scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 79

Merge branch 'BerriAI:main' into fix/vertex-gemini-multimodal-drop

Browse source
This commit is contained in:
Vivek Vijayan 2026-03-26 16:51:49 +05:30 • committed by GitHub
commit f6b458ec2f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
121 changed files with 2777 additions and 1356 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

36
.claude/settings.json
View file

@ -1,36 +0,0 @@
{
"permissions": {
"allow": [
"Bash(git show:*)",
"Bash(git worktree add:*)",
"Read(//Users/krrishdholakia/Documents/litellm/**)",
"Read(//Users/krrishdholakia/Documents/litellm-claude-code-guardrails/litellm/types/**)",
"Read(//Users/krrishdholakia/Documents/litellm-claude-code-guardrails/**)",
"Read(//Users/krrishdholakia/Documents/litellm-claude-code-guardrails/litellm/**)",
"Bash(python:*)",
"Bash(python -c \"\nimport sys; sys.path.insert\\(0, ''.''\\)\nfrom litellm.proxy.guardrails.guardrail_hooks.claude_code.guardrail import ClaudeCodeGuardrail, HOSTED_TOOL_PREFIXES\nprint\\(''HOSTED_TOOL_PREFIXES:'', HOSTED_TOOL_PREFIXES\\)\nprint\\(''ClaudeCodeGuardrail imported OK''\\)\n\")",
"Read(//Users/krrishdholakia/Documents/litellm-mcp-jwt-groups/litellm/proxy/**)",
"Read(//Users/krrishdholakia/Documents/litellm-mcp-jwt-groups/**)",
"Bash(poetry run pytest:*)",
"Bash(git add:*)",
"Bash(git commit:*)",
"Bash(poetry run python:*)",
"Bash(poetry run pip:*)",
"Bash(git reset:*)",
"Bash(git cherry-pick:*)",
"Bash(git checkout:*)",
"Read(//Users/krrishdholakia/Documents/litellm/litellm/proxy/guardrails/guardrail_hooks/**)",
"Read(//Users/krrishdholakia/Documents/**)",
"Bash(git -C /Users/krrishdholakia/Documents/litellm-mcp-user-permissions worktree list)",
"Bash(ls:*)"
],
"additionalDirectories": [
"/Users/krrishdholakia/Documents/litellm-mcp-group-plan/plan",
"/Users/krrishdholakia/Documents/litellm-claude-code-guardrails/litellm/proxy/guardrails/guardrail_hooks/claude_code",
"/Users/krrishdholakia/Documents/litellm-claude-code-guardrails/litellm/types",
"/Users/krrishdholakia/Documents/litellm-claude-code-guardrails",
"/Users/krrishdholakia/Documents/litellm-mcp-jwt-groups/litellm/proxy",
"/Users/krrishdholakia/Documents/litellm-mcp-jwt-groups/tests/test_litellm/proxy/auth"
]
}
}

2
.github/ISSUE_TEMPLATE/config.yml vendored
View file

@ -1,7 +1,7 @@
blank_issues_enabled: true
contact_links:
- name: Schedule Demo
url: https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions
url: https://enterprise.litellm.ai/demo
about: Speak directly with Krrish and Ishaan, the founders, to discuss issues, share feedback, or explore improvements for LiteLLM
- name: Discord
url: https://discord.com/invite/wuPM9dRgDw

6
.github/workflows/auto_update_price_and_context_window.yml vendored
View file

@ -2,7 +2,7 @@ name: Updates model_prices_and_context_window.json and Create Pull Request
on:
schedule:
- cron: "0 0 * * 0" # Run every Sundays at midnight
- cron: "0 0 * * 0" # Run every Sundays at midnight
#- cron: "0 0 * * *" # Run daily at midnight
jobs:
@ -10,7 +10,7 @@ jobs:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Install Dependencies
run: |
pip install aiohttp
@ -26,4 +26,4 @@ jobs:
--head auto-update-price-and-context-window-$(date +'%Y-%m-%d') \
--base main
env:
GH_TOKEN: ${{ secrets.GH_TOKEN }}
GH_TOKEN: ${{ secrets.GH_TOKEN }}

6
.github/workflows/check_duplicate_issues.yml vendored
View file

@ -12,7 +12,7 @@ jobs:
contents: read
steps:
- name: Check for potential duplicates
uses: wow-actions/potential-duplicates@v1
uses: wow-actions/potential-duplicates@4d4ea0352e0383859279938e255179dd1dbb67b5 # v1.1.0
with:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
label: potential-duplicate
@ -30,13 +30,13 @@ jobs:
- name: Checkout close script
if: github.event.action == 'opened'
uses: actions/checkout@v4
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
sparse-checkout: .github/scripts
- name: Set up Python
if: github.event.action == 'opened'
uses: actions/setup-python@v5
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: "3.11"

7
.github/workflows/codeql.yml vendored
View file

@ -15,6 +15,7 @@ concurrency:
jobs:
analyze:
if: github.event_name != 'schedule' || github.repository == 'BerriAI/litellm'
name: Analyze (${{ matrix.language }})
runs-on: ubuntu-latest
timeout-minutes: 30
@ -37,16 +38,16 @@ jobs:
steps:
- name: Checkout repository
uses: actions/checkout@v4
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Initialize CodeQL
uses: github/codeql-action/init@v3
uses: github/codeql-action/init@ebcb5b36ded6beda4ceefea6a8bc4cc885255bb3 # v3
with:
languages: ${{ matrix.language }}
build-mode: ${{ matrix.build-mode }}
config-file: ./.github/codeql/codeql-config.yml
- name: Perform CodeQL Analysis
uses: github/codeql-action/analyze@v3
uses: github/codeql-action/analyze@ebcb5b36ded6beda4ceefea6a8bc4cc885255bb3 # v3
with:
category: "/language:${{ matrix.language }}"

6
.github/workflows/codspeed.yml vendored
View file

@ -25,10 +25,10 @@ jobs:
timeout-minutes: 15
steps:
- uses: actions/checkout@v4
- uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Set up Python
uses: actions/setup-python@v5
uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
with:
python-version: "3.12"
@ -38,7 +38,7 @@ jobs:
pip install pytest pytest-codspeed==4.3.0
- name: Run benchmarks
uses: CodSpeedHQ/action@v4
uses: CodSpeedHQ/action@1c8ae4843586d3ba879736b7f6b7b0c990757fab # v4.12.1
with:
mode: simulation
run: pytest tests/benchmarks/ --codspeed

10
.github/workflows/create_daily_staging_branch.yml vendored
View file

@ -2,16 +2,17 @@ name: Create Daily Staging Branch
on:
schedule:
- cron: '0 0,12 * * *' # Runs every 12 hours at midnight and noon UTC
workflow_dispatch: # Allow manual trigger
- cron: "0 0,12 * * *" # Runs every 12 hours at midnight and noon UTC
workflow_dispatch: # Allow manual trigger
jobs:
create-staging-branch:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
fetch-depth: 0
@ -43,11 +44,12 @@ jobs:
fi
create-internal-dev-branch:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
with:
fetch-depth: 0

444
.github/workflows/ghcr_deploy.yml vendored
View file

@ -1,444 +0,0 @@
# this workflow is triggered by an API call when there is a new PyPI release of LiteLLM
name: Build, Publish LiteLLM Docker Image. New Release
on:
workflow_dispatch:
inputs:
tag:
description: "The tag version you want to build"
required: true
release_type:
description: "The release type you want to build. Can be 'latest', 'stable', 'dev', 'rc'"
type: string
default: "latest"
commit_hash:
description: "Commit hash"
required: true
# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
CHART_NAME: litellm-helm
# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
jobs:
# print commit hash, tag, and release type
print:
runs-on: ubuntu-latest
steps:
- run: |
echo "Commit hash: ${{ github.event.inputs.commit_hash }}"
echo "Tag: ${{ github.event.inputs.tag }}"
echo "Release type: ${{ github.event.inputs.release_type }}"
docker-hub-deploy:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
steps:
-
name: Checkout
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
-
name: Set up QEMU
uses: docker/setup-qemu-action@v3
-
name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
-
name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKERHUB_USERNAME }}
password: ${{ secrets.DOCKERHUB_TOKEN }}
-
name: Build and push
uses: docker/build-push-action@v5
with:
context: .
push: true
tags: litellm/litellm:${{ github.event.inputs.tag || 'latest' }}
-
name: Build and push litellm-database image
uses: docker/build-push-action@v5
with:
context: .
push: true
file: ./docker/Dockerfile.database
tags: litellm/litellm-database:${{ github.event.inputs.tag || 'latest' }}
-
name: Build and push litellm-spend-logs image
uses: docker/build-push-action@v5
with:
context: .
push: true
file: ./litellm-js/spend-logs/Dockerfile
tags: litellm/litellm-spend_logs:${{ github.event.inputs.tag || 'latest' }}
-
name: Build and push litellm-non_root image
uses: docker/build-push-action@v5
with:
context: .
push: true
file: ./docker/Dockerfile.non_root
tags: litellm/litellm-non_root:${{ github.event.inputs.tag || 'latest' }}
build-and-push-image:
runs-on: ubuntu-latest
# Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
# Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
# This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
# Configure multi platform Docker builds
- name: Set up QEMU
uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
# This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
# It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
# It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
- name: Build and push Docker image
uses: docker/build-push-action@4976231911ebf5f32aad765192d35f942aa48cb8
with:
context: .
push: true
tags: |
${{ steps.meta.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
${{ steps.meta.outputs.tags }}-${{ github.event.inputs.release_type }}
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-stable', env.REGISTRY) || '' }},
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm:{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
labels: ${{ steps.meta.outputs.labels }}
platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
build-and-push-image-ee:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata (tags, labels) for EE Dockerfile
id: meta-ee
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-ee
# Configure multi platform Docker builds
- name: Set up QEMU
uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
- name: Build and push EE Docker image
uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
with:
context: .
file: Dockerfile
push: true
tags: |
${{ steps.meta-ee.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
${{ steps.meta-ee.outputs.tags }}-${{ github.event.inputs.release_type }}
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-ee:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-ee:main-stable', env.REGISTRY) || '' }}
labels: ${{ steps.meta-ee.outputs.labels }}
platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
build-and-push-image-database:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata (tags, labels) for database Dockerfile
id: meta-database
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-database
# Configure multi platform Docker builds
- name: Set up QEMU
uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
- name: Build and push Database Docker image
uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
with:
context: .
file: ./docker/Dockerfile.database
push: true
tags: |
${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.release_type }}
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-database:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-stable', env.REGISTRY) || '' }}
labels: ${{ steps.meta-database.outputs.labels }}
platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
build-and-push-image-non_root:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata (tags, labels) for non_root Dockerfile
id: meta-non_root
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-non_root
# Configure multi platform Docker builds
- name: Set up QEMU
uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
- name: Build and push non_root Docker image
uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
with:
context: .
file: ./docker/Dockerfile.non_root
push: true
tags: |
${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.release_type }}
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-non_root:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-stable', env.REGISTRY) || '' }}
labels: ${{ steps.meta-non_root.outputs.labels }}
platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
build-and-push-image-spend-logs:
runs-on: ubuntu-latest
permissions:
contents: read
packages: write
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.commit_hash }}
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Extract metadata (tags, labels) for spend-logs Dockerfile
id: meta-spend-logs
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
with:
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-spend_logs
# Configure multi platform Docker builds
- name: Set up QEMU
uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
- name: Build and push Database Docker image
uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
with:
context: .
file: ./litellm-js/spend-logs/Dockerfile
push: true
tags: |
${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.release_type }}
${{ (github.event.inputs.release_type == 'stable' || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-spend_logs:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-stable', env.REGISTRY) || '' }}
platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
run-observatory-tests:
if: github.event.inputs.release_type == 'rc' || github.event.inputs.release_type == 'stable'
needs: [docker-hub-deploy]
uses: ./.github/workflows/run_observatory_tests.yml
with:
tag: ${{ github.event.inputs.tag }}
commit_hash: ${{ github.event.inputs.commit_hash }}
secrets: inherit
build-and-push-helm-chart:
if: github.event.inputs.release_type != 'dev'
needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: lowercase github.repository_owner
run: |
echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
# Sync Helm chart version with LiteLLM release version (1-1 versioning)
# This allows users to easily map Helm chart versions to LiteLLM versions
# See: https://codefresh.io/docs/docs/ci-cd-guides/helm-best-practices/
- name: Calculate chart and app versions
id: chart_version
shell: bash
run: |
INPUT_TAG="${{ github.event.inputs.tag }}"
RELEASE_TYPE="${{ github.event.inputs.release_type }}"
# Chart version = LiteLLM version without 'v' prefix (Helm semver convention)
# v1.81.0 -> 1.81.0, v1.81.0.rc.1 -> 1.81.0.rc.1
CHART_VERSION="${INPUT_TAG#v}"
# Add suffix for 'latest' releases (rc already has suffix in tag)
if [ "$RELEASE_TYPE" = "latest" ]; then
CHART_VERSION="${CHART_VERSION}-latest"
fi
# App version = Docker tag (keeps 'v' prefix to match Docker image tags)
APP_VERSION="${INPUT_TAG}"
echo "version=${CHART_VERSION}" | tee -a $GITHUB_OUTPUT
echo "app_version=${APP_VERSION}" | tee -a $GITHUB_OUTPUT
- uses: ./.github/actions/helm-oci-chart-releaser
with:
name: ${{ env.CHART_NAME }}
repository: ${{ env.REPO_OWNER }}
tag: ${{ steps.chart_version.outputs.version }}
app_version: ${{ steps.chart_version.outputs.app_version }}
path: deploy/charts/${{ env.CHART_NAME }}
registry: ${{ env.REGISTRY }}
registry_username: ${{ github.actor }}
registry_password: ${{ secrets.GITHUB_TOKEN }}
update_dependencies: true
release:
name: "New LiteLLM Release"
needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
permissions:
contents: write
runs-on: "ubuntu-latest"
steps:
- name: Display version
run: echo "Current version is ${{ github.event.inputs.tag }}"
- name: "Set Release Tag"
run: echo "RELEASE_TAG=${{ github.event.inputs.tag }}" >> $GITHUB_ENV
- name: Display release tag
run: echo "RELEASE_TAG is $RELEASE_TAG"
- name: "Create release"
uses: "actions/github-script@v6"
with:
github-token: "${{ secrets.GITHUB_TOKEN }}"
script: |
const commitHash = "${{ github.event.inputs.commit_hash}}";
console.log("Commit Hash:", commitHash); // Add this line for debugging
try {
const response = await github.rest.repos.createRelease({
draft: false,
generate_release_notes: true,
target_commitish: commitHash,
name: process.env.RELEASE_TAG,
owner: context.repo.owner,
prerelease: false,
repo: context.repo.repo,
tag_name: process.env.RELEASE_TAG,
});
core.exportVariable('RELEASE_ID', response.data.id);
core.exportVariable('RELEASE_UPLOAD_URL', response.data.upload_url);
} catch (error) {
core.setFailed(error.message);
}
- name: Fetch Release Notes
id: release-notes
uses: actions/github-script@v6
with:
github-token: "${{ secrets.GITHUB_TOKEN }}"
script: |
try {
const response = await github.rest.repos.getRelease({
owner: context.repo.owner,
repo: context.repo.repo,
release_id: process.env.RELEASE_ID,
});
const formattedBody = JSON.stringify(response.data.body).slice(1, -1);
return formattedBody;
} catch (error) {
core.setFailed(error.message);
}
env:
RELEASE_ID: ${{ env.RELEASE_ID }}
- name: Github Releases To Discord
env:
WEBHOOK_URL: ${{ secrets.WEBHOOK_URL }}
REALEASE_TAG: ${{ env.RELEASE_TAG }}
RELEASE_NOTES: ${{ steps.release-notes.outputs.result }}
run: |
curl -H "Content-Type: application/json" -X POST -d '{
"content": "New LiteLLM release '"${RELEASE_TAG}"'",
"username": "Release Changelog",
"avatar_url": "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png",
"embeds": [
{
"title": "Changelog for LiteLLM '"${RELEASE_TAG}"'",
"description": "'"${RELEASE_NOTES}"'",
"color": 2105893
}
]
}' $WEBHOOK_URL

67
.github/workflows/ghcr_helm_deploy.yml vendored
View file

@ -1,67 +0,0 @@
# Standalone workflow to publish LiteLLM Helm Chart
# Note: The main ghcr_deploy.yml workflow also publishes the Helm chart as part of a full release
name: Build, Publish LiteLLM Helm Chart. New Release
on:
workflow_dispatch:
inputs:
tag:
description: "LiteLLM version tag (e.g., v1.81.0)"
required: true
# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
env:
REGISTRY: ghcr.io
IMAGE_NAME: ${{ github.repository }}
REPO_OWNER: ${{github.repository_owner}}
# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
jobs:
build-and-push-helm-chart:
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Log in to the Container registry
uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
with:
registry: ${{ env.REGISTRY }}
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: lowercase github.repository_owner
run: |
echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
# Sync Helm chart version with LiteLLM release version (1-1 versioning)
- name: Calculate chart and app versions
id: chart_version
shell: bash
run: |
INPUT_TAG="${{ github.event.inputs.tag }}"
# Chart version = LiteLLM version without 'v' prefix
# v1.81.0 -> 1.81.0
CHART_VERSION="${INPUT_TAG#v}"
# App version = Docker tag (keeps 'v' prefix)
APP_VERSION="${INPUT_TAG}"
echo "version=${CHART_VERSION}" | tee -a $GITHUB_OUTPUT
echo "app_version=${APP_VERSION}" | tee -a $GITHUB_OUTPUT
- name: Lint helm chart
run: helm lint deploy/charts/litellm-helm
- uses: ./.github/actions/helm-oci-chart-releaser
with:
name: litellm-helm
repository: ${{ env.REPO_OWNER }}
tag: ${{ steps.chart_version.outputs.version }}
app_version: ${{ steps.chart_version.outputs.app_version }}
path: deploy/charts/litellm-helm
registry: ${{ env.REGISTRY }}
registry_username: ${{ github.actor }}
registry_password: ${{ secrets.GITHUB_TOKEN }}
update_dependencies: true

19
.github/workflows/helm_unit_test.yml vendored
View file

@ -11,17 +11,26 @@ jobs:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v2
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Set up Helm 3.11.1
uses: azure/setup-helm@v1
uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
with:
version: '3.11.1'
version: "3.11.1"
- name: Install Helm Unit Test Plugin
run: |
helm plugin install https://github.com/helm-unittest/helm-unittest --version v0.4.4
- name: Verify Helm Unit Test Plugin integrity
run: |
EXPECTED_SHA="e251ba198448629678ff2168e1a469249d998155"
PLUGIN_DIR="$(helm env HELM_PLUGINS)/helm-unittest"
ACTUAL_SHA="$(git -C "$PLUGIN_DIR" rev-parse HEAD)"
if [ "$ACTUAL_SHA" != "$EXPECTED_SHA" ]; then
echo "::error::Helm unittest plugin checksum mismatch! Expected $EXPECTED_SHA but got $ACTUAL_SHA"
exit 1
fi
echo "Helm unittest plugin integrity verified: $ACTUAL_SHA"
- name: Run unit tests
run:
helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm
run: helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm

2
.github/workflows/interpret_load_test.py vendored
View file

@ -123,7 +123,7 @@ if __name__ == "__main__":
+ docker_run_command
+ "\n\n"
+ "### Don't want to maintain your internal proxy? get in touch 🎉"
+ "\nHosted Proxy Alpha: https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions"
+ "\nHosted Proxy Alpha: https://enterprise.litellm.ai/demo"
+ "\n\n"
+ "## Load Test LiteLLM Proxy Results"
+ "\n\n"

11
.github/workflows/issue-keyword-labeler.yml vendored
View file

@ -2,8 +2,8 @@ name: Issue Keyword Labeler
on:
issues:
types:
- opened
types:
- opened
jobs:
scan-and-label:
@ -13,7 +13,7 @@ jobs:
contents: read
steps:
- name: Checkout code
uses: actions/checkout@v4
uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
- name: Scan for provider keywords
id: scan
@ -24,7 +24,7 @@ jobs:
- name: Ensure label exists
if: steps.scan.outputs.found == 'true'
uses: actions/github-script@v7
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
@ -51,7 +51,7 @@ jobs:
- name: Add label to the issue
if: steps.scan.outputs.found == 'true'
uses: actions/github-script@v7
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |
@ -61,4 +61,3 @@ jobs:
issue_number: context.issue.number,
labels: ['llm translation']
});

2
.github/workflows/label-component.yml vendored
View file

@ -12,7 +12,7 @@ jobs:
issues: write
steps:
- name: Add component labels
uses: actions/github-script@v7
uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
script: |

34
.github/workflows/main.yml vendored
View file

@ -1,34 +0,0 @@
name: Publish Dev Release to PyPI
on:
workflow_dispatch:
jobs:
publish-dev-release:
runs-on: ubuntu-latest
steps:
- name: Checkout code
uses: actions/checkout@v2
- name: Set up Python
uses: actions/setup-python@v2
with:
python-version: 3.8 # Adjust the Python version as needed
- name: Install dependencies
run: pip install toml twine
- name: Read version from pyproject.toml
id: read-version
run: |
version=$(python -c 'import toml; print(toml.load("pyproject.toml")["tool"]["commitizen"]["version"])')
printf "LITELLM_VERSION=%s" "$version" >> $GITHUB_ENV
- name: Check if version exists on PyPI
id: check-version
run: |
set -e
if twine check --repository-url https://pypi.org/simple/ "litellm==$LITELLM_VERSION" >/dev/null 2>&1; then
echo "Version $LITELLM_VERSION already exists on PyPI. Skipping publish."

207
.github/workflows/publish-migrations.yml vendored
View file

@ -1,207 +0,0 @@
name: Publish Prisma Migrations
permissions:
contents: write
pull-requests: write
on:
push:
paths:
- 'schema.prisma' # Check root schema.prisma
branches:
- main
jobs:
publish-migrations:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
services:
postgres:
image: postgres:14
env:
POSTGRES_DB: temp_db
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
ports:
- 5432:5432
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
# Add shadow database service
postgres_shadow:
image: postgres:14
env:
POSTGRES_DB: shadow_db
POSTGRES_USER: postgres
POSTGRES_PASSWORD: postgres
ports:
- 5433:5432
options: >-
--health-cmd pg_isready
--health-interval 10s
--health-timeout 5s
--health-retries 5
steps:
- uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.x'
- name: Install Dependencies
run: |
pip install prisma
pip install python-dotenv
- name: Generate Initial Migration if None Exists
env:
DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
run: |
mkdir -p deploy/migrations
echo 'provider = "postgresql"' > deploy/migrations/migration_lock.toml
if [ -z "$(ls -A deploy/migrations/2* 2>/dev/null)" ]; then
echo "No existing migrations found, creating baseline..."
VERSION=$(date +%Y%m%d%H%M%S)
mkdir -p deploy/migrations/${VERSION}_initial
echo "Generating initial migration..."
# Save raw output for debugging
prisma migrate diff \
--from-empty \
--to-schema-datamodel schema.prisma \
--shadow-database-url "${SHADOW_DATABASE_URL}" \
--script > deploy/migrations/${VERSION}_initial/raw_migration.sql
echo "Raw migration file content:"
cat deploy/migrations/${VERSION}_initial/raw_migration.sql
echo "Cleaning migration file..."
# Clean the file
sed '/^Installing/d' deploy/migrations/${VERSION}_initial/raw_migration.sql > deploy/migrations/${VERSION}_initial/migration.sql
# Verify the migration file
if [ ! -s deploy/migrations/${VERSION}_initial/migration.sql ]; then
echo "ERROR: Migration file is empty after cleaning"
echo "Original content was:"
cat deploy/migrations/${VERSION}_initial/raw_migration.sql
exit 1
fi
echo "Final migration file content:"
cat deploy/migrations/${VERSION}_initial/migration.sql
# Verify it starts with SQL
if ! head -n 1 deploy/migrations/${VERSION}_initial/migration.sql | grep -q "^--\|^CREATE\|^ALTER"; then
echo "ERROR: Migration file does not start with SQL command or comment"
echo "First line is:"
head -n 1 deploy/migrations/${VERSION}_initial/migration.sql
echo "Full content is:"
cat deploy/migrations/${VERSION}_initial/migration.sql
exit 1
fi
echo "Initial migration generated at $(date -u)" > deploy/migrations/${VERSION}_initial/README.md
fi
- name: Compare and Generate Migration
if: success()
env:
DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
run: |
# Create temporary migration workspace
mkdir -p temp_migrations
# Copy existing migrations (will not fail if directory is empty)
cp -r deploy/migrations/* temp_migrations/ 2>/dev/null || true
VERSION=$(date +%Y%m%d%H%M%S)
# Generate diff against existing migrations or empty state
prisma migrate diff \
--from-migrations temp_migrations \
--to-schema-datamodel schema.prisma \
--shadow-database-url "${SHADOW_DATABASE_URL}" \
--script > temp_migrations/migration_${VERSION}.sql
# Check if there are actual changes
if [ -s temp_migrations/migration_${VERSION}.sql ]; then
echo "Changes detected, creating new migration"
mkdir -p deploy/migrations/${VERSION}_schema_update
mv temp_migrations/migration_${VERSION}.sql deploy/migrations/${VERSION}_schema_update/migration.sql
echo "Migration generated at $(date -u)" > deploy/migrations/${VERSION}_schema_update/README.md
else
echo "No schema changes detected"
exit 0
fi
- name: Verify Migration
if: success()
env:
DATABASE_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
DIRECT_URL: "postgresql://postgres:postgres@localhost:5432/temp_db"
SHADOW_DATABASE_URL: "postgresql://postgres:postgres@localhost:5433/shadow_db"
run: |
# Create test database
psql "${SHADOW_DATABASE_URL}" -c 'CREATE DATABASE migration_test;'
# Apply all migrations in order to verify
for migration in deploy/migrations/*/migration.sql; do
echo "Applying migration: $migration"
psql "${SHADOW_DATABASE_URL}" -f $migration
done
# Add this step before create-pull-request to debug permissions
- name: Check Token Permissions
run: |
echo "Checking token permissions..."
curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
-H "Accept: application/vnd.github.v3+json" \
https://api.github.com/repos/BerriAI/litellm/collaborators
echo "\nChecking if token can create PRs..."
curl -H "Authorization: token ${{ secrets.GITHUB_TOKEN }}" \
-H "Accept: application/vnd.github.v3+json" \
https://api.github.com/repos/BerriAI/litellm
# Add this debug step before git push
- name: Debug Changed Files
run: |
echo "Files staged for commit:"
git diff --name-status --staged
echo "\nAll changed files:"
git status
- name: Create Pull Request
if: success()
uses: peter-evans/create-pull-request@v5
with:
token: ${{ secrets.GITHUB_TOKEN }}
commit-message: "chore: update prisma migrations"
title: "Update Prisma Migrations"
body: |
Auto-generated migration based on schema.prisma changes.
Generated files:
- deploy/migrations/${VERSION}_schema_update/migration.sql
- deploy/migrations/${VERSION}_schema_update/README.md
branch: feat/prisma-migration-${{ env.VERSION }}
base: main
delete-branch: true
- name: Generate and Save Migrations
run: |
# Only add migration files
git add deploy/migrations/
git status # Debug what's being committed
git commit -m "chore: update prisma migrations"

94
.github/workflows/publish_enterprise.yml vendored
View file

@ -1,94 +0,0 @@
name: Publish litellm-enterprise to PyPI
on:
workflow_dispatch:
inputs:
bump:
description: "Version bump type"
required: true
default: "patch"
type: choice
options:
- patch
- minor
- major
jobs:
publish:
runs-on: ubuntu-latest
if: github.repository == 'BerriAI/litellm'
permissions:
contents: write
pull-requests: write
defaults:
run:
working-directory: enterprise
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install Poetry
run: pip install poetry
- name: Bump version
id: bump
run: |
OLD=$(poetry version -s)
poetry version ${{ github.event.inputs.bump }}
NEW=$(poetry version -s)
echo "old=$OLD" >> $GITHUB_OUTPUT
echo "new=$NEW" >> $GITHUB_OUTPUT
- name: Update version refs in root pyproject.toml and requirements.txt
run: |
OLD=${{ steps.bump.outputs.old }}
NEW=${{ steps.bump.outputs.new }}
sed -i "s/litellm-enterprise = {version = \"${OLD}\"/litellm-enterprise = {version = \"${NEW}\"/" ../pyproject.toml
sed -i "s/litellm-enterprise==${OLD}/litellm-enterprise==${NEW}/" ../requirements.txt
- name: Update poetry.lock
working-directory: .
run: poetry lock
- name: Build
run: poetry build
- name: Commit version bump and create PR
id: create-pr
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
cd ..
BRANCH="bump/enterprise-${{ steps.bump.outputs.new }}"
git checkout -b "$BRANCH"
git add enterprise/pyproject.toml pyproject.toml requirements.txt poetry.lock
git commit -m "bump: litellm-enterprise ${{ steps.bump.outputs.old }} → ${{ steps.bump.outputs.new }}"
git push origin "$BRANCH" --force
gh pr create \
--title "bump: litellm-enterprise ${{ steps.bump.outputs.old }} → ${{ steps.bump.outputs.new }}" \
--body "Version bump for litellm-enterprise. Merge to update main." \
--head "$BRANCH" \
--base main \
|| true
PR_URL=$(gh pr list --head "$BRANCH" --json url -q '.[0].url')
echo "pr_url=$PR_URL" >> $GITHUB_OUTPUT
env:
GH_TOKEN: ${{ github.token }}
- name: Enable auto-merge
run: |
gh pr merge "${{ steps.create-pr.outputs.pr_url }}" --auto --squash
env:
GH_TOKEN: ${{ github.token }}
- name: Publish to PyPI
env:
TWINE_USERNAME: __token__
TWINE_PASSWORD: ${{ secrets.PYPI_ENTERPRISE }}
run: |
pip install twine
twine upload dist/litellm_enterprise-${{ steps.bump.outputs.new }}*

74
.github/workflows/publish_proxy_extras.yml vendored
View file

@ -1,74 +0,0 @@
name: Publish litellm-proxy-extras to PyPI
on:
workflow_dispatch:
inputs:
bump:
description: "Version bump type"
required: true
default: "patch"
type: choice
options:
- patch
- minor
- major
jobs:
publish:
runs-on: ubuntu-latest
if: github.repository == 'BerriAI/litellm'
permissions:
contents: write
defaults:
run:
working-directory: litellm-proxy-extras
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: "3.11"
- name: Install Poetry
run: pip install poetry
- name: Bump version
id: bump
run: |
OLD=$(poetry version -s)
poetry version ${{ github.event.inputs.bump }}
NEW=$(poetry version -s)
echo "old=$OLD" >> $GITHUB_OUTPUT
echo "new=$NEW" >> $GITHUB_OUTPUT
- name: Update version refs in root pyproject.toml and requirements.txt
run: |
OLD=${{ steps.bump.outputs.old }}
NEW=${{ steps.bump.outputs.new }}
sed -i "s/litellm-proxy-extras = {version = \"${OLD}\"/litellm-proxy-extras = {version = \"${NEW}\"/" ../pyproject.toml
sed -i "s/litellm-proxy-extras==${OLD}/litellm-proxy-extras==${NEW}/" ../requirements.txt
- name: Update poetry.lock
working-directory: .
run: poetry lock
- name: Build
run: poetry build
- name: Commit version bump
run: |
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
cd ..
git add litellm-proxy-extras/pyproject.toml pyproject.toml requirements.txt poetry.lock
git commit -m "bump: litellm-proxy-extras ${{ steps.bump.outputs.old }} → ${{ steps.bump.outputs.new }}"
git push
- name: Publish to PyPI
env:
TWINE_USERNAME: __token__
TWINE_PASSWORD: ${{ secrets.PYPI_PUBLISH_PASSWORD }}
run: |
pip install twine
twine upload dist/litellm_proxy_extras-${{ steps.bump.outputs.new }}*

39
.github/workflows/reset_stable.yml vendored
View file

@ -1,39 +0,0 @@
name: Reset litellm_stable branch
on:
release:
types: [published, created]
jobs:
update-stable-branch:
if: ${{ startsWith(github.event.release.tag_name, 'v') && !endsWith(github.event.release.tag_name, '-stable') }}
runs-on: ubuntu-latest
steps:
- name: Checkout repository
uses: actions/checkout@v3
- name: Reset litellm_stable_release_branch branch to the release commit
env:
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
run: |
# Configure Git user
git config user.name "github-actions[bot]"
git config user.email "github-actions[bot]@users.noreply.github.com"
# Fetch all branches and tags
git fetch --all
# Check if the litellm_stable_release_branch branch exists
if git show-ref --verify --quiet refs/remotes/origin/litellm_stable_release_branch; then
echo "litellm_stable_release_branch branch exists."
git checkout litellm_stable_release_branch
else
echo "litellm_stable_release_branch branch does not exist. Creating it."
git checkout -b litellm_stable_release_branch
fi
# Reset litellm_stable_release_branch branch to the release commit
git reset --hard $GITHUB_SHA
# Push the updated litellm_stable_release_branch branch
git push origin litellm_stable_release_branch --force

67
.github/workflows/simple_pypi_publish.yml vendored
View file

@ -1,67 +0,0 @@
name: Simple PyPI Publish
on:
workflow_dispatch:
inputs:
version:
description: 'Version to publish (e.g., 1.74.10)'
required: true
type: string
env:
TWINE_USERNAME: __token__
jobs:
publish:
runs-on: ubuntu-latest
if: github.repository == 'BerriAI/litellm'
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: '3.8'
- name: Install dependencies
run: |
python -m pip install --upgrade pip
pip install toml build wheel twine
- name: Update version in pyproject.toml
run: |
python -c "
import toml
with open('pyproject.toml', 'r') as f:
data = toml.load(f)
data['tool']['poetry']['version'] = '${{ github.event.inputs.version }}'
with open('pyproject.toml', 'w') as f:
toml.dump(data, f)
print(f'Updated version to ${{ github.event.inputs.version }}')
"
- name: Copy model prices file
run: |
cp model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json
- name: Build package
run: |
rm -rf build dist
python -m build
- name: Publish to PyPI
env:
TWINE_PASSWORD: ${{ secrets.PYPI_PUBLISH_PASSWORD }}
run: |
twine upload dist/*
- name: Output success
run: |
echo "✅ Successfully published litellm v${{ github.event.inputs.version }} to PyPI"
echo "📦 Package: https://pypi.org/project/litellm/${{ github.event.inputs.version }}/"

1
.github/workflows/stale.yml vendored
View file

@ -7,6 +7,7 @@ on:
jobs:
stale:
if: github.repository == 'BerriAI/litellm'
runs-on: ubuntu-latest
steps:
- uses: actions/stale@v8

18
.semgrep/rules/security/no-claude-directory.yml Normal file
View file

@ -0,0 +1,18 @@
rules:
- id: no-claude-directory-committed
message: >
.claude/ directory must not be committed to the repository.
It contains local Claude Code settings (permissions, worktree paths) that are
developer-machine-specific and may expose internal paths or credentials.
Add .claude/ to .gitignore instead.
severity: ERROR
languages: [generic]
paths:
include:
- "/.claude/**"
- "/.claude/*"
pattern-regex: '[\s\S]+'
metadata:
category: security
tags: [supply-chain, secrets]
confidence: HIGH

3
README.md
View file

@ -402,7 +402,7 @@ Support for more providers. Missing a provider or LLM Platform, raise a [feature
# Enterprise
For companies that need better security, user management and professional support
[Talk to founders](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Talk to founders](https://enterprise.litellm.ai/demo)
This covers:
- ✅ **Features under the [LiteLLM Commercial License](https://docs.litellm.ai/docs/proxy/enterprise):**
@ -452,7 +452,6 @@ All these checks must pass before your PR can be merged.
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- [Community Slack 💭](https://www.litellm.ai/support)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
# Why did we build this

12
ci_cd/security_scans.sh
View file

@ -10,13 +10,13 @@ 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 apt-transport-https gnupg lsb-release jq curl bsdmainutils
wget -qO - https://aquasecurity.github.io/trivy-repo/deb/public.key | sudo apt-key add -
echo "deb https://aquasecurity.github.io/trivy-repo/deb $(lsb_release -sc) main" | sudo tee -a /etc/apt/sources.list.d/trivy.list
sudo apt-get update
sudo apt-get install trivy
echo "Trivy and required tools installed successfully"
sudo apt-get install -y wget jq curl bsdmainutils
wget -qO trivy.deb "https://github.com/aquasecurity/trivy/releases/download/v${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

2
cookbook/benchmark/readme.md
View file

@ -178,4 +178,4 @@ Benchmark Results for 'When will BerriAI IPO?':
```
## Support
**🤝 Schedule a 1-on-1 Session:** Book a [1-on-1 session](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions) with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.
**🤝 Schedule a 1-on-1 Session:** Book a [1-on-1 session](https://enterprise.litellm.ai/demo) with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.

1
cookbook/codellama-server/README.MD
View file

@ -143,7 +143,6 @@ All responses from the server are returned in the following format (for all LLM
- [Our calendar 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
## Roadmap

1
cookbook/litellm_proxy_server/readme.md
View file

@ -164,7 +164,6 @@ All responses from the server are returned in the following format (for all LLM
- [Our calendar 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
## Roadmap

709
docs/my-website/blog/security_update_march_2026/index.md Normal file
View file

@ -0,0 +1,709 @@
---
slug: security-update-march-2026
title: "Security Update: Suspected Supply Chain Incident"
date: 2026-03-24T14:00:00
authors:
- krrish
- ishaan-alt
description: "As of 2:00 PM ET on March 24, 2026"
tags: [security, incident-report]
hide_table_of_contents: false
---
import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
> **Status:** Active investigation
> **Last updated:** March 25, 2026
> **Update (March 25):** Added community-contributed scripts for scanning GitHub Actions and GitLab CI pipelines for the compromised versions. See [How to check if you are affected](#how-to-check-if-you-are-affected). s/o [@Zach Fury](https://www.linkedin.com/in/fryware/) for these scripts.
## TLDR;
- The compromised PyPI packages were **litellm==1.82.7** and **litellm==1.82.8**. Those packages have now been removed from PyPI.
- We believe that the compromise originated from the Trivy dependency used in our CI/CD security scanning workflow.
- Customers running the official LiteLLM Proxy Docker image were not impacted. That deployment path pins dependencies in requirements.txt and does not rely on the compromised PyPI packages.
- We are pausing new LiteLLM releases until we complete a broader supply-chain review and confirm the release path is safe.
## Overview
LiteLLM AI Gateway is investigating a suspected supply chain attack involving unauthorized PyPI package publishes. Current evidence suggests a maintainer's PyPI account may have been compromised and used to distribute malicious code.
At this time, we believe this incident may be linked to the broader [Trivy security compromise](https://www.aquasec.com/blog/trivy-supply-chain-attack-what-you-need-to-know/), in which stolen credentials were reportedly used to gain unauthorized access to the LiteLLM publishing pipeline.
This investigation is ongoing. Details below may change as we confirm additional findings.
## Confirmed affected versions
The following LiteLLM versions published to PyPI were impacted:
- **v1.82.7**: contained a malicious payload in the LiteLLM AI Gateway `proxy_server.py`
- **v1.82.8**: contained `litellm_init.pth` and a malicious payload in the LiteLLM AI Gateway `proxy_server.py`
If you installed or ran either of these versions, review the recommendations below immediately.
Note: These versions have already been removed from PyPI.
## What happened
Initial evidence suggests the attacker bypassed official CI/CD workflows and uploaded malicious packages directly to PyPI.
These compromised versions appear to have included a credential stealer designed to:
- Harvest secrets by scanning for:
- environment variables
- SSH keys
- cloud provider credentials (AWS, GCP, Azure)
- Kubernetes tokens
- database passwords
- Encrypt and exfiltrate data via a `POST` request to `models.litellm.cloud`, which is **not** an official BerriAI / LiteLLM domain
## Who is affected
You may be affected if **any** of the following are true:
- You installed or upgraded LiteLLM via `pip` on **March 24, 2026**, between **10:39 UTC and 16:00 UTC**
- You ran `pip install litellm` without pinning a version and received **v1.82.7** or **v1.82.8**
- You built a Docker image during this window that included `pip install litellm` without a pinned version
- A dependency in your project pulled in LiteLLM as a transitive, unpinned dependency
(for example through AI agent frameworks, MCP servers, or LLM orchestration tools)
You are **not** affected if any of the following are true:
**LiteLLM AI Gateway/Proxy users:** Customers running the official LiteLLM Proxy Docker image were not impacted. That deployment path pins dependencies in requirements.txt and does not rely on the compromised PyPI packages.
- You are using **LiteLLM Cloud**
- You are using the official LiteLLM AI Gateway Docker image: `ghcr.io/berriai/litellm`
- You are on **v1.82.6 or earlier** and did not upgrade during the affected window
- You installed LiteLLM from source via the GitHub repository, which was **not** compromised
### How to check if you are affected
<Tabs>
<TabItem value="sdk" label="SDK">
```bash
pip show litellm
```
</TabItem>
<TabItem value="proxy" label="PROXY">
Go to the proxy base url, and check the version of the installed LiteLLM.
![Proxy version check](../../img/security_update_march_2026/proxy_version.png)
</TabItem>
<TabItem value="github" label="GitHub Actions">
Scans all repositories in a GitHub organization for workflow jobs that installed the compromised versions.
**Requirements:** Python 3 and `requests` (`pip install requests`).
**Setup:**
```bash
export GITHUB_TOKEN="your-github-pat"
```
**Run:**
```bash
python find_litellm_github.py
```
Set the `ORG` variable in the script to your GitHub organization name.
Both scripts default to scanning jobs from **today**. Adjust the `WINDOW_START` and `WINDOW_END` constants to cover **March 24, 2026** (the incident date) if running on a different day.
<details>
<summary>View full script (find_litellm_github.py)</summary>
```python
#!/usr/bin/env python3
"""
Scan all GitHub Actions jobs in a GitHub org that ran between
0800-1244 UTC today and identify any that installed litellm 1.82.7 or 1.82.8.
Adjust WINDOW_START / WINDOW_END to cover March 24, 2026 if running later.
"""
import io
import os
import re
import sys
import zipfile
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timezone
import requests
GITHUB_URL = "https://api.github.com"
ORG = "your-org" # <-- set to your GitHub organization
TOKEN = os.environ.get("GITHUB_TOKEN", "")
TODAY = datetime.now(timezone.utc).date()
WINDOW_START = datetime(TODAY.year, TODAY.month, TODAY.day, 8, 0, 0, tzinfo=timezone.utc)
WINDOW_END = datetime(TODAY.year, TODAY.month, TODAY.day, 12, 44, 0, tzinfo=timezone.utc)
TARGET_VERSIONS = {"1.82.7", "1.82.8"}
VERSION_PATTERN = re.compile(r"litellm[=\-](\d+\.\d+\.\d+)", re.IGNORECASE)
SESSION = requests.Session()
SESSION.headers.update({
"Authorization": f"Bearer {TOKEN}",
"Accept": "application/vnd.github+json",
"X-GitHub-Api-Version": "2022-11-28",
})
def get_paginated(url, params=None):
params = dict(params or {})
params.setdefault("per_page", 100)
page = 1
while True:
params["page"] = page
resp = SESSION.get(url, params=params, timeout=30)
if resp.status_code == 404:
return
resp.raise_for_status()
data = resp.json()
if isinstance(data, dict):
items = next((v for v in data.values() if isinstance(v, list)), [])
else:
items = data
if not items:
break
yield from items
if len(items) < params["per_page"]:
break
page += 1
def parse_ts(ts_str):
if not ts_str:
return None
return datetime.fromisoformat(ts_str.replace("Z", "+00:00"))
def get_repos():
repos = []
for r in get_paginated(f"{GITHUB_URL}/orgs/{ORG}/repos", {"type": "all"}):
repos.append({"id": r["id"], "name": r["name"], "full_name": r["full_name"]})
return repos
def get_runs_in_window(repo_full_name):
created_filter = (
f"{WINDOW_START.strftime('%Y-%m-%dT%H:%M:%SZ')}"
f"..{WINDOW_END.strftime('%Y-%m-%dT%H:%M:%SZ')}"
)
url = f"{GITHUB_URL}/repos/{repo_full_name}/actions/runs"
runs = []
for run in get_paginated(url, {"created": created_filter, "per_page": 100}):
ts = parse_ts(run.get("run_started_at") or run.get("created_at"))
if ts and WINDOW_START <= ts <= WINDOW_END:
runs.append(run)
return runs
def get_jobs_for_run(repo_full_name, run_id):
url = f"{GITHUB_URL}/repos/{repo_full_name}/actions/runs/{run_id}/jobs"
jobs = []
for job in get_paginated(url, {"filter": "all"}):
ts = parse_ts(job.get("started_at"))
if ts and WINDOW_START <= ts <= WINDOW_END:
jobs.append(job)
return jobs
def fetch_job_log(repo_full_name, job_id):
url = f"{GITHUB_URL}/repos/{repo_full_name}/actions/jobs/{job_id}/logs"
resp = SESSION.get(url, timeout=60, allow_redirects=True)
if resp.status_code in (403, 404, 410):
return ""
resp.raise_for_status()
content_type = resp.headers.get("Content-Type", "")
if "zip" in content_type or resp.content[:2] == b"PK":
try:
with zipfile.ZipFile(io.BytesIO(resp.content)) as zf:
parts = []
for name in sorted(zf.namelist()):
with zf.open(name) as f:
parts.append(f.read().decode("utf-8", errors="replace"))
return "\n".join(parts)
except zipfile.BadZipFile:
pass
return resp.text
def check_job(repo_full_name, job):
job_id = job["id"]
job_name = job["name"]
run_id = job["run_id"]
started = job.get("started_at", "")
log_text = fetch_job_log(repo_full_name, job_id)
if not log_text:
return None
found_versions = set()
context_lines = []
for line in log_text.splitlines():
m = VERSION_PATTERN.search(line)
if m:
ver = m.group(1)
if ver in TARGET_VERSIONS:
found_versions.add(ver)
context_lines.append(line.strip())
if not found_versions:
return None
return {
"repo": repo_full_name,
"run_id": run_id,
"job_id": job_id,
"job_name": job_name,
"started_at": started,
"versions": sorted(found_versions),
"context": context_lines[:10],
"job_url": job.get("html_url", f"https://github.com/{repo_full_name}/actions/runs/{run_id}"),
}
def main():
if not TOKEN:
print("ERROR: Set GITHUB_TOKEN environment variable.", file=sys.stderr)
sys.exit(1)
print(f"Time window : {WINDOW_START.isoformat()} -> {WINDOW_END.isoformat()}")
print(f"Hunting for : litellm {', '.join(sorted(TARGET_VERSIONS))}")
print()
print(f"Fetching repositories for org '{ORG}'...")
repos = get_repos()
print(f" Found {len(repos)} repositories")
print()
jobs_to_check = []
print("Scanning workflow runs for time window...")
for repo in repos:
full_name = repo["full_name"]
try:
runs = get_runs_in_window(full_name)
except requests.HTTPError as e:
print(f" WARN: {full_name} - {e}", file=sys.stderr)
continue
if not runs:
continue
print(f" {full_name}: {len(runs)} run(s) in window")
for run in runs:
try:
jobs = get_jobs_for_run(full_name, run["id"])
except requests.HTTPError as e:
print(f" WARN: run {run['id']} - {e}", file=sys.stderr)
continue
for job in jobs:
jobs_to_check.append((full_name, job))
total = len(jobs_to_check)
print(f"\nFetching logs for {total} job(s)...")
print()
hits = []
with ThreadPoolExecutor(max_workers=8) as pool:
futures = {
pool.submit(check_job, full_name, job): (full_name, job["id"])
for full_name, job in jobs_to_check
}
done = 0
for future in as_completed(futures):
done += 1
full_name, jid = futures[future]
try:
result = future.result()
except Exception as e:
print(f" ERROR {full_name} job {jid}: {e}", file=sys.stderr)
continue
if result:
hits.append(result)
print(
f" [{done}/{total}] {full_name} job {jid}" +
(f" *** HIT: litellm {result['versions']} ***" if result else ""),
flush=True,
)
print()
print("=" * 72)
print(f"RESULTS: {len(hits)} job(s) installed litellm {' or '.join(sorted(TARGET_VERSIONS))}")
print("=" * 72)
if not hits:
print("No matches found.")
return
for h in sorted(hits, key=lambda x: x["started_at"]):
print()
print(f" Repo : {h['repo']}")
print(f" Job : {h['job_name']} (#{h['job_id']})")
print(f" Run ID : {h['run_id']}")
print(f" Started : {h['started_at']}")
print(f" Versions : litellm {', '.join(h['versions'])}")
print(f" URL : {h['job_url']}")
print(f" Log lines :")
for line in h["context"]:
print(f" {line}")
if __name__ == "__main__":
main()
```
</details>
</TabItem>
<TabItem value="gitlab" label="GitLab CI">
Scans all projects in a GitLab group (including subgroups) for CI/CD jobs that installed the compromised versions.
**Requirements:** Python 3 and `requests` (`pip install requests`).
**Setup:**
```bash
export GITLAB_TOKEN="your-gitlab-pat"
```
**Run:**
```bash
python find_litellm_jobs.py
```
Set the `GROUP_NAME` variable in the script to your GitLab group name.
Both scripts default to scanning jobs from **today**. Adjust the `WINDOW_START` and `WINDOW_END` constants to cover **March 24, 2026** (the incident date) if running on a different day.
<details>
<summary>View full script (find_litellm_jobs.py)</summary>
```python
#!/usr/bin/env python3
"""
Scan all GitLab CI/CD jobs in a GitLab group that ran between
0800-1244 UTC today and identify any that installed litellm 1.82.7 or 1.82.8.
Adjust WINDOW_START / WINDOW_END to cover March 24, 2026 if running later.
"""
import os
import re
import sys
from concurrent.futures import ThreadPoolExecutor, as_completed
from datetime import datetime, timezone
import requests
GITLAB_URL = "https://gitlab.com"
GROUP_NAME = "YourGroup" # <-- set to your GitLab group name
TOKEN = os.environ.get("GITLAB_TOKEN", "")
TODAY = datetime.now(timezone.utc).date()
WINDOW_START = datetime(TODAY.year, TODAY.month, TODAY.day, 8, 0, 0, tzinfo=timezone.utc)
WINDOW_END = datetime(TODAY.year, TODAY.month, TODAY.day, 12, 44, 0, tzinfo=timezone.utc)
TARGET_VERSIONS = {"1.82.7", "1.82.8"}
VERSION_PATTERN = re.compile(r"litellm[=\-](\d+\.\d+\.\d+)", re.IGNORECASE)
HEADERS = {"PRIVATE-TOKEN": TOKEN}
SESSION = requests.Session()
SESSION.headers.update(HEADERS)
def get_paginated(url, params=None):
params = dict(params or {})
params.setdefault("per_page", 100)
page = 1
while True:
params["page"] = page
resp = SESSION.get(url, params=params, timeout=30)
resp.raise_for_status()
data = resp.json()
if not data:
break
yield from data
if len(data) < params["per_page"]:
break
page += 1
def get_group_id(group_name):
resp = SESSION.get(f"{GITLAB_URL}/api/v4/groups/{group_name}", timeout=30)
resp.raise_for_status()
return resp.json()["id"]
def get_all_projects(group_id):
projects = []
for p in get_paginated(
f"{GITLAB_URL}/api/v4/groups/{group_id}/projects",
{"include_subgroups": "true", "archived": "false"},
):
projects.append({"id": p["id"], "name": p["path_with_namespace"]})
return projects
def parse_ts(ts_str):
if not ts_str:
return None
ts_str = ts_str.replace("Z", "+00:00")
return datetime.fromisoformat(ts_str)
def jobs_in_window(project_id):
matching = []
url = f"{GITLAB_URL}/api/v4/projects/{project_id}/jobs"
params = {"per_page": 100, "scope[]": ["success", "failed", "canceled", "running"]}
page = 1
while True:
params["page"] = page
resp = SESSION.get(url, params=params, timeout=30)
if resp.status_code == 403:
return matching
resp.raise_for_status()
jobs = resp.json()
if not jobs:
break
stop_early = False
for job in jobs:
ts = parse_ts(job.get("started_at") or job.get("created_at"))
if ts is None:
continue
if ts > WINDOW_END:
continue
if ts < WINDOW_START:
stop_early = True
continue
matching.append(job)
if stop_early or len(jobs) < 100:
break
page += 1
return matching
def fetch_trace(project_id, job_id):
url = f"{GITLAB_URL}/api/v4/projects/{project_id}/jobs/{job_id}/trace"
resp = SESSION.get(url, timeout=60)
if resp.status_code in (403, 404):
return ""
resp.raise_for_status()
return resp.text
def check_job(project_name, project_id, job):
job_id = job["id"]
job_name = job["name"]
ref = job.get("ref", "")
started = job.get("started_at", job.get("created_at", ""))
trace = fetch_trace(project_id, job_id)
if not trace:
return None
found_versions = set()
for match in VERSION_PATTERN.finditer(trace):
ver = match.group(1)
if ver in TARGET_VERSIONS:
found_versions.add(ver)
if not found_versions:
return None
context_lines = []
for line in trace.splitlines():
if VERSION_PATTERN.search(line):
ver_match = VERSION_PATTERN.search(line)
if ver_match and ver_match.group(1) in TARGET_VERSIONS:
context_lines.append(line.strip())
return {
"project": project_name,
"project_id": project_id,
"job_id": job_id,
"job_name": job_name,
"ref": ref,
"started_at": started,
"versions": sorted(found_versions),
"context": context_lines[:10],
"job_url": f"{GITLAB_URL}/{project_name}/-/jobs/{job_id}",
}
def main():
if not TOKEN:
print("ERROR: Set GITLAB_TOKEN environment variable.", file=sys.stderr)
sys.exit(1)
print(f"Time window : {WINDOW_START.isoformat()} -> {WINDOW_END.isoformat()}")
print(f"Hunting for : litellm {', '.join(sorted(TARGET_VERSIONS))}")
print()
print(f"Resolving group '{GROUP_NAME}'...")
group_id = get_group_id(GROUP_NAME)
print("Fetching projects...")
projects = get_all_projects(group_id)
print(f" Found {len(projects)} projects")
print()
all_jobs_to_check = []
print("Scanning job listings for time window...")
for proj in projects:
try:
jobs = jobs_in_window(proj["id"])
except requests.HTTPError as e:
print(f" WARN: {proj['name']} - {e}", file=sys.stderr)
continue
if jobs:
print(f" {proj['name']}: {len(jobs)} job(s) in window")
for j in jobs:
all_jobs_to_check.append((proj["name"], proj["id"], j))
total = len(all_jobs_to_check)
print(f"\nFetching traces for {total} job(s)...")
print()
hits = []
with ThreadPoolExecutor(max_workers=10) as pool:
futures = {
pool.submit(check_job, pname, pid, job): (pname, job["id"])
for pname, pid, job in all_jobs_to_check
}
done = 0
for future in as_completed(futures):
done += 1
pname, jid = futures[future]
try:
result = future.result()
except Exception as e:
print(f" ERROR checking {pname} job {jid}: {e}", file=sys.stderr)
continue
if result:
hits.append(result)
print(f" [{done}/{total}] checked {pname} job {jid}" +
(f" *** HIT: litellm {result['versions']} ***" if result else ""),
flush=True)
print()
print("=" * 72)
print(f"RESULTS: {len(hits)} job(s) installed litellm {' or '.join(sorted(TARGET_VERSIONS))}")
print("=" * 72)
if not hits:
print("No matches found.")
return
for h in sorted(hits, key=lambda x: x["started_at"]):
print()
print(f" Project : {h['project']}")
print(f" Job : {h['job_name']} (#{h['job_id']})")
print(f" Branch/tag: {h['ref']}")
print(f" Started : {h['started_at']}")
print(f" Versions : litellm {', '.join(h['versions'])}")
print(f" URL : {h['job_url']}")
print(f" Log lines :")
for line in h["context"]:
print(f" {line}")
if __name__ == "__main__":
main()
```
</details>
</TabItem>
</Tabs>
*CI/CD scripts contributed by the community ([original gist](https://gist.github.com/fryz/93ec8d4898ffe5b5ac5706a208823ef3)). Review before running.*
## Indicators of compromise (IoCs)
Review affected systems for the following indicators:
- `litellm_init.pth` present in your `site-packages`
- Outbound traffic or requests to `models.litellm[.]cloud`
This domain is **not** affiliated with LiteLLM
## Immediate actions for affected users
If you installed or ran **v1.82.7** or **v1.82.8**, take the following actions immediately.
### 1. Rotate all secrets
Treat any credentials present on the affected systems as compromised, including:
- API keys
- Cloud access keys
- Database passwords
- SSH keys
- Kubernetes tokens
- Any secrets stored in environment variables or configuration files
### 2. Inspect your filesystem
Check your `site-packages` directory for a file named `litellm_init.pth`:
```bash
find /usr/lib/python3.13/site-packages/ -name "litellm_init.pth"
```
If present:
- remove it immediately
- investigate the host for further compromise
- preserve relevant artifacts if your security team is performing forensics
### 3. Audit version history
Review your:
- Local environments
- CI/CD pipelines
- Docker builds
- Deployment logs
Confirm whether **v1.82.7** or **v1.82.8** was installed anywhere.
Pin LiteLLM to a known safe version such as **v1.82.6 or earlier**, or to a later verified release once announced.
## Response and remediation
The LiteLLM AI Gateway team has already taken the following steps:
- Removed compromised packages from PyPI
- Rotated maintainer credentials and established new authorized maintainers
- Engaged Google's Mandiant security team to assist with forensic analysis of the build and publishing chain
## Questions and support
If you believe your systems may be affected, contact us immediately:
- **Security:** `security@berri.ai`
- **Support:** `support@berri.ai`
- **Slack:** