chore: sync dev to main

.devcontainer/Dockerfile

@@ -0,0 +1,18 @@
+FROM mcr.microsoft.com/devcontainers/cpp:1-ubuntu-24.04
+
+ARG REINSTALL_CMAKE_VERSION_FROM_SOURCE="none"
+
+# Optionally install the cmake for vcpkg
+COPY ./reinstall-cmake.sh /tmp/
+
+RUN if [ "${REINSTALL_CMAKE_VERSION_FROM_SOURCE}" != "none" ]; then \
+        chmod +x /tmp/reinstall-cmake.sh && /tmp/reinstall-cmake.sh ${REINSTALL_CMAKE_VERSION_FROM_SOURCE}; \
+    fi \
+    && rm -f /tmp/reinstall-cmake.sh
+
+# [Optional] Uncomment this section to install additional vcpkg ports.
+# RUN su vscode -c "${VCPKG_ROOT}/vcpkg install <your-port-name-here>"
+
+# [Optional] Uncomment this section to install additional packages.
+# RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
+#     && apt-get -y install --no-install-recommends <your-package-list-here>

.devcontainer/devcontainer.json

@@ -0,0 +1,35 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/cpp
+{
+	"hostRequirements": {
+		"cpus": 4,
+		"memory": "8gb",
+		"storage": "32gb"
+	},
+	"name": "C++",
+	"build": {
+		"dockerfile": "Dockerfile"
+	},
+	"features": {
+		"ghcr.io/stuartleeks/dev-container-features/shell-history:0": {},
+		"ghcr.io/sebst/devcontainer-features/pkgx:1": {},
+		"ghcr.io/devcontainers-extra/features/apt-packages:1": {
+			"clean_ppas": true,
+			"preserve_apt_list": true,
+			"packages": "build-essential linux-libc-dev",
+			"ppas": "ppa:deadsnakes/ppa"
+		}
+	},
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+	// Use 'postCreateCommand' to run commands after the container is created.
+	"postCreateCommand": "git submodule update --init",
+	// Use 'postAttachCommand' to run commands after the container is attached.
+	"postAttachCommand": "pkgx install npx && npx -y runme run --filename README.md -t devcontainer -y"
+	// Configure tool-specific properties.
+	// "customizations": {},
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.devcontainer/reinstall-cmake.sh

@@ -0,0 +1,59 @@
+#!/usr/bin/env bash
+#-------------------------------------------------------------------------------------------------------------
+# Copyright (c) Microsoft Corporation. All rights reserved.
+# Licensed under the MIT License. See https://go.microsoft.com/fwlink/?linkid=2090316 for license information.
+#-------------------------------------------------------------------------------------------------------------
+#
+set -e
+
+CMAKE_VERSION=${1:-"none"}
+
+if [ "${CMAKE_VERSION}" = "none" ]; then
+    echo "No CMake version specified, skipping CMake reinstallation"
+    exit 0
+fi
+
+# Cleanup temporary directory and associated files when exiting the script.
+cleanup() {
+    EXIT_CODE=$?
+    set +e
+    if [[ -n "${TMP_DIR}" ]]; then
+        echo "Executing cleanup of tmp files"
+        rm -Rf "${TMP_DIR}"
+    fi
+    exit $EXIT_CODE
+}
+trap cleanup EXIT
+
+
+echo "Installing CMake..."
+apt-get -y purge --auto-remove cmake
+mkdir -p /opt/cmake
+
+architecture=$(dpkg --print-architecture)
+case "${architecture}" in
+    arm64)
+        ARCH=aarch64 ;;
+    amd64)
+        ARCH=x86_64 ;;
+    *)
+        echo "Unsupported architecture ${architecture}."
+        exit 1
+        ;;
+esac
+
+CMAKE_BINARY_NAME="cmake-${CMAKE_VERSION}-linux-${ARCH}.sh"
+CMAKE_CHECKSUM_NAME="cmake-${CMAKE_VERSION}-SHA-256.txt"
+TMP_DIR=$(mktemp -d -t cmake-XXXXXXXXXX)
+
+echo "${TMP_DIR}"
+cd "${TMP_DIR}"
+
+curl -sSL "https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/${CMAKE_BINARY_NAME}" -O
+curl -sSL "https://github.com/Kitware/CMake/releases/download/v${CMAKE_VERSION}/${CMAKE_CHECKSUM_NAME}" -O
+
+sha256sum -c --ignore-missing "${CMAKE_CHECKSUM_NAME}"
+sh "${TMP_DIR}/${CMAKE_BINARY_NAME}" --prefix=/opt/cmake --skip-license
+
+ln -s /opt/cmake/bin/cmake /usr/local/bin/cmake
+ln -s /opt/cmake/bin/ctest /usr/local/bin/ctest

.github/workflows/beta-build.yml

@@ -156,9 +156,9 @@ jobs:
               - Network Installer: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-amd64-network-installer.deb
               - Local Installer: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-amd64-local-installer.deb
               - Binary: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-amd64.tar.gz
-            - Linux amd64 Deb:
+            - Linux arm64 Deb:
               - Network Installer: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-arm64-network-installer.deb
               - Local Installer: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-arm64-local-installer.deb
               - Binary: https://github.com/janhq/cortex.cpp/releases/download/v${{ env.VERSION }}/cortex-${{ env.VERSION }}-linux-arm64.tar.gz
             - Docker: menloltd/cortex:beta-${{ env.VERSION }}
-            - Github Release: https://github.com/janhq/cortex.cpp/releases/tag/v${{ env.VERSION }}
+            - Github Release: https://github.com/janhq/cortex.cpp/releases/tag/v${{ env.VERSION }}

.github/workflows/cortex-cpp-quality-gate.yml

@@ -14,6 +14,7 @@ env:
 
 jobs:
   build-and-test:
+    if: (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository) || github.event_name == 'workflow_dispatch'
     runs-on: ${{ matrix.runs-on }}
     timeout-minutes: 60
     strategy:
@@ -255,6 +256,7 @@ jobs:
           AWS_DEFAULT_REGION: "${{ secrets.MINIO_REGION }}"
 
   build-docker-and-test:
+    if: (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository) || github.event_name == 'workflow_dispatch'
     runs-on: ubuntu-24-04-docker
     steps:
       - name: Getting the repo
@@ -309,3 +311,249 @@ jobs:
           docker stop cortex
           docker rm cortex
           echo "y\n" | docker system prune -af
+
+  build-and-test-target-pr:
+    permissions:
+      contents: read
+    if: github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name != github.repository
+    runs-on: ${{ matrix.runs-on }}
+    timeout-minutes: 60
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - os: "linux"
+            name: "arm64"
+            runs-on: "ubuntu-2004-arm64"
+            cmake-flags: "-DCORTEX_CPP_VERSION=${{github.event.pull_request.head.sha}} -DCMAKE_BUILD_TEST=ON -DCMAKE_TOOLCHAIN_FILE=vcpkg/scripts/buildsystems/vcpkg.cmake"
+            build-deps-cmake-flags: ""
+            ccache-dir: ""
+          - os: "linux"
+            name: "amd64"
+            runs-on: "ubuntu-20-04-cuda-12-0"
+            cmake-flags: "-DCORTEX_CPP_VERSION=${{github.event.pull_request.head.sha}} -DCMAKE_BUILD_TEST=ON -DCMAKE_TOOLCHAIN_FILE=vcpkg/scripts/buildsystems/vcpkg.cmake"
+            build-deps-cmake-flags: ""
+            ccache-dir: ""
+          - os: "mac"
+            name: "amd64"
+            runs-on: "macos-selfhosted-12"
+            cmake-flags: "-DCORTEX_CPP_VERSION=${{github.event.pull_request.head.sha}} -DCMAKE_BUILD_TEST=ON -DCMAKE_TOOLCHAIN_FILE=vcpkg/scripts/buildsystems/vcpkg.cmake"
+            build-deps-cmake-flags: ""
+            ccache-dir: ""
+          - os: "mac"
+            name: "arm64"
+            runs-on: "macos-selfhosted-12-arm64"
+            cmake-flags: "-DCORTEX_CPP_VERSION=${{github.event.pull_request.head.sha}} -DCMAKE_BUILD_TEST=ON -DMAC_ARM64=ON -DCMAKE_TOOLCHAIN_FILE=vcpkg/scripts/buildsystems/vcpkg.cmake"
+            build-deps-cmake-flags: ""
+            ccache-dir: ""
+          - os: "windows"
+            name: "amd64"
+            runs-on: "windows-cuda-12-0"
+            cmake-flags: "-DCORTEX_CPP_VERSION=${{github.event.pull_request.head.sha}} -DCMAKE_BUILD_TEST=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_TOOLCHAIN_FILE=C:/w/cortex.cpp/cortex.cpp/engine/vcpkg/scripts/buildsystems/vcpkg.cmake -DVCPKG_TARGET_TRIPLET=x64-windows-static -DCMAKE_BUILD_TYPE=RELEASE -DCMAKE_CXX_COMPILER_LAUNCHER=ccache -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache -GNinja"
+            build-deps-cmake-flags: "-DCMAKE_CXX_COMPILER_LAUNCHER=ccache -DCMAKE_C_COMPILER_LAUNCHER=ccache -DCMAKE_CUDA_COMPILER_LAUNCHER=ccache -GNinja"
+            ccache-dir: 'C:\Users\ContainerAdministrator\AppData\Local\ccache'
+    steps:
+      - name: Clone
+        id: checkout
+        uses: actions/checkout@v3
+        with:
+          submodules: recursive
+
+      - name: use python
+        continue-on-error: true
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Install tools on Linux
+        if: runner.os == 'Linux'
+        run: |
+          python3 -m pip install awscli
+
+      - name: Install choco on Windows
+        if: runner.os == 'Windows'
+        run: |
+          choco install make pkgconfiglite ccache awscli 7zip ninja -y
+
+      - name: Configure vcpkg
+        if: runner.os != 'Linux'
+        run: |
+          cd engine
+          make configure-vcpkg
+
+      - name: Configure vcpkg linux amd64
+        if: runner.os != 'Linux'
+        run: |
+          cd engine
+          make configure-vcpkg
+
+      - name: Configure vcpkg linux arm64
+        if: runner.os == 'Linux'
+        run: |
+          cd engine
+          # Set env if arch is arm64
+          if [ "${{ matrix.name }}" == "arm64" ]; then
+            sudo apt install ninja-build pkg-config -y
+            export VCPKG_FORCE_SYSTEM_BINARIES=1
+          fi
+          make configure-vcpkg
+
+      - name: Build
+        if: runner.os != 'Linux'
+        run: |
+          cd engine
+          make build CMAKE_EXTRA_FLAGS="${{ matrix.cmake-flags }}" BUILD_DEPS_CMAKE_EXTRA_FLAGS="${{ matrix.build-deps-cmake-flags }}"
+
+      - name: Build
+        if: runner.os == 'Linux'
+        run: |
+          cd engine
+          if [ "${{ matrix.name }}" == "arm64" ]; then
+            export VCPKG_FORCE_SYSTEM_BINARIES=1
+          fi
+          make build CMAKE_EXTRA_FLAGS="${{ matrix.cmake-flags }}" BUILD_DEPS_CMAKE_EXTRA_FLAGS="${{ matrix.build-deps-cmake-flags }}"
+
+      - name: Run setup config
+        run: |
+          cd engine
+          echo "gitHubToken: ${{ secrets.GITHUB_TOKEN }}" > ~/.cortexrc
+          # ./build/cortex
+          cat ~/.cortexrc
+
+      - name: Run unit tests
+        run: |
+          cd engine
+          make run-unit-tests
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_SERVICE_ACCOUNT }}
+
+      - name: Run setup config
+        run: |
+          cd engine
+          echo "apiServerPort: 3928" > ~/.cortexrc
+          echo "gitHubToken: ${{ secrets.GITHUB_TOKEN }}" > ~/.cortexrc
+          # ./build/cortex
+          cat ~/.cortexrc
+
+      - name: Run e2e tests
+        if: github.event_name != 'schedule' && runner.os != 'Windows' && github.event.pull_request.draft == false
+        run: |
+          cd engine
+          cp build/cortex build/cortex-nightly
+          cp build/cortex build/cortex-beta
+          python -m pip install --upgrade pip
+          python -m pip install -r e2e-test/requirements.txt
+          python e2e-test/main.py
+          rm build/cortex-nightly
+          rm build/cortex-beta
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_SERVICE_ACCOUNT }}
+
+      - name: Run e2e tests
+        if: github.event_name != 'schedule' && runner.os == 'Windows' && github.event.pull_request.draft == false
+        run: |
+          cd engine
+          cp build/cortex.exe build/cortex-nightly.exe
+          cp build/cortex.exe build/cortex-beta.exe
+          python -m pip install --upgrade pip
+          python -m pip install -r e2e-test/requirements.txt
+          python e2e-test/main.py
+          rm build/cortex-nightly.exe
+          rm build/cortex-beta.exe
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_SERVICE_ACCOUNT }}
+
+      - name: Run e2e tests
+        if: github.event_name == 'schedule' && runner.os != 'Windows' && github.event.pull_request.draft == false
+        run: |
+          cd engine
+          cp build/cortex build/cortex-nightly
+          cp build/cortex build/cortex-beta
+          python -m pip install --upgrade pip
+          python -m pip install -r e2e-test/requirements.txt
+          python e2e-test/cortex-llamacpp-e2e-nightly.py
+          rm build/cortex-nightly
+          rm build/cortex-beta
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_SERVICE_ACCOUNT }}
+
+      - name: Run e2e tests
+        if: github.event_name == 'schedule' &&  runner.os == 'Windows' && github.event.pull_request.draft == false
+        run: |
+          cd engine
+          cp build/cortex.exe build/cortex-nightly.exe
+          cp build/cortex.exe build/cortex-beta.exe
+          python -m pip install --upgrade pip
+          python -m pip install -r e2e-test/requirements.txt
+          python e2e-test/cortex-llamacpp-e2e-nightly.py
+          rm build/cortex-nightly.exe
+          rm build/cortex-beta.exe
+        env:
+          GITHUB_TOKEN: ${{ secrets.PAT_SERVICE_ACCOUNT }}
+
+      - name: Pre-package
+        run: |
+          cd engine
+          make pre-package DESTINATION_BINARY_NAME="cortex"
+
+      - name: Package
+        run: |
+          cd engine
+          make package
+
+      - name: Upload Artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: cortex-${{ matrix.os }}-${{ matrix.name }}
+          path: ./engine/cortex
+
+  build-docker-and-test-target-pr:
+    permissions:
+      contents: read
+    if: github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name != github.repository
+    runs-on: ubuntu-24-04-docker
+    steps:
+      - name: Getting the repo
+        uses: actions/checkout@v3
+        with:
+          submodules: 'recursive'
+
+      - name: Run Docker
+        if: github.event_name != 'schedule'
+        run: |
+          docker build \
+            -t menloltd/cortex:test -f docker/Dockerfile .
+          docker run -it -d -p 3928:39281 --name cortex menloltd/cortex:test
+          sleep 20
+
+      - name: Run Docker
+        if: github.event_name == 'schedule'
+        run: |
+          latest_prerelease=$(curl -s https://api.github.com/repos/cortexcpp/cortex.cpp/releases | jq -r '.[] | select(.prerelease == true) | .tag_name' | head -n 1)
+          echo "cortex.llamacpp latest release: $latest_prerelease"
+          docker build \
+            --build-arg CORTEX_CPP_VERSION="${latest_prerelease}" \
+            -t menloltd/cortex:test -f docker/Dockerfile .
+          docker run -it -d -p 3928:39281 --name cortex menloltd/cortex:test
+          sleep 20
+
+      - name: use python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+
+      - name: Run e2e tests
+        run: |
+          cd engine
+          python -m pip install --upgrade pip
+          python -m pip install -r e2e-test/requirements.txt
+          pytest e2e-test/test_api_docker.py
+
+      - name: Run Docker
+        continue-on-error: true
+        if: always()  
+        run: |
+          docker logs cortex
+          docker stop cortex
+          docker rm cortex
+          echo "y\n" | docker system prune -af