[pull] master from mudler:master

.agents/ci-caching.md

@@ -125,7 +125,7 @@ The per-backend prefix match only sees files under a backend's own directory, so
 | `backend/backend.proto` | nothing if the edit is additive-only, otherwise everything (see below) |
 | `backend/Dockerfile.<x>` | the Linux entries whose `dockerfile:` names it |
 | `backend/python/common/` | Python, Linux + Darwin |
-| `scripts/build/package-gpu-libs.sh` | Python, Linux only |
+| `scripts/build/package-gpu-libs.sh` | every Linux entry (Python, Go and C++ all run it) |
 | `scripts/build/<lang>-darwin.sh` | the Darwin entries that build target routes to |
 | `.github/workflows/backend_build[_darwin].yml` | everything on that OS |
 | anything else under `scripts/build/` (except `*_test.sh`) | everything — conservative default for unclassified packaging inputs |

.docker/install-base-deps.sh

@@ -113,6 +113,54 @@ if [ "${BUILD_TYPE:-}" = "vulkan" ] && [ "${SKIP_DRIVERS:-false}" = "false" ]; t
     rm -rf /var/lib/apt/lists/*
 fi
 
+# --- 2b. Intel graphics driver (BUILD_TYPE=sycl*) ---
+# The Intel oneAPI base image brings the compilers and the oneAPI libraries, but
+# not the driver that talks to the graphics card. The packaging step copies that
+# driver into the backend, so that the backend works on a machine which has no
+# Intel graphics packages of its own, for the same reason the Vulkan section
+# above installs the Mesa drivers. Install it here so there is something to copy.
+#
+# Only the sycl builds are covered, because those are the ones whose packaging
+# copies the driver. See package_intel_libs in scripts/build/package-gpu-libs.sh.
+#
+# The driver comes from Intel's own package repository, not from the Ubuntu
+# archive. The archive has 23.43 from late 2023, which does not know any card
+# released since, so a machine with a recent Intel GPU would end up carrying a
+# driver that cannot drive it. Intel's repository has 25.18 for the same Ubuntu
+# release.
+#
+# Anything that goes wrong here fails the build, on purpose. An unreachable
+# repository is a passing problem that a retry fixes, whereas carrying a
+# different driver than intended, or none, is a difference nobody would notice
+# until a user reports an idle GPU.
+if case "${BUILD_TYPE:-}" in sycl*) true;; *) false;; esac \
+    && [ "${SKIP_DRIVERS:-false}" = "false" ]; then
+    # Ubuntu release name, which is what the repository is indexed by.
+    ubuntu_codename=$(. /etc/os-release && echo "${VERSION_CODENAME:-}")
+    if [ -z "$ubuntu_codename" ]; then
+        echo "ERROR: cannot tell which Ubuntu release this image is, so cannot pick the Intel driver repository" >&2
+        exit 1
+    fi
+
+    # The key is armored text, which apt reads directly from a .asc file, so
+    # there is no need for gnupg here. "unified" is the component Intel ships
+    # its current driver in.
+    mkdir -p /usr/share/keyrings
+    curl -fsSL https://repositories.intel.com/gpu/intel-graphics.key \
+        -o /usr/share/keyrings/intel-graphics.asc
+    echo "deb [arch=amd64 signed-by=/usr/share/keyrings/intel-graphics.asc] https://repositories.intel.com/gpu/ubuntu ${ubuntu_codename} unified" \
+        > /etc/apt/sources.list.d/intel-graphics.list
+    apt-get update
+    # The first package holds the driver OpenCL talks to, the second the driver
+    # Level Zero talks to. Between them they pull in the compiler and the memory
+    # manager that both need.
+    apt-get install -y --no-install-recommends \
+        intel-opencl-icd \
+        libze-intel-gpu1
+    apt-get clean
+    rm -rf /var/lib/apt/lists/*
+fi
+
 # --- 3. CUDA toolkit (BUILD_TYPE=cublas|l4t) ---
 if { [ "${BUILD_TYPE:-}" = "cublas" ] || [ "${BUILD_TYPE:-}" = "l4t" ]; } && [ "${SKIP_DRIVERS:-false}" = "false" ]; then
     apt-get update

