(page.locator('.table')).toBeVisible({ timeout: 10_000 })
 
@@ -55,7 +55,7 @@ test.describe('Model Editor — Back navigation', () => {
     await page.getByRole('menuitem', { name: 'Edit configuration' }).click()
 
     await expect(page).toHaveURL(/\/app\/model-editor\//)
-    const back = page.getByRole('button', { name: /Back to Manage/ })
+    const back = page.getByRole('button', { name: /Back to System/ })
     await expect(back).toBeVisible({ timeout: 10_000 })
 
     await back.click()
@@ -89,6 +89,6 @@ test.describe('Model Editor — Back navigation', () => {
 
   test('falls back to "Back to Manage" on a direct visit with no origin state', async ({ page }) => {
     await page.goto('/app/model-editor/mock-model')
-    await expect(page.getByRole('button', { name: /Back to Manage/ })).toBeVisible({ timeout: 10_000 })
+    await expect(page.getByRole('button', { name: /Back to System/ })).toBeVisible({ timeout: 10_000 })
   })
 })

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

@@ -86,7 +86,8 @@
     "type": "Type",
     "value": "Value",
     "search": "Search...",
-    "selectPlaceholder": "Select an option..."
+    "selectPlaceholder": "Select an option...",
+    "noMatch": "No matches"
   },
   "time": {
     "now": "now",

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

@@ -0,0 +1,38 @@
+{
+    "title": {
+        "add": "Add Model",
+        "edit": "Model Editor"
+    },
+    "subtitle": {
+        "chooseModelType": "Choose a model type to get started",
+        "newModel": "New model"
+    },
+    "actions": {
+        "backTo": "Back to {{page}}",
+        "system": "System",
+        "templates": "Templates",
+        "createModel": "Create Model",
+        "saveChanges": "Save Changes",
+        "saving": "Saving...",
+        "saved": "Saved",
+        "switchWarning": "Save or discard changes before switching tabs.",
+        "discardAndSwitch": "Discard & Switch"
+    },
+    "tabs": {
+        "interactive": "Interactive",
+        "yaml": "YAML",
+        "yamlDescription": "Edit the YAML directly. The model name must be set in the YAML for create to work."
+    },
+    "forms": {
+        "modelName": {
+            "label": "Model Name",
+            "placeholder": "my-model-name",
+            "hint": "Use letters, numbers, hyphens, underscores, and dots only."
+        },
+        "empty": {
+            "nav": "Use the search bar above to add fields",
+            "title": "No fields configured",
+            "text": "Use the search bar above to find and add configuration fields."
+        }
+    }
+}

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

@@ -1,6 +1,7 @@
 {
   "title": "Install Models",
   "subtitle": "Browse and install AI models from the gallery",
+  "models": "Models",
   "stats": {
     "available": "Available",
     "installed": "Installed"
@@ -89,5 +90,11 @@
     "loadFailed": "Failed to load models: {{message}}",
     "installFailed": "Failed to install: {{message}}",
     "deleteFailed": "Failed to delete: {{message}}"
+  },
+  "selector": {
+    "loading": "Loading models...",
+    "selectModel": "Select model...",
+    "searchPlaceholder": "Search models...",
+    "noModels": "No models available"
   }
 }

core/http/react-ui/public/locales/id/common.json

@@ -86,7 +86,8 @@
     "type": "Tipe",
     "value": "Nilai",
     "search": "Cari...",
-    "selectPlaceholder": "Pilih opsi..."
+    "selectPlaceholder": "Pilih opsi...",
+    "noMatch": "Tidak ada yang cocok"
   },
   "time": {
     "now": "baru saja",
@@ -106,4 +107,4 @@
     "gigabytes": "GB",
     "terabytes": "TB"
   }
-}
+}

core/http/react-ui/public/locales/id/importModel.json

@@ -1,7 +1,7 @@
 {
   "title": "Impor Model Baru",
   "subtitle": {
-    "simple": "Import model dari URI — deteksi otomatis memilih backend.",
+    "simple": "Impor model dari URI — deteksi otomatis memilih backend.",
     "powerYaml": "Tulis konfigurasi YAML lengkap untuk model.",
     "powerPrefs": "Preferensi impor tingkat lanjut."
   },
@@ -139,4 +139,4 @@
       "local": "File konfigurasi YAML lokal"
     }
   }
-}
+}

core/http/react-ui/public/locales/id/modelEditor.json

@@ -0,0 +1,38 @@
+{
+    "title": {
+        "add": "Tambah Model",
+        "edit": "Editor Model"
+    },
+    "subtitle": {
+        "chooseModelType": "Pilih tipe model untuk memulai",
+        "newModel": "Model baru"
+    },
+    "actions": {
+        "backTo": "Kembali ke {{page}}",
+        "system": "Sistem",
+        "templates": "Templat",
+        "createModel": "Buat Model",
+        "saveChanges": "Simpan Perubahan",
+        "saving": "Menyimpan...",
+        "saved": "Tersimpan",
+        "switchWarning": "Simpan atau buang perubahan sebelum beralih tab.",
+        "discardAndSwitch": "Buang & Beralih"
+    },
+    "tabs": {
+        "interactive": "Interaktif",
+        "yaml": "YAML",
+        "yamlDescription": "Edit YAML secara langsung. Nama model harus diatur di YAML agar pembuatan berhasil."
+    },
+    "forms": {
+        "modelName": {
+            "label": "Nama Model",
+            "placeholder": "nama-model-saya",
+            "hint": "Gunakan huruf, angka, tanda hubung, garis bawah, dan titik saja."
+        },
+        "empty": {
+            "nav": "Gunakan kolom pencarian di atas untuk menambahkan field",
+            "title": "Tidak ada field yang dikonfigurasi",
+            "text": "Gunakan kolom pencarian di atas untuk menemukan dan menambahkan field konfigurasi."
+        }
+    }
+}

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

@@ -1,6 +1,7 @@
 {
   "title": "Instal Model",
   "subtitle": "Telusuri dan instal model AI dari galeri",
+  "models": "Model",
   "stats": {
     "available": "Tersedia",
     "installed": "Terinstal"
@@ -89,5 +90,11 @@
     "loadFailed": "Gagal memuat model: {{message}}",
     "installFailed": "Gagal menginstal: {{message}}",
     "deleteFailed": "Gagal menghapus: {{message}}"
+  },
+  "selector": {
+    "loading": "Memuat model...",
+    "selectModel": "Pilih model...",
+    "searchPlaceholder": "Cari model...",
+    "noModels": "Model tidak tersedia"
   }
-}
+}

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

@@ -1,12 +1,14 @@
 import { useEffect, useMemo } from 'react'
 import { useModels } from '../hooks/useModels'
 import SearchableSelect from './SearchableSelect'
+import { useTranslation } from 'react-i18next'
 
 export default function ModelSelector({
   value, onChange, capability, className = '',
   options: externalOptions, loading: externalLoading,
   disabled: externalDisabled, searchPlaceholder, style,
 }) {
+  const { t } = useTranslation('models')
   // Skip capability fetch when external options are provided (capability will be undefined)
   const { models: hookModels, loading: hookLoading } = useModels(externalOptions ? undefined : capability)
 
@@ -28,8 +30,8 @@ export default function ModelSelector({
       value={value || ''}
       onChange={onChange}
       options={modelNames}
-      placeholder={isLoading ? 'Loading models...' : (modelNames.length === 0 ? 'No models available' : 'Select model...')}
-      searchPlaceholder={searchPlaceholder || 'Search models...'}
+      placeholder={isLoading ? t('selector.loading') : (modelNames.length === 0 ? t('selector.noModels') : t('selector.selectModel'))}
+      searchPlaceholder={searchPlaceholder || t('selector.searchPlaceholder')}
       disabled={isDisabled}
       className={className}
       style={style}

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

@@ -1,10 +1,12 @@
 import { useState, useEffect, useRef, useMemo } from 'react'
+import { useTranslation } from 'react-i18next'
 
 export default function SearchableSelect({
   value, onChange, options, placeholder = 'Select...',
   allOption, searchPlaceholder = 'Search...',
   disabled = false, style, className = '',
 }) {
+  const { t } = useTranslation('common')
   const [open, setOpen] = useState(false)
   const [query, setQuery] = useState('')
   const [focusIndex, setFocusIndex] = useState(-1)
@@ -226,7 +228,7 @@ export default function SearchableSelect({
             })}
             {filtered.length === 0 && !allOption && (
               <div style={{ padding: '6px 10px', fontSize: '0.8125rem', color: 'var(--color-text-muted)', fontStyle: 'italic' }}>
-                No matches
+                {t('forms.noMatch')}
               </div>
             )}
           </div>

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

@@ -675,7 +675,7 @@ export default function Manage() {
                               onClick: () => handleTogglePinned(model.id, model.pinned),
                               disabled: pinningModels.has(model.id) || !!model.disabled },
                             { key: 'edit', icon: 'fa-pen-to-square', label: 'Edit configuration',
-                              onClick: () => navigate(`/app/model-editor/${encodeURIComponent(model.id)}`, { state: fromState(location, 'Manage') }) },
+                              onClick: () => navigate(`/app/model-editor/${encodeURIComponent(model.id)}`, { state: fromState(location, t('manage.title')) }) },
                             { key: 'logs', icon: 'fa-terminal', label: 'Backend logs',
                               onClick: () => navigate(`/app/backend-logs/${encodeURIComponent(model.id)}`) },
                             { divider: true },

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

@@ -12,6 +12,7 @@ import ConfigFieldRenderer from '../components/ConfigFieldRenderer'
 import { FormContextProvider } from '../contexts/FormContext'
 import TemplateSelector from '../components/TemplateSelector'
 import MODEL_TEMPLATES from '../utils/modelTemplates'
+import { useTranslation } from 'react-i18next'
 
 const SECTION_ICONS = {
   general: 'fa-cog', llm: 'fa-microchip', parameters: 'fa-sliders',
@@ -70,6 +71,7 @@ function defaultForType(uiType) {
 }
 
 export default function ModelEditor() {
+  const { t } = useTranslation('modelEditor')
   const { name } = useParams()
   const [searchParams] = useSearchParams()
   const navigate = useNavigate()
@@ -397,6 +399,10 @@ export default function ModelEditor() {
   if (loading) return <div className="page page--medium" style={{ display: 'flex', justifyContent: 'center', padding: 'var(--spacing-xl)' }}><LoadingSpinner size="lg" /></div>
   if (metaError) return <div className="page page--medium"><div className="empty-state"><p className="empty-state-text">Failed to load config metadata: {metaError}</p></div></div>
 
+  const backPage = isCreateMode && selectedTemplate ? t('actions.templates')
+    : backState ? backState.fromLabel
+    : isCreateMode ? t('actions.models') : t('actions.system')
+
   return (
     <FormContextProvider formData={values}>
     <div className="page page--medium" style={{ padding: 0 }}>
@@ -406,10 +412,10 @@ export default function ModelEditor() {
         padding: 'var(--spacing-lg) var(--spacing-lg) var(--spacing-md)',
       }}>
         <div>
-          <h1 className="page-title">{isCreateMode ? 'Add Model' : 'Model Editor'}</h1>
+          <h1 className="page-title">{isCreateMode ? t('title.add') : t('title.edit')}</h1>
           <p className="page-subtitle">
             {isCreateMode
-              ? (showTemplateSelector ? 'Choose a model type to get started' : `New model${selectedTemplate ? ` — ${selectedTemplate.label}` : ''}`)
+              ? (showTemplateSelector ? t('subtitle.chooseModelType') : `${t('subtitle.newModel')}${selectedTemplate ? ` — ${selectedTemplate.label}` : ''}`)
               : decodeURIComponent(name)}
           </p>
         </div>
@@ -419,20 +425,16 @@ export default function ModelEditor() {
             else if (backState) navigate(backState.from)
             else navigate(isCreateMode ? '/app/models' : '/app/manage')
           }}>
-            <i className="fas fa-arrow-left" /> Back to {
-              isCreateMode && selectedTemplate ? 'Templates'
-                : backState ? backState.fromLabel
-                  : isCreateMode ? 'Models' : 'Manage'
-            }
+            <i className="fas fa-arrow-left" /> {t('actions.backTo', {page: backPage})}
           </button>
           {!showTemplateSelector && tab === 'interactive' && (
             <button className={`btn ${isDirty ? 'btn-primary' : 'btn-secondary'}`} onClick={handleInteractiveSave} disabled={saving || !isDirty}>
-              {saving ? <><LoadingSpinner size="sm" /> Saving...</> : <><i className="fas fa-save" /> {isCreateMode ? 'Create Model' : (isDirty ? 'Save Changes' : 'Saved')}</>}
+              {saving ? <><LoadingSpinner size="sm" /> {t('actions.saving')}</> : <><i className="fas fa-save" /> {isCreateMode ? t('actions.createModel') : (isDirty ? t('actions.saveChanges') : t('actions.saved'))}</>}
             </button>
           )}
           {!showTemplateSelector && tab === 'yaml' && (
             <button className={`btn ${isDirty ? 'btn-primary' : 'btn-secondary'}`} onClick={handleYamlSave} disabled={saving || !isDirty}>
-              {saving ? <><LoadingSpinner size="sm" /> Saving...</> : <><i className="fas fa-save" /> {isCreateMode ? 'Create Model' : (isDirty ? 'Save Changes' : 'Saved')}</>}
+              {saving ? <><LoadingSpinner size="sm" /> {t('actions.saving')}</> : <><i className="fas fa-save" /> {isCreateMode ? t('actions.createModel') : (isDirty ? t('actions.saveChanges') : t('actions.saved'))}</>}
             </button>
           )}
         </div>
@@ -448,17 +450,17 @@ export default function ModelEditor() {
             display: 'flex', gap: 0, padding: '0 var(--spacing-lg)',
             borderBottom: '1px solid var(--color-border)',
           }}>
-            {['interactive', 'yaml'].map(t => {
-              const active = tab === t
+            {['interactive', 'yaml'].map(tb => {
+              const active = tab === tb
               const blocked = !active && isDirty
               return (
                 <button
-                  key={t}
+                  key={tb}
                   onClick={() => {
                     if (active) return
                     if (blocked) { setTabSwitchWarning(true); return }
                     setTabSwitchWarning(false)
-                    setTab(t)
+                    setTab(tb)
                   }}
                   style={{
                     padding: 'var(--spacing-sm) var(--spacing-md)', border: 'none',
@@ -471,8 +473,8 @@ export default function ModelEditor() {
                     transition: 'all 150ms',
                   }}
                 >
-                  <i className={`fas ${t === 'interactive' ? 'fa-sliders' : 'fa-code'}`} style={{ marginRight: 6 }} />
-                  {t === 'interactive' ? 'Interactive' : 'YAML'}
+                  <i className={`fas ${tb === 'interactive' ? 'fa-sliders' : 'fa-code'}`} style={{ marginRight: 6 }} />
+                  {tb === 'interactive' ? t('tabs.interactive') : t('tabs.yaml')}
                 </button>
               )
             })}
@@ -485,7 +487,7 @@ export default function ModelEditor() {
               background: 'var(--color-warning-light, rgba(245, 158, 11, 0.08))',
             }}>
               <i className="fas fa-exclamation-triangle" />
-              <span>Save or discard changes before switching tabs.</span>
+              <span>{t('actions.switchWarning')}</span>
               <button
                 className="btn btn-secondary"
                 style={{ marginLeft: 'auto', padding: '2px 10px', fontSize: '0.75rem' }}
@@ -500,7 +502,7 @@ export default function ModelEditor() {
                   setTab(tab === 'yaml' ? 'interactive' : 'yaml')
                 }}
               >
-                Discard &amp; Switch
+                {t('actions.discardAndSwitch')}
               </button>
             </div>
           )}
@@ -512,7 +514,7 @@ export default function ModelEditor() {
         <div style={{ padding: '0 var(--spacing-lg) var(--spacing-lg)' }}>
           {isCreateMode && (
             <p style={{ fontSize: '0.8125rem', color: 'var(--color-text-secondary)', marginBottom: 'var(--spacing-sm)' }}>
-              Edit the YAML directly. The model name must be set in the YAML for create to work.
+              {t('tabs.yamlDescription')}
             </p>
           )}
           <CodeEditor
@@ -533,18 +535,18 @@ export default function ModelEditor() {
               <div className="card" style={{ padding: 'var(--spacing-md)' }}>
                 <label className="form-label" style={{ fontWeight: 600 }}>
                   <i className="fas fa-tag" style={{ marginRight: '6px', color: 'var(--color-primary)' }} />
-                  Model Name
+                  {t('forms.modelName.label')}
                 </label>
                 <input
                   className="input"
                   type="text"
                   value={values['name'] || ''}
                   onChange={e => handleFieldChange('name', e.target.value)}
-                  placeholder="my-model-name"
+                  placeholder={t('forms.modelName.placeholder')}
                   style={{ maxWidth: 400 }}
                 />
                 <p style={{ marginTop: 'var(--spacing-xs)', fontSize: '0.75rem', color: 'var(--color-text-muted)' }}>
-                  Use letters, numbers, hyphens, underscores, and dots only.
+                  {t('forms.modelName.hint')}
                 </p>
               </div>
             </div>
@@ -596,7 +598,7 @@ export default function ModelEditor() {
               ))}
               {activeSections.length === 0 && (
                 <div style={{ padding: '12px', fontSize: '0.8125rem', color: 'var(--color-text-muted)' }}>
-                  Use the search bar above to add fields
+                  {t('forms.empty.nav')}
                 </div>
               )}
             </nav>
@@ -610,9 +612,9 @@ export default function ModelEditor() {
               {activeSections.length === 0 && (
                 <div className="card" style={{ padding: 'var(--spacing-xl)', textAlign: 'center' }}>
                   <i className="fas fa-sliders" style={{ fontSize: '2rem', color: 'var(--color-text-muted)', marginBottom: 'var(--spacing-md)' }} />
-                  <h3 style={{ marginBottom: 'var(--spacing-sm)' }}>No fields configured</h3>
+                  <h3 style={{ marginBottom: 'var(--spacing-sm)' }}>{t('forms.empty.title')}</h3>
                   <p style={{ color: 'var(--color-text-secondary)', fontSize: '0.875rem' }}>
-                    Use the search bar above to find and add configuration fields.
+                    {t('forms.empty.text')}
                   </p>
                 </div>
               )}

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

@@ -288,7 +288,7 @@ export default function Models() {
               </a>
             </div>
           </div>
-          <button className="btn btn-primary btn-sm" onClick={() => navigate('/app/model-editor', { state: fromState(location, 'Models') })}>
+          <button className="btn btn-primary btn-sm" onClick={() => navigate('/app/model-editor', { state: fromState(location, t('models')) })}>
             <i className="fas fa-plus" /> {t('actions.addModel')}
           </button>
           <button className="btn btn-secondary btn-sm" onClick={() => navigate('/app/import-model')}>

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

@@ -294,7 +294,7 @@ export default function Settings() {
             </h3>
             <div className="card">
               <SettingRow label="Enable Watchdog" description="Automatically monitor and manage backend processes">
-                <Toggle checked={settings.watchdog_idle_enabled || settings.watchdog_busy_enabled} onChange={(v) => { update('watchdog_idle_enabled', v); update('watchdog_busy_enabled', v) }} />
+                <Toggle checked={settings.watchdog_idle_enabled || settings.watchdog_busy_enabled} onChange={(v) => { update('watchdog_idle_enabled', v); update('watchdog_busy_enabled', v); update('watchdog_enabled', v) }} />
               </SettingRow>
               <SettingRow label="Enable Idle Check" description="Automatically stop backends that have been idle too long">
                 <Toggle checked={settings.watchdog_idle_enabled} onChange={(v) => update('watchdog_idle_enabled', v)} disabled={!watchdogEnabled} />

core/http/routes/localai.go

@@ -98,6 +98,12 @@ func RegisterLocalAIRoutes(router *echo.Echo,
 		requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_DETECTION)),
 		requestExtractor.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.DetectionRequest) }))
 
+	depthHandler := localai.DepthEndpoint(cl, ml, appConfig)
+	router.POST("/v1/depth",
+		depthHandler,
+		requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_DEPTH)),
+		requestExtractor.SetModelAndConfig(func() schema.LocalAIRequest { return new(schema.DepthRequest) }))
+
 	// Face recognition endpoints
 	faceMw := []echo.MiddlewareFunc{
 		requestExtractor.BuildFilteredFirstAvailableDefaultModel(config.BuildUsecaseFilterFn(config.FLAG_FACE_RECOGNITION)),

core/schema/localai.go

@@ -181,6 +181,40 @@ type Detection struct {
 	Mask       string  `json:"mask,omitempty"` // base64-encoded PNG segmentation mask
 }
 
+// DepthRequest is the request body for the /v1/depth endpoint. It exposes the
+// full Depth Anything 3 output surface; the include_* flags and exports let a
+// caller ask for less work (e.g. depth only, or depth+pose without the point
+// cloud).
+type DepthRequest struct {
+	BasicModelRequest
+	Image             string   `json:"image"`                        // URL or base64-encoded image to analyze
+	Dst               string   `json:"dst,omitempty"`                // optional output directory for exports (glb/colmap)
+	IncludeDepth      bool     `json:"include_depth,omitempty"`      // return the per-pixel depth map
+	IncludeConfidence bool     `json:"include_confidence,omitempty"` // return the per-pixel confidence map (DualDPT)
+	IncludePose       bool     `json:"include_pose,omitempty"`       // return camera extrinsics/intrinsics (DualDPT)
+	IncludeSky        bool     `json:"include_sky,omitempty"`        // return the per-pixel sky map (mono models)
+	IncludePoints     bool     `json:"include_points,omitempty"`     // back-project to a 3D point cloud (DualDPT)
+	PointsConfThresh  float32  `json:"points_conf_thresh,omitempty"` // keep points with confidence >= this threshold
+	Exports           []string `json:"exports,omitempty"`            // requested exports: "glb", "colmap"
+}
+
+// DepthResponse is the JSON response for the /v1/depth endpoint, mirroring the
+// DepthResponse proto.
+type DepthResponse struct {
+	Width       int32     `json:"width"`
+	Height      int32     `json:"height"`
+	Depth       []float32 `json:"depth,omitempty"`        // width*height row-major metric depth
+	Confidence  []float32 `json:"confidence,omitempty"`   // width*height row-major confidence (DualDPT)
+	Sky         []float32 `json:"sky,omitempty"`          // width*height row-major sky map (mono)
+	Extrinsics  []float32 `json:"extrinsics,omitempty"`   // 12 floats, 3x4 row-major (world-to-camera)
+	Intrinsics  []float32 `json:"intrinsics,omitempty"`   // 9 floats, 3x3 row-major
+	NumPoints   int32     `json:"num_points,omitempty"`   // number of 3D points
+	Points      []float32 `json:"points,omitempty"`       // num_points*3 xyz, world space
+	PointColors string    `json:"point_colors,omitempty"` // base64-encoded num_points*3 uint8 rgb
+	ExportPaths []string  `json:"export_paths,omitempty"` // paths written for the requested exports
+	IsMetric    bool      `json:"is_metric"`              // depth is in metric units
+}
+
 // ─── Face recognition ──────────────────────────────────────────────
 //
 // FacialArea describes a bounding box for a detected face.

core/services/nodes/health_mock_test.go

@@ -169,6 +169,9 @@ func (c *fakeBackendClient) SoundGeneration(_ context.Context, _ *pb.SoundGenera
 func (c *fakeBackendClient) Detect(_ context.Context, _ *pb.DetectOptions, _ ...ggrpc.CallOption) (*pb.DetectResponse, error) {
 	return nil, nil
 }
+func (c *fakeBackendClient) Depth(_ context.Context, _ *pb.DepthRequest, _ ...ggrpc.CallOption) (*pb.DepthResponse, error) {
+	return nil, nil
+}
 func (c *fakeBackendClient) FaceVerify(_ context.Context, _ *pb.FaceVerifyRequest, _ ...ggrpc.CallOption) (*pb.FaceVerifyResponse, error) {
 	return nil, nil
 }

core/services/nodes/inflight.go

@@ -152,6 +152,12 @@ func (c *InFlightTrackingClient) Detect(ctx context.Context, in *pb.DetectOption
 	return res, c.reconcile(err)
 }
 
+func (c *InFlightTrackingClient) Depth(ctx context.Context, in *pb.DepthRequest, opts ...ggrpc.CallOption) (*pb.DepthResponse, error) {
+	defer c.track(ctx)()
+	res, err := c.Backend.Depth(ctx, in, opts...)
+	return res, c.reconcile(err)
+}
+
 func (c *InFlightTrackingClient) Rerank(ctx context.Context, in *pb.RerankRequest, opts ...ggrpc.CallOption) (*pb.RerankResult, error) {
 	defer c.track(ctx)()
 	res, err := c.Backend.Rerank(ctx, in, opts...)

core/services/nodes/inflight_test.go

@@ -100,6 +100,10 @@ func (f *fakeGRPCBackend) Detect(_ context.Context, _ *pb.DetectOptions, _ ...gg
 	return &pb.DetectResponse{}, nil
 }
 
+func (f *fakeGRPCBackend) Depth(_ context.Context, _ *pb.DepthRequest, _ ...ggrpc.CallOption) (*pb.DepthResponse, error) {
+	return &pb.DepthResponse{}, nil
+}
+
 func (f *fakeGRPCBackend) FaceVerify(_ context.Context, _ *pb.FaceVerifyRequest, _ ...ggrpc.CallOption) (*pb.FaceVerifyResponse, error) {
 	return &pb.FaceVerifyResponse{}, nil
 }

core/services/nodes/router.go

@@ -908,6 +908,17 @@ func (r *SmartRouter) stageModelFiles(ctx context.Context, node *BackendNode, op
 		frontendModelsDir = filepath.Clean(strings.TrimSuffix(opts.ModelFile, opts.Model))
 	}
 
+	// Local model directory, captured before the ModelFile field is rewritten to
+	// its remote path below. Companion assets declared as option paths (e.g.
+	// sherpa-onnx's tokens.txt / espeak-ng-data) live beside the model, so option
+	// values are resolved relative to this dir as well as frontendModelsDir —
+	// letting a shared config declare them with bare names regardless of whether
+	// Model includes a subdirectory.
+	localModelDir := ""
+	if opts.ModelFile != "" {
+		localModelDir = filepath.Dir(opts.ModelFile)
+	}
+
 	// keyMapper generates storage keys namespaced under trackingKey, preserving
 	// subdirectory structure relative to frontendModelsDir. This ensures:
 	// 1. All files for a model land in one directory on the worker for clean deletion
@@ -1079,8 +1090,8 @@ func (r *SmartRouter) stageModelFiles(ctx context.Context, node *BackendNode, op
 
 	// Stage file paths referenced in generic Options (key:value pairs where values
 	// are file paths). Options stay as relative paths — backends resolve them via ModelPath.
-	r.stageGenericOptions(ctx, node, opts.Options, frontendModelsDir, keyMapper.Key)
-	r.stageGenericOptions(ctx, node, opts.Overrides, frontendModelsDir, keyMapper.Key)
+	r.stageGenericOptions(ctx, node, opts.Options, frontendModelsDir, localModelDir, keyMapper.Key)
+	r.stageGenericOptions(ctx, node, opts.Overrides, frontendModelsDir, localModelDir, keyMapper.Key)
 
 	return opts, nil
 }
@@ -1196,36 +1207,86 @@ func (r *SmartRouter) stageCompanionFiles(ctx context.Context, node *BackendNode
 }
 
 // stageGenericOptions iterates key:value option strings and stages any values
-// that resolve to existing files relative to the frontend models directory.
-// Option values are NOT rewritten — backends resolve them via ModelPath.
-// keyFn generates the namespaced storage key for each file path.
-func (r *SmartRouter) stageGenericOptions(ctx context.Context, node *BackendNode, options []string, frontendModelsDir string, keyFn func(string) string) {
+// that resolve to existing files relative to the frontend models directory or
+// the model's own directory. Option values are NOT rewritten — backends resolve
+// them via ModelPath. keyFn generates the namespaced storage key for each file.
+func (r *SmartRouter) stageGenericOptions(ctx context.Context, node *BackendNode, options []string, frontendModelsDir, modelDir string, keyFn func(string) string) {
 	for _, opt := range options {
 		optKey, val, ok := strings.Cut(opt, ":")
 		if !ok || val == "" {
 			continue
 		}
 
-		// Check if value is an existing file path (absolute or relative to frontend models dir)
-		absPath := val
-		if !filepath.IsAbs(val) && frontendModelsDir != "" {
-			absPath = filepath.Join(frontendModelsDir, val)
+		// Resolve the value to an existing path: absolute as-is, otherwise
+		// relative to frontendModelsDir first, then the model's own directory
+		// (where backends like sherpa-onnx keep companion assets such as
+		// tokens.txt and espeak-ng-data).
+		absPath, ok := resolveOptionPath(val, frontendModelsDir, modelDir)
+		if !ok {
+			continue
 		}
-		if _, err := os.Stat(absPath); os.IsNotExist(err) {
+		info, err := os.Stat(absPath)
+		if err != nil {
+			continue
+		}
+
+		// A directory option value (e.g. sherpa-onnx's espeak-ng-data) is staged
+		// file-by-file so the whole tree is recreated beside the model on the
+		// worker; a single file is staged directly. Values are never rewritten —
+		// backends resolve relative paths via ModelPath.
+		if err == nil && info.IsDir() {
+			r.stageOptionDir(ctx, node, absPath, keyFn)
+			xlog.Debug("Staged option directory", "option", optKey, "localPath", absPath)
 			continue
 		}
 
-		// Stage the file to the worker using the namespaced key
 		key := keyFn(absPath)
 		if _, err := r.fileStager.EnsureRemote(ctx, node.ID, absPath, key); err != nil {
 			xlog.Warn("Failed to stage option file, skipping", "option", opt, "path", absPath, "error", err)
 			continue
 		}
-		// Leave option value unchanged — backend resolves relative paths via ModelPath
 		xlog.Debug("Staged option file", "option", optKey, "localPath", absPath)
 	}
 }
 
+// resolveOptionPath finds an existing local path for an option value: an
+// absolute path as-is, otherwise relative to frontendModelsDir, then to the
+// model's own directory. Returns false when none exists.
+func resolveOptionPath(val, frontendModelsDir, modelDir string) (string, bool) {
+	if filepath.IsAbs(val) {
+		if _, err := os.Stat(val); err == nil {
+			return val, true
+		}
+		return "", false
+	}
+	for _, base := range []string{frontendModelsDir, modelDir} {
+		if base == "" {
+			continue
+		}
+		p := filepath.Join(base, val)
+		if _, err := os.Stat(p); err == nil {
+			return p, true
+		}
+	}
+	return "", false
+}
+
+// stageOptionDir stages every regular file under an option-declared directory
+// (e.g. sherpa-onnx's espeak-ng-data) using the structure-preserving key, so the
+// tree is recreated beside the model on the worker. Per-file errors are logged
+// and skipped; the option value itself is not rewritten.
+func (r *SmartRouter) stageOptionDir(ctx context.Context, node *BackendNode, dir string, keyFn func(string) string) {
+	_ = filepath.WalkDir(dir, func(path string, d fs.DirEntry, walkErr error) error {
+		if walkErr != nil || d.IsDir() {
+			return nil
+		}
+		if _, err := r.fileStager.EnsureRemote(ctx, node.ID, path, keyFn(path)); err != nil {
+			xlog.Warn("Failed to stage option directory file, skipping", "path", path, "error", err)
+		}
+		return nil
+	})
+}
+
 // probeHealth checks whether a backend process on the given node/addr is alive
 // via a gRPC health check with a 2-second timeout. The client is closed after
 // the check.

core/services/nodes/router_optionstage_test.go

@@ -0,0 +1,77 @@
+package nodes
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	pb "github.com/mudler/LocalAI/pkg/grpc/proto"
+)
+
+// These tests cover staging of companion assets declared as option file paths
+// (the "vae_path:..." convention). Backends like sherpa-onnx keep a single-file
+// ModelFile (the .onnx) but resolve sibling assets — tokens.txt and the
+// espeak-ng-data directory — relative to the model dir. Those siblings must be
+// shipped to remote workers too, including directory-valued options expanded
+// file-by-file.
+var _ = Describe("stageGenericOptions companion assets", func() {
+	var (
+		stager *fakeFileStager
+		router *SmartRouter
+		node   *BackendNode
+		tmp    string
+	)
+
+	BeforeEach(func() {
+		stager = &fakeFileStager{}
+		router = &SmartRouter{
+			fileStager:     stager,
+			stagingTracker: NewStagingTracker(),
+		}
+		node = &BackendNode{ID: "node-1", Name: "node-1", Address: "10.0.0.1:50051"}
+		tmp = GinkgoT().TempDir()
+	})
+
+	It("stages option-declared sibling files and expands directory options", func() {
+		modelRel := "vits-piper-it_IT-paola-medium"
+		modelDir := filepath.Join(tmp, "models", modelRel)
+		dataDir := filepath.Join(modelDir, "espeak-ng-data")
+		Expect(os.MkdirAll(filepath.Join(dataDir, "lang"), 0o755)).To(Succeed())
+
+		onnx := filepath.Join(modelDir, "it_IT-paola-medium.onnx")
+		tokens := filepath.Join(modelDir, "tokens.txt")
+		phontab := filepath.Join(dataDir, "phontab")
+		langIt := filepath.Join(dataDir, "lang", "it")
+		for _, f := range []string{onnx, tokens, phontab, langIt} {
+			Expect(os.WriteFile(f, []byte("x"), 0o644)).To(Succeed())
+		}
+
+		opts := &pb.ModelOptions{
+			Model:     filepath.Join(modelRel, "it_IT-paola-medium.onnx"),
+			ModelFile: onnx,
+			// Bare names: not found under the models root (Model includes a
+			// subdir), so they must resolve relative to the model's own dir.
+			Options: []string{
+				"tts.noise_scale=0.667", // not a path; ignored by staging
+				"tokens:tokens.txt",
+				"data_dir:espeak-ng-data",
+			},
+		}
+
+		_, err := router.stageModelFiles(context.Background(), node, opts, "track-key")
+		Expect(err).ToNot(HaveOccurred())
+
+		staged := make([]string, 0, len(stager.ensureCalls))
+		for _, c := range stager.ensureCalls {
+			staged = append(staged, c.localPath)
+		}
+		// The .onnx (ModelFile), the tokens.txt file option, and every file under
+		// the espeak-ng-data directory option are staged; the directory path
+		// itself is never handed to the stager.
+		Expect(staged).To(ContainElements(onnx, tokens, phontab, langIt))
+		Expect(staged).ToNot(ContainElement(dataDir))
+	})
+})

core/trace/backend_trace.go

@@ -25,6 +25,7 @@ const (
 	BackendTraceRerank          BackendTraceType = "rerank"
 	BackendTraceTokenize        BackendTraceType = "tokenize"
 	BackendTraceDetection       BackendTraceType = "detection"
+	BackendTraceDepth           BackendTraceType = "depth"
 	BackendTraceFaceVerify      BackendTraceType = "face_verify"
 	BackendTraceFaceAnalyze     BackendTraceType = "face_analyze"
 	BackendTraceVoiceVerify     BackendTraceType = "voice_verify"

docs/data/version.json

@@ -1,3 +1,3 @@
 {
-  "version": "v4.4.2"
+  "version": "v4.4.3"
 }

gallery/sherpa-onnx-tts.yaml

@@ -12,3 +12,17 @@ config_file: |
     # Speech rate multiplier. Applied at every TTS / TTSStream call
     # since the TTSRequest proto has no speed field.
     - tts.speed=1.0
+    # Companion assets that sherpa-onnx TTS voices load from beside the .onnx
+    # (tokens, lexicons, espeak-ng phonemization data, Kokoro voices bank / jieba
+    # dict). Declared as option paths so distributed inference stages them to
+    # remote worker nodes too; the backend ignores these keys and resolves the
+    # files relative to the model dir. Bare names resolve against the model's own
+    # directory; any that a given voice doesn't ship are skipped during staging.
+    - tokens:tokens.txt
+    - lexicon:lexicon.txt
+    - data_dir:espeak-ng-data
+    - voices:voices.bin
+    - dict_dir:dict
+    - lexicon_us:lexicon-us-en.txt
+    - lexicon_gb:lexicon-gb-en.txt
+    - lexicon_zh:lexicon-zh.txt

gallery/supertonic.yaml

@@ -0,0 +1,19 @@
+---
+name: "supertonic"
+
+config_file: |
+  backend: supertonic
+  options:
+    # Generation knobs read by the supertonic backend at TTS time.
+    # steps = flow-matching denoising steps (quality); speed = rate;
+    # silence = inter-chunk silence seconds for long inputs.
+    - supertonic.steps=8
+    - supertonic.speed=1.05
+    - supertonic.silence=0.3
+    # Voice style used when a request omits `voice`. The model ships
+    # F1-F5 / M1-M5 under voice_styles/; override per request via the
+    # OpenAI `voice` field.
+    - supertonic.default_voice=F1
+    # Default language tag when a request omits `language`. "na" is the
+    # model's language-agnostic mode.
+    - supertonic.default_lang=na

go.mod

@@ -65,6 +65,7 @@ require (
 	github.com/testcontainers/testcontainers-go/modules/nats v0.42.0
 	github.com/testcontainers/testcontainers-go/modules/postgres v0.42.0
 	github.com/timbutler/zxcvbn v1.0.4
+	github.com/yalue/onnxruntime_go v1.11.0
 	go.opentelemetry.io/otel v1.44.0
 	go.opentelemetry.io/otel/exporters/prometheus v0.66.0
 	go.opentelemetry.io/otel/metric v1.44.0
@@ -497,7 +498,7 @@ require (
 	golang.org/x/sync v0.20.0
 	golang.org/x/sys v0.45.0 // indirect
 	golang.org/x/term v0.43.0
-	golang.org/x/text v0.37.0 // indirect
+	golang.org/x/text v0.37.0
 	golang.org/x/tools v0.45.0 // indirect
 	golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 // indirect
 	golang.zx2c4.com/wireguard v0.0.0-20250521234502-f333402bd9cb // indirect

go.sum

@@ -1377,6 +1377,8 @@ github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e h1:JVG44RsyaB9T2KIHavM
 github.com/xo/terminfo v0.0.0-20220910002029-abceb7e1c41e/go.mod h1:RbqR21r5mrJuqunuUZ/Dhy/avygyECGrLceyNeo4LiM=
 github.com/xyproto/randomstring v1.0.5 h1:YtlWPoRdgMu3NZtP45drfy1GKoojuR7hmRcnhZqKjWU=
 github.com/xyproto/randomstring v1.0.5/go.mod h1:rgmS5DeNXLivK7YprL0pY+lTuhNQW3iGxZ18UQApw/E=
+github.com/yalue/onnxruntime_go v1.11.0 h1:aKH4yPIbqfcB3SfnQWq/WxzLelkyolntHnffL3eMBHY=
+github.com/yalue/onnxruntime_go v1.11.0/go.mod h1:b4X26A8pekNb1ACJ58wAXgNKeUCGEAQ9dmACut9Sm/4=
 github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
 github.com/yuin/goldmark v1.1.25/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=

pkg/grpc/backend.go

@@ -54,6 +54,7 @@ type Backend interface {
 	TTSStream(ctx context.Context, in *pb.TTSRequest, f func(reply *pb.Reply), opts ...grpc.CallOption) error
 	SoundGeneration(ctx context.Context, in *pb.SoundGenerationRequest, opts ...grpc.CallOption) (*pb.Result, error)
 	Detect(ctx context.Context, in *pb.DetectOptions, opts ...grpc.CallOption) (*pb.DetectResponse, error)
+	Depth(ctx context.Context, in *pb.DepthRequest, opts ...grpc.CallOption) (*pb.DepthResponse, error)
 	FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest, opts ...grpc.CallOption) (*pb.FaceVerifyResponse, error)
 	FaceAnalyze(ctx context.Context, in *pb.FaceAnalyzeRequest, opts ...grpc.CallOption) (*pb.FaceAnalyzeResponse, error)
 	VoiceVerify(ctx context.Context, in *pb.VoiceVerifyRequest, opts ...grpc.CallOption) (*pb.VoiceVerifyResponse, error)

pkg/grpc/base/base.go

@@ -82,6 +82,10 @@ func (llm *Base) Detect(*pb.DetectOptions) (pb.DetectResponse, error) {
 	return pb.DetectResponse{}, fmt.Errorf("unimplemented")
 }
 
+func (llm *Base) Depth(*pb.DepthRequest) (pb.DepthResponse, error) {
+	return pb.DepthResponse{}, fmt.Errorf("unimplemented")
+}
+
 func (llm *Base) FaceVerify(*pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error) {
 	return pb.FaceVerifyResponse{}, fmt.Errorf("unimplemented")
 }

pkg/grpc/client.go

@@ -634,6 +634,24 @@ func (c *Client) Detect(ctx context.Context, in *pb.DetectOptions, opts ...grpc.
 	return client.Detect(ctx, in, opts...)
 }
 
+func (c *Client) Depth(ctx context.Context, in *pb.DepthRequest, opts ...grpc.CallOption) (*pb.DepthResponse, error) {
+	if !c.parallel {
+		c.opMutex.Lock()
+		defer c.opMutex.Unlock()
+	}
+	c.setBusy(true)
+	defer c.setBusy(false)
+	c.wdMark()
+	defer c.wdUnMark()
+	conn, err := c.dial()
+	if err != nil {
+		return nil, err
+	}
+	defer conn.Close()
+	client := pb.NewBackendClient(conn)
+	return client.Depth(ctx, in, opts...)
+}
+
 func (c *Client) FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest, opts ...grpc.CallOption) (*pb.FaceVerifyResponse, error) {
 	if !c.parallel {
 		c.opMutex.Lock()

pkg/grpc/embed.go

@@ -73,6 +73,10 @@ func (e *embedBackend) Detect(ctx context.Context, in *pb.DetectOptions, opts ..
 	return e.s.Detect(ctx, in)
 }
 
+func (e *embedBackend) Depth(ctx context.Context, in *pb.DepthRequest, opts ...grpc.CallOption) (*pb.DepthResponse, error) {
+	return e.s.Depth(ctx, in)
+}
+
 func (e *embedBackend) FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest, opts ...grpc.CallOption) (*pb.FaceVerifyResponse, error) {
 	return e.s.FaceVerify(ctx, in)
 }

pkg/grpc/interface.go

@@ -19,6 +19,7 @@ type AIModel interface {
 	GenerateImage(*pb.GenerateImageRequest) error
 	GenerateVideo(*pb.GenerateVideoRequest) error
 	Detect(*pb.DetectOptions) (pb.DetectResponse, error)
+	Depth(*pb.DepthRequest) (pb.DepthResponse, error)
 	FaceVerify(*pb.FaceVerifyRequest) (pb.FaceVerifyResponse, error)
 	FaceAnalyze(*pb.FaceAnalyzeRequest) (pb.FaceAnalyzeResponse, error)
 	VoiceVerify(*pb.VoiceVerifyRequest) (pb.VoiceVerifyResponse, error)

pkg/grpc/server.go

@@ -156,6 +156,18 @@ func (s *server) Detect(ctx context.Context, in *pb.DetectOptions) (*pb.DetectRe
 	return &res, nil
 }
 
+func (s *server) Depth(ctx context.Context, in *pb.DepthRequest) (*pb.DepthResponse, error) {
+	if s.llm.Locking() {
+		s.llm.Lock()
+		defer s.llm.Unlock()
+	}
+	res, err := s.llm.Depth(in)
+	if err != nil {
+		return nil, err
+	}
+	return &res, nil
+}
+
 func (s *server) FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest) (*pb.FaceVerifyResponse, error) {
 	if s.llm.Locking() {
 		s.llm.Lock()

pkg/model/connection_evicting_client.go

@@ -108,6 +108,12 @@ func (c *ConnectionEvictingClient) Detect(ctx context.Context, in *pb.DetectOpti
 	return result, err
 }
 
+func (c *ConnectionEvictingClient) Depth(ctx context.Context, in *pb.DepthRequest, opts ...ggrpc.CallOption) (*pb.DepthResponse, error) {
+	result, err := c.Backend.Depth(ctx, in, opts...)
+	c.checkErr(err)
+	return result, err
+}
+
 func (c *ConnectionEvictingClient) Rerank(ctx context.Context, in *pb.RerankRequest, opts ...ggrpc.CallOption) (*pb.RerankResult, error) {
 	result, err := c.Backend.Rerank(ctx, in, opts...)
 	c.checkErr(err)

swagger/docs.go

@@ -5767,11 +5767,11 @@ const docTemplate = `{
                     }
                 },
                 "redacted_preview": {
-                    "description": "RedactedPreview is the input with mask-action spans replaced\nby their placeholders. Identical to Text when no findings or\nwhen the strongest action is block/route_local (which don't\nrewrite content).",
+                    "description": "RedactedPreview is the input with mask-action spans replaced\nby their placeholders. Identical to Text when no findings or\nwhen the strongest action is block/allow (which don't rewrite\ncontent).",
                     "type": "string"
                 },
                 "suggested_action": {
-                    "description": "SuggestedAction is the strongest action across all findings:\n\"block\", \"route_local\", \"mask\", or \"allow\" (no findings).",
+                    "description": "SuggestedAction is the strongest action across all findings:\n\"block\", \"mask\", or \"allow\" (no findings, or all findings\nresolved to the allow action).",
                     "type": "string"
                 }
             }

swagger/swagger.json

@@ -5764,11 +5764,11 @@
                     }
                 },
                 "redacted_preview": {
-                    "description": "RedactedPreview is the input with mask-action spans replaced\nby their placeholders. Identical to Text when no findings or\nwhen the strongest action is block/route_local (which don't\nrewrite content).",
+                    "description": "RedactedPreview is the input with mask-action spans replaced\nby their placeholders. Identical to Text when no findings or\nwhen the strongest action is block/allow (which don't rewrite\ncontent).",
                     "type": "string"
                 },
                 "suggested_action": {
-                    "description": "SuggestedAction is the strongest action across all findings:\n\"block\", \"route_local\", \"mask\", or \"allow\" (no findings).",
+                    "description": "SuggestedAction is the strongest action across all findings:\n\"block\", \"mask\", or \"allow\" (no findings, or all findings\nresolved to the allow action).",
                     "type": "string"
                 }
             }

swagger/swagger.yaml

@@ -1884,13 +1884,14 @@ definitions:
         description: |-
           RedactedPreview is the input with mask-action spans replaced
           by their placeholders. Identical to Text when no findings or
-          when the strongest action is block/route_local (which don't
-          rewrite content).
+          when the strongest action is block/allow (which don't rewrite
+          content).
         type: string
       suggested_action:
         description: |-
           SuggestedAction is the strongest action across all findings:
-          "block", "route_local", "mask", or "allow" (no findings).
+          "block", "mask", or "allow" (no findings, or all findings
+          resolved to the allow action).
         type: string
     type: object
   schema.PIIFinding: