chore: fixes

2026-09-07 08:26:10 +00:00 · 2026-04-05 01:14:47 -07:00 · 2026-04-05 01:14:47 -07:00 · d96f87014d
commit d96f87014d
parent 8f425ec3ff
58 changed files with 1594 additions and 1348 deletions
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
--- a/.circleci/requirements.txt
+++ b/.circleci/requirements.txt
@ -7,15 +7,15 @@ cohere
 redis==5.2.1
 redisvl==0.4.1
 anthropic
-orjson==3.10.12 # fast /embedding responses
-pydantic==2.11.0
-google-cloud-aiplatform==1.43.0
+orjson==3.10.15 # fast /embedding responses
+pydantic==2.12.5
+google-cloud-aiplatform==1.133.0
 google-cloud-iam==2.19.1
 fastapi-sso==0.16.0 
 uvloop==0.21.0
-mcp==1.25.0    # for MCP server  
+mcp==1.26.0    # for MCP server
 semantic_router==0.1.10 # for auto-routing with litellm
-fastuuid==0.12.0
+fastuuid==0.14.0
 responses==0.25.7  # for proxy client tests
 pytest-retry==1.6.3  # for automatic test retries
 litellm-proxy-extras  # for prisma migrations
--- a/.github/actions/helm-oci-chart-releaser/action.yml
+++ b/.github/actions/helm-oci-chart-releaser/action.yml
@ -41,32 +41,54 @@ runs:
  using: composite
  steps:
    - name: Helm | Setup
-      uses: azure/setup-helm@v4
+      uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
      with:
        version: v3.20.0

    - name: Helm | Login
      shell: bash
-      run: echo ${{ inputs.registry_password }} | helm registry login -u ${{ inputs.registry_username }} --password-stdin ${{ inputs.registry }}
+      env:
+        REGISTRY_PASSWORD: ${{ inputs.registry_password }}
+        REGISTRY_USERNAME: ${{ inputs.registry_username }}
+        REGISTRY: ${{ inputs.registry }}
+      run: echo "$REGISTRY_PASSWORD" | helm registry login -u "$REGISTRY_USERNAME" --password-stdin "$REGISTRY"

    - name: Helm | Dependency
      if: inputs.update_dependencies == 'true'
      shell: bash
-      run: helm dependency update ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+      env:
+        CHART_PATH: ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+      run: helm dependency update "$CHART_PATH"

    - name: Helm | Package
      shell: bash
-      run: helm package ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }} --version ${{ inputs.tag }} --app-version ${{ inputs.app_version }}
+      env:
+        CHART_PATH: ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+        TAG: ${{ inputs.tag }}
+        APP_VERSION: ${{ inputs.app_version }}
+      run: helm package "$CHART_PATH" --version "$TAG" --app-version "$APP_VERSION"

    - name: Helm | Push
      shell: bash
-      run: helm push ${{ inputs.name }}-${{ inputs.tag }}.tgz oci://${{ inputs.registry }}/${{ inputs.repository }}
+      env:
+        NAME: ${{ inputs.name }}
+        TAG: ${{ inputs.tag }}
+        REGISTRY: ${{ inputs.registry }}
+        REPOSITORY: ${{ inputs.repository }}
+      run: helm push "${NAME}-${TAG}.tgz" "oci://${REGISTRY}/${REPOSITORY}"

    - name: Helm | Logout
      shell: bash
-      run: helm registry logout ${{ inputs.registry }}
+      env:
+        REGISTRY: ${{ inputs.registry }}
+      run: helm registry logout "$REGISTRY"

    - name: Helm | Output
      id: output
      shell: bash
-      run: echo "image=${{ inputs.registry }}/${{ inputs.repository }}/${{ inputs.name }}:${{ inputs.tag }}" >> $GITHUB_OUTPUT
+      env:
+        REGISTRY: ${{ inputs.registry }}
+        REPOSITORY: ${{ inputs.repository }}
+        NAME: ${{ inputs.name }}
+        TAG: ${{ inputs.tag }}
+      run: echo "image=${REGISTRY}/${REPOSITORY}/${NAME}:${TAG}" >> $GITHUB_OUTPUT
--- a/.github/dependabot.yaml
+++ b/.github/dependabot.yaml
@ -4,6 +4,9 @@ updates:
    directory: "/"
    schedule:
      interval: "daily"
+    cooldown:
+      default-days: 7
+      semver-major-days: 14
    groups:
      github-actions:
        patterns:
--- a/.github/workflows/_test-unit-base.yml
+++ b/.github/workflows/_test-unit-base.yml
@ -0,0 +1,96 @@
+name: _Unit Test Base (Reusable)
+
+on:
+  workflow_call:
+    inputs:
+      test-path:
+        description: "Pytest path(s) to run"
+        required: true
+        type: string
+      workers:
+        description: "Number of pytest-xdist workers"
+        required: false
+        type: number
+        default: 2
+      reruns:
+        description: "Number of reruns for flaky tests"
+        required: false
+        type: number
+        default: 2
+      timeout-minutes:
+        description: "Job timeout in minutes"
+        required: false
+        type: number
+        default: 20
+      max-failures:
+        description: "Stop after this many failures"
+        required: false
+        type: number
+        default: 10
+
+permissions:
+  contents: read
+
+jobs:
+  run:
+    name: Run tests
+    runs-on: ubuntu-latest
+    timeout-minutes: ${{ inputs.timeout-minutes }}
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Install Poetry
+        run: pip install 'poetry==2.3.2'
+
+      - name: Cache Poetry dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+            .venv
+          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+
+      - name: Install dependencies
+        run: |
+          poetry config virtualenvs.in-project true
+          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
+          poetry run pip install google-genai==1.22.0 \
+            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
+
+      - name: Setup litellm-enterprise
+        run: |
+          poetry run pip install --force-reinstall --no-deps -e enterprise/
+
+      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
+          poetry run prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Run tests
+        env:
+          TEST_PATH: ${{ inputs.test-path }}
+          MAX_FAILURES: ${{ inputs.max-failures }}
+          WORKERS: ${{ inputs.workers }}
+          RERUNS: ${{ inputs.reruns }}
+        run: |
+          poetry run pytest ${TEST_PATH:?} \
+            --tb=short -vv \
+            --maxfail="${MAX_FAILURES}" \
+            -n "${WORKERS}" \
+            --reruns "${RERUNS}" \
+            --reruns-delay 1 \
+            --dist=loadscope \
+            --durations=20
--- a/.github/workflows/_test-unit-services-base.yml
+++ b/.github/workflows/_test-unit-services-base.yml
@ -0,0 +1,164 @@
+name: _Unit Test Services Base (Reusable)
+
+on:
+  workflow_call:
+    inputs:
+      test-path:
+        description: "Pytest path(s) to run"
+        required: true
+        type: string
+      workers:
+        description: "Number of pytest-xdist workers (0 = no parallelism)"
+        required: false
+        type: number
+        default: 2
+      reruns:
+        description: "Number of reruns for flaky tests"
+        required: false
+        type: number
+        default: 2
+      timeout-minutes:
+        description: "Job timeout in minutes"
+        required: false
+        type: number
+        default: 20
+      max-failures:
+        description: "Stop after this many failures"
+        required: false
+        type: number
+        default: 10
+      enable-redis:
+        description: "Pass Redis Cloud credentials to tests via REDIS_HOST/PORT/PASSWORD env vars"
+        required: false
+        type: boolean
+        default: false
+      enable-postgres:
+        description: "Start a local Postgres service container and run Prisma migrations"
+        required: false
+        type: boolean
+        default: false
+    secrets:
+      REDIS_HOST:
+        required: false
+      REDIS_PORT:
+        required: false
+      REDIS_PASSWORD:
+        required: false
+      DATABASE_URL:
+        required: false
+      POSTGRES_USER:
+        required: false
+      POSTGRES_PASSWORD:
+        required: false
+
+permissions:
+  contents: read
+
+jobs:
+  run:
+    name: Run tests
+    runs-on: ubuntu-latest
+    timeout-minutes: ${{ inputs.timeout-minutes }}
+    # Environment is derived from the enable-* flags, not caller-controllable.
+    # This prevents callers from passing arbitrary environment names to bypass secret scoping.
+    # Note: Postgres service container always starts (GHA limitation), so any Redis job
+    # also needs Postgres secrets → uses integration-redis-postgres, not integration-redis.
+    environment: >-
+      ${{
+        inputs.enable-redis && 'integration-redis-postgres' ||
+        inputs.enable-postgres && 'integration-postgres' ||
+        ''
+      }}
+
+    services:
+      postgres:
+        image: postgres@sha256:705a5d5b5836f3fcba0d02c4d281e6a7dd9ed2dd4078640f08a1e1e9896e097d # postgres:14
+        env:
+          POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
+          POSTGRES_DB: litellm_test
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd "pg_isready"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Install Poetry
+        run: pip install 'poetry==2.3.2'
+
+      - name: Cache Poetry dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+            .venv
+          key: ${{ runner.os }}-poetry-services-${{ hashFiles('poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-services-
+
+      - name: Install dependencies
+        run: |
+          poetry config virtualenvs.in-project true
+          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
+          poetry run pip install google-genai==1.22.0 \
+            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
+
+      - name: Setup litellm-enterprise
+        run: |
+          poetry run pip install --force-reinstall --no-deps -e enterprise/
+
+      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
+          poetry run prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Run Prisma migrations
+        if: ${{ inputs.enable-postgres }}
+        env:
+          DATABASE_URL: ${{ secrets.DATABASE_URL }}
+        run: |
+          poetry run prisma db push --schema litellm/proxy/schema.prisma --accept-data-loss
+
+      - name: Run tests
+        env:
+          TEST_PATH: ${{ inputs.test-path }}
+          MAX_FAILURES: ${{ inputs.max-failures }}
+          WORKERS: ${{ inputs.workers }}
+          RERUNS: ${{ inputs.reruns }}
+          DATABASE_URL: ${{ inputs.enable-postgres && secrets.DATABASE_URL || '' }}
+          REDIS_HOST: ${{ inputs.enable-redis && secrets.REDIS_HOST || '' }}
+          REDIS_PORT: ${{ inputs.enable-redis && secrets.REDIS_PORT || '' }}
+          REDIS_PASSWORD: ${{ inputs.enable-redis && secrets.REDIS_PASSWORD || '' }}
+        run: |
+          if [ "${WORKERS}" = "0" ]; then
+            poetry run pytest ${TEST_PATH:?} \
+              --tb=short -vv \
+              --maxfail="${MAX_FAILURES}" \
+              --reruns "${RERUNS}" \
+              --reruns-delay 1 \
+              --durations=20
+          else
+            poetry run pytest ${TEST_PATH:?} \
+              --tb=short -vv \
+              --maxfail="${MAX_FAILURES}" \
+              -n "${WORKERS}" \
+              --reruns "${RERUNS}" \
+              --reruns-delay 1 \
+              --dist=loadscope \
+              --durations=20
+          fi
--- a/.github/workflows/auto_update_price_and_context_window.yml
+++ b/.github/workflows/auto_update_price_and_context_window.yml
@ -5,12 +5,18 @@ on:
    - cron: "0 0 * * 0" # Run every Sundays at midnight
    #- cron: "0 0 * * *" # Run daily at midnight

+permissions:
+  contents: write
+  pull-requests: write
+
 jobs:
  auto_update_price_and_context_window:
    if: github.repository == 'BerriAI/litellm'
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
      - name: Install Dependencies
        run: |
          pip install 'aiohttp==3.13.3'
--- a/.github/workflows/check-schema-sync.yml
+++ b/.github/workflows/check-schema-sync.yml
@ -0,0 +1,58 @@
+name: Check Schema Sync
+
+on:
+  pull_request:
+    paths:
+      - 'schema.prisma'
+      - 'litellm/proxy/schema.prisma'
+      - 'litellm-proxy-extras/litellm_proxy_extras/schema.prisma'
+
+permissions:
+  contents: read
+
+jobs:
+  check-sync:
+    name: Verify schema.prisma copies match root
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    steps:
+      - name: Checkout PR
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Reject symlinked schema files
+        run: |
+          for f in schema.prisma litellm/proxy/schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma; do
+            if [ -L "$f" ]; then
+              echo "::error file=$f::$f is a symlink, which is not allowed"
+              exit 1
+            fi
+          done
+
+      - name: Check all schemas match root
+        run: |
+          EXIT=0
+
+          diff schema.prisma litellm/proxy/schema.prisma || {
+            echo "::error file=litellm/proxy/schema.prisma::litellm/proxy/schema.prisma differs from root schema.prisma"
+            EXIT=1
+          }
+
+          diff schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma || {
+            echo "::error file=litellm-proxy-extras/litellm_proxy_extras/schema.prisma::litellm-proxy-extras/litellm_proxy_extras/schema.prisma differs from root schema.prisma"
+            EXIT=1
+          }
+
+          if [ "$EXIT" -ne 0 ]; then
+            echo ""
+            echo "Schema files are out of sync."
+            echo "The root schema.prisma is the source of truth."
+            echo ""
+            echo "To fix, run from the repo root:"
+            echo "  cp schema.prisma litellm/proxy/schema.prisma"
+            echo "  cp schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma"
+            exit 1
+          fi
+
+          echo "All schema copies are in sync with root."
--- a/.github/workflows/check_duplicate_issues.yml
+++ b/.github/workflows/check_duplicate_issues.yml
@ -33,6 +33,7 @@ jobs:
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          sparse-checkout: .github/scripts
+          persist-credentials: false

      - name: Set up Python
        if: github.event.action == 'opened'
--- a/.github/workflows/codeql.yml
+++ b/.github/workflows/codeql.yml
@ -6,8 +6,8 @@ on:
  pull_request:
    branches: [main]
  schedule:
-    # Run weekly on Sundays at 04:00 UTC
-    - cron: "0 4 * * 0"
+    # Run daily at 04:00 UTC
+    - cron: "0 4 * * *"

 concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
@ -39,6 +39,8 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Initialize CodeQL
        uses: github/codeql-action/init@ebcb5b36ded6beda4ceefea6a8bc4cc885255bb3 # v3
--- a/.github/workflows/codspeed.yml
+++ b/.github/workflows/codspeed.yml
@ -26,6 +26,8 @@ jobs:

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
--- a/.github/workflows/create-release.yml
+++ b/.github/workflows/create-release.yml
@ -0,0 +1,93 @@
+name: Create Release
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Release tag (e.g. v1.83.0-stable)"
+        required: true
+        type: string
+      commit_hash:
+        description: "Full 40-char commit SHA to target"
+        required: true
+        type: string
+
+permissions: {}
+
+jobs:
+  release:
+    name: Create Release
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Validate inputs
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        run: |
+          if ! echo "${COMMIT_HASH}" | grep -qE '^[0-9a-f]{40}$'; then
+            echo "::error::commit_hash must be a full 40-character commit SHA"
+            exit 1
+          fi
+          if ! echo "${TAG}" | grep -qE '^v[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::tag must start with vX.Y.Z"
+            exit 1
+          fi
+
+      - name: Create release
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const tag = process.env.TAG;
+            const commitHash = process.env.COMMIT_HASH;
+
+            const cosignSection = [
+              `## Verify Docker Image Signature`,
+              ``,
+              `All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). To verify the integrity of an image before deploying:`,
+              ``,
+              '```bash',
+              `cosign verify \\`,
+              `  --key https://raw.githubusercontent.com/BerriAI/litellm/${tag}/cosign.pub \\`,
+              `  ghcr.io/berriai/litellm:${tag}`,
+              '```',
+              ``,
+              `Expected output:`,
+              ``,
+              '```',
+              `The following checks were performed on each of these signatures:`,
+              `  - The cosign claims were validated`,
+              `  - The signatures were verified against the specified public key`,
+              '```',
+              ``,
+              `---`,
+              ``,
+            ].join('\n');
+
+            try {
+              const response = await github.rest.repos.createRelease({
+                draft: true,
+                generate_release_notes: true,
+                target_commitish: commitHash,
+                name: tag,
+                owner: context.repo.owner,
+                prerelease: false,
+                repo: context.repo.repo,
+                tag_name: tag,
+              });
+
+              const updatedBody = cosignSection + (response.data.body ?? '');
+              await github.rest.repos.updateRelease({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                release_id: response.data.id,
+                body: updatedBody,
+                draft: false,
+              });
+            } catch (error) {
+              core.setFailed(error.message);
+            }
--- a/.github/workflows/create_daily_staging_branch.yml
+++ b/.github/workflows/create_daily_staging_branch.yml
@ -9,12 +9,15 @@ jobs:
  create-staging-branch:
    if: github.repository == 'BerriAI/litellm'
    runs-on: ubuntu-latest
+    permissions:
+      contents: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          fetch-depth: 0
+          persist-credentials: false

      - name: Create daily staging branch
        env:
@ -46,12 +49,15 @@ jobs:
  create-internal-dev-branch:
    if: github.repository == 'BerriAI/litellm'
    runs-on: ubuntu-latest
+    permissions:
+      contents: write

    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          fetch-depth: 0
+          persist-credentials: false

      - name: Create internal dev branch
        env:
--- a/.github/workflows/helm_unit_test.yml
+++ b/.github/workflows/helm_unit_test.yml
@ -6,12 +6,17 @@ on:
    branches:
      - main

+permissions:
+  contents: read
+
 jobs:
  unit-test:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Set up Helm 3.11.1
        uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
--- a/.github/workflows/issue-keyword-labeler.yml
+++ b/.github/workflows/issue-keyword-labeler.yml
@ -14,6 +14,8 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Scan for provider keywords
        id: scan
--- a/.github/workflows/llm-translation-testing.yml
+++ b/.github/workflows/llm-translation-testing.yml
@ -11,6 +11,9 @@ on:
    tags:
      - "v*-rc*" # Triggers on release candidate tags like v1.0.0-rc1

+permissions:
+  contents: read
+
 jobs:
  run-llm-translation-tests:
    runs-on: ubuntu-latest
@ -20,6 +23,7 @@ jobs:
      - name: Checkout code
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
+          persist-credentials: false
          ref: ${{ github.event.inputs.release_candidate_tag || github.ref }}

      - name: Set up Python
@ -33,8 +37,8 @@ jobs:
          poetry config virtualenvs.create true
          poetry config virtualenvs.in-project true

-      - name: Cache Poetry dependencies
-        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.0.0
+      - name: Restore Poetry dependencies cache
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.0.0
        with:
          path: |
            ~/.cache/pypoetry
@ -60,11 +64,12 @@ jobs:
          AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
          AZURE_API_BASE: ${{ secrets.AZURE_API_BASE }}
          AZURE_API_VERSION: ${{ secrets.AZURE_API_VERSION }}
-          # Add other API keys as needed
+          RC_TAG: ${{ github.event.inputs.release_candidate_tag || github.ref_name }}
+          COMMIT_SHA: ${{ github.sha }}
        run: |
          python .github/workflows/run_llm_translation_tests.py \
-            --tag "${{ github.event.inputs.release_candidate_tag || github.ref_name }}" \
-            --commit "${{ github.sha }}" \
+            --tag "$RC_TAG" \
+            --commit "$COMMIT_SHA" \
            || true  # Continue even if tests fail

      - name: Display test summary
--- a/.github/workflows/publish_to_pypi.yml
+++ b/.github/workflows/publish_to_pypi.yml
@ -0,0 +1,136 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  preflight-checks:
+    name: Preflight Checks
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+    # No environment — read-only checks, no approval needed
+    outputs:
+      needs_publish: ${{ steps.check-litellm.outputs.needs_publish }}
+      version: ${{ steps.check-litellm.outputs.version }}
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Check litellm version on PyPI
+        id: check-litellm
+        run: |
+          VERSION=$(grep -m1 '^version' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
+          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
+          echo "Checking if litellm $VERSION exists on PyPI..."
+
+          HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://pypi.org/pypi/litellm/$VERSION/json")
+          if [ "$HTTP_STATUS" = "200" ]; then
+            echo "litellm $VERSION already exists on PyPI. Skipping publish."
+            echo "needs_publish=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "litellm $VERSION not found on PyPI. Publish needed."
+            echo "needs_publish=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Sanity check proxy-extras version
+        run: |
+          # Read pinned version from requirements.txt
+          REQ_VERSION=$(grep -oP 'litellm-proxy-extras==\K[0-9.]+' requirements.txt)
+          if [ -z "$REQ_VERSION" ]; then
+            echo "::error::Could not find litellm-proxy-extras version in requirements.txt"
+            exit 1
+          fi
+          echo "requirements.txt pins litellm-proxy-extras==$REQ_VERSION"
+
+          # Read pinned version from pyproject.toml dependency
+          PYPROJECT_VERSION=$(python3 -c "
+          import re
+          with open('pyproject.toml') as f:
+              content = f.read()
+          match = re.search(r'litellm-proxy-extras\s*=\s*\{version\s*=\s*\"([^\"]+)\"', content)
+          if match:
+              print(match.group(1).lstrip('^~>='))
+          else:
+              import sys
+              print('::error::Could not find litellm-proxy-extras dependency in pyproject.toml', file=sys.stderr)
+              sys.exit(1)
+          ")
+          echo "pyproject.toml pins litellm-proxy-extras version: $PYPROJECT_VERSION"
+
+          # Check that both pinned versions match
+          if [ "$REQ_VERSION" != "$PYPROJECT_VERSION" ]; then
+            echo "::error::Version mismatch: requirements.txt has $REQ_VERSION but pyproject.toml has $PYPROJECT_VERSION"
+            exit 1
+          fi
+
+          # Check that the pinned version exists on PyPI
+          echo "Checking if litellm-proxy-extras $REQ_VERSION exists on PyPI..."
+          HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://pypi.org/pypi/litellm-proxy-extras/$REQ_VERSION/json")
+          if [ "$HTTP_STATUS" != "200" ]; then
+            echo "::error::litellm-proxy-extras $REQ_VERSION is not published on PyPI yet. Publish it before releasing litellm."
+            exit 1
+          fi
+          echo "litellm-proxy-extras $REQ_VERSION exists on PyPI. Sanity check passed."
+
+  publish-litellm:
+    name: Publish litellm to PyPI
+    needs: preflight-checks
+    if: needs.preflight-checks.outputs.needs_publish == 'true'
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      id-token: write
+      contents: read
+    environment: pypi-publish
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Copy model prices backup
+        run: cp model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json
+
+      - name: Install build tools
+        run: python -m pip install --upgrade pip build==1.4.2
+
+      - name: Build package
+        run: |
+          rm -rf build dist
+          python -m build
+
+      - name: Verify build artifacts
+        env:
+          EXPECTED_VERSION: ${{ needs.preflight-checks.outputs.version }}
+        run: |
+          echo "Contents of dist/:"
+          ls -la dist/
+          # Ensure we have both sdist and wheel
+          ls dist/*.tar.gz
+          ls dist/*.whl
+          # Verify built version matches expected
+          ls dist/ | grep -q "litellm-${EXPECTED_VERSION}" || {
+            echo "::error::Built artifacts do not match expected version $EXPECTED_VERSION"
+            ls dist/
+            exit 1
+          }
+
+      - name: Validate package metadata
+        run: |
+          pip install twine==6.2.0
+          twine check dist/*
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0
--- a/.github/workflows/read_pyproject_version.yml
+++ b/.github/workflows/read_pyproject_version.yml
@ -5,6 +5,9 @@ on:
    branches:
      - main # Change this to the default branch of your repository

+permissions:
+  contents: read
+
 jobs:
  read-version:
    runs-on: ubuntu-latest
@ -12,6 +15,8 @@ jobs:
    steps:
      - name: Checkout code
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Read version from pyproject.toml
        id: read-version
--- a/.github/workflows/run_llm_translation_tests.py
+++ b/.github/workflows/run_llm_translation_tests.py
--- a/.github/workflows/run_observatory_tests.yml
+++ b/.github/workflows/run_observatory_tests.yml
@ -34,6 +34,8 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Validate tag input
        env:
@ -49,11 +51,12 @@ jobs:
          TAG: ${{ inputs.tag }}
          AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
          AZURE_API_BASE: ${{ secrets.AZURE_API_BASE }}
+          WORKSPACE: ${{ github.workspace }}
        run: |
          docker run -d \
            --name litellm-rc \
            -p 4000:4000 \
-            -v "${{ github.workspace }}/.github/observatory/litellm_config.yaml:/app/config.yaml" \
+            -v "${WORKSPACE}/.github/observatory/litellm_config.yaml:/app/config.yaml" \
            -e LITELLM_MASTER_KEY="${LITELLM_MASTER_KEY}" \
            -e AZURE_API_KEY="${AZURE_API_KEY}" \
            -e AZURE_API_BASE="${AZURE_API_BASE}" \
@ -104,11 +107,11 @@ jobs:

      - name: Verify tunnel connectivity
        run: |
-          echo "Testing tunnel at ${{ env.TUNNEL_URL }}..."
+          echo "Testing tunnel at ${TUNNEL_URL}..."
          # Quick tunnels need time for DNS propagation; retry to avoid
          # transient NXDOMAIN (curl exit code 6) on first attempt.
          for i in $(seq 1 10); do
-            if curl -sf "${{ env.TUNNEL_URL }}/health/liveliness" > /dev/null 2>&1; then
+            if curl -sf "${TUNNEL_URL}/health/liveliness" > /dev/null 2>&1; then
              echo "Tunnel is working (attempt $i)"
              exit 0
            fi
@ -222,5 +225,5 @@ jobs:
      - name: Cleanup
        if: always()
        run: |
-          kill "${{ env.CLOUDFLARED_PID }}" 2>/dev/null || true
+          kill "$CLOUDFLARED_PID" 2>/dev/null || true
          docker rm -f litellm-rc 2>/dev/null || true
--- a/.github/workflows/scan_duplicate_issues.yml
+++ b/.github/workflows/scan_duplicate_issues.yml
@ -24,6 +24,7 @@ jobs:
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          sparse-checkout: .github/scripts
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
--- a/.github/workflows/scorecard.yml
+++ b/.github/workflows/scorecard.yml
@ -0,0 +1,47 @@
+name: Scorecard supply-chain security
+
+on:
+  branch_protection_rule:
+  schedule:
+    - cron: '27 12 * * 4'
+  push:
+    branches: ["main"]
+
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    if: github.event.repository.default_branch == github.ref_name
+    permissions:
+      security-events: write
+      id-token: write
+      # Uncomment for private repos if needed:
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          persist-credentials: false
+
+      - name: Run analysis
+        uses: ossf/scorecard-action@f49aabe0b5af0936a0987cfb85d86b75731b0186 # v2.4.1
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          publish_results: true
+
+      - name: Upload artifact
+        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      - name: Upload to code scanning
+        uses: github/codeql-action/upload-sarif@c10b8064de6f491fea524254123dbe5e09572f13 # v4.35.1
+        with:
+          sarif_file: results.sarif
--- a/.github/workflows/stale.yml
+++ b/.github/workflows/stale.yml
@ -5,6 +5,10 @@ on:
    - cron: "0 0 * * *" # Runs daily at midnight UTC
  workflow_dispatch:

+permissions:
+  issues: write
+  pull-requests: write
+
 jobs:
  stale:
    if: github.repository == 'BerriAI/litellm'
--- a/.github/workflows/sync-schema.yml
+++ b/.github/workflows/sync-schema.yml
@ -0,0 +1,73 @@
+name: Sync schema.prisma copies
+
+on:
+  pull_request:
+    paths:
+      - 'schema.prisma'
+
+# Scoped to ONLY the permissions needed:
+# - contents:write to push the sync commit to the PR branch
+# - pull-requests:read is implicit (needed to check out the PR)
+permissions:
+  contents: write
+
+jobs:
+  sync:
+    name: Copy root schema to proxy and proxy-extras
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    # Only run on PRs from branches in THIS repo (not forks).
+    # Fork PRs cannot push back to the head branch with GITHUB_TOKEN,
+    # and pull_request events from forks have read-only tokens anyway.
+    # Also reject PRs from branches named after protected branches to
+    # prevent pushing directly to main/master.
+    if: >-
+      github.event.pull_request.head.repo.full_name == github.repository
+      && github.head_ref != 'main'
+      && github.head_ref != 'master'
+    steps:
+      - name: Checkout PR branch by SHA
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          # Use the merge commit SHA for safety — github.head_ref is an
+          # attacker-controlled string (the branch name) and could contain
+          # unusual characters that cause unexpected git behavior.
+          ref: ${{ github.event.pull_request.head.sha }}
+          persist-credentials: true  # needed for git push
+
+      - name: Reject symlinked schema files
+        run: |
+          for f in schema.prisma litellm/proxy/schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma; do
+            if [ -L "$f" ]; then
+              echo "::error file=$f::$f is a symlink, which is not allowed"
+              exit 1
+            fi
+          done
+
+      - name: Copy root schema to other locations
+        run: |
+          cp schema.prisma litellm/proxy/schema.prisma
+          cp schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+
+      - name: Check for changes
+        id: diff
+        run: |
+          if git diff --quiet -- litellm/proxy/schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma; then
+            echo "changed=false" >> "$GITHUB_OUTPUT"
+            echo "Schemas already in sync. Nothing to do."
+          else
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+            echo "Schema copies need updating."
+          fi
+
+      - name: Commit synced schemas
+        if: steps.diff.outputs.changed == 'true'
+        run: |
+          # Push to the PR's head branch (need the branch name for git push).
+          # We checked out by SHA above for safety, so configure the push target explicitly.
+          git config user.name "github-actions[bot]"
+          git config user.email "41898282+github-actions[bot]@users.noreply.github.com"
+          git checkout -B "$GITHUB_HEAD_REF"
+          git add -- litellm/proxy/schema.prisma litellm-proxy-extras/litellm_proxy_extras/schema.prisma
+          git commit -m "chore: sync schema.prisma copies from root"
+          git push origin "HEAD:$GITHUB_HEAD_REF"
--- a/.github/workflows/test-linting.yml
+++ b/.github/workflows/test-linting.yml
@ -4,6 +4,9 @@ on:
  pull_request:
    branches: [main]

+permissions:
+  contents: read
+
 jobs:
  lint:
    runs-on: ubuntu-latest
@ -14,6 +17,7 @@ jobs:
        with:
          fetch-depth: 0
          clean: true
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
@ -87,6 +91,7 @@ jobs:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
        with:
          fetch-depth: 0
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
--- a/.github/workflows/test-litellm-matrix.yml
+++ b/.github/workflows/test-litellm-matrix.yml
@ -4,6 +4,9 @@ on:
  pull_request:
    branches: [main]

+permissions:
+  contents: read
+
 # Cancel in-progress runs for the same PR
 concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
@ -118,6 +121,8 @@ jobs:

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
@ -151,7 +156,10 @@ jobs:
          poetry run pip install --force-reinstall --no-deps -e enterprise/

      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
          poetry run prisma generate --schema litellm/proxy/schema.prisma

      - name: Run tests - ${{ matrix.test-group.name }}
@ -163,4 +171,44 @@ jobs:
            --reruns ${{ matrix.test-group.reruns }} \
            --reruns-delay 1 \
            --dist=loadscope \
-            --durations=20
+            --durations=20 \
+            --cov=litellm \
+            --cov-report=xml:coverage-${{ matrix.test-group.name }}.xml \
+            --cov-config=pyproject.toml
+
+      - name: Save coverage report
+        if: always()
+        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
+        with:
+          name: coverage-${{ matrix.test-group.name }}
+          path: coverage-${{ matrix.test-group.name }}.xml
+          retention-days: 1
+
+  upload-coverage:
+    name: Upload coverage to Codecov
+    needs: test
+    if: always()
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write        # Required for OIDC tokenless upload
+      pull-requests: write   # Required for Codecov PR comments
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+
+      - name: Download all coverage reports
+        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
+        with:
+          pattern: coverage-*
+          path: coverage-reports
+          merge-multiple: true
+
+      - name: Upload to Codecov
+        uses: codecov/codecov-action@aa56896cf108bd10b5eb883cd1d24196da57f695 # v5.5.4
+        with:
+          use_oidc: true
+          directory: coverage-reports
+          root_dir: ${{ github.workspace }}
+          fail_ci_if_error: false
--- a/.github/workflows/test-litellm-ui-build.yml
+++ b/.github/workflows/test-litellm-ui-build.yml
@ -17,6 +17,8 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Setup Node.js
        uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0
@ -26,7 +28,7 @@ jobs:
          cache-dependency-path: ui/litellm-dashboard/package-lock.json

      - name: Install dependencies
-        run: npm install
+        run: npm ci

      - name: Build
        run: npm run build
--- a/.github/workflows/test-litellm.yml
+++ b/.github/workflows/test-litellm.yml
@ -8,6 +8,9 @@ on:
  # pull_request:
  #   branches: [ main ]

+permissions:
+  contents: read
+
 jobs:
  test:
    runs-on: ubuntu-latest
@ -15,6 +18,8 @@ jobs:

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Thank You Message
        run: |
--- a/.github/workflows/test-mcp.yml
+++ b/.github/workflows/test-mcp.yml
@ -4,6 +4,9 @@ on:
  pull_request:
    branches: [main]

+permissions:
+  contents: read
+
 jobs:
  test:
    runs-on: ubuntu-latest
@ -11,6 +14,8 @@ jobs:

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Thank You Message
        run: |
--- a/.github/workflows/test-model-map.yaml
+++ b/.github/workflows/test-model-map.yaml
@ -4,11 +4,16 @@ on:
  pull_request:
    branches: [main]

+permissions:
+  contents: read
+
 jobs:
  validate-model-prices-json:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Validate model_prices_and_context_window.json
        run: |
--- a/.github/workflows/test-proxy-e2e-azure-batches.yml
+++ b/.github/workflows/test-proxy-e2e-azure-batches.yml
@ -9,6 +9,9 @@ concurrency:
  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: true

+permissions:
+  contents: read
+
 jobs:
  proxy_e2e_azure_batches_tests:
    runs-on: ubuntu-latest
@ -31,6 +34,8 @@ jobs:

    steps:
      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
@ -63,7 +68,10 @@ jobs:
          poetry run pip install --force-reinstall --no-deps -e enterprise/

      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
          poetry run prisma generate --schema litellm/proxy/schema.prisma

      - name: Run Prisma migrations
--- a/.github/workflows/test-unit-caching-redis.yml
+++ b/.github/workflows/test-unit-caching-redis.yml
@ -0,0 +1,38 @@
+name: "Unit Tests: Caching (Redis)"
+
+# Uses cloud Redis credentials — only runs on trusted branches, not PRs.
+# This prevents external PRs from accessing Redis credentials.
+on:
+  push:
+    branches: [main, "litellm_*"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  caching-redis:
+    uses: ./.github/workflows/_test-unit-services-base.yml
+    with:
+      # Redis-only tests that do NOT require provider API keys.
+      # Tests needing API keys (test_caching.py, test_caching_ssl.py, test_prometheus_service.py,
+      # test_router_caching.py) are in Phase 3 integration workflows.
+      test-path: >-
+        tests/local_testing/test_dual_cache.py
+        tests/local_testing/test_redis_batch_optimizations.py
+        tests/local_testing/test_router_utils.py
+      workers: 2
+      reruns: 2
+      timeout-minutes: 20
+      enable-redis: true
+      enable-postgres: false
+    secrets:
+      REDIS_HOST: ${{ secrets.REDIS_HOST }}
+      REDIS_PORT: ${{ secrets.REDIS_PORT }}
+      REDIS_PASSWORD: ${{ secrets.REDIS_PASSWORD }}
+      DATABASE_URL: ${{ secrets.DATABASE_URL }}
+      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
--- a/.github/workflows/test-unit-core-utils.yml
+++ b/.github/workflows/test-unit-core-utils.yml
@ -0,0 +1,20 @@
+name: "Unit Tests: Core Utilities"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  core-utils:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/litellm_core_utils"
+      workers: 2
+      reruns: 1
--- a/.github/workflows/test-unit-documentation.yml
+++ b/.github/workflows/test-unit-documentation.yml
@ -0,0 +1,67 @@
+name: "Unit Tests: Documentation Validation"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  documentation:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Install Poetry
+        run: pip install 'poetry==2.3.2'
+
+      - name: Cache Poetry dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+            .venv
+          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+
+      - name: Install dependencies
+        run: |
+          poetry config virtualenvs.in-project true
+          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
+          poetry run pip install google-genai==1.22.0 \
+            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
+
+      - name: Setup litellm-enterprise
+        run: |
+          poetry run pip install --force-reinstall --no-deps -e enterprise/
+
+      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
+          poetry run prisma generate --schema litellm/proxy/schema.prisma
+
+      # Run the same documentation tests that CircleCI ran (as direct Python scripts)
+      - name: Run documentation validation tests
+        run: |
+          poetry run python ./tests/documentation_tests/test_env_keys.py
+          poetry run python ./tests/documentation_tests/test_router_settings.py
+          poetry run python ./tests/documentation_tests/test_api_docs.py
+          poetry run python ./tests/documentation_tests/test_circular_imports.py
--- a/.github/workflows/test-unit-enterprise-routing.yml
+++ b/.github/workflows/test-unit-enterprise-routing.yml
@ -0,0 +1,24 @@
+name: "Unit Tests: Enterprise, Google GenAI & Routing"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  enterprise-routing:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/enterprise
+        tests/test_litellm/google_genai
+        tests/test_litellm/router_utils
+        tests/test_litellm/router_strategy
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-integrations.yml
+++ b/.github/workflows/test-unit-integrations.yml
@ -0,0 +1,20 @@
+name: "Unit Tests: Integrations (Callbacks & Logging)"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  integrations:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/integrations"
+      workers: 2
+      reruns: 3
--- a/.github/workflows/test-unit-llm-providers.yml
+++ b/.github/workflows/test-unit-llm-providers.yml
@ -0,0 +1,29 @@
+name: "Unit Tests: LLM Provider Transformations"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  vertex-ai:
+    name: Vertex AI
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/llms/vertex_ai"
+      workers: 1
+      reruns: 2
+
+  other-providers:
+    name: All Other Providers
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-misc.yml
+++ b/.github/workflows/test-unit-misc.yml
@ -0,0 +1,31 @@
+name: "Unit Tests: MCP, Secrets, Containers & Misc"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  misc:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/secret_managers
+        tests/test_litellm/a2a_protocol
+        tests/test_litellm/anthropic_interface
+        tests/test_litellm/completion_extras
+        tests/test_litellm/containers
+        tests/test_litellm/experimental_mcp_client
+        tests/test_litellm/images
+        tests/test_litellm/interactions
+        tests/test_litellm/passthrough
+        tests/test_litellm/vector_stores
+        tests/test_litellm/test_*.py
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-proxy-auth.yml
+++ b/.github/workflows/test-unit-proxy-auth.yml
@ -0,0 +1,20 @@
+name: "Unit Tests: Proxy Auth & Key Management"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-auth:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/proxy/auth tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine tests/test_litellm/proxy/client"
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-proxy-db.yml
+++ b/.github/workflows/test-unit-proxy-db.yml
@ -0,0 +1,45 @@
+name: "Unit Tests: Proxy DB Operations"
+
+# Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
+on:
+  push:
+    branches: [main, "litellm_*"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-db:
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          # Key generation tests must NOT run in parallel (event loop conflicts with logging worker)
+          - test-group: key-generation
+            test-path: "tests/proxy_unit_tests/test_key_generate_prisma.py"
+            workers: 0
+            timeout: 30
+          - test-group: auth-checks
+            test-path: "tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py"
+            workers: 8
+            timeout: 20
+          - test-group: remaining
+            test-path: "tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py"
+            workers: 8
+            timeout: 20
+    uses: ./.github/workflows/_test-unit-services-base.yml
+    with:
+      test-path: ${{ matrix.test-path }}
+      workers: ${{ matrix.workers }}
+      reruns: 2
+      timeout-minutes: ${{ matrix.timeout }}
+      enable-redis: false
+      enable-postgres: true
+    secrets:
+      DATABASE_URL: ${{ secrets.DATABASE_URL }}
+      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
--- a/.github/workflows/test-unit-proxy-endpoints.yml
+++ b/.github/workflows/test-unit-proxy-endpoints.yml
@ -0,0 +1,35 @@
+name: "Unit Tests: Proxy API Endpoints"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-endpoints:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/proxy/management_endpoints
+        tests/test_litellm/proxy/guardrails
+        tests/test_litellm/proxy/management_helpers
+        tests/test_litellm/proxy/anthropic_endpoints
+        tests/test_litellm/proxy/google_endpoints
+        tests/test_litellm/proxy/openai_files_endpoint
+        tests/test_litellm/proxy/response_api_endpoints
+        tests/test_litellm/proxy/image_endpoints
+        tests/test_litellm/proxy/vector_store_endpoints
+        tests/test_litellm/proxy/agent_endpoints
+        tests/test_litellm/proxy/discovery_endpoints
+        tests/test_litellm/proxy/health_endpoints
+        tests/test_litellm/proxy/public_endpoints
+        tests/test_litellm/proxy/prompts
+        tests/test_litellm/proxy/ui_crud_endpoints
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-proxy-infra.yml
+++ b/.github/workflows/test-unit-proxy-infra.yml
@ -0,0 +1,28 @@
+name: "Unit Tests: Proxy Infrastructure"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-infra:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/proxy/db
+        tests/test_litellm/proxy/middleware
+        tests/test_litellm/proxy/spend_tracking
+        tests/test_litellm/proxy/pass_through_endpoints
+        tests/test_litellm/proxy/_experimental
+        tests/test_litellm/proxy/experimental
+        tests/test_litellm/proxy/common_utils
+        tests/test_litellm/proxy/test_*.py
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-proxy-legacy.yml
+++ b/.github/workflows/test-unit-proxy-legacy.yml
@ -0,0 +1,96 @@
+name: "Unit Tests: Proxy Legacy Tests"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    strategy:
+      fail-fast: false
+      matrix:
+        test-group:
+          - name: "auth-and-jwt"
+            path: "tests/proxy_unit_tests/test_[a-j]*.py"
+          - name: "key-generation"
+            path: "tests/proxy_unit_tests/test_[k-o]*.py"
+          - name: "proxy-config"
+            path: "tests/proxy_unit_tests/test_prisma*.py tests/proxy_unit_tests/test_project*.py tests/proxy_unit_tests/test_prompt*.py tests/proxy_unit_tests/test_proxy_[c-r]*.py"
+          - name: "proxy-server"
+            path: "tests/proxy_unit_tests/test_proxy_server.py"
+          - name: "proxy-server-extras"
+            path: "tests/proxy_unit_tests/test_proxy_server_*.py tests/proxy_unit_tests/test_proxy_setting_guardrails.py"
+          - name: "proxy-utils"
+            path: "tests/proxy_unit_tests/test_proxy_utils.py"
+          - name: "proxy-token-counter"
+            path: "tests/proxy_unit_tests/test_proxy_token_counter.py"
+          - name: "proxy-response-and-misc"
+            path: "tests/proxy_unit_tests/test_[r-t]*.py"
+          - name: "proxy-user-auth-and-spend"
+            path: "tests/proxy_unit_tests/test_[u-z]*.py"
+
+    name: ${{ matrix.test-group.name }}
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Install Poetry
+        run: pip install 'poetry==2.3.2'
+
+      - name: Cache Poetry dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/pypoetry
+            ~/.cache/pip
+            .venv
+          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-poetry-
+
+      - name: Install dependencies
+        run: |
+          poetry config virtualenvs.in-project true
+          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
+          poetry run pip install google-genai==1.22.0 \
+            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
+
+      - name: Setup litellm-enterprise
+        run: |
+          poetry run pip install --force-reinstall --no-deps -e enterprise/
+
+      - name: Generate Prisma client
+        env:
+          PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
+        run: |
+          poetry run pip install nodejs-wheel-binaries==24.13.1
+          poetry run prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Run tests - ${{ matrix.test-group.name }}
+        env:
+          TEST_PATH: ${{ matrix.test-group.path }}
+        run: |
+          poetry run pytest ${TEST_PATH} \
+            --tb=short -vv \
+            --maxfail=10 \
+            -n 2 \
+            --reruns 1 \
+            --reruns-delay 1 \
+            --dist=loadscope \
+            --durations=20
--- a/.github/workflows/test-unit-responses-caching-types.yml
+++ b/.github/workflows/test-unit-responses-caching-types.yml
@ -0,0 +1,20 @@
+name: "Unit Tests: Responses, Caching & Types"
+
+on:
+  pull_request:
+    branches: [main]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  responses-caching-types:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/responses tests/test_litellm/caching tests/test_litellm/types"
+      workers: 2
+      reruns: 2
--- a/.github/workflows/test-unit-security.yml
+++ b/.github/workflows/test-unit-security.yml
@ -0,0 +1,28 @@
+name: "Unit Tests: Security"
+
+# Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
+on:
+  push:
+    branches: [main, "litellm_*"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  security:
+    uses: ./.github/workflows/_test-unit-services-base.yml
+    with:
+      test-path: "tests/proxy_security_tests/"
+      workers: 1
+      reruns: 2
+      timeout-minutes: 20
+      enable-redis: false
+      enable-postgres: true
+    secrets:
+      DATABASE_URL: ${{ secrets.DATABASE_URL }}
+      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
--- a/.github/workflows/test_server_root_path.yml
+++ b/.github/workflows/test_server_root_path.yml
@ -18,6 +18,8 @@ jobs:
    steps:
      - name: Checkout repository
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false

      - name: Set up Docker Buildx
        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12
--- a/.github/workflows/zizmor.yml
+++ b/.github/workflows/zizmor.yml
@ -0,0 +1,31 @@
+name: GitHub Actions Security Analysis
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+permissions: {}
+
+jobs:
+  zizmor:
+    name: zizmor
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      security-events: write
+      contents: read
+      actions: read
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Run zizmor
+        uses: zizmorcore/zizmor-action@71321a20a9ded102f6e9ce5718a2fcec2c4f70d8 # v0.5.2
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@ -1,40 +0,0 @@
-repos:
-   repo: local
-    hooks:
-    -   id: pyright
-        name: pyright
-        entry: pyright
-        language: system
-        types: [python]
-        files: ^(litellm/|litellm_proxy_extras/|enterprise/)
-    -   id: isort
-        name: isort
-        entry: isort
-        language: system
-        types: [python]
-        files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
-        exclude: ^litellm/__init__.py$
-    -   id: black
-        name: black
-        entry: poetry run black
-        language: system
-        types: [python]
-        files: (litellm/|litellm_proxy_extras/).*\.py
-   repo: https://github.com/pycqa/flake8
-    rev: 7.0.0  # The version of flake8 to use
-    hooks:
-    -  id: flake8
-       exclude: ^litellm/tests/|^litellm/proxy/tests/|^litellm/tests/test_litellm/|^tests/test_litellm/|^tests/enterprise/
-       additional_dependencies: [flake8-print]
-       files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
-   repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
-    hooks:
-      - id: poetry-check
-        files: ^(pyproject.toml|litellm-proxy-extras/pyproject.toml)$
-   repo: local
-    hooks:
-    -   id: check-files-match
-        name: Check if files match
-        entry: python3 ci_cd/check_files_match.py
-        language: system
--- a/.trivyignore
+++ b/.trivyignore
@ -1,12 +0,0 @@
-# LiteLLM Trivy Ignore File
-# CVEs listed here are temporarily allowlisted pending fixes
-
-# Next.js vulnerabilities in UI dashboard (next@14.2.35)
-# Allowlisted: 2026-01-31, 7-day fix timeline
-# Fix: Upgrade to Next.js 15.5.10+ or 16.1.5+
-
-# HIGH: DoS via request deserialization
-GHSA-h25m-26qc-wcjf
-
-# MEDIUM: Image Optimizer DoS
-CVE-2025-59471
--- a/ci_cd/.grype.yaml
+++ b/ci_cd/.grype.yaml
@ -1,36 +0,0 @@
-ignore:
-  - vulnerability: CVE-2026-22184
-    reason: no fixed zlib package is available yet in the Wolfi repositories, so this is ignored temporarily until an upstream release exists
-  # Wolfi base image: Python 3.13 and Node from apk have no fixed builds in Wolfi yet / not applicable
-  - vulnerability: CVE-2025-55130
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-59465
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-55131
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-59466
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2026-21637
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-55132
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: GHSA-hx9q-6w63-j58v
-    reason: orjson dumps recursion; allowlisted
-  - vulnerability: GHSA-73rr-hh4g-fpgx
-    reason: diff npm transitive dep; override in package.json, allowlisted
-  - vulnerability: CVE-2026-0865
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15282
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2026-0672
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15366
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15367
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-11468
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-12781
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2026-1299
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
--- a/ci_cd/publish-proxy-extras.sh
+++ b/ci_cd/publish-proxy-extras.sh
@ -1,19 +0,0 @@
-#!/bin/bash
-
-# Exit on error
-set -e
-
-echo "🚀 Building and publishing litellm-proxy-extras"
-
-# Navigate to litellm-proxy-extras directory
-cd "$(dirname "$0")/../litellm-proxy-extras"
-
-# Build the package
-echo "📦 Building package..."
-poetry build
-
-# Publish to PyPI
-echo "🌎 Publishing to PyPI..."
-poetry publish
-
-echo "✅ Done! Package published successfully"
--- a/ci_cd/security_scans.sh
+++ b/ci_cd/security_scans.sh
@ -1,262 +0,0 @@
-#!/bin/bash
-
-# Security Scans Script for LiteLLM
-# This script runs comprehensive security scans including Trivy and Grype
-
-set -e
-
-echo "Starting security scans for LiteLLM..."
-
-# Function to install Trivy and required tools
-install_trivy() {
-    echo "Installing Trivy and required tools..."
-    TRIVY_VERSION="0.35.0"
-    sudo apt-get update
-    sudo apt-get install -y wget jq curl bsdmainutils
-    wget -qO trivy.deb "https://github.com/aquasecurity/trivy/releases/download/v${TRIVY_VERSION}/trivy_${TRIVY_VERSION}_Linux-64bit.deb"
-    sudo dpkg -i trivy.deb
-    rm trivy.deb
-    echo "Trivy ${TRIVY_VERSION} installed successfully"
-}
-
-# Function to install Grype
-install_grype() {
-    echo "Installing Grype..."
-    curl -sSfL https://raw.githubusercontent.com/anchore/grype/main/install.sh | sudo sh -s -- -b /usr/local/bin
-    echo "Grype installed successfully"
-}
-
-# Function to install ggshield
-install_ggshield() {
-    echo "Installing ggshield..."
-    pip3 install --upgrade pip
-    pip3 install ggshield
-    echo "ggshield installed successfully"
-}
-
-# # Function to run secret detection scans
-# run_secret_detection() {
-#     echo "Running secret detection scans..."
-    
-#     if ! command -v ggshield &> /dev/null; then
-#         install_ggshield
-#     fi
-    
-#     # Check if GITGUARDIAN_API_KEY is set (required for CI/CD)
-#     if [ -z "$GITGUARDIAN_API_KEY" ]; then
-#         echo "Warning: GITGUARDIAN_API_KEY environment variable is not set."
-#         echo "ggshield requires a GitGuardian API key to scan for secrets."
-#         echo "Please set GITGUARDIAN_API_KEY in your CI/CD environment variables."
-#         exit 1
-#     fi
-    
-#     echo "Scanning codebase for secrets..."
-#     echo "Note: Large codebases may take several minutes due to API rate limits (50 requests/minute on free plan)"
-#     echo "ggshield will automatically handle rate limits and retry as needed."
-#     echo "Binary files, cache files, and build artifacts are excluded via .gitguardian.yaml"
-    
-#     # Use --recursive for directory scanning and auto-confirm if prompted
-#     # .gitguardian.yaml will automatically exclude binary files, wheel files, etc.
-#     # GITGUARDIAN_API_KEY environment variable will be used for authentication
-#     echo y | ggshield secret scan path . --recursive || {
-#         echo ""
-#         echo "=========================================="
-#         echo "ERROR: Secret Detection Failed"
-#         echo "=========================================="
-#         echo "ggshield has detected secrets in the codebase."
-#         echo "Please review discovered secrets above, revoke any actively used secrets"
-#         echo "from underlying systems and make changes to inject secrets dynamically at runtime."
-#         echo ""
-#         echo "For more information, see: https://docs.gitguardian.com/secrets-detection/"
-#         echo "=========================================="
-#         echo ""
-#         exit 1
-#     }
-    
-#     echo "Secret detection scans completed successfully"
-# }
-
-# Function to run Trivy scans
-run_trivy_scans() {
-    echo "Running Trivy scans..."
-    
-    echo "Scanning LiteLLM Docs..."
-    trivy fs --ignorefile .trivyignore --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./docs/
-    
-    echo "Scanning LiteLLM UI..."
-    trivy fs --ignorefile .trivyignore --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./ui/
-    
-    echo "Trivy scans completed successfully"
-}
-
-# Function to build and scan Docker images with Grype
-run_grype_scans() {
-    echo "Running Grype scans..."
-    
-    # Temporarily add wheel files to .dockerignore for security scans
-    echo "Temporarily modifying .dockerignore to exclude problematic wheel files..."
-    cp .dockerignore .dockerignore.backup 2>/dev/null || touch .dockerignore.backup
-    echo "/*.whl" >> .dockerignore
-    
-    # Build and scan Dockerfile.database
-    echo "Building and scanning Dockerfile.database..."
-    docker build --no-cache -t litellm-database:latest -f ./docker/Dockerfile.database .
-    grype litellm-database:latest --config ci_cd/.grype.yaml --fail-on critical
-    
-    # Build and scan main Dockerfile
-    echo "Building and scanning main Dockerfile..."
-    docker build --no-cache -t litellm:latest .
-    grype litellm:latest --config ci_cd/.grype.yaml --fail-on critical
-    
-    # Restore original .dockerignore
-    echo "Restoring original .dockerignore..."
-    mv .dockerignore.backup .dockerignore
-    
-    # Scan the locally built LiteLLM image for vulnerabilities with CVSS >= 4.0
-    echo "Scanning locally built LiteLLM image for high-severity vulnerabilities..."
-    echo "Using locally built image: litellm:latest"
-    
-    # Allowlist of CVEs to be ignored in failure threshold/reporting
-    # - CVE-2025-8869: Not applicable on Python >=3.13 (PEP 706 implemented); pip fallback unused; no OS-level fix
-    # - GHSA-4xh5-x5gv-qwph: GitHub Security Advisory alias for CVE-2025-8869
-    # - GHSA-5j98-mcp5-4vw2: glob CLI command injection via -c/--cmd; glob CLI is not used in the litellm runtime image,
-    #   and the vulnerable versions are pulled in only via OS-level/node tooling outside of our application code
-    ALLOWED_CVES=(
-        "CVE-2025-8869"
-        "GHSA-4xh5-x5gv-qwph"
-        "CVE-2025-8291" # no fix available as of Oct 11, 2025
-        "GHSA-5j98-mcp5-4vw2"
-        "CVE-2025-13836" # Python 3.13 HTTP response reading OOM/DoS - no fix available in base image
-        "CVE-2025-12084" # Python 3.13 xml.dom.minidom quadratic algorithm - no fix available in base image
-        "CVE-2025-60876" # BusyBox wget HTTP request splitting - no fix available in Chainguard Wolfi base image
-        "CVE-2026-0861" # Wolfi glibc still flagged even on 2.42-r5; upstream patched build unavailable yet
-        "CVE-2010-4756" # glibc glob DoS - awaiting patched Wolfi glibc build
-        "CVE-2019-1010022" # glibc stack guard bypass - awaiting patched Wolfi glibc build
-        "CVE-2019-1010023" # glibc ldd remap issue - awaiting patched Wolfi glibc build
-        "CVE-2019-1010024" # glibc ASLR mitigation bypass - awaiting patched Wolfi glibc build
-        "CVE-2019-1010025" # glibc pthread heap address leak - awaiting patched Wolfi glibc build
-        "CVE-2026-22184" # zlib untgz buffer overflow - untgz unused + no fixed Wolfi build yet
-        "GHSA-58pv-8j8x-9vj2" # jaraco.context path traversal - setuptools vendored only (v5.3.0), not used in application code (using v6.1.0+)
-        "GHSA-34x7-hfp2-rc4v" # node-tar hardlink path traversal - not applicable, tar CLI not exposed in application code
-        "GHSA-r6q2-hw4h-h46w" # node-tar not used by application runtime, Linux-only container, not affect by macOS APFS-specific exploit
-        "GHSA-8rrh-rw8j-w5fx" # wheel is from chainguard and will be handled by then TODO: Remove this after Chainguard updates the wheel
-        "CVE-2025-59465" # Node only used for Admin UI build/prisma
-        "CVE-2025-55131" # Node only used for Admin UI build/prisma
-        "CVE-2025-59466" # Node only used for Admin UI build/prisma
-        "CVE-2025-55130" # Node only used for Admin UI build/prisma
-        "CVE-2025-59467" # Node only used for Admin UI build/prisma
-        "CVE-2026-21637" # Node only used for Admin UI build/prisma
-        "CVE-2025-55132" # Node only used for Admin UI build/prisma
-        "GHSA-hx9q-6w63-j58v" # orjson dumps recursion; allowlisted
-        "CVE-2025-15281" # No fix available yet
-        "CVE-2026-0865" # No fix available yet
-        "CVE-2025-15282" # No fix available yet
-        "CVE-2026-0672" # No fix available yet
-        "CVE-2025-15366" # No fix available yet
-        "CVE-2025-15367" # No fix available yet
-        "CVE-2025-12781" # No fix available yet
-        "CVE-2025-11468" # No fix available yet
-        "CVE-2026-1299" # Python 3.13 email module header injection - not applicable, LiteLLM doesn't use BytesGenerator for email serialization
-        "CVE-2026-0775" # npm cli incorrect permission assignment - no fix available yet, npm is only used at build/prisma-generate time
-        "GHSA-3ppc-4f35-3m26" # minimatch ReDoS via repeated wildcards - from nodejs_wheel bundled npm, not used in application runtime code
-        "GHSA-83g3-92jg-28cx" # tar arbitrary file read/write via hardlink - from nodejs_wheel bundled npm, not used in application runtime code
-        "CVE-2026-25639" # axios - full fix requires 1.x major version bump; pinned to >=0.30.2 to clear other axios CVEs, upgrade to 1.x in follow-up
-        "CVE-2026-2297" # Python 3.13 SourcelessFileLoader audit hook bypass - no fix available in base image
-        "GHSA-qffp-2rhf-9h96" # tar hardlink path traversal - from nodejs_wheel bundled npm, not used in application runtime code
-        "CVE-2026-2673" # OpenSSL 3.6.1 TLS 1.3 key exchange group negotiation issue - no fix available yet
-        "CVE-2026-3644" # Python 3.13 vulnerability - no fix available in base image
-        "CVE-2026-4224" # Python 3.13 Expat parser stack overflow in ElementDeclHandler - no fix available in base image
-    )
-
-    # Build JSON array of allowlisted CVE IDs for jq
-    ALLOWED_IDS_JSON=$(printf '%s\n' "${ALLOWED_CVES[@]}" | jq -R . | jq -s .)
-
-    echo "Checking for vulnerabilities with CVSS score >= 4.0..."
-    echo "Allowlisted CVEs (ignored in threshold): ${ALLOWED_CVES[*]}"
-    echo ""
-    
-    # Show all high-severity vulnerabilities for transparency
-    TOTAL_HIGH_SEVERITY=$(grype litellm:latest -o json | jq -r '
-        .matches[]
-        | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-        | .vulnerability.id' | wc -l)
-    
-    if [ "$TOTAL_HIGH_SEVERITY" -gt 0 ]; then
-        echo "Total vulnerabilities found with CVSS >= 4.0: $TOTAL_HIGH_SEVERITY"
-        echo ""
-        echo "All high-severity vulnerabilities (including allowlisted):"
-        grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        ["Package", "Version", "Vulnerability ID", "CVSS Score", "Allowlisted"],
-        (.matches[]
-          | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-          | [.artifact.name, .artifact.version, .vulnerability.id, .vulnerability.cvss[0].metrics.baseScore, (if (.vulnerability.id as $id | $allow | index($id)) then "YES" else "NO" end)])
-        | @tsv' | column -t -s $'\t'
-        echo ""
-    fi
-
-    HIGH_SEVERITY_COUNT=$(grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        .matches[]
-        | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-        | select((.vulnerability.id as $id | $allow | index($id) | not))
-        | .vulnerability.id' | wc -l)
-    
-    if [ "$HIGH_SEVERITY_COUNT" -gt 0 ]; then
-        echo ""
-        echo "=========================================="
-        echo "ERROR: Security Scan Failed"
-        echo "=========================================="
-        echo "Found $HIGH_SEVERITY_COUNT non-allowlisted vulnerabilities with CVSS score >= 4.0 in litellm:latest"
-        echo ""
-        echo "These vulnerabilities are NOT in the allowlist and must be addressed."
-        echo "Current allowlisted CVEs: ${ALLOWED_CVES[*]}"
-        echo ""
-        echo "Detailed vulnerability report:"
-        echo ""
-        grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        ["Package", "Version", "Vulnerability ID", "CVSS Score", "Severity", "Fix Version", "Description"],
-        (.matches[]
-          | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-          | select((.vulnerability.id as $id | $allow | index($id) | not))
-          | [.artifact.name, .artifact.version, .vulnerability.id, .vulnerability.cvss[0].metrics.baseScore, .vulnerability.severity, (.vulnerability.fix.versions[0] // "No fix available"), .vulnerability.description])
-        | @tsv' | column -t -s $'\t'
-        echo ""
-        echo "=========================================="
-        echo "Action Required:"
-        echo "=========================================="
-        echo "1. If a fix is available, update the package to the fixed version"
-        echo "2. If the vulnerability is not applicable or has no fix:"
-        echo "   - Add the CVE/GHSA ID to ALLOWED_CVES array in ci_cd/security_scans.sh"
-        echo "   - Add a comment explaining why it's safe to ignore"
-        echo ""
-        echo "Note: Some vulnerabilities may have multiple IDs (CVE-XXXX and GHSA-XXXX)."
-        echo "Add all relevant IDs to the allowlist if they refer to the same issue."
-        echo "=========================================="
-        echo ""
-        exit 1
-    else
-        echo "No high-severity vulnerabilities (CVSS >= 4.0) found in litellm:latest"
-    fi
-    
-    echo "Grype scans completed successfully"
-}
-
-# Main execution
-main() {
-    echo "Installing security scanning tools..."
-    install_trivy
-    install_grype
-    
-    # echo "Running secret detection scans..."
-    # run_secret_detection
-    
-    echo "Running filesystem vulnerability scans..."
-    run_trivy_scans
-    
-    echo "Running Docker image vulnerability scans..."
-    run_grype_scans
-    
-    echo "All security scans completed successfully!"
-}
-
-# Execute main function
-main "$@"
--- a/docker/build_admin_ui.sh
+++ b/docker/build_admin_ui.sh
@ -40,11 +40,22 @@ else
        exit 1
    fi
 fi
-curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.38.0/install.sh | bash
+NVM_VERSION="v0.40.4"
+NVM_CHECKSUM="4b7412c49960c7d31e8df72da90c1fb5b8cccb419ac99537b737028d497aba4f"
+NVM_SCRIPT=$(mktemp)
+trap 'rm -f "$NVM_SCRIPT"' EXIT
+curl -fsSL "https://raw.githubusercontent.com/nvm-sh/nvm/${NVM_VERSION}/install.sh" -o "$NVM_SCRIPT"
+if command -v sha256sum &>/dev/null; then
+  echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | sha256sum -c -
+elif command -v shasum &>/dev/null; then
+  echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | shasum -a 256 -c -
+else
+  echo "No sha256 tool found; cannot verify nvm checksum"; exit 1
+fi || { echo "nvm checksum verification failed"; exit 1; }
+bash "$NVM_SCRIPT"
 source ~/.nvm/nvm.sh
 nvm install v18.17.0
 nvm use v18.17.0
-npm install -g npm

 # copy _enterprise.json from this directory to /ui/litellm-dashboard, and rename it to ui_colors.json
 cp enterprise/enterprise_ui/enterprise_colors.json ui/litellm-dashboard/ui_colors.json
--- a/docs/my-website/.trivyignore
+++ b/docs/my-website/.trivyignore
@ -1,7 +0,0 @@
-# js-yaml CVE-2025-64718
-# This vulnerability is not applicable because we've forced js-yaml to version 4.1.1
-# via npm overrides in package.json. Trivy incorrectly reports this based on
-# dependency requirements in the lockfile, but the actual installed version is 4.1.1.
-# Verified with: npm list js-yaml
-CVE-2025-64718
-
--- a/scripts/install.sh
+++ b/scripts/install.sh
@ -83,8 +83,8 @@ echo ""
 header "Installing litellm[proxy]…"
 echo ""

-"$PYTHON_BIN" -m pip install --upgrade "${LITELLM_PACKAGE}" \
-  || die "pip install failed. Try manually: $PYTHON_BIN -m pip install '${LITELLM_PACKAGE}'"
+"$PYTHON_BIN" -m pip install --only-binary :all: --upgrade "${LITELLM_PACKAGE}" \
+  || die "pip install failed. Try manually: $PYTHON_BIN -m pip install --only-binary :all: '${LITELLM_PACKAGE}'"

 # ── find the litellm binary installed by pip for this Python ───────────────
 # sysconfig.get_path('scripts') is where pip puts console scripts — reliable
--- a/ui/litellm-dashboard/.trivyignore
+++ b/ui/litellm-dashboard/.trivyignore
@ -1,7 +0,0 @@
-# js-yaml CVE-2025-64718
-# This vulnerability is not applicable because we've forced js-yaml to version 4.1.1
-# via npm overrides in package.json. Trivy incorrectly reports this based on
-# dependency requirements in the lockfile, but the actual installed version is 4.1.1.
-# Verified with: npm list js-yaml
-CVE-2025-64718
-
--- a/ui/litellm-dashboard/build_ui.sh
+++ b/ui/litellm-dashboard/build_ui.sh
@ -2,8 +2,20 @@

 # Check if nvm is not installed
 if ! command -v nvm &> /dev/null; then
-  # Install nvm
-  curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.38.0/install.sh | bash
+  # Install nvm with checksum verification
+  NVM_VERSION="v0.40.4"
+  NVM_CHECKSUM="4b7412c49960c7d31e8df72da90c1fb5b8cccb419ac99537b737028d497aba4f"
+  NVM_SCRIPT=$(mktemp)
+  trap 'rm -f "$NVM_SCRIPT"' EXIT
+  curl -fsSL "https://raw.githubusercontent.com/nvm-sh/nvm/${NVM_VERSION}/install.sh" -o "$NVM_SCRIPT"
+  if command -v sha256sum &>/dev/null; then
+    echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | sha256sum -c -
+  elif command -v shasum &>/dev/null; then
+    echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | shasum -a 256 -c -
+  else
+    echo "No sha256 tool found; cannot verify nvm checksum"; exit 1
+  fi || { echo "nvm checksum verification failed"; exit 1; }
+  bash "$NVM_SCRIPT"

  # Source nvm script in the current session
  export NVM_DIR="$HOME/.nvm"
--- a/ui/litellm-dashboard/build_ui_custom_path.sh
+++ b/ui/litellm-dashboard/build_ui_custom_path.sh
@ -12,8 +12,20 @@ UI_BASE_PATH="$1"

 # Check if nvm is not installed
 if ! command -v nvm &> /dev/null; then
-    # Install nvm
-    curl -o- https://raw.githubusercontent.com/nvm-sh/nvm/v0.38.0/install.sh | bash
+    # Install nvm with checksum verification
+    NVM_VERSION="v0.40.4"
+    NVM_CHECKSUM="4b7412c49960c7d31e8df72da90c1fb5b8cccb419ac99537b737028d497aba4f"
+    NVM_SCRIPT=$(mktemp)
+    trap 'rm -f "$NVM_SCRIPT"' EXIT
+    curl -fsSL "https://raw.githubusercontent.com/nvm-sh/nvm/${NVM_VERSION}/install.sh" -o "$NVM_SCRIPT"
+    if command -v sha256sum &>/dev/null; then
+      echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | sha256sum -c -
+    elif command -v shasum &>/dev/null; then
+      echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | shasum -a 256 -c -
+    else
+      echo "No sha256 tool found; cannot verify nvm checksum"; exit 1
+    fi || { echo "nvm checksum verification failed"; exit 1; }
+    bash "$NVM_SCRIPT"

    # Source nvm script in the current session
    export NVM_DIR="$HOME/.nvm"