docs(llama-cpp): correct run.sh comment for arm64/darwin cpu-all

arm64 and darwin CPU images now also ship llama-cpp-cpu-all (not fallback-only);
only GPU images ship fallback-only. Fix the stale comment to match.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: Claude:claude-opus-4-8 [Claude Code]

.docker/llama-cpp-compile.sh

@@ -17,19 +17,29 @@ if [[ -n "${CUDA_DOCKER_ARCH:-}" ]]; then
   rm -rf /LocalAI/backend/cpp/llama-cpp-*-build
 fi
 
-if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
-  cd /LocalAI/backend/cpp/llama-cpp
-  make llama-cpp-fallback
-  make llama-cpp-grpc
-  make llama-cpp-rpc-server
+cd /LocalAI/backend/cpp/llama-cpp
+if [ -z "${BUILD_TYPE:-}" ]; then
+  # Pure CPU image (BUILD_TYPE empty): one build with ggml CPU_ALL_VARIANTS replaces the
+  # per-microarch binaries (x86: avx/avx2/avx512/fallback; arm64: armv8.x/armv9.x). ggml
+  # dlopens the best libggml-cpu-*.so at runtime by probing host CPU features.
+  #
+  # arm64: the CPU_ALL_VARIANTS table includes armv9.2 SME variants whose -march=...+sme is
+  # rejected by the Ubuntu 24.04 default gcc-13. gcc-14 accepts it, so build the arm64
+  # variants with it (the host never *selects* SME unless it has it, but every variant must
+  # still compile).
+  if [ "${TARGETARCH}" = "arm64" ]; then
+    apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
+    export CC=gcc-14 CXX=g++-14
+  fi
+  make llama-cpp-cpu-all
 else
-  cd /LocalAI/backend/cpp/llama-cpp
-  make llama-cpp-avx
-  make llama-cpp-avx2
-  make llama-cpp-avx512
+  # GPU build (cublas/hipblas/sycl/vulkan/...): the accelerator does the compute, so a
+  # single fallback CPU build is enough - no per-microarch CPU variants needed. (This also
+  # keeps the heavy GPU backend compile from also building the whole CPU variant matrix,
+  # and avoids the gcc-14 apt step on GPU base images such as nvidia l4t.)
   make llama-cpp-fallback
-  make llama-cpp-grpc
-  make llama-cpp-rpc-server
 fi
+make llama-cpp-grpc
+make llama-cpp-rpc-server
 
 ccache -s || true

.docker/turboquant-compile.sh

@@ -19,17 +19,21 @@ fi
 
 cd /LocalAI/backend/cpp/turboquant
 
-if [ "${TARGETARCH}" = "arm64" ] || [ "${BUILD_TYPE}" = "hipblas" ]; then
-  make turboquant-fallback
-  make turboquant-grpc
-  make turboquant-rpc-server
+if [ -z "${BUILD_TYPE:-}" ]; then
+  # Pure CPU image: one ggml CPU_ALL_VARIANTS build replaces the per-microarch binaries.
+  # arm64: the armv9.2 SME variants need gcc-14 (gcc-13 rejects +sme).
+  if [ "${TARGETARCH}" = "arm64" ]; then
+    apt-get update -qq && apt-get install -y -qq gcc-14 g++-14
+    export CC=gcc-14 CXX=g++-14
+  fi
+  make turboquant-cpu-all
 else
-  make turboquant-avx
-  make turboquant-avx2
-  make turboquant-avx512
+  # GPU build (cublas/hipblas/sycl/vulkan/...): single fallback CPU build, the accelerator
+  # does the compute. Keeps the GPU compile from also building the CPU variant matrix and
+  # avoids the gcc-14 apt step on GPU base images such as nvidia l4t.
   make turboquant-fallback
-  make turboquant-grpc
-  make turboquant-rpc-server
 fi
+make turboquant-grpc
+make turboquant-rpc-server
 
 ccache -s || true

.github/workflows/backend.yml

@@ -44,7 +44,7 @@ jobs:
       has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2

.github/workflows/backend_build.yml

@@ -101,7 +101,7 @@ jobs:
     steps:
 
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
 

.github/workflows/backend_build_darwin.yml

@@ -57,7 +57,7 @@ jobs:
       HOMEBREW_NO_ANALYTICS: '1'
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
 

.github/workflows/backend_merge.yml

@@ -49,7 +49,7 @@ jobs:
       # Sparse checkout: the merge job needs `.github/scripts/` (for the
       # keepalive cleanup script) but none of the source tree.
       - name: Checkout (.github/scripts only)
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           sparse-checkout: |
             .github/scripts

.github/workflows/backend_pr.yml

@@ -23,7 +23,7 @@ jobs:
       has-merges-singlearch: ${{ steps.set-matrix.outputs['has-merges-singlearch'] }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2

.github/workflows/base-images.yml

@@ -127,7 +127,7 @@ jobs:
             # the original l4t matrix entry which set skip-drivers: 'true'.
             skip-drivers: 'true'
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           submodules: false
       - name: Free disk space

.github/workflows/build-test.yaml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -25,7 +25,7 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -47,7 +47,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Configure apt mirror on runner

.github/workflows/bump-inference-defaults.yml

@@ -14,7 +14,7 @@ jobs:
   bump:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
 
       - uses: actions/setup-go@v5
         with:

.github/workflows/bump_deps.yaml

@@ -92,7 +92,7 @@ jobs:
             file: "backend/go/vibevoice-cpp/Makefile"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Bump dependencies 🔧
         id: bump
         run: |
@@ -128,7 +128,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Bump vLLM cu130 wheel pin 🔧
         id: bump
         run: |

.github/workflows/bump_docs.yaml

@@ -13,7 +13,7 @@ jobs:
           - repository: "mudler/LocalAI"
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Bump dependencies 🔧
         run: |
           bash .github/bump_docs.sh ${{ matrix.repository }}

.github/workflows/checksum_checker.yaml

@@ -8,7 +8,7 @@ jobs:
     if: github.repository == 'mudler/LocalAI'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Configure apt mirror on runner
         uses: ./.github/actions/configure-apt-mirror
       - name: Install dependencies

.github/workflows/deploy-explorer.yaml

@@ -16,7 +16,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - uses: actions/setup-go@v5

.github/workflows/gallery-agent.yaml

@@ -31,7 +31,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           token: ${{ secrets.GITHUB_TOKEN }}
 

.github/workflows/generate_intel_image.yaml

@@ -44,7 +44,7 @@ jobs:
         uses: docker/setup-buildx-action@master
 
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Cache Intel images
         uses: docker/build-push-action@v7

.github/workflows/gh-pages.yml

@@ -28,7 +28,7 @@ jobs:
       HUGO_VERSION: "0.146.3"
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0  # needed for enableGitInfo
           submodules: true

.github/workflows/image_build.yml

@@ -80,7 +80,7 @@ jobs:
     steps:
 
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
 
       - name: Configure apt mirror on runner
         id: apt_mirror

.github/workflows/image_merge.yml

@@ -36,7 +36,7 @@ jobs:
       # Sparse checkout: needed for .github/scripts/ (the keepalive cleanup
       # script). Skips the rest of the source tree.
       - name: Checkout (.github/scripts only)
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           sparse-checkout: |
             .github/scripts

.github/workflows/lint.yml

@@ -20,7 +20,7 @@ jobs:
   golangci-lint:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
         with:
           # Full history so golangci-lint's new-from-merge-base can reach
           # origin/master and compute the diff against it.

.github/workflows/release.yaml

@@ -10,7 +10,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -28,7 +28,7 @@ jobs:
     runs-on: macos-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Set up Go
@@ -46,7 +46,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           fetch-depth: 0
       - name: Configure apt mirror on runner

.github/workflows/secscan.yaml

@@ -14,7 +14,7 @@ jobs:
       GO111MODULE: on
     steps:
       - name: Checkout Source
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         if: ${{ github.actor != 'dependabot[bot]' }}
       - name: Run Gosec Security Scanner
         if: ${{ github.actor != 'dependabot[bot]' }}

.github/workflows/test-extra.yml

@@ -50,7 +50,7 @@ jobs:
       parakeet-cpp: ${{ steps.detect.outputs.parakeet-cpp }}
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
       - name: Setup Bun
         uses: oven-sh/setup-bun@v2
       - name: Install dependencies
@@ -67,7 +67,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -90,7 +90,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -113,7 +113,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -137,7 +137,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -158,7 +158,7 @@ jobs:
   #  runs-on: ubuntu-latest
   #  steps:
   #    - name: Clone
-  #      uses: actions/checkout@v6
+  #      uses: actions/checkout@v7
   #      with:
   #        submodules: true
   #    - name: Dependencies
@@ -178,7 +178,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -240,7 +240,7 @@ jobs:
   #           sudo rm -rf "$AGENT_TOOLSDIRECTORY" || true
   #           df -h
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -265,7 +265,7 @@ jobs:
   #   runs-on: ubuntu-latest
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -288,7 +288,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -309,7 +309,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -330,7 +330,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -351,7 +351,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -373,7 +373,7 @@ jobs:
   #   timeout-minutes: 45
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -394,7 +394,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -415,7 +415,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -436,7 +436,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -462,7 +462,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -484,7 +484,7 @@ jobs:
     timeout-minutes: 30
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -513,7 +513,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -530,7 +530,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -552,7 +552,7 @@ jobs:
     timeout-minutes: 20
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -579,7 +579,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -604,7 +604,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -625,7 +625,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -645,7 +645,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -664,7 +664,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -681,7 +681,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -698,7 +698,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -741,7 +741,7 @@ jobs:
   #   timeout-minutes: 90
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -783,7 +783,7 @@ jobs:
   #   timeout-minutes: 90
   #   steps:
   #     - name: Clone
-  #       uses: actions/checkout@v6
+  #       uses: actions/checkout@v7
   #       with:
   #         submodules: true
   #     - name: Dependencies
@@ -808,7 +808,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -840,7 +840,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -876,7 +876,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -915,7 +915,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -952,7 +952,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -987,7 +987,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -1013,7 +1013,7 @@ jobs:
     timeout-minutes: 150
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -1042,7 +1042,7 @@ jobs:
     timeout-minutes: 60
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go
@@ -1058,7 +1058,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -1091,7 +1091,7 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -1114,7 +1114,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies
@@ -1140,7 +1140,7 @@ jobs:
     timeout-minutes: 90
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies

.github/workflows/test.yml

@@ -21,7 +21,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Free disk space
@@ -84,7 +84,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Setup Go ${{ matrix.go-version }}

.github/workflows/tests-aio.yml

@@ -62,7 +62,7 @@ jobs:
           sudo rm -rfv build || true
           df -h
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Dependencies

.github/workflows/tests-e2e.yml

@@ -21,7 +21,7 @@ jobs:
         go-version: ['1.25.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Configure apt mirror on runner

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

@@ -0,0 +1,97 @@
+---
+name: 'PII NER tier E2E (live GGUF, CPU)'
+
+# Runs the real privacy-filter GGUF NER tier end-to-end on CPU — the gap the
+# hermetic tests/e2e suite cannot cover (it only exercises the in-process
+# pattern tier). Heavy (builds the C++ backend image + downloads a ~2.7 GB
+# GGUF), so it is path-filtered on PRs and otherwise runs nightly / on demand.
+#
+# This drives the container-level harness (tests/e2e-backends) via
+# `make test-extra-backend-privacy-filter`: it builds the privacy-filter image,
+# downloads the model, loads it on CPU, and asserts byte-correct, UTF-8-aligned
+# TokenClassify spans. The complementary HTTP-path specs in tests/e2e
+# (e2e_pii_ner_test.go) Skip unless PII_NER_MODEL_GGUF is wired.
+
+on:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 3 * * *'
+  push:
+    branches:
+      - master
+    paths:
+      - 'backend/cpp/privacy-filter/**'
+      - 'backend/Dockerfile.privacy-filter'
+      - 'core/services/routing/pii/**'
+      - 'core/services/routing/piidetector/**'
+      - 'core/backend/token_classify.go'
+      - 'core/http/endpoints/localai/pii.go'
+      - 'core/schema/pii.go'
+      - 'tests/e2e-backends/**'
+      - 'tests/e2e/e2e_pii_ner_test.go'
+      - 'tests/e2e/e2e_suite_test.go'
+      - '.github/workflows/tests-pii-ner-e2e.yml'
+  pull_request:
+    paths:
+      - 'backend/cpp/privacy-filter/**'
+      - 'backend/Dockerfile.privacy-filter'
+      - 'core/services/routing/pii/**'
+      - 'core/services/routing/piidetector/**'
+      - 'core/backend/token_classify.go'
+      - 'core/http/endpoints/localai/pii.go'
+      - 'core/schema/pii.go'
+      - 'tests/e2e-backends/**'
+      - 'tests/e2e/e2e_pii_ner_test.go'
+      - 'tests/e2e/e2e_suite_test.go'
+      - '.github/workflows/tests-pii-ner-e2e.yml'
+
+concurrency:
+  group: ci-tests-pii-ner-e2e-${{ github.event.pull_request.number || github.sha }}-${{ github.repository }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  tests-pii-ner-e2e:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        go-version: ['1.25.x']
+    steps:
+      - name: Clone
+        uses: actions/checkout@v7
+        with:
+          submodules: true
+      - name: Free disk space
+        run: |
+          sudo rm -rf /usr/share/dotnet /usr/local/lib/android /opt/ghc /opt/hostedtoolcache/CodeQL || true
+          sudo docker image prune --all --force || true
+          df -h
+      - name: Configure apt mirror on runner
+        uses: ./.github/actions/configure-apt-mirror
+      - name: Setup Go ${{ matrix.go-version }}
+        uses: actions/setup-go@v5
+        with:
+          go-version: ${{ matrix.go-version }}
+          cache: false
+      - name: Proto Dependencies
+        run: |
+          curl -L -s https://github.com/protocolbuffers/protobuf/releases/download/v26.1/protoc-26.1-linux-x86_64.zip -o protoc.zip && \
+          unzip -j -d /usr/local/bin protoc.zip bin/protoc && \
+          rm protoc.zip
+          go install google.golang.org/protobuf/cmd/protoc-gen-go@v1.34.2
+          go install google.golang.org/grpc/cmd/protoc-gen-go-grpc@1958fcbe2ca8bd93af633f11e97d44e567e945af
+          PATH="$PATH:$HOME/go/bin" make protogen-go
+      - name: Dependencies
+        run: |
+          sudo apt-get update
+          sudo apt-get install -y build-essential
+      # Builds local-ai-backend:privacy-filter, downloads the GGUF, loads it on
+      # CPU and runs the token_classify capability spec (byte-offset contract).
+      - name: Run live PII NER backend E2E
+        run: PATH="$PATH:$HOME/go/bin" make test-extra-backend-privacy-filter
+      - name: Setup tmate session if tests fail
+        if: ${{ failure() }}
+        uses: mxschmitt/action-tmate@v3.23
+        with:
+          detached: true
+          connect-timeout-seconds: 180
+          limit-access-to-actor: true

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

@@ -23,7 +23,7 @@ jobs:
         go-version: ['1.26.x']
     steps:
       - name: Clone
-        uses: actions/checkout@v6
+        uses: actions/checkout@v7
         with:
           submodules: true
       - name: Configure apt mirror on runner

.github/workflows/update_swagger.yaml

@@ -10,7 +10,7 @@ jobs:
       fail-fast: false
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@v7
       - name: Configure apt mirror on runner
         uses: ./.github/actions/configure-apt-mirror
       - uses: actions/setup-go@v5

.gitignore

@@ -91,3 +91,6 @@ core/http/react-ui/test-results/
 
 # Local worktrees
 .worktrees/
+
+# SDD / brainstorm scratch (agent-driven development)
+.superpowers/

Makefile

@@ -690,6 +690,16 @@ test-extra-backend-llama-cpp-transcription: docker-build-llama-cpp
 	BACKEND_TEST_CTX_SIZE=2048 \
 	$(MAKE) test-extra-backend
 
+## privacy-filter: the PII/NER token-classification backend. Exercises the
+## TokenClassify RPC and asserts byte-correct, UTF-8-aligned span offsets
+## against the openai-privacy-filter multilingual GGUF (CPU-runnable, ~50M
+## active params). This is the live-backend coverage for the PII NER tier.
+test-extra-backend-privacy-filter: docker-build-privacy-filter
+	BACKEND_IMAGE=local-ai-backend:privacy-filter \
+	BACKEND_TEST_MODEL_URL=https://huggingface.co/LocalAI-io/privacy-filter-multilingual-GGUF/resolve/main/privacy-filter-multilingual-f16.gguf \
+	BACKEND_TEST_CAPS=health,load,token_classify \
+	$(MAKE) test-extra-backend
+
 ## vllm is resolved from a HuggingFace model id (no file download) and
 ## exercises Predict + streaming + tool-call extraction via the hermes parser.
 ## Requires a host CPU with the SIMD instructions the prebuilt vllm CPU

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=6c00e87ac84404af588ad2e65935bd6f079c696f
+IK_LLAMA_VERSION?=7ccf1d209588962b96eacca325b37e9b3e8faf5e
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/CMakeLists.txt

@@ -50,8 +50,13 @@ add_custom_command(
         "${hw_proto}"
       DEPENDS "${hw_proto}")
 
-# hw_grpc_proto
-add_library(hw_grpc_proto
+# hw_grpc_proto: force STATIC. Under the CPU_ALL_VARIANTS build BUILD_SHARED_LIBS=ON
+# (ggml/llama become shared), which would otherwise make this glue library a DSO. As a
+# DSO it references the hidden-visibility symbols in the static libprotobuf.a, which the
+# linker cannot satisfy ("hidden symbol ... in libprotobuf.a is referenced by DSO").
+# Keeping it STATIC links protobuf/gRPC directly into the grpc-server executable while
+# only ggml/llama stay shared. No effect on the static variants (already BUILD_SHARED_LIBS=OFF).
+add_library(hw_grpc_proto STATIC
   ${hw_grpc_srcs}
   ${hw_grpc_hdrs}
   ${hw_proto_srcs}

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=e475fa2b5f9fb50c3d6fc3e7c6fdf1e004465b62
+LLAMA_VERSION?=be4a6a63eb2b848e19c277bdcf2bd399e8af76d9
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=
@@ -10,8 +10,16 @@ TARGET?=--target grpc-server
 JOBS?=$(shell nproc 2>/dev/null || sysctl -n hw.ncpu 2>/dev/null || echo 1)
 ARCH?=$(shell uname -m)
 
-# Disable Shared libs as we are linking on static gRPC and we can't mix shared and static
-CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF -DLLAMA_CURL=OFF
+# Shared libs default to OFF: we link static gRPC and the avx/avx2/avx512/fallback
+# variants are fully static. The CPU_ALL_VARIANTS build flips SHARED_LIBS=ON (ggml/llama
+# become shared so the dynamic CPU backends work; gRPC stays static via its imported
+# targets). SHARED_LIBS is a make variable, not an appended -D, so it survives the
+# recursive sub-make into the VARIANT build dir (which re-parses this Makefile) instead
+# of being re-clobbered by a second -DBUILD_SHARED_LIBS=OFF. EXTRA_CMAKE_ARGS is the hook
+# the CPU_ALL_VARIANTS target uses to inject -DGGML_BACKEND_DL/-DGGML_CPU_ALL_VARIANTS.
+SHARED_LIBS?=OFF
+EXTRA_CMAKE_ARGS?=
+CMAKE_ARGS+=-DBUILD_SHARED_LIBS=$(SHARED_LIBS) -DLLAMA_CURL=OFF $(EXTRA_CMAKE_ARGS)
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))
 ifeq ($(NATIVE),false)
@@ -120,6 +128,30 @@ llama-cpp-fallback: llama.cpp
 	CMAKE_ARGS="$(CMAKE_ARGS) -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off" $(MAKE) VARIANT="llama-cpp-fallback-build" build-llama-cpp-grpc-server
 	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-fallback-build/grpc-server llama-cpp-fallback
 
+# Single-build CPU backend using ggml's CPU_ALL_VARIANTS. Produces ONE grpc-server
+# plus a set of dlopen-able libggml-cpu-*.so (sandybridge/haswell/skylakex/...) that
+# ggml's backend registry selects from at runtime by probing host CPU features.
+# Replaces the avx/avx2/avx512/fallback multi-binary build on x86.
+#
+# CPU_ALL_VARIANTS requires GGML_BACKEND_DL, which requires BUILD_SHARED_LIBS=ON, so we
+# pass SHARED_LIBS=ON and the DL flags as make variables (NOT pre-expanded into the
+# CMAKE_ARGS env string): command-line make variables propagate through every recursive
+# sub-make, so the deepest VARIANT-dir build computes BUILD_SHARED_LIBS=ON consistently.
+# Only ggml/llama go shared - gRPC is found via its static imported targets, so the
+# grpc-server binary keeps static gRPC and only dynamically links ggml.
+#
+# TARGET adds "ggml": the per-microarch backends are runtime-dlopened, not link deps of
+# grpc-server, so they only build because each is an add_dependencies() of the ggml target.
+llama-cpp-cpu-all: llama.cpp
+	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build purge
+	$(info ${GREEN}I llama-cpp build info:cpu-all-variants${RESET})
+	$(MAKE) SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" VARIANT="llama-cpp-cpu-all-build" build-llama-cpp-grpc-server
+	cp -rfv $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/grpc-server llama-cpp-cpu-all
+	rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
+	find $(CURRENT_MAKEFILE_DIR)/../llama-cpp-cpu-all-build/llama.cpp/build \( -name '*.so*' -o -name '*.dylib' \) -exec cp -av {} ggml-shared-libs/ \;
+	@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
+
 llama-cpp-grpc: llama.cpp
 	cp -rf $(CURRENT_MAKEFILE_DIR)/../llama-cpp $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build
 	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../llama-cpp-grpc-build purge

backend/cpp/llama-cpp/package.sh

@@ -14,6 +14,22 @@ mkdir -p $CURDIR/package/lib
 cp -avrf $CURDIR/llama-cpp-* $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 
+# Bundle the ggml shared backends produced by the CPU_ALL_VARIANTS build (libggml-base.so,
+# libggml.so, libllama.so and the per-microarch libggml-cpu-*.so), all into package/lib.
+#
+# Two distinct resolution mechanisms both land here:
+#   - NEEDED deps (libggml-base/libggml/libllama): resolved by the dynamic linker via the
+#     LD_LIBRARY_PATH=$CURDIR/lib that run.sh exports.
+#   - The per-microarch libggml-cpu-*.so are NOT linked; ggml *discovers* them at runtime by
+#     scanning the executable's own directory (readlink /proc/self/exe). run.sh launches via
+#     the bundled $CURDIR/lib/ld.so, so /proc/self/exe -> .../lib/ld.so and ggml scans lib/.
+#     That is why the variants must sit in lib/ (next to ld.so), not just on the link path.
+# No-op on builds (arm64/darwin) that don't produce the all-variants set.
+if [ -d "$CURDIR/ggml-shared-libs" ]; then
+    echo "Bundling ggml shared backends (CPU_ALL_VARIANTS)..."
+    cp -avf $CURDIR/ggml-shared-libs/*.so* $CURDIR/package/lib/
+fi
+
 # Detect architecture and copy appropriate libraries
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     # x86_64 architecture

backend/cpp/llama-cpp/run.sh

@@ -12,26 +12,12 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=llama-cpp-fallback
 
-if grep -q -e "\savx\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX    found OK"
-	if [ -e $CURDIR/llama-cpp-avx ]; then
-		BINARY=llama-cpp-avx
-	fi
-fi
-
-if grep -q -e "\savx2\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX2   found OK"
-	if [ -e $CURDIR/llama-cpp-avx2 ]; then
-		BINARY=llama-cpp-avx2
-	fi
-fi
-
-# Check avx 512
-if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX512F found OK"
-	if [ -e $CURDIR/llama-cpp-avx512 ]; then
-		BINARY=llama-cpp-avx512
-	fi
+# CPU images (x86, arm64, darwin) ship a single llama-cpp-cpu-all built with ggml
+# CPU_ALL_VARIANTS: ggml's backend registry dlopens the best libggml-cpu-*.so for this
+# host, so no shell-side AVX probing. GPU images (cublas/sycl/vulkan/hipblas) ship only
+# llama-cpp-fallback (the accelerator does the compute), so fall back to it when absent.
+if [ -e $CURDIR/llama-cpp-cpu-all ]; then
+	BINARY=llama-cpp-cpu-all
 fi
 
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then

backend/cpp/turboquant/Makefile

@@ -65,6 +65,29 @@ turboquant-avx:
 turboquant-fallback:
 	$(call turboquant-build,fallback,-DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server)
 
+# Single-build CPU backend via ggml CPU_ALL_VARIANTS (mirrors llama-cpp-cpu-all).
+# turboquant reuses backend/cpp/llama-cpp's CMakeLists.txt (hw_grpc_proto STATIC) and
+# Makefile (SHARED_LIBS make-var + EXTRA_CMAKE_ARGS), so this passes the same overrides
+# through to the copied build: SHARED_LIBS=ON, the DL flags, and --target ggml (which
+# pulls in the per-microarch libggml-cpu-*.so via ggml's add_dependencies). The .so set
+# is collected for package.sh to bundle into package/lib.
+turboquant-cpu-all:
+	rm -rf $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
+	cp -rf $(LLAMA_CPP_DIR) $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build purge
+	bash $(CURRENT_MAKEFILE_DIR)/patch-grpc-server.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server.cpp
+	$(info $(GREEN)I turboquant build info:cpu-all-variants$(RESET))
+	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build llama.cpp
+	bash $(CURRENT_MAKEFILE_DIR)/apply-patches.sh $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/llama.cpp $(PATCHES_DIR)
+	SHARED_LIBS=ON EXTRA_CMAKE_ARGS="-DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON" TARGET="--target grpc-server --target ggml" \
+	LLAMA_REPO=$(LLAMA_REPO) LLAMA_VERSION=$(TURBOQUANT_VERSION) \
+	$(MAKE) -C $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build grpc-server
+	cp -rfv $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/grpc-server turboquant-cpu-all
+	rm -rf ggml-shared-libs && mkdir -p ggml-shared-libs
+	find $(CURRENT_MAKEFILE_DIR)/../turboquant-cpu-all-build/llama.cpp/build \( -name '*.so*' -o -name '*.dylib' \) -exec cp -av {} ggml-shared-libs/ \;
+	@echo "Collected ggml shared backends:" && ls -la ggml-shared-libs/
+
 turboquant-grpc:
 	$(call turboquant-build,grpc,-DGGML_RPC=ON -DGGML_AVX=off -DGGML_AVX2=off -DGGML_AVX512=off -DGGML_FMA=off -DGGML_F16C=off -DGGML_BMI2=off,--target grpc-server --target rpc-server)
 

backend/cpp/turboquant/package.sh

@@ -14,6 +14,15 @@ mkdir -p $CURDIR/package/lib
 cp -avrf $CURDIR/turboquant-* $CURDIR/package/
 cp -rfv $CURDIR/run.sh $CURDIR/package/
 
+# Bundle the ggml shared backends from the CPU_ALL_VARIANTS build into package/lib. ggml
+# discovers the per-microarch libggml-cpu-*.so by scanning the executable directory, which
+# (via the bundled lib/ld.so that run.sh launches through) resolves to lib/. See the
+# matching comment in backend/cpp/llama-cpp/package.sh. No-op on the fallback/ROCm builds.
+if [ -d "$CURDIR/ggml-shared-libs" ]; then
+    echo "Bundling ggml shared backends (CPU_ALL_VARIANTS)..."
+    cp -avf $CURDIR/ggml-shared-libs/*.so* $CURDIR/package/lib/
+fi
+
 # Detect architecture and copy appropriate libraries
 if [ -f "/lib64/ld-linux-x86-64.so.2" ]; then
     # x86_64 architecture

backend/cpp/turboquant/run.sh

@@ -12,26 +12,11 @@ grep -e "flags" /proc/cpuinfo | head -1
 
 BINARY=turboquant-fallback
 
-if grep -q -e "\savx\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX    found OK"
-	if [ -e $CURDIR/turboquant-avx ]; then
-		BINARY=turboquant-avx
-	fi
-fi
-
-if grep -q -e "\savx2\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX2   found OK"
-	if [ -e $CURDIR/turboquant-avx2 ]; then
-		BINARY=turboquant-avx2
-	fi
-fi
-
-# Check avx 512
-if grep -q -e "\savx512f\s" /proc/cpuinfo ; then
-	echo "CPU:    AVX512F found OK"
-	if [ -e $CURDIR/turboquant-avx512 ]; then
-		BINARY=turboquant-avx512
-	fi
+# x86/arm64 ship a single turboquant-cpu-all built with ggml CPU_ALL_VARIANTS: ggml's
+# backend registry dlopens the best libggml-cpu-*.so for this host, so no shell-side
+# probing. ROCm ships only turboquant-fallback, so fall back to it when cpu-all is absent.
+if [ -e $CURDIR/turboquant-cpu-all ]; then
+	BINARY=turboquant-cpu-all
 fi
 
 if [ -n "$LLAMACPP_GRPC_SERVERS" ]; then

backend/go/crispasr/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # CrispASR version (release tag)
 CRISPASR_REPO?=https://github.com/CrispStrobe/CrispASR
-CRISPASR_VERSION?=d745bda4386ae0f9d1d2f23fff8ec95d76428221
+CRISPASR_VERSION?=96b2a6ee31d30389fed8a7ef1a54239b75231ddc
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/parakeet-cpp/Makefile

@@ -1,6 +1,6 @@
 # parakeet-cpp backend Makefile.
 #
-# Upstream pin lives below as PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
+# Upstream pin lives below as PARAKEET_VERSION?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
 # (.github/bump_deps.sh) can find and update it - matches the
 # whisper.cpp / ds4 / vibevoice-cpp convention.
 #
@@ -15,7 +15,7 @@
 # That's what the L0 smoke test uses. The default target below does the
 # proper clone-at-pin + cmake build so CI doesn't need a side-checkout.
 
-PARAKEET_VERSION?=db755a78d39f789bb7d4e3935158a9e8105dbe36
+PARAKEET_VERSION?=89f5e2977b4d8bccd45e7bcc6f2ef7c4ed49e89a
 PARAKEET_REPO?=https://github.com/mudler/parakeet.cpp
 
 GOCMD?=go

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=b12098f5d09fc83da36e65c784f7bdb16a5a5ebf
+STABLEDIFFUSION_GGML_VERSION?=f440ad9c29dd8bc34e5d1f4b863832b96d6ea05f
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

backend/go/whisper/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # whisper.cpp version
 WHISPER_REPO?=https://github.com/ggml-org/whisper.cpp
-WHISPER_CPP_VERSION?=5ed76e9a079962f1c85cfce44edd325c27ef1f97
+WHISPER_CPP_VERSION?=43d78af5be58f41d6ffbc227d608f104577741ea
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/python/diffusers/requirements-cpu.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cpu
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision==0.22.1
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch==2.7.1
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-cublas12.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu121
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch
 ftfy
 optimum-quanto
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-cublas13.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu130
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 torchvision
 accelerate
 git+https://github.com/xhinker/sd_embed
@@ -10,9 +10,15 @@ sentencepiece
 torch
 ftfy
 optimum-quanto
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-hipblas.txt

@@ -1,17 +1,23 @@
 --extra-index-url https://download.pytorch.org/whl/rocm7.0
 torch==2.10.0+rocm7.0
 torchvision==0.25.0+rocm7.0
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 accelerate
 peft
 sentencepiece
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-intel.txt

@@ -3,18 +3,24 @@ torch
 torchvision
 optimum[openvino]
 setuptools
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 accelerate
 git+https://github.com/xhinker/sd_embed
 peft
 sentencepiece
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-l4t12.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://pypi.jetson-ai-lab.io/jp6/cu129/
 torch
-git+https://github.com/huggingface/diffusers
-transformers
+diffusers==0.38.0
+transformers==4.57.6
 accelerate
 peft
 optimum-quanto
@@ -9,9 +9,15 @@ numpy<2
 sentencepiece
 torchvision
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-l4t13.txt

@@ -1,7 +1,7 @@
 --extra-index-url https://download.pytorch.org/whl/cu130
 torch
-git+https://github.com/huggingface/diffusers
-transformers
+diffusers==0.38.0
+transformers==4.57.6
 accelerate
 peft
 optimum-quanto
@@ -10,9 +10,15 @@ sentencepiece
 torchvision
 ftfy
 chardet
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

backend/python/diffusers/requirements-mps.txt

@@ -1,16 +1,22 @@
 torch==2.7.1
 torchvision==0.22.1
-git+https://github.com/huggingface/diffusers
+diffusers==0.38.0
 opencv-python
-transformers
+transformers==4.57.6
 accelerate
 peft
 sentencepiece
 optimum-quanto
 ftfy
-# TODO: re-add compel once it supports transformers >= 5.
-# Tracking: https://github.com/damian0815/compel/pull/129
-#           https://github.com/damian0815/compel/issues/128
-# compel currently pins transformers~=4.25, which forced pip into multi-hour
-# resolver backtracking storms in CI. backend.py imports it lazily and gates
-# the COMPEL=1 env var on the import succeeding, so dropping it here is safe.
+# diffusers and transformers are pinned together on purpose. transformers v5
+# restructured CLIPTextModel and dropped the `.text_model` attribute, which
+# breaks single-file Stable Diffusion loading on every released diffusers
+# (<=0.38.0); only unreleased diffusers main supports transformers v5. Tracking
+# main via git froze whichever broken pair existed at image-build time. Pin the
+# last known-good released pair so builds are reproducible and can't drift into
+# the broken window. See https://github.com/mudler/LocalAI/issues/9979
+#
+# compel is intentionally omitted: it pins transformers~=4.25, which conflicts
+# with this pin and previously forced pip into multi-hour resolver backtracking
+# storms in CI. backend.py imports it lazily and gates the COMPEL=1 env var on
+# the import succeeding, so dropping it here is safe.

core/application/application.go

@@ -341,11 +341,9 @@ func (a *Application) ResolvePIIPolicy(cfg *config.ModelConfig) (enabled bool, d
 	}
 	appCfg := a.ApplicationConfig()
 
-	if cfg.PII.Enabled != nil {
-		enabled = *cfg.PII.Enabled
-	} else {
-		enabled = cfg.PIIIsEnabled() // backend default (cloud-proxy)
-	}
+	// PIIIsEnabled already encodes "explicit pii.enabled wins, else backend
+	// default (cloud-proxy)" — the single source of that rule.
+	enabled = cfg.PIIIsEnabled()
 	if !enabled {
 		return false, nil
 	}
@@ -354,7 +352,7 @@ func (a *Application) ResolvePIIPolicy(cfg *config.ModelConfig) (enabled bool, d
 	if len(detectors) == 0 {
 		detectors = append([]string(nil), appCfg.PIIDefaultDetectors...)
 	}
-	return enabled, detectors
+	return true, detectors // enabled is necessarily true past the !enabled guard
 }
 
 // PIIPolicyResolver adapts ResolvePIIPolicy to pii.PolicyResolver for

core/application/config_file_watcher.go

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

core/application/distributed.go

@@ -357,6 +357,15 @@ func initDistributed(cfg *config.ApplicationConfig, authDB *gorm.DB, configLoade
 		Pressure:         pressure,
 	})
 
+	// Wire staging-progress broadcasting so file-staging shows up on every
+	// replica, not just the one performing the transfer. Without this, a
+	// /api/operations poll that round-robins onto a peer sees no staging row and
+	// the progress flickers. The origin publishes; peers mirror via the wildcard.
+	router.StagingTracker().SetPublisher(natsClient)
+	if _, err := router.StagingTracker().SubscribeBroadcasts(natsClient); err != nil {
+		xlog.Warn("Failed to subscribe to staging progress broadcasts", "error", err)
+	}
+
 	// Create ReplicaReconciler for auto-scaling model replicas. Adapter +
 	// RegistrationToken feed the state-reconciliation passes: pending op
 	// drain uses the adapter, and model health probes use the token to auth

core/application/runtime_settings_branding_test.go

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

core/application/startup.go

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

core/cli/run.go

@@ -181,6 +181,8 @@ type RunCMD struct {
 	// Cloud-proxy MITM listener (off by default).
 	MITMListen string `env:"LOCALAI_MITM_LISTEN" help:"Address (host:port) for the cloudproxy MITM listener. Empty = disabled. Clients set HTTPS_PROXY=http://<this>:<port>. Intercept hosts are declared per-model via the model YAML mitm.hosts: block; create one from the Add Model UI." group:"middleware"`
 	MITMCADir  string `env:"LOCALAI_MITM_CA_DIR" type:"path" help:"Directory holding the MITM proxy CA cert + key. Defaults to <data-path>/mitm-ca." group:"middleware"`
+
+	PIIDefaultDetectors []string `env:"LOCALAI_PII_DEFAULT_DETECTORS" help:"Instance-wide default PII/secret detector model names applied to any PII-enabled model (chiefly cloud-proxy / MITM models) that names no pii.detectors of its own. Comma-separated, e.g. privacy-filter-nemotron,secret-filter. Takes precedence over the value persisted via the Middleware UI." group:"middleware"`
 }
 
 func (r *RunCMD) Run(ctx *cliContext.Context) error {
@@ -243,6 +245,7 @@ func (r *RunCMD) Run(ctx *cliContext.Context) error {
 		config.WithAPIAddress(r.Address),
 		config.WithMITMListen(r.MITMListen),
 		config.WithMITMCADir(r.MITMCADir),
+		config.WithPIIDefaultDetectors(r.PIIDefaultDetectors),
 		config.WithAgentJobRetentionDays(r.AgentJobRetentionDays),
 		config.WithLlamaCPPTunnelCallback(func(tunnels []string) {
 			tunnelEnvVar := strings.Join(tunnels, ",")

core/config/application_config.go

@@ -712,6 +712,18 @@ func WithMITMCADir(dir string) AppOption {
 	}
 }
 
+// WithPIIDefaultDetectors sets the instance-wide default PII/secret detector
+// model names applied to any PII-enabled model (chiefly cloud-proxy / MITM
+// models) that names no pii.detectors of its own. CLI/env:
+// LOCALAI_PII_DEFAULT_DETECTORS. Empty leaves the value to
+// runtime_settings.json / the Middleware UI; a non-empty value takes
+// precedence over the file (env > file).
+func WithPIIDefaultDetectors(detectors []string) AppOption {
+	return func(o *ApplicationConfig) {
+		o.PIIDefaultDetectors = detectors
+	}
+}
+
 func WithDynamicConfigDir(dynamicConfigsDir string) AppOption {
 	return func(o *ApplicationConfig) {
 		o.DynamicConfigsDir = dynamicConfigsDir

core/config/meta/registry.go

@@ -537,6 +537,36 @@ func DefaultRegistry() map[string]FieldMetaOverride {
 			Component:   "number",
 			Order:       79,
 		},
+		"pipeline.compaction.enabled": {
+			Section:     "pipeline",
+			Label:       "Compaction Enabled",
+			Description: "Fold conversation items that age out of the live window (Max History Items) into a rolling summary instead of dropping them, so long realtime sessions stay cheap without losing earlier context. Off by default.",
+			Component:   "toggle",
+			Order:       80,
+		},
+		"pipeline.compaction.trigger_items": {
+			Section:     "pipeline",
+			Label:       "Compaction Trigger Items",
+			Description: "High-water mark: once the live conversation exceeds this many items, the overflow above Max History Items is summarized and evicted. Must be greater than Max History Items; defaults to twice it. The gap controls how often summarization runs.",
+			Component:   "number",
+			Order:       81,
+		},
+		"pipeline.compaction.summary_model": {
+			Section:     "pipeline",
+			Label:       "Compaction Summary Model",
+			Description: "Optional smaller/cheaper model used to produce the rolling summary. Empty reuses the pipeline's own LLM. On CPU, a tiny model here keeps compaction from competing with the conversation LLM.",
+			Component:   "input",
+			Advanced:    true,
+			Order:       82,
+		},
+		"pipeline.compaction.max_summary_tokens": {
+			Section:     "pipeline",
+			Label:       "Compaction Max Summary Tokens",
+			Description: "Advisory cap on the rolling summary length (fed to the summarizer prompt). Defaults to 512.",
+			Component:   "number",
+			Advanced:    true,
+			Order:       83,
+		},
 
 		// --- Functions ---
 		"function.grammar.parallel_calls": {

core/config/model_config.go

@@ -641,11 +641,32 @@ type Pipeline struct {
 	// context fills.
 	MaxHistoryItems *int `yaml:"max_history_items,omitempty" json:"max_history_items,omitempty"`
 
+	// Compaction folds conversation items that age out of the live window
+	// (max_history_items) into a rolling summary instead of dropping them, so
+	// long realtime sessions stay cheap without losing earlier context. Nil
+	// (block absent) means disabled, preserving existing behavior.
+	Compaction *PipelineCompaction `yaml:"compaction,omitempty" json:"compaction,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"`
 }
 
+// PipelineCompaction configures summarize-then-drop for a realtime pipeline.
+type PipelineCompaction struct {
+	// Enabled turns summarize-then-drop on. Default false.
+	Enabled bool `yaml:"enabled,omitempty" json:"enabled,omitempty"`
+	// TriggerItems is the high-water mark: once live items exceed it, overflow
+	// above max_history_items is summarized and evicted. Must exceed
+	// max_history_items; clamped up if not. Default: 2x max_history_items.
+	TriggerItems int `yaml:"trigger_items,omitempty" json:"trigger_items,omitempty"`
+	// SummaryModel optionally names a smaller/cheaper model for the summary
+	// call. Empty uses the pipeline's own LLM.
+	SummaryModel string `yaml:"summary_model,omitempty" json:"summary_model,omitempty"`
+	// MaxSummaryTokens advises the summary length (fed to the prompt). Default 512.
+	MaxSummaryTokens int `yaml:"max_summary_tokens,omitempty" json:"max_summary_tokens,omitempty"`
+}
+
 // ApplyReasoningEffort resolves the effective reasoning effort — a per-request
 // value (requestEffort) overrides the config's own ReasoningEffort default —
 // stores it on the config so gRPCPredictOpts forwards it to the backend as the

core/config/runtime_settings_persist.go

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

core/config/runtime_settings_persist_test.go

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

core/http/endpoints/localai/agent_collections.go

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

core/http/endpoints/localai/agent_collections_param_test.go

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

core/http/endpoints/localai/agents.go

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

core/http/endpoints/localai/nodes.go

@@ -385,6 +385,23 @@ func GetNodeModelsEndpoint(registry *nodes.NodeRegistry) echo.HandlerFunc {
 	}
 }
 
+// ListAllNodeModelsEndpoint returns all loaded models across all healthy nodes.
+// @Summary List all loaded models cluster-wide
+// @Tags Nodes
+// @Success 200 {array} nodes.NodeModel
+// @Router /api/nodes/models [get]
+func ListAllNodeModelsEndpoint(registry *nodes.NodeRegistry) echo.HandlerFunc {
+	return func(c echo.Context) error {
+		ctx := c.Request().Context()
+		models, err := registry.ListAllLoadedModels(ctx)
+		if err != nil {
+			xlog.Error("Failed to list all node models", "error", err)
+			return c.JSON(http.StatusInternalServerError, nodeError(http.StatusInternalServerError, "failed to list node models"))
+		}
+		return c.JSON(http.StatusOK, models)
+	}
+}
+
 // DrainNodeEndpoint sets a node to draining status (no new requests).
 func DrainNodeEndpoint(registry *nodes.NodeRegistry) echo.HandlerFunc {
 	return func(c echo.Context) error {

core/http/endpoints/localai/nodes_test.go

@@ -407,4 +407,44 @@ var _ = Describe("Node HTTP handlers", func() {
 			Expect(names).To(ConsistOf("alpha", "beta"))
 		})
 	})
+
+	Describe("ListAllNodeModelsEndpoint", func() {
+		It("returns an empty list when no models are loaded", func() {
+			e := echo.New()
+			req := httptest.NewRequest(http.MethodGet, "/", nil)
+			rec := httptest.NewRecorder()
+			c := e.NewContext(req, rec)
+
+			handler := ListAllNodeModelsEndpoint(registry)
+			Expect(handler(c)).To(Succeed())
+			Expect(rec.Code).To(Equal(http.StatusOK))
+
+			var list []nodes.NodeModel
+			Expect(json.Unmarshal(rec.Body.Bytes(), &list)).To(Succeed())
+			Expect(list).To(BeEmpty())
+		})
+
+		It("returns loaded models across healthy nodes", func() {
+			ctx := context.Background()
+			Expect(registry.Register(ctx, &nodes.BackendNode{
+				ID: "n1", Name: "alpha", Address: "10.0.0.1:50051", Status: nodes.StatusHealthy,
+			}, true)).To(Succeed())
+			Expect(registry.SetNodeModel(ctx, "n1", "llama-3.3", 0, "loaded", "10.0.0.1:50051", 0)).To(Succeed())
+
+			e := echo.New()
+			req := httptest.NewRequest(http.MethodGet, "/", nil)
+			rec := httptest.NewRecorder()
+			c := e.NewContext(req, rec)
+
+			handler := ListAllNodeModelsEndpoint(registry)
+			Expect(handler(c)).To(Succeed())
+			Expect(rec.Code).To(Equal(http.StatusOK))
+
+			var list []nodes.NodeModel
+			Expect(json.Unmarshal(rec.Body.Bytes(), &list)).To(Succeed())
+			Expect(list).To(HaveLen(1))
+			Expect(list[0].ModelName).To(Equal("llama-3.3"))
+			Expect(list[0].NodeID).To(Equal("n1"))
+		})
+	})
 })

core/http/endpoints/localai/settings.go

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

core/http/endpoints/localai/settings_test.go

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

core/http/endpoints/openai/realtime.go

@@ -12,6 +12,7 @@ import (
 	"os"
 	"strconv"
 	"sync"
+	"sync/atomic"
 	"time"
 
 	"net/http"
@@ -134,6 +135,18 @@ type Session struct {
 	// pairs are kept together so we never feed an orphaned tool result.
 	MaxHistoryItems int
 
+	// Compaction settings resolved from pipeline.compaction (see resolveCompaction).
+	CompactionEnabled bool
+	CompactionTrigger int
+	SummaryModel      string
+	MaxSummaryTokens  int
+
+	// summarizerFactory lazily builds the model used for compaction summaries
+	// when summary_model is configured; nil means reuse the pipeline LLM.
+	summarizerFactory func() (Model, error)
+	summarizerOnce    sync.Once
+	summarizerCached  Model
+
 	// AssistantExecutor is non-nil when the session opted into the in-process
 	// LocalAI Assistant tool surface. Tool calls whose name matches this
 	// executor's catalog are run inproc and their output is fed back to the
@@ -241,6 +254,12 @@ type Conversation struct {
 	ID    string
 	Items []*types.MessageItemUnion
 	Lock  sync.Mutex
+	// Memory is the rolling summary of items already evicted by compaction. It
+	// is kept out of Items (so trimRealtimeItems never drops it) and rendered
+	// as a system message right after the session instructions.
+	Memory string
+	// compacting ensures at most one background compaction runs per conversation.
+	compacting atomic.Bool
 }
 
 func (c *Conversation) ToServer() types.Conversation {
@@ -540,13 +559,12 @@ func runRealtimeSession(application *application.Application, t Transport, model
 		SoundDetectionWindowMs:  cfg.Pipeline.SoundDetectionWindowMs,
 		SoundDetectionHopMs:     cfg.Pipeline.SoundDetectionHopMs,
 	}
+	session.CompactionEnabled, session.CompactionTrigger, session.MaxSummaryTokens, session.SummaryModel = resolveCompaction(cfg, session.MaxHistoryItems)
 
 	// Create a default conversation
 	conversationID := generateConversationID()
 	conversation := &Conversation{
-		ID: conversationID,
-		// TODO: We need to truncate the conversation items when a new item is added and we have run out of space. There are multiple places where items
-		//       can be added so we could use a datastructure here that enforces truncation upon addition
+		ID:    conversationID,
 		Items: []*types.MessageItemUnion{},
 	}
 	session.Conversations[conversationID] = conversation
@@ -577,6 +595,18 @@ func runRealtimeSession(application *application.Application, t Transport, model
 	}
 	session.ModelInterface = m
 
+	if session.SummaryModel != "" {
+		summaryModelName := session.SummaryModel
+		sid := sessionID
+		session.summarizerFactory = func() (Model, error) {
+			summaryCfg, lerr := application.ModelConfigLoader().LoadModelConfigFileByNameDefaultOptions(summaryModelName, application.ApplicationConfig())
+			if lerr != nil {
+				return nil, fmt.Errorf("load summary model config %q: %w", summaryModelName, lerr)
+			}
+			return newModel(&summaryCfg.Pipeline, application.ModelConfigLoader(), application.ModelLoader(), application.ApplicationConfig(), evaluator, buildRealtimeRoutingContext(application, sid))
+		}
+	}
+
 	if cfg.Pipeline.VoiceGateEnabled() {
 		gate, gerr := newVoiceGate(
 			*cfg.Pipeline.VoiceRecognition,
@@ -807,6 +837,15 @@ func runRealtimeSession(application *application.Application, t Transport, model
 				commitUtterance(respCtx, allAudio, session, conversation, t)
 			}()
 
+		case types.InputAudioBufferClearEvent:
+			xlog.Debug("recv", "message", string(msg))
+			// Discard a partially-captured utterance so the client can restart
+			// input cleanly without the stale buffer leaking into the next commit.
+			clearInputAudio(session)
+			sendEvent(t, types.InputAudioBufferClearedEvent{
+				ServerEventBase: types.ServerEventBase{EventID: e.EventID},
+			})
+
 		case types.ConversationItemCreateEvent:
 			xlog.Debug("recv", "message", string(msg))
 			// Add the item to the conversation
@@ -841,7 +880,39 @@ func runRealtimeSession(application *application.Application, t Transport, model
 			})
 
 		case types.ConversationItemDeleteEvent:
-			sendError(t, "not_implemented", "Deleting items not implemented", "", "event_TODO")
+			xlog.Debug("recv", "message", string(msg))
+			if e.ItemID == "" {
+				sendError(t, "invalid_item_id", "Need item_id, but none specified", "", "event_TODO")
+				continue
+			}
+			conversation.Lock.Lock()
+			updated, ok := deleteItem(conversation.Items, e.ItemID)
+			conversation.Items = updated
+			conversation.Lock.Unlock()
+			if !ok {
+				sendError(t, "invalid_item_id", "Item to delete not found", "", "event_TODO")
+				continue
+			}
+			sendEvent(t, types.ConversationItemDeletedEvent{
+				ServerEventBase: types.ServerEventBase{EventID: e.EventID},
+				ItemID:          e.ItemID,
+			})
+
+		case types.ConversationItemTruncateEvent:
+			xlog.Debug("recv", "message", string(msg))
+			conversation.Lock.Lock()
+			ok := truncateAssistantText(conversation.Items, e.ItemID, e.ContentIndex)
+			conversation.Lock.Unlock()
+			if !ok {
+				sendError(t, "invalid_item_id", "Item to truncate not found", "", "event_TODO")
+				continue
+			}
+			sendEvent(t, types.ConversationItemTruncatedEvent{
+				ServerEventBase: types.ServerEventBase{EventID: e.EventID},
+				ItemID:          e.ItemID,
+				ContentIndex:    e.ContentIndex,
+				AudioEndMs:      e.AudioEndMs,
+			})
 
 		case types.ConversationItemRetrieveEvent:
 			xlog.Debug("recv", "message", string(msg))
@@ -854,21 +925,7 @@ func runRealtimeSession(application *application.Application, t Transport, model
 			conversation.Lock.Lock()
 			var retrievedItem types.MessageItemUnion
 			for _, item := range conversation.Items {
-				// We need to check ID in the union
-				var id string
-				if item.System != nil {
-					id = item.System.ID
-				} else if item.User != nil {
-					id = item.User.ID
-				} else if item.Assistant != nil {
-					id = item.Assistant.ID
-				} else if item.FunctionCall != nil {
-					id = item.FunctionCall.ID
-				} else if item.FunctionCallOutput != nil {
-					id = item.FunctionCallOutput.ID
-				}
-
-				if id == e.ItemID {
+				if itemID(item) == e.ItemID {
 					retrievedItem = *item
 					break
 				}
@@ -1666,6 +1723,9 @@ const maxAssistantToolTurns = 10
 
 func triggerResponse(ctx context.Context, session *Session, conv *Conversation, t Transport, overrides *types.ResponseCreateParams) {
 	triggerResponseAtTurn(ctx, session, conv, t, overrides, 0)
+	// Fold aged-out turns into the rolling memory off the critical path; the
+	// next turn reaps the smaller buffer.
+	session.maybeCompact(conv)
 }
 
 func triggerResponseAtTurn(ctx context.Context, session *Session, conv *Conversation, t Transport, overrides *types.ResponseCreateParams, toolTurn int) {
@@ -1721,6 +1781,7 @@ func triggerResponseAtTurn(ctx context.Context, session *Session, conv *Conversa
 	var lastUserSpeaker *types.Speaker
 	personalize := session.voiceGate != nil && session.voiceGate.cfg.PersonalizeEnabled()
 	conv.Lock.Lock()
+	conversationHistory = withMemory(conversationHistory, conv.Memory)
 	items := trimRealtimeItems(conv.Items, session.MaxHistoryItems)
 	for _, item := range items {
 		if item.User != nil {

core/http/endpoints/openai/realtime_compaction.go

@@ -0,0 +1,326 @@
+package openai
+
+import (
+	"context"
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/http/endpoints/openai/types"
+	"github.com/mudler/LocalAI/core/schema"
+	"github.com/mudler/LocalAI/pkg/reasoning"
+	"github.com/mudler/xlog"
+)
+
+const (
+	defaultMaxSummaryTokens = 512
+	memoryPrefix            = "Summary of earlier conversation:\n"
+	// compactionTimeout bounds the summarizer call so a stuck model can't pin the
+	// compacting flag (and thus block all further compaction) forever.
+	compactionTimeout = 60 * time.Second
+)
+
+// withMemory inserts the rolling summary as a system message after the existing
+// (instructions) history. No-op when memory is empty.
+func withMemory(history schema.Messages, memory string) schema.Messages {
+	if memory == "" {
+		return history
+	}
+	content := memoryPrefix + memory
+	return append(history, schema.Message{
+		Role:          string(types.MessageRoleSystem),
+		StringContent: content,
+		Content:       content,
+	})
+}
+
+// renderItemsTranscript renders conversation items as a plain "role: text"
+// transcript for summarization. Non-text items (bare tool calls) are labelled
+// so the summarizer keeps track of actions taken.
+func renderItemsTranscript(items []*types.MessageItemUnion) string {
+	var b strings.Builder
+	for _, item := range items {
+		switch {
+		case item.User != nil:
+			b.WriteString("user: ")
+			for _, c := range item.User.Content {
+				if c.Text != "" {
+					b.WriteString(c.Text)
+				}
+				if c.Transcript != "" {
+					b.WriteString(c.Transcript)
+				}
+			}
+			b.WriteString("\n")
+		case item.Assistant != nil:
+			b.WriteString("assistant: ")
+			// Realtime assistant *audio* turns store the spoken words in
+			// .Transcript (not .Text), so emit both or spoken turns are dropped.
+			for _, c := range item.Assistant.Content {
+				if c.Text != "" {
+					b.WriteString(c.Text)
+				}
+				if c.Transcript != "" {
+					b.WriteString(c.Transcript)
+				}
+			}
+			b.WriteString("\n")
+		case item.FunctionCall != nil:
+			b.WriteString(fmt.Sprintf("assistant called tool %s(%s)\n", item.FunctionCall.Name, item.FunctionCall.Arguments))
+		case item.FunctionCallOutput != nil:
+			b.WriteString(fmt.Sprintf("tool result: %s\n", item.FunctionCallOutput.Output))
+		}
+	}
+	return strings.TrimSpace(b.String())
+}
+
+// buildSummaryMessages builds the chat messages for the summarizer LLM: a system
+// instruction plus prior memory and the new transcript to fold in. maxTokens is
+// advisory (fed to the prompt; not hard-enforced in v1).
+func buildSummaryMessages(priorMemory, transcript string, maxTokens int) schema.Messages {
+	system := fmt.Sprintf("You maintain a running memory of a live voice conversation. "+
+		"Merge the prior memory with the new exchanges into an updated memory. "+
+		"Keep names, decisions, facts, preferences, and open threads. Be concise "+
+		"(under ~%d tokens). Output only the updated memory, with no reasoning or tags.", maxTokens)
+	var user strings.Builder
+	if priorMemory != "" {
+		user.WriteString("Prior memory:\n")
+		user.WriteString(priorMemory)
+		user.WriteString("\n\n")
+	}
+	user.WriteString("New exchanges to fold in:\n")
+	user.WriteString(transcript)
+	return schema.Messages{
+		{Role: string(types.MessageRoleSystem), StringContent: system, Content: system},
+		{Role: string(types.MessageRoleUser), StringContent: user.String(), Content: user.String()},
+	}
+}
+
+// clearInputAudio resets the session's pending input audio buffer (the raw
+// PCM and any buffered Opus frames). Used by the input_audio_buffer.clear
+// realtime event so a client can discard a partially-captured utterance.
+func clearInputAudio(s *Session) {
+	s.AudioBufferLock.Lock()
+	s.InputAudioBuffer = nil
+	s.AudioBufferLock.Unlock()
+	s.OpusFramesLock.Lock()
+	s.OpusFrames = nil
+	s.OpusFramesLock.Unlock()
+}
+
+// itemID extracts the id from any MessageItemUnion variant ("" if none).
+func itemID(item *types.MessageItemUnion) string {
+	switch {
+	case item == nil:
+		return ""
+	case item.System != nil:
+		return item.System.ID
+	case item.User != nil:
+		return item.User.ID
+	case item.Assistant != nil:
+		return item.Assistant.ID
+	case item.FunctionCall != nil:
+		return item.FunctionCall.ID
+	case item.FunctionCallOutput != nil:
+		return item.FunctionCallOutput.ID
+	default:
+		return ""
+	}
+}
+
+// deleteItem removes the item with id from items, returning the new slice and
+// whether it was found.
+func deleteItem(items []*types.MessageItemUnion, id string) ([]*types.MessageItemUnion, bool) {
+	for i, item := range items {
+		if itemID(item) == id {
+			return append(items[:i:i], items[i+1:]...), true
+		}
+	}
+	return items, false
+}
+
+// truncateAssistantText clears the text of the assistant item's content part at
+// contentIndex. Minimal truncate: used to discard an interrupted/barge-in
+// response tail. Both .Text and .Transcript are cleared because realtime audio
+// turns store the spoken words in .Transcript (clearing only .Text would no-op).
+func truncateAssistantText(items []*types.MessageItemUnion, id string, contentIndex int) bool {
+	for _, item := range items {
+		if itemID(item) != id || item.Assistant == nil {
+			continue
+		}
+		if contentIndex >= 0 && contentIndex < len(item.Assistant.Content) {
+			item.Assistant.Content[contentIndex].Text = ""
+			item.Assistant.Content[contentIndex].Transcript = ""
+		}
+		return true
+	}
+	return false
+}
+
+// compactionCut returns the index splitting items into overflow (items[:cut],
+// to be summarized+evicted) and the kept live tail (items[cut:]), keeping the
+// last `keep` items. It mirrors trimRealtimeItems' pair-safety: the cut is
+// pulled left so a function_call and its function_call_output are never split
+// across the boundary (the whole pair lands in the kept tail). Returns 0 when
+// there is nothing to cut.
+func compactionCut(items []*types.MessageItemUnion, keep int) int {
+	// keep <= 0 means no live-window cap (the "unlimited history" sentinel, as
+	// in trimRealtimeItems): there is nothing to evict, so cut nothing. This
+	// also avoids indexing items[len(items)] in the pair-safety loop below.
+	if keep <= 0 {
+		return 0
+	}
+	cut := len(items) - keep
+	if cut <= 0 {
+		return 0
+	}
+	for cut > 0 && items[cut] != nil && items[cut].FunctionCallOutput != nil {
+		cut--
+	}
+	return cut
+}
+
+// resolveCompaction reads the pipeline.compaction block, applying defaults and
+// the trigger>max_history invariant. maxHistory is the already-resolved live
+// window size. Returns enabled=false (and zero values) when compaction is off.
+func resolveCompaction(cfg *config.ModelConfig, maxHistory int) (enabled bool, trigger, maxSummaryTokens int, summaryModel string) {
+	if cfg == nil || cfg.Pipeline.Compaction == nil || !cfg.Pipeline.Compaction.Enabled {
+		return false, 0, 0, ""
+	}
+	c := cfg.Pipeline.Compaction
+	trigger = c.TriggerItems
+	if trigger <= 0 {
+		trigger = maxHistory * 2
+	}
+	if trigger <= maxHistory {
+		trigger = maxHistory + 1
+	}
+	maxSummaryTokens = c.MaxSummaryTokens
+	if maxSummaryTokens <= 0 {
+		maxSummaryTokens = defaultMaxSummaryTokens
+	}
+	return true, trigger, maxSummaryTokens, c.SummaryModel
+}
+
+// prefixMatches reports whether items begins with the same ids, in order, as
+// snapshot — i.e. the overflow we summarized is still at the head (no concurrent
+// client delete reshuffled it).
+func prefixMatches(items, snapshot []*types.MessageItemUnion) bool {
+	if len(items) < len(snapshot) {
+		return false
+	}
+	for i := range snapshot {
+		if itemID(items[i]) != itemID(snapshot[i]) {
+			return false
+		}
+	}
+	return true
+}
+
+// compact folds overflow items into conv.Memory and evicts them. It never holds
+// conv.Lock across the summarizer call: snapshot under lock, summarize unlocked,
+// commit under lock (re-validating the head is unchanged). On any error it
+// leaves the conversation untouched — items are never dropped without a summary.
+func (s *Session) compact(conv *Conversation, model Model) {
+	if model == nil {
+		return
+	}
+	// Snapshot.
+	conv.Lock.Lock()
+	if len(conv.Items) <= s.CompactionTrigger {
+		conv.Lock.Unlock()
+		return
+	}
+	cut := compactionCut(conv.Items, s.MaxHistoryItems)
+	if cut <= 0 {
+		conv.Lock.Unlock()
+		return
+	}
+	overflow := append([]*types.MessageItemUnion(nil), conv.Items[:cut]...)
+	prior := conv.Memory
+	conv.Lock.Unlock()
+
+	// Summarize (unlocked).
+	msgs := buildSummaryMessages(prior, renderItemsTranscript(overflow), s.MaxSummaryTokens)
+	ctx, cancel := context.WithTimeout(context.Background(), compactionTimeout)
+	defer cancel()
+	predFunc, err := model.Predict(ctx, msgs, nil, nil, nil, nil, nil, nil, nil, nil, nil)
+	if err != nil {
+		xlog.Warn("realtime compaction: summarizer predict failed", "error", err)
+		return
+	}
+	pred, err := predFunc()
+	if err != nil {
+		xlog.Warn("realtime compaction: summarizer inference failed", "error", err)
+		return
+	}
+	// Strip any leaked reasoning/thinking spans using the same extractor the
+	// rest of the realtime path uses, rather than a bespoke regex.
+	rcfg := reasoning.Config{}
+	if mc := model.PredictConfig(); mc != nil {
+		rcfg = spokenReasoningConfig(mc.ReasoningConfig)
+	}
+	_, summary := reasoning.ExtractReasoningComplete(pred.Response, "", rcfg)
+	summary = strings.TrimSpace(summary)
+	if summary == "" {
+		xlog.Warn("realtime compaction: empty summary, skipping eviction")
+		return
+	}
+
+	// Commit.
+	conv.Lock.Lock()
+	defer conv.Lock.Unlock()
+	if !prefixMatches(conv.Items, overflow) {
+		xlog.Debug("realtime compaction: head changed during summary, skipping")
+		return
+	}
+	conv.Memory = summary
+	conv.Items = conv.Items[len(overflow):]
+	xlog.Debug("realtime compaction: evicted items into memory", "evicted", len(overflow), "remaining", len(conv.Items))
+}
+
+// summarizerModel resolves the model used to produce compaction summaries.
+// Without a configured summary_model (or factory) it reuses the pipeline LLM.
+func (s *Session) summarizerModel() Model {
+	if s.SummaryModel == "" || s.summarizerFactory == nil {
+		return s.ModelInterface
+	}
+	s.summarizerOnce.Do(func() {
+		m, err := s.summarizerFactory()
+		if err != nil {
+			xlog.Warn("realtime compaction: summary_model load failed, falling back to pipeline LLM", "model", s.SummaryModel, "error", err)
+			m = s.ModelInterface
+		}
+		s.summarizerCached = m
+	})
+	return s.summarizerCached
+}
+
+// maybeCompact schedules a background compaction when the live buffer has grown
+// past the trigger and none is already running. Returns immediately.
+func (s *Session) maybeCompact(conv *Conversation) {
+	if !s.CompactionEnabled {
+		return
+	}
+	conv.Lock.Lock()
+	over := len(conv.Items) > s.CompactionTrigger
+	conv.Lock.Unlock()
+	if !over {
+		return
+	}
+	if !conv.compacting.CompareAndSwap(false, true) {
+		return
+	}
+	go func() {
+		defer conv.compacting.Store(false)
+		// Resolve (and, for a configured summary_model, lazily load) the
+		// summarizer only when a compaction actually runs, off the response
+		// path — so the model load never blocks a user turn.
+		model := s.summarizerModel()
+		if model == nil {
+			return
+		}
+		s.compact(conv, model)
+	}()
+}

core/http/endpoints/openai/realtime_compaction_test.go

@@ -0,0 +1,308 @@
+package openai
+
+import (
+	"errors"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+
+	"github.com/mudler/LocalAI/core/backend"
+	"github.com/mudler/LocalAI/core/config"
+	"github.com/mudler/LocalAI/core/http/endpoints/openai/types"
+	"github.com/mudler/LocalAI/core/schema"
+)
+
+var _ = Describe("resolveCompaction", func() {
+	It("disables when the block is absent", func() {
+		enabled, _, _, _ := resolveCompaction(&config.ModelConfig{}, 6)
+		Expect(enabled).To(BeFalse())
+	})
+
+	It("defaults trigger to 2x max history and tokens to 512", func() {
+		cfg := &config.ModelConfig{Pipeline: config.Pipeline{Compaction: &config.PipelineCompaction{Enabled: true}}}
+		enabled, trigger, maxTok, _ := resolveCompaction(cfg, 6)
+		Expect(enabled).To(BeTrue())
+		Expect(trigger).To(Equal(12))
+		Expect(maxTok).To(Equal(512))
+	})
+
+	It("clamps trigger to max history + 1 when misconfigured", func() {
+		cfg := &config.ModelConfig{Pipeline: config.Pipeline{Compaction: &config.PipelineCompaction{Enabled: true, TriggerItems: 4}}}
+		_, trigger, _, _ := resolveCompaction(cfg, 6)
+		Expect(trigger).To(Equal(7))
+	})
+
+	It("honors explicit values", func() {
+		cfg := &config.ModelConfig{Pipeline: config.Pipeline{Compaction: &config.PipelineCompaction{
+			Enabled: true, TriggerItems: 20, MaxSummaryTokens: 256, SummaryModel: "tiny"}}}
+		enabled, trigger, maxTok, model := resolveCompaction(cfg, 6)
+		Expect(enabled).To(BeTrue())
+		Expect(trigger).To(Equal(20))
+		Expect(maxTok).To(Equal(256))
+		Expect(model).To(Equal("tiny"))
+	})
+})
+
+var _ = Describe("deleteItem", func() {
+	mk := func(ids ...string) []*types.MessageItemUnion {
+		out := make([]*types.MessageItemUnion, len(ids))
+		for i, id := range ids {
+			out[i] = &types.MessageItemUnion{User: &types.MessageItemUser{ID: id}}
+		}
+		return out
+	}
+
+	It("removes the item with the given id", func() {
+		items, ok := deleteItem(mk("a", "b", "c"), "b")
+		Expect(ok).To(BeTrue())
+		Expect(len(items)).To(Equal(2))
+		Expect(itemID(items[0])).To(Equal("a"))
+		Expect(itemID(items[1])).To(Equal("c"))
+	})
+
+	It("reports not found for an unknown id", func() {
+		_, ok := deleteItem(mk("a"), "zzz")
+		Expect(ok).To(BeFalse())
+	})
+})
+
+var _ = Describe("clearInputAudio", func() {
+	It("resets the pending PCM and buffered Opus frames", func() {
+		s := &Session{InputAudioBuffer: []byte{1, 2, 3}, OpusFrames: [][]byte{{9}}}
+		clearInputAudio(s)
+		Expect(s.InputAudioBuffer).To(BeNil())
+		Expect(s.OpusFrames).To(BeNil())
+	})
+})
+
+var _ = Describe("truncateAssistantText", func() {
+	It("clears the text of the assistant content part at the index", func() {
+		items := []*types.MessageItemUnion{{Assistant: &types.MessageItemAssistant{
+			ID:      "a1",
+			Content: []types.MessageContentOutput{{Type: types.MessageContentTypeText, Text: "hello world"}},
+		}}}
+		ok := truncateAssistantText(items, "a1", 0)
+		Expect(ok).To(BeTrue())
+		Expect(items[0].Assistant.Content[0].Text).To(Equal(""))
+	})
+
+	// Realtime assistant *audio* turns store the spoken words in .Transcript, not
+	// .Text, so a barge-in truncate must clear .Transcript too or it would no-op.
+	It("clears the transcript of an assistant audio content part", func() {
+		items := []*types.MessageItemUnion{{Assistant: &types.MessageItemAssistant{
+			ID:      "a1",
+			Content: []types.MessageContentOutput{{Type: types.MessageContentTypeAudio, Transcript: "hello world"}},
+		}}}
+		ok := truncateAssistantText(items, "a1", 0)
+		Expect(ok).To(BeTrue())
+		Expect(items[0].Assistant.Content[0].Transcript).To(Equal(""))
+	})
+
+	It("returns false for an unknown id", func() {
+		Expect(truncateAssistantText(nil, "nope", 0)).To(BeFalse())
+	})
+})
+
+var _ = Describe("compactionCut", func() {
+	user := func(id string) *types.MessageItemUnion {
+		return &types.MessageItemUnion{User: &types.MessageItemUser{ID: id}}
+	}
+	call := func(id string) *types.MessageItemUnion {
+		return &types.MessageItemUnion{FunctionCall: &types.MessageItemFunctionCall{ID: id}}
+	}
+	out := func(id string) *types.MessageItemUnion {
+		return &types.MessageItemUnion{FunctionCallOutput: &types.MessageItemFunctionCallOutput{ID: id}}
+	}
+
+	It("cuts exactly len-keep when no pairs straddle the boundary", func() {
+		items := []*types.MessageItemUnion{user("1"), user("2"), user("3"), user("4")}
+		Expect(compactionCut(items, 2)).To(Equal(2))
+	})
+
+	It("returns 0 when nothing to cut", func() {
+		Expect(compactionCut([]*types.MessageItemUnion{user("1")}, 2)).To(Equal(0))
+	})
+
+	It("returns 0 (cuts nothing) when keep is 0 — the unlimited-window sentinel", func() {
+		items := []*types.MessageItemUnion{user("1"), user("2"), user("3")}
+		Expect(compactionCut(items, 0)).To(Equal(0))
+	})
+
+	It("moves the boundary so a call/output pair is not split", func() {
+		// keep=2 -> naive cut=2, but items[2] is the output of items[1]'s call;
+		// pull the cut right so the whole pair stays in the kept tail.
+		items := []*types.MessageItemUnion{user("1"), call("c"), out("c"), user("4")}
+		Expect(compactionCut(items, 2)).To(Equal(1))
+	})
+})
+
+var _ = Describe("withMemory", func() {
+	It("inserts a memory system message when memory is non-empty", func() {
+		base := schema.Messages{{Role: "system", StringContent: "instructions"}}
+		out := withMemory(base, "user is Bob; wants pizza")
+		Expect(len(out)).To(Equal(2))
+		Expect(out[1].Role).To(Equal("system"))
+		Expect(out[1].StringContent).To(ContainSubstring("user is Bob"))
+		Expect(out[1].StringContent).To(ContainSubstring("Summary of earlier conversation"))
+	})
+
+	It("is a no-op when memory is empty", func() {
+		base := schema.Messages{{Role: "system", StringContent: "instructions"}}
+		Expect(withMemory(base, "")).To(HaveLen(1))
+	})
+})
+
+var _ = Describe("renderItemsTranscript", func() {
+	It("renders user and assistant text turns", func() {
+		items := []*types.MessageItemUnion{
+			{User: &types.MessageItemUser{Content: []types.MessageContentInput{{Type: types.MessageContentTypeInputText, Text: "hi"}}}},
+			{Assistant: &types.MessageItemAssistant{Content: []types.MessageContentOutput{{Type: types.MessageContentTypeText, Text: "hello"}}}},
+		}
+		out := renderItemsTranscript(items)
+		Expect(out).To(ContainSubstring("user: hi"))
+		Expect(out).To(ContainSubstring("assistant: hello"))
+	})
+
+	// Realtime assistant *audio* turns store the spoken words in .Transcript, not
+	// .Text, so the transcript builder must emit .Transcript too or spoken turns
+	// would be dropped from the summary.
+	It("renders an assistant audio turn from its transcript", func() {
+		items := []*types.MessageItemUnion{
+			{Assistant: &types.MessageItemAssistant{Content: []types.MessageContentOutput{{Type: types.MessageContentTypeAudio, Transcript: "spoken words"}}}},
+		}
+		Expect(renderItemsTranscript(items)).To(ContainSubstring("assistant: spoken words"))
+	})
+})
+
+var _ = Describe("buildSummaryMessages", func() {
+	It("includes prior memory and the new transcript", func() {
+		msgs := buildSummaryMessages("prior facts", "user: hi", 512)
+		Expect(len(msgs)).To(Equal(2))
+		Expect(msgs[0].Role).To(Equal("system"))
+		Expect(msgs[1].StringContent).To(ContainSubstring("prior facts"))
+		Expect(msgs[1].StringContent).To(ContainSubstring("user: hi"))
+	})
+})
+
+var _ = Describe("compact", func() {
+	user := func(id, text string) *types.MessageItemUnion {
+		return &types.MessageItemUnion{User: &types.MessageItemUser{ID: id,
+			Content: []types.MessageContentInput{{Type: types.MessageContentTypeInputText, Text: text}}}}
+	}
+
+	It("summarizes overflow into Memory and evicts it, keeping the live tail", func() {
+		conv := &Conversation{Items: []*types.MessageItemUnion{
+			user("1", "a"), user("2", "b"), user("3", "c"), user("4", "d"),
+			user("5", "e"), user("6", "f"), user("7", "g"), user("8", "h"),
+		}}
+		s := &Session{CompactionEnabled: true, CompactionTrigger: 7, MaxHistoryItems: 4, MaxSummaryTokens: 512}
+		m := &fakeModel{predictResp: backend.LLMResponse{Response: "ROLLED UP"}}
+
+		s.compact(conv, m)
+
+		Expect(conv.Memory).To(Equal("ROLLED UP"))
+		Expect(len(conv.Items)).To(Equal(4))
+		Expect(itemID(conv.Items[0])).To(Equal("5"))
+		// The summarizer saw the evicted turns.
+		Expect(m.lastMessages[1].StringContent).To(ContainSubstring("a"))
+	})
+
+	It("leaves Items and Memory untouched when the summarizer errors", func() {
+		items := []*types.MessageItemUnion{user("1", "a"), user("2", "b"), user("3", "c")}
+		conv := &Conversation{Items: items}
+		s := &Session{CompactionEnabled: true, CompactionTrigger: 2, MaxHistoryItems: 1, MaxSummaryTokens: 512}
+		m := &fakeModel{predictErr: errors.New("boom")}
+
+		s.compact(conv, m)
+
+		Expect(conv.Memory).To(Equal(""))
+		Expect(len(conv.Items)).To(Equal(3))
+	})
+
+	It("strips leaked reasoning tags from the summary via the shared extractor", func() {
+		conv := &Conversation{Items: []*types.MessageItemUnion{
+			user("1", "a"), user("2", "b"), user("3", "c"), user("4", "d"),
+			user("5", "e"), user("6", "f"), user("7", "g"), user("8", "h"),
+		}}
+		s := &Session{CompactionEnabled: true, CompactionTrigger: 7, MaxHistoryItems: 4, MaxSummaryTokens: 512}
+		m := &fakeModel{predictResp: backend.LLMResponse{Response: "<think>planning the summary</think>CLEAN SUMMARY"}}
+
+		s.compact(conv, m)
+
+		Expect(conv.Memory).To(Equal("CLEAN SUMMARY"))
+		Expect(conv.Memory).ToNot(ContainSubstring("planning"))
+	})
+
+	It("does nothing when items are at or below the trigger", func() {
+		conv := &Conversation{Items: []*types.MessageItemUnion{user("1", "a")}}
+		s := &Session{CompactionEnabled: true, CompactionTrigger: 7, MaxHistoryItems: 4}
+		s.compact(conv, &fakeModel{predictResp: backend.LLMResponse{Response: "x"}})
+		Expect(conv.Memory).To(Equal(""))
+		Expect(len(conv.Items)).To(Equal(1))
+	})
+})
+
+var _ = Describe("prefixMatches", func() {
+	user := func(id string) *types.MessageItemUnion {
+		return &types.MessageItemUnion{User: &types.MessageItemUser{ID: id}}
+	}
+
+	It("matches when items begins with the snapshot ids in order", func() {
+		items := []*types.MessageItemUnion{user("1"), user("2"), user("3")}
+		snap := []*types.MessageItemUnion{user("1"), user("2")}
+		Expect(prefixMatches(items, snap)).To(BeTrue())
+	})
+
+	It("matches an empty snapshot", func() {
+		Expect(prefixMatches([]*types.MessageItemUnion{user("1")}, nil)).To(BeTrue())
+	})
+
+	It("fails when items is shorter than the snapshot (a concurrent delete shrank the head)", func() {
+		items := []*types.MessageItemUnion{user("1")}
+		snap := []*types.MessageItemUnion{user("1"), user("2")}
+		Expect(prefixMatches(items, snap)).To(BeFalse())
+	})
+
+	It("fails when the head ids differ (a concurrent delete reordered the head)", func() {
+		items := []*types.MessageItemUnion{user("2"), user("3")}
+		snap := []*types.MessageItemUnion{user("1"), user("2")}
+		Expect(prefixMatches(items, snap)).To(BeFalse())
+	})
+})
+
+var _ = Describe("summarizerModel", func() {
+	It("returns the pipeline model when no summary_model is set", func() {
+		m := &fakeModel{}
+		s := &Session{ModelInterface: m}
+		Expect(s.summarizerModel()).To(Equal(m))
+	})
+
+	It("uses the factory (once) when summary_model is set", func() {
+		pipeline := &fakeModel{}
+		small := &fakeModel{}
+		calls := 0
+		s := &Session{ModelInterface: pipeline, SummaryModel: "tiny",
+			summarizerFactory: func() (Model, error) { calls++; return small, nil }}
+		Expect(s.summarizerModel()).To(Equal(small))
+		Expect(s.summarizerModel()).To(Equal(small))
+		Expect(calls).To(Equal(1))
+	})
+
+	It("falls back to the pipeline model when the factory errors", func() {
+		pipeline := &fakeModel{}
+		s := &Session{ModelInterface: pipeline, SummaryModel: "tiny",
+			summarizerFactory: func() (Model, error) { return nil, errors.New("nope") }}
+		Expect(s.summarizerModel()).To(Equal(pipeline))
+	})
+})
+
+var _ = Describe("itemID", func() {
+	It("returns the id for each variant and empty for nil", func() {
+		Expect(itemID(nil)).To(Equal(""))
+		Expect(itemID(&types.MessageItemUnion{User: &types.MessageItemUser{ID: "u1"}})).To(Equal("u1"))
+		Expect(itemID(&types.MessageItemUnion{Assistant: &types.MessageItemAssistant{ID: "a1"}})).To(Equal("a1"))
+		Expect(itemID(&types.MessageItemUnion{System: &types.MessageItemSystem{ID: "s1"}})).To(Equal("s1"))
+		Expect(itemID(&types.MessageItemUnion{FunctionCall: &types.MessageItemFunctionCall{ID: "f1"}})).To(Equal("f1"))
+		Expect(itemID(&types.MessageItemUnion{FunctionCallOutput: &types.MessageItemFunctionCallOutput{ID: "o1"}})).To(Equal("o1"))
+	})
+})

core/http/endpoints/openai/realtime_model.go

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

core/http/endpoints/openai/realtime_model_alias_test.go

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

core/http/react-ui/e2e/model-config.spec.js

@@ -288,6 +288,21 @@ test.describe('Model Editor - Interactive Tab', () => {
     await expect(page.locator('input[placeholder^="match,"]')).toBeVisible()
   })
 
+  test('pattern min_len clamps a directly-typed negative to 0', async ({ page }) => {
+    const searchInput = page.locator('input[placeholder="Search fields to add..."]')
+    await searchInput.fill('Custom Secret Patterns')
+    const dropdown = searchInput.locator('..').locator('..')
+    await dropdown.locator('div', { hasText: 'Custom Secret Patterns' }).first().click()
+
+    await page.locator('button', { hasText: 'Add pattern' }).click()
+    // The number input's min={0} only limits the spinner arrows, not keyboard
+    // entry; the editor must sanitise a typed negative so a meaningless
+    // negative length floor never reaches the saved config.
+    const minLen = page.locator('input[aria-label="Minimum length"]')
+    await minLen.fill('-5')
+    await expect(minLen).toHaveValue('0')
+  })
+
   // Regression: a map-typed field (entity_actions) present in the loaded YAML
   // must render WITH its values. flattenConfig used to recurse into the map,
   // scattering it across pii_detection.entity_actions.<GROUP> paths that match
@@ -329,4 +344,37 @@ test.describe('Model Editor - Interactive Tab', () => {
     await expect(page.getByText(/block —/i).first()).toBeVisible()
   })
 
+  // A map cannot hold two values for one key, so renaming a row to an existing
+  // group must collapse to a single row (Object.fromEntries, last write wins)
+  // rather than rendering two conflicting rows that silently lose one on save.
+  test('entity_actions collapses a duplicate group to a single row', async ({ page }) => {
+    await page.route('**/api/models/edit/ner-model', (route) => {
+      route.fulfill({
+        contentType: 'application/json',
+        body: JSON.stringify({
+          name: 'ner-model',
+          config: [
+            'name: ner-model',
+            'backend: llama-cpp',
+            'pii_detection:',
+            '    entity_actions:',
+            '        SSN: block',
+            '        EMAIL: mask',
+            '',
+          ].join('\n'),
+        }),
+      })
+    })
+
+    await page.goto('/app/model-editor/ner-model')
+
+    const groupInputs = page.locator('input[aria-label="Entity group"]')
+    await expect(groupInputs).toHaveCount(2)
+
+    // Rename the EMAIL row to duplicate SSN; the editor collapses to one SSN row.
+    await groupInputs.nth(1).fill('SSN')
+    await expect(groupInputs).toHaveCount(1)
+    await expect(groupInputs.nth(0)).toHaveValue('SSN')
+  })
+
 })

core/http/react-ui/e2e/nodes-detail.spec.js

@@ -0,0 +1,34 @@
+import { test, expect } from './coverage-fixtures.js'
+
+const ID = 'n1'
+async function mockNode(page) {
+  await page.route(`**/api/nodes/${ID}`, r => r.fulfill({ status: 200, contentType: 'application/json',
+    body: JSON.stringify({ id: ID, name: 'alpha', node_type: 'backend', address: '10.0.0.1:50051', status: 'healthy', total_vram: 24e9, available_vram: 12e9, max_replicas_per_model: 1, labels: { env: 'prod' } }) }))
+  await page.route(`**/api/nodes/${ID}/models`, r => r.fulfill({ status: 200, contentType: 'application/json',
+    body: JSON.stringify([{ node_id: ID, model_name: 'llama-3.3', state: 'loaded', in_flight: 0, replica_index: 0 }]) }))
+  await page.route(`**/api/nodes/${ID}/backends`, r => r.fulfill({ status: 200, contentType: 'application/json',
+    body: JSON.stringify([{ name: 'llama-cpp', is_system: true, installed_at: '2026-06-01T00:00:00Z' }]) }))
+}
+
+test.describe('Node detail page', () => {
+  test('renders sections for a node', async ({ page }) => {
+    await mockNode(page)
+    await page.goto(`/app/nodes/${ID}`)
+    await expect(page.locator('.page-title').first()).toBeVisible({ timeout: 15_000 })
+    await expect(page.getByText('alpha')).toBeVisible()
+    await expect(page.getByText('llama-3.3')).toBeVisible()
+    await expect(page.getByText('llama-cpp')).toBeVisible()
+    await expect(page.getByText('env=prod')).toBeVisible()
+  })
+
+  test('is reachable by clicking a roster panel', async ({ page }) => {
+    await page.route('**/api/nodes', r => r.fulfill({ status: 200, contentType: 'application/json',
+      body: JSON.stringify([{ id: ID, name: 'alpha', node_type: 'backend', address: '10.0.0.1:50051', status: 'healthy' }]) }))
+    await page.route('**/api/nodes/models', r => r.fulfill({ status: 200, contentType: 'application/json', body: '[]' }))
+    await page.route('**/api/nodes/scheduling', r => r.fulfill({ status: 200, contentType: 'application/json', body: '[]' }))
+    await mockNode(page)
+    await page.goto('/app/nodes')
+    await page.locator('.node-panel').filter({ hasText: 'alpha' }).getByText('alpha').click()
+    await expect(page).toHaveURL(new RegExp(`/app/nodes/${ID}$`))
+  })
+})

core/http/react-ui/e2e/nodes-per-node-backend-actions.spec.js

@@ -12,28 +12,37 @@ const NODE_NAME = 'worker-test'
 const BACKEND_NAME = 'cuda12-vllm-development'
 
 async function mockDistributedNodes(page, { onDelete } = {}) {
+  const nodeRecord = {
+    id: NODE_ID,
+    name: NODE_NAME,
+    node_type: 'backend',
+    address: '10.0.0.1:50051',
+    http_address: '10.0.0.1:8090',
+    status: 'healthy',
+    total_vram: 0,
+    available_vram: 0,
+    total_ram: 8_000_000_000,
+    available_ram: 4_000_000_000,
+    gpu_vendor: '',
+    last_heartbeat: new Date().toISOString(),
+    created_at: new Date().toISOString(),
+    updated_at: new Date().toISOString(),
+  }
+
   await page.route('**/api/nodes', (route) => {
     route.fulfill({
       status: 200,
       contentType: 'application/json',
-      body: JSON.stringify([
-        {
-          id: NODE_ID,
-          name: NODE_NAME,
-          node_type: 'backend',
-          address: '10.0.0.1:50051',
-          http_address: '10.0.0.1:8090',
-          status: 'healthy',
-          total_vram: 0,
-          available_vram: 0,
-          total_ram: 8_000_000_000,
-          available_ram: 4_000_000_000,
-          gpu_vendor: '',
-          last_heartbeat: new Date().toISOString(),
-          created_at: new Date().toISOString(),
-          updated_at: new Date().toISOString(),
-        },
-      ]),
+      body: JSON.stringify([nodeRecord]),
+    })
+  })
+
+  // The detail page fetches the single node via nodesApi.get(id).
+  await page.route(`**/api/nodes/${NODE_ID}`, (route) => {
+    route.fulfill({
+      status: 200,
+      contentType: 'application/json',
+      body: JSON.stringify(nodeRecord),
     })
   })
 
@@ -80,24 +89,18 @@ async function mockDistributedNodes(page, { onDelete } = {}) {
   })
 }
 
-async function expandNodeAndWaitForBackends(page) {
-  await page.goto('/app/nodes')
-  // Click the row to expand it. The chevron toggle and the row both work,
-  // but clicking the name cell is the most user-like.
-  await page.getByText(NODE_NAME).first().click()
-  // Backends, Capacity and Labels live behind a "Manage" <details>
-  // disclosure (the drawer was distilled to keep at-a-glance content
-  // lean — see distill refactor in the multi-replica branch). Open it
-  // by clicking the summary inside the .node-manage scope so the
-  // per-node backend table is in the DOM before assertions run.
-  await page.locator('.node-manage > summary').first().click()
+async function openNodeDetail(page) {
+  // The per-node backend table now lives on the deep-linkable detail page
+  // at /app/nodes/:id (the old expand-row + "Manage" disclosure was removed
+  // when the roster was restructured). Navigate straight there.
+  await page.goto(`/app/nodes/${NODE_ID}`)
   await expect(page.getByRole('cell', { name: BACKEND_NAME, exact: true })).toBeVisible({ timeout: 10_000 })
 }
 
 test.describe('Nodes page — per-node backend actions', () => {
   test('upgrade affordance is self-explanatory (not "Reinstall backend" with a sync icon)', async ({ page }) => {
     await mockDistributedNodes(page)
-    await expandNodeAndWaitForBackends(page)
+    await openNodeDetail(page)
 
     // Negative: the old, ambiguous wording must not be used.
     await expect(page.locator('button[title="Reinstall backend"]')).toHaveCount(0)
@@ -114,7 +117,7 @@ test.describe('Nodes page — per-node backend actions', () => {
 
   test('per-node backend row shows a delete (trash) button next to upgrade', async ({ page }) => {
     await mockDistributedNodes(page)
-    await expandNodeAndWaitForBackends(page)
+    await openNodeDetail(page)
 
     const deleteBtn = page.locator('button[title="Delete backend from this node"]')
     await expect(deleteBtn).toBeVisible()
@@ -128,7 +131,7 @@ test.describe('Nodes page — per-node backend actions', () => {
         postedBody = route.request().postDataJSON()
       },
     })
-    await expandNodeAndWaitForBackends(page)
+    await openNodeDetail(page)
 
     await page.locator('button[title="Delete backend from this node"]').click()
 
@@ -150,7 +153,7 @@ test.describe('Nodes page — per-node backend actions', () => {
         deleteCalls += 1
       },
     })
-    await expandNodeAndWaitForBackends(page)
+    await openNodeDetail(page)
 
     await page.locator('button[title="Delete backend from this node"]').click()
 

core/http/react-ui/e2e/nodes-roster.spec.js

@@ -0,0 +1,47 @@
+import { test, expect } from './coverage-fixtures.js'
+
+async function mockCluster(page, nodes) {
+  await page.route('**/api/nodes', r => r.fulfill({ status: 200, contentType: 'application/json', body: JSON.stringify(nodes) }))
+  await page.route('**/api/nodes/models', r => r.fulfill({ status: 200, contentType: 'application/json', body: '[]' }))
+  await page.route('**/api/nodes/scheduling', r => r.fulfill({ status: 200, contentType: 'application/json', body: '[]' }))
+}
+
+test.describe('Nodes roster header', () => {
+  test('shows a cluster pulse line and no stat-card grid', async ({ page }) => {
+    await mockCluster(page, [
+      { id: 'n1', name: 'alpha', node_type: 'backend', address: '10.0.0.1:50051', status: 'healthy' },
+      { id: 'n2', name: 'beta', node_type: 'backend', address: '10.0.0.2:50051', status: 'draining' },
+    ])
+    await page.goto('/app/nodes')
+    await expect(page.locator('.cluster-pulse')).toBeVisible({ timeout: 15_000 })
+    await expect(page.locator('.cluster-pulse')).toContainText('2 nodes')
+    await expect(page.locator('.stat-grid')).toHaveCount(0)
+  })
+
+  test('shows an approval callout for pending nodes', async ({ page }) => {
+    await mockCluster(page, [{ id: 'n3', name: 'gamma', node_type: 'backend', address: '10.0.0.3:50051', status: 'pending' }])
+    await page.goto('/app/nodes')
+    await expect(page.locator('.attention-callout')).toContainText('approval', { timeout: 15_000 })
+  })
+})
+
+test.describe('Nodes roster panels', () => {
+  test('shows model chips without clicking and filters by type', async ({ page }) => {
+    await page.route('**/api/nodes', r => r.fulfill({ status: 200, contentType: 'application/json', body: JSON.stringify([
+      { id: 'n1', name: 'alpha', node_type: 'backend', address: '10.0.0.1:50051', status: 'healthy' },
+      { id: 'a1', name: 'agent-1', node_type: 'agent', address: '10.0.0.9:50051', status: 'healthy' },
+    ]) }))
+    await page.route('**/api/nodes/models', r => r.fulfill({ status: 200, contentType: 'application/json', body: JSON.stringify([
+      { node_id: 'n1', model_name: 'llama-3.3', state: 'loaded', in_flight: 2, replica_index: 0 },
+    ]) }))
+    await page.route('**/api/nodes/scheduling', r => r.fulfill({ status: 200, contentType: 'application/json', body: '[]' }))
+
+    await page.goto('/app/nodes')
+    // model chip visible without any expand click
+    await expect(page.locator('.node-panel').filter({ hasText: 'alpha' }).getByText('llama-3.3')).toBeVisible({ timeout: 15_000 })
+    // segmented filter: Agent shows the agent node, hides the backend node
+    await page.getByRole('radio', { name: /Agent/ }).click()
+    await expect(page.getByText('agent-1')).toBeVisible()
+    await expect(page.getByText('alpha')).toHaveCount(0)
+  })
+})

core/http/react-ui/e2e/page-render-smoke.spec.js

@@ -21,6 +21,7 @@ const PAGES = [
   ['/app/backends', 'Backends'],
   ['/app/settings', 'Settings'],
   ['/app/nodes', 'Nodes'],
+  ['/app/scheduling', 'Scheduling'],
   ['/app/face', 'Face recognition'],
   ['/app/voice', 'Voice recognition'],
   ['/app/fine-tune', 'Fine-tuning'],

core/http/react-ui/e2e/scheduling.spec.js

@@ -0,0 +1,16 @@
+import { test, expect } from './coverage-fixtures.js'
+
+test.describe('Scheduling page', () => {
+  test('renders at /app/scheduling with rules from the API', async ({ page }) => {
+    await page.route('**/api/nodes/scheduling', (route) => {
+      route.fulfill({
+        status: 200, contentType: 'application/json',
+        body: JSON.stringify([{ model_name: 'llama-3.3', spread_all: true, min_replicas: 0, max_replicas: 0 }]),
+      })
+    })
+    await page.goto('/app/scheduling')
+    await expect(page.locator('.page-title').first()).toBeVisible({ timeout: 15_000 })
+    await expect(page).toHaveURL(/\/app\/scheduling$/)
+    await expect(page.getByText('llama-3.3')).toBeVisible()
+  })
+})

core/http/react-ui/public/locales/de/admin.json

@@ -43,6 +43,10 @@
     "title": "Verteilte Knoten",
     "subtitle": "Backend- und Agenten-Worker-Knoten verwalten"
   },
+  "scheduling": {
+    "title": "Planung",
+    "subtitle": "Modellplatzierung und Replikat-Regeln im gesamten Cluster"
+  },
   "p2p": {
     "title": "Verteilte KI-Berechnung",
     "subtitle": "Skalieren Sie Ihre KI-Workloads über mehrere Geräte mit Peer-to-Peer-Verteilung"

core/http/react-ui/public/locales/de/nav.json

@@ -50,6 +50,7 @@
     "backends": "Backends",
     "traces": "Traces",
     "nodes": "Knoten",
+    "scheduling": "Planung",
     "swarm": "Swarm",
     "system": "System",
     "settings": "Einstellungen",

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

@@ -43,6 +43,10 @@
     "title": "Distributed Nodes",
     "subtitle": "Manage backend and agent worker nodes"
   },
+  "scheduling": {
+    "title": "Scheduling",
+    "subtitle": "Model placement and replica rules across the cluster"
+  },
   "p2p": {
     "title": "Distributed AI Computing",
     "subtitle": "Scale your AI workloads across multiple devices with peer-to-peer distribution"

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

@@ -51,6 +51,7 @@
     "backends": "Backends",
     "traces": "Traces",
     "nodes": "Nodes",
+    "scheduling": "Scheduling",
     "swarm": "Swarm",
     "system": "System",
     "settings": "Settings",

core/http/react-ui/public/locales/es/admin.json

@@ -43,6 +43,10 @@
     "title": "Nodos distribuidos",
     "subtitle": "Administra nodos worker de backends y agentes"
   },
+  "scheduling": {
+    "title": "Planificación",
+    "subtitle": "Reglas de ubicación de modelos y réplicas en el clúster"
+  },
   "p2p": {
     "title": "Computación de IA distribuida",
     "subtitle": "Escala tus cargas de trabajo de IA en múltiples dispositivos con distribución peer-to-peer"

core/http/react-ui/public/locales/es/nav.json

@@ -50,6 +50,7 @@
     "backends": "Backends",
     "traces": "Trazas",
     "nodes": "Nodos",
+    "scheduling": "Planificación",
     "swarm": "Swarm",
     "system": "Sistema",
     "settings": "Configuración",

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

@@ -43,6 +43,10 @@
     "title": "Node Terdistribusi",
     "subtitle": "Kelola node backend dan node worker"
   },
+  "scheduling": {
+    "title": "Penjadwalan",
+    "subtitle": "Aturan penempatan model dan replika di seluruh kluster"
+  },
   "p2p": {
     "title": "Komputasi AI Terdistribusi",
     "subtitle": "Skalakan beban kerja AI Anda ke beberapa perangkat dengan distribusi peer-to-peer"
@@ -82,4 +86,4 @@
     "title": "Penjelajah",
     "subtitle": "Jelajahi file dan konfigurasi"
   }
-}
+}

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

@@ -72,7 +72,7 @@
   "actions": {
     "copy": "Salin",
     "regenerate": "Hasilkan ulang",
-    "jumpToLatest": "Jump to latest"
+    "jumpToLatest": "Lompat ke terbaru"
   },
   "streaming": {
     "transferring": "Mentransfer model...",
@@ -115,4 +115,4 @@
     "clearAll": "Hapus semua",
     "deleteAllTitle": "Hapus semua percakapan"
   }
-}
+}

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

@@ -1,8 +1,8 @@
 {
   "unsaved": {
-    "title": "Discard unsaved changes?",
-    "message": "You have unsaved changes that will be lost if you leave this page.",
-    "leave": "Leave"
+    "title": "Buang perubahan yang belum disimpan?",
+    "message": "Anda memiliki perubahan yang belum disimpan. Perubahan tersebut akan hilang jika Anda meninggalkan halaman ini.",
+    "leave": "Tinggalkan Halaman"
   },
   "actions": {
     "save": "Simpan",

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

@@ -7,15 +7,15 @@
   "resourceGpu": "GPU",
   "resourceRam": "RAM",
   "greeting": {
-    "morning": "Good morning",
-    "afternoon": "Good afternoon",
-    "evening": "Good evening",
-    "night": "Working late"
+    "morning": "Selamat pagi",
+    "afternoon": "Selamat siang",
+    "evening": "Selamat malam",
+    "night": "Selamat lembur"
   },
   "statusLine": {
-    "modelsLoaded_one": "{{count}} model loaded",
-    "modelsLoaded_other": "{{count}} models loaded",
-    "noModelsLoaded": "No models loaded",
+    "modelsLoaded_one": "{{count}} model dimuat",
+    "modelsLoaded_other": "{{count}} model dimuat",
+    "noModelsLoaded": "Tidak ada model yang dimuat",
     "nodes_one": "{{count}} node",
     "nodes_other": "{{count}} nodes"
   },
@@ -79,14 +79,14 @@
   },
   "connect": {
     "title": "Satu endpoint, semua API",
-    "subtitle": "LocalAI menyediakan API miliknya sendiri yang lengkap — pembuatan gambar & video, depth, deteksi objek, reranking, audio, pengenalan wajah & suara, serta suara realtime melalui WebRTC dan WebSocket. Di atas itu, lapisan kompatibilitas drop-in membuat aplikasi apa pun yang dibuat untuk OpenAI, Anthropic, Ollama, atau OpenAI Responses bekerja tanpa perubahan.",
+    "subtitle": "LocalAI menyediakan API miliknya sendiri yang lengkap — pembuatan gambar & video, depth, deteksi objek, reranking, audio, pengenalan wajah & suara, serta suara realtime melalui WebRTC dan WebSocket. Selain itu, lapisan kompatibilitas drop-in membuat aplikasi apa pun yang dibuat untuk OpenAI, Anthropic, Ollama, atau OpenAI Responses bekerja tanpa perubahan.",
     "nativeTitle": "API native",
     "compatTitle": "Kompatibilitas drop-in",
     "apiReference": "Referensi API lengkap",
     "copy": "Salin",
     "copied": "Disalin",
-    "browse": "Browse the API",
-    "hide": "Hide endpoints",
-    "dismiss": "Dismiss"
+    "browse": "Jelajahi API",
+    "hide": "Sembunyikan endpoint",
+    "dismiss": "Abaikan"
   }
 }

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

@@ -5,7 +5,7 @@
       "video": "Video",
       "tts": "TTS",
       "sound": "Suara",
-      "transform": "Transform"
+      "transform": "Transformasi"
     }
   },
   "image": {
@@ -30,7 +30,7 @@
       "refImagesAdded_other": "{{count}} gambar ditambahkan"
     },
     "actions": {
-      "view": "View",
+      "view": "Lihat",
       "generate": "Hasilkan",
       "generating": "Menghasilkan..."
     },
@@ -153,4 +153,4 @@
     "clearConfirm": "Hapus",
     "cleared": "Riwayat dihapus"
   }
-}
+}

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

@@ -19,11 +19,11 @@
     "operate": "Operasikan"
   },
   "operate": {
-    "inference": "Inference",
-    "cluster": "Cluster",
-    "observability": "Observability",
-    "access": "Access",
-    "system": "System"
+    "inference": "Inferensi",
+    "cluster": "Kluster",
+    "observability": "Observabilitas",
+    "access": "Akses",
+    "system": "Sistem"
   },
   "items": {
     "home": "Beranda",
@@ -51,6 +51,7 @@
     "backends": "Backend",
     "traces": "Trace",
     "nodes": "Node",
+    "scheduling": "Penjadwalan",
     "swarm": "Swarm",
     "system": "Sistem",
     "settings": "Pengaturan",
@@ -63,7 +64,7 @@
     "copyright": "© 2023-{{year}} {{author}}"
   },
   "console": {
-    "automation": "Otomasi",
+    "automation": "Automasi",
     "training": "Pelatihan"
   }
 }

core/http/react-ui/public/locales/it/admin.json

@@ -43,6 +43,10 @@
     "title": "Nodi distribuiti",
     "subtitle": "Gestisci i nodi worker dei backend e degli agenti"
   },
+  "scheduling": {
+    "title": "Pianificazione",
+    "subtitle": "Regole di posizionamento dei modelli e delle repliche nel cluster"
+  },
   "p2p": {
     "title": "Calcolo AI distribuito",
     "subtitle": "Scala i tuoi carichi di lavoro AI su più dispositivi con la distribuzione peer-to-peer"

core/http/react-ui/public/locales/it/nav.json

@@ -50,6 +50,7 @@
     "backends": "Backend",
     "traces": "Tracce",
     "nodes": "Nodi",
+    "scheduling": "Pianificazione",
     "swarm": "Swarm",
     "system": "Sistema",
     "settings": "Impostazioni",

core/http/react-ui/public/locales/ko/admin.json

@@ -43,6 +43,10 @@
     "title": "분산 노드",
     "subtitle": "백엔드 및 에이전트 워커 노드를 관리합니다"
   },
+  "scheduling": {
+    "title": "스케줄링",
+    "subtitle": "클러스터 전반의 모델 배치 및 복제본 규칙"
+  },
   "p2p": {
     "title": "분산 AI 컴퓨팅",
     "subtitle": "피어 투 피어 분산으로 여러 기기에 걸쳐 AI 워크로드를 확장합니다"

core/http/react-ui/public/locales/ko/nav.json

@@ -51,6 +51,7 @@
     "backends": "백엔드",
     "traces": "트레이스",
     "nodes": "노드",
+    "scheduling": "스케줄링",
     "swarm": "Swarm",
     "system": "시스템",
     "settings": "설정",

core/http/react-ui/public/locales/zh-CN/admin.json

@@ -43,6 +43,10 @@
     "title": "分布式节点",
     "subtitle": "管理后端和智能体工作节点"
   },
+  "scheduling": {
+    "title": "调度",
+    "subtitle": "集群中的模型放置和副本规则"
+  },
   "p2p": {
     "title": "分布式 AI 计算",
     "subtitle": "通过点对点分发将您的 AI 工作负载扩展到多个设备"

core/http/react-ui/public/locales/zh-CN/nav.json

@@ -50,6 +50,7 @@
     "backends": "后端",
     "traces": "追踪",
     "nodes": "节点",
+    "scheduling": "调度",
     "swarm": "Swarm",
     "system": "系统",
     "settings": "设置",

core/http/react-ui/src/App.css

@@ -8471,3 +8471,56 @@ select.input {
 .status-pill--error   .status-pill__dot { background: var(--color-error); }
 .status-pill--info    .status-pill__dot { background: var(--color-info); }
 .status-pill--muted   .status-pill__dot { background: var(--color-text-muted); }
+
+/* Nodes: cluster pulse + attention callout (replaces the stat-card strip) */
+.cluster-pulse {
+  font-size: var(--text-sm);
+  color: var(--color-text-muted);
+  margin: 0 0 var(--spacing-lg);
+}
+.cluster-pulse__strong { color: var(--color-text-primary); font-weight: 600; }
+
+.attention-callout {
+  display: flex;
+  align-items: center;
+  justify-content: space-between;
+  gap: var(--spacing-md);
+  padding: var(--spacing-sm) var(--spacing-md);
+  border-radius: var(--radius-md);
+  margin-bottom: var(--spacing-lg);
+  font-size: var(--text-sm);
+}
+.attention-callout--warn {
+  background: var(--color-warning-light);
+  border: 1px solid var(--color-warning-border);
+  color: var(--color-text-primary);
+}
+.attention-callout--error {
+  background: var(--color-error-light);
+  border: 1px solid var(--color-error-border);
+  color: var(--color-text-primary);
+}
+
+/* Node roster panels (Nodes page) */
+.node-roster { display: flex; flex-direction: column; gap: var(--spacing-sm); }
+.node-panel {
+  background: var(--color-bg-secondary);
+  border: 1px solid var(--color-border-subtle);
+  border-radius: var(--radius-lg);
+}
+.node-panel__main { padding: var(--spacing-md) var(--spacing-lg); cursor: pointer; }
+.node-panel:hover { border-color: var(--color-border); }
+.node-panel__head { display: flex; align-items: flex-start; justify-content: space-between; gap: var(--spacing-md); }
+.node-panel__id { display: flex; align-items: center; gap: var(--spacing-sm); flex-wrap: wrap; }
+.node-panel__name { font-weight: 600; }
+.node-panel__meta { display: flex; gap: var(--spacing-lg); margin-top: var(--spacing-sm); color: var(--color-text-muted); font-size: var(--text-xs); }
+.node-panel__models { display: flex; flex-wrap: wrap; gap: 6px; margin-top: var(--spacing-sm); }
+.model-chip {
+  display: inline-flex; align-items: center; gap: 5px;
+  font-family: var(--font-mono); font-size: 0.6875rem;
+  padding: 2px 8px; border-radius: var(--radius-sm); border: 1px solid;
+}
+.model-chip__dot { width: 6px; height: 6px; border-radius: 50%; }
+.model-chip__state { opacity: 0.85; font-style: normal; }
+.node-filter { margin-bottom: var(--spacing-lg); }
+.node-detail__metrics { display: flex; gap: var(--spacing-xl); margin: var(--spacing-md) 0 var(--spacing-lg); flex-wrap: wrap; }

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

@@ -74,7 +74,18 @@ export default function PatternListEditor({ value, onChange }) {
             min={0}
             value={r.min_len || 0}
             title="Minimum match length (0 = no floor)"
-            onChange={e => update(i, { min_len: parseInt(e.target.value, 10) || 0 })}
+            // min={0} only constrains the spinner, not keyboard entry. Clamp a
+            // typed negative to 0 (a negative floor is meaningless and would
+            // disable the length filter). When we clamp, force the DOM value
+            // too: the resulting 0->0 state change is a no-op, so React's
+            // controlled input would otherwise keep displaying the rejected
+            // "-5" even though the saved value is 0.
+            onChange={e => {
+              const parsed = parseInt(e.target.value, 10)
+              const n = Math.max(0, parsed || 0)
+              if (parsed < 0) e.target.value = String(n)
+              update(i, { min_len: n })
+            }}
             style={{ width: 80, fontSize: '0.8125rem' }}
             aria-label="Minimum length"
           />