.github/ci/refresh-site-counters.sh

@@ -0,0 +1,64 @@
+#!/usr/bin/env bash
+# Refreshes the counters shown on the landing page from the GitHub API.
+#
+# The numbers used to be typed into the templates by hand, which meant they
+# only moved when somebody remembered, and a stale star count on the front
+# page is worse than no star count. Everything the API can answer for lives
+# in website/data/stats.yaml and is rewritten wholesale by this script.
+#
+# Anything the API cannot answer for (the Discord member count) is read back
+# out of the existing file and carried through untouched.
+set -euo pipefail
+
+REPO="${REPO:-mudler/LocalAI}"
+OUT="${OUT:-website/data/stats.yaml}"
+
+# The contributors and releases endpoints are paginated and never report a
+# total. Asking for one item per page makes the last page number equal to the
+# item count, which the Link header hands over.
+count_via_link_header() {
+  local path="$1" link last
+  link=$(gh api -i "${path}?per_page=1" 2>/dev/null | tr -d '\r' | grep -i '^link:' || true)
+  if [ -z "$link" ]; then
+    # No Link header means a single page, so count that page directly.
+    gh api "${path}?per_page=100" --jq 'length'
+    return
+  fi
+  last=$(sed -n 's/.*[?&]page=\([0-9]*\)>; rel="last".*/\1/p' <<<"$link")
+  [ -n "$last" ] || { gh api "${path}?per_page=100" --jq 'length'; return; }
+  printf '%s\n' "$last"
+}
+
+read -r stars forks < <(gh api "repos/${REPO}" --jq '"\(.stargazers_count) \(.forks_count)"')
+contributors=$(count_via_link_header "repos/${REPO}/contributors")
+releases=$(count_via_link_header "repos/${REPO}/releases")
+
+# Not derivable from the GitHub API, so keep whatever is already on disk.
+discord=$(sed -n 's/^discord: *\([0-9]*\).*/\1/p' "$OUT" 2>/dev/null | head -1)
+discord="${discord:-0}"
+
+for n in stars forks contributors releases; do
+  v="${!n}"
+  [[ "$v" =~ ^[0-9]+$ ]] && [ "$v" -gt 0 ] || {
+    echo "refusing to write: ${n} came back as '${v}'" >&2
+    exit 1
+  }
+done
+
+cat > "$OUT" <<YAML
+# Counters shown on the landing page.
+#
+# The four GitHub fields are rewritten by .github/ci/refresh-site-counters.sh,
+# which runs weekly from .github/workflows/refresh-site-counters.yml. Editing
+# them by hand works but will be overwritten on the next run.
+stars: ${stars}
+forks: ${forks}
+contributors: ${contributors}
+releases: ${releases}
+
+# The GitHub API cannot answer for this one, so it is maintained by hand and
+# the refresh script carries it through untouched.
+discord: ${discord}
+YAML
+
+echo "stars=${stars} forks=${forks} contributors=${contributors} releases=${releases} discord=${discord}"

.github/workflows/refresh-site-counters.yml

@@ -0,0 +1,44 @@
+name: Refresh site counters
+
+# The landing page shows a star count, a contributor count and a release
+# count. They were typed in by hand, so they drifted the moment somebody
+# forgot. This pulls the real numbers once a week and commits them only when
+# they have actually moved, which in turn triggers the usual Pages deploy.
+
+on:
+  schedule:
+    # Mondays, 06:17 UTC. Off the hour on purpose, since the scheduler queues
+    # everything that asks for :00 and drops what it cannot run.
+    - cron: '17 6 * * 1'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+concurrency:
+  group: refresh-site-counters
+  cancel-in-progress: false
+
+jobs:
+  refresh:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Read the counts off the GitHub API
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: ./.github/ci/refresh-site-counters.sh
+
+      - name: Commit only if something moved
+        run: |
+          if git diff --quiet -- website/data/stats.yaml; then
+            echo "counters unchanged, nothing to commit"
+            exit 0
+          fi
+          git diff --unified=0 -- website/data/stats.yaml
+          git config user.name  "github-actions[bot]"
+          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git add website/data/stats.yaml
+          git commit -m "chore(website): refresh the counters"
+          git push

backend/cpp/audio-cpp/Makefile

@@ -9,7 +9,7 @@
 # recipe is a make target (not a prepare.sh) so 'make purge && make' is a clean
 # rebuild and so the bump bot can see the pin.
 
-AUDIO_CPP_VERSION?=f32876cfb45732dd4f43264e9104d229e95b0bc3
+AUDIO_CPP_VERSION?=f78227c52736a4792a50aa3f82ead7e7385c891b
 AUDIO_CPP_REPO?=https://github.com/0xShug0/audio.cpp
 
 CURRENT_MAKEFILE_DIR := $(dir $(abspath $(lastword $(MAKEFILE_LIST))))

backend/cpp/bonsai/run.sh

@@ -40,6 +40,27 @@ else
 	if [ -d "$CURDIR/lib/hipblaslt/library" ]; then
 		export HIPBLASLT_TENSILE_LIBPATH="$CURDIR"/lib/hipblaslt/library
 	fi
+	# Backends built for Intel GPUs carry a copy of the Intel graphics driver,
+	# and libze_loader is only there in those builds. Level Zero looks for a
+	# driver on its own, so point it at the copy that came with this backend: it
+	# was built against the same C library, while the machine's own driver may
+	# not have been, and loading that one can crash on start.
+	#
+	# Anything the user set is left alone, so a machine with a graphics card
+	# newer than the driver carried here can still be told to use its own.
+	# Nothing is said about OpenCL: no OpenCL driver is carried, so anything we
+	# set there would leave OpenCL worse off than the machine's own setup.
+	if [ -e "$CURDIR/lib/libze_loader.so.1" ]; then
+		if [ -e "$CURDIR/lib/libze_intel_gpu.so.1" ] && [ -z "${ZE_ENABLE_ALT_DRIVERS:-}" ]; then
+			export ZE_ENABLE_ALT_DRIVERS="$CURDIR"/lib/libze_intel_gpu.so.1
+		fi
+		# Ask the driver how much graphics memory is free. Without this, the
+		# backend reads zero on an integrated graphics chip, because such a chip
+		# shares the system memory instead of having its own.
+		if [ -z "${ZES_ENABLE_SYSMAN:-}" ]; then
+			export ZES_ENABLE_SYSMAN=1
+		fi
+	fi
 fi
 
 # If there is a lib/ld.so, use it

backend/cpp/ik-llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-IK_LLAMA_VERSION?=9992f6b515ee63c7d6f7beee6b8414b0a6d1dd43
+IK_LLAMA_VERSION?=3f53a059024039358e9fef75b5dc0c99dbcb40f9
 LLAMA_REPO?=https://github.com/ikawrakow/ik_llama.cpp
 
 CMAKE_ARGS?=

backend/cpp/llama-cpp/run.sh

@@ -42,6 +42,27 @@ else
 	if [ -d "$CURDIR/lib/hipblaslt/library" ]; then
 		export HIPBLASLT_TENSILE_LIBPATH="$CURDIR"/lib/hipblaslt/library
 	fi
+	# Backends built for Intel GPUs carry a copy of the Intel graphics driver,
+	# and libze_loader is only there in those builds. Level Zero looks for a
+	# driver on its own, so point it at the copy that came with this backend: it
+	# was built against the same C library, while the machine's own driver may
+	# not have been, and loading that one can crash on start.
+	#
+	# Anything the user set is left alone, so a machine with a graphics card
+	# newer than the driver carried here can still be told to use its own.
+	# Nothing is said about OpenCL: no OpenCL driver is carried, so anything we
+	# set there would leave OpenCL worse off than the machine's own setup.
+	if [ -e "$CURDIR/lib/libze_loader.so.1" ]; then
+		if [ -e "$CURDIR/lib/libze_intel_gpu.so.1" ] && [ -z "${ZE_ENABLE_ALT_DRIVERS:-}" ]; then
+			export ZE_ENABLE_ALT_DRIVERS="$CURDIR"/lib/libze_intel_gpu.so.1
+		fi
+		# Ask the driver how much graphics memory is free. Without this,
+		# llama.cpp reads zero on an integrated graphics chip, because such a
+		# chip shares the system memory instead of having its own.
+		if [ -z "${ZES_ENABLE_SYSMAN:-}" ]; then
+			export ZES_ENABLE_SYSMAN=1
+		fi
+	fi
 fi
 
 # If there is a lib/ld.so, use it

backend/cpp/turboquant/run.sh

@@ -40,6 +40,27 @@ else
 	if [ -d "$CURDIR/lib/hipblaslt/library" ]; then
 		export HIPBLASLT_TENSILE_LIBPATH="$CURDIR"/lib/hipblaslt/library
 	fi
+	# Backends built for Intel GPUs carry a copy of the Intel graphics driver,
+	# and libze_loader is only there in those builds. Level Zero looks for a
+	# driver on its own, so point it at the copy that came with this backend: it
+	# was built against the same C library, while the machine's own driver may
+	# not have been, and loading that one can crash on start.
+	#
+	# Anything the user set is left alone, so a machine with a graphics card
+	# newer than the driver carried here can still be told to use its own.
+	# Nothing is said about OpenCL: no OpenCL driver is carried, so anything we
+	# set there would leave OpenCL worse off than the machine's own setup.
+	if [ -e "$CURDIR/lib/libze_loader.so.1" ]; then
+		if [ -e "$CURDIR/lib/libze_intel_gpu.so.1" ] && [ -z "${ZE_ENABLE_ALT_DRIVERS:-}" ]; then
+			export ZE_ENABLE_ALT_DRIVERS="$CURDIR"/lib/libze_intel_gpu.so.1
+		fi
+		# Ask the driver how much graphics memory is free. Without this, the
+		# backend reads zero on an integrated graphics chip, because such a chip
+		# shares the system memory instead of having its own.
+		if [ -z "${ZES_ENABLE_SYSMAN:-}" ]; then
+			export ZES_ENABLE_SYSMAN=1
+		fi
+	fi
 fi
 
 # If there is a lib/ld.so, use it

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?=677e95d0e60010f10636c3a0b1ba215b38a4a943
+CRISPASR_VERSION?=b5211ac635489049ee8ce86a82d69faa18e8d8da
 SO_TARGET?=libgocrispasr.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

backend/go/rfdetr-cpp/Makefile

@@ -11,7 +11,7 @@ JOBS?=$(shell nproc --ignore=1)
 # build; leaving this on `master` always picks up the latest C-API surface
 # (incl. the per-detection accessor functions used by gorfdetrcpp.go).
 RFDETR_REPO?=https://github.com/localai-org/rf-detr.cpp.git
-RFDETR_VERSION?=65c0ffcc9a9bc9dae38252f63d0417c9845a6cf7
+RFDETR_VERSION?=98d0f381b832ef08a608b65c7dd78db066ed8b9a
 
 ifeq ($(NATIVE),false)
 	CMAKE_ARGS+=-DGGML_NATIVE=OFF

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?=4523d0ce373ee4b2176b3251fff29fd4864fcf38
+WHISPER_CPP_VERSION?=2ca53bb45e38748d07b310eeb36245a7157ac882
 SO_TARGET?=libgowhisper.so
 
 CMAKE_ARGS+=-DBUILD_SHARED_LIBS=OFF

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

@@ -3,6 +3,7 @@ import { test, expect } from './coverage-fixtures.js'
 // Seeds two-message chat into localStorage so we don't need a live model.
 async function seedChat(page, history) {
   await page.addInitScript((h) => {
+    if (localStorage.getItem('localai_chats_data')) return
     const chat = {
       id: 'seed1', name: 'Seeded Chat', model: 'test-model',
       history: h, systemPrompt: '', mcpMode: false, mcpServers: [],
@@ -33,6 +34,56 @@ const TWO_TURNS = [
   { role: 'assistant', content: 'second answer' },
 ]
 
+test('saved message edits persist without sending a completion request', async ({ page }) => {
+  await mockModels(page)
+  let completionRequests = 0
+  await page.route('**/v1/chat/completions', (route) => {
+    completionRequests++
+    route.abort()
+  })
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  const firstUser = page.locator('.chat-message-user').first()
+  await firstUser.hover()
+  await firstUser.getByTitle('Edit').click()
+  await firstUser.getByRole('textbox').fill('edited first question')
+  await firstUser.getByRole('button', { name: 'Save' }).click()
+
+  const firstAssistant = page.locator('.chat-message-assistant').first()
+  await firstAssistant.hover()
+  await firstAssistant.getByTitle('Edit').click()
+  await firstAssistant.getByRole('textbox').fill('edited first answer')
+  await firstAssistant.getByRole('button', { name: 'Save' }).click()
+
+  await expect(firstUser).toContainText('edited first question')
+  await expect(firstAssistant).toContainText('edited first answer')
+  await expect.poll(() => page.evaluate(() => {
+    const data = JSON.parse(localStorage.getItem('localai_chats_data'))
+    return data.chats[0].history.slice(0, 2).map(message => message.content)
+  })).toEqual(['edited first question', 'edited first answer'])
+
+  await page.reload()
+  await expect(page.locator('.chat-message-user').first()).toContainText('edited first question')
+  await expect(page.locator('.chat-message-assistant').first()).toContainText('edited first answer')
+  expect(completionRequests).toBe(0)
+})
+
+test('cancelling a message edit leaves the original content unchanged', async ({ page }) => {
+  await mockModels(page)
+  await seedChat(page, TWO_TURNS)
+  await page.goto('/app/chat')
+
+  const firstUser = page.locator('.chat-message-user').first()
+  await firstUser.hover()
+  await firstUser.getByTitle('Edit').click()
+  await firstUser.getByRole('textbox').fill('discard this draft')
+  await firstUser.getByRole('button', { name: 'Cancel' }).click()
+
+  await expect(firstUser).toContainText('first question')
+  await expect(firstUser).not.toContainText('discard this draft')
+})
+
 test('duplicate creates an independent copy and switches to it', async ({ page }) => {
   await mockModels(page)
   await seedChat(page, TWO_TURNS)
@@ -112,6 +163,29 @@ const FILE_TURNS = [
   { role: 'assistant', content: 'nope, that is it' },
 ]
 
+test('editing a file prompt preserves its content blocks and attachment metadata', async ({ page }) => {
+  await mockModels(page)
+  await seedChat(page, FILE_TURNS)
+  await page.goto('/app/chat')
+
+  const firstUser = page.locator('.chat-message-user').first()
+  await firstUser.hover()
+  await firstUser.getByTitle('Edit').click()
+  await firstUser.getByRole('textbox').fill('edited file question')
+  await firstUser.getByRole('button', { name: 'Save' }).click()
+
+  await expect.poll(() => page.evaluate(() => {
+    const data = JSON.parse(localStorage.getItem('localai_chats_data'))
+    return data.chats[0].history[0]
+  })).toEqual({
+    ...FILE_TURNS[0],
+    content: [
+      { type: 'text', text: 'edited file question' },
+      FILE_TURNS[0].content[1],
+    ],
+  })
+})
+
 test('regenerating a non-last answer in a fork still sends the uploaded file content', async ({ page }) => {
   await mockModels(page)
   let sentMessages = null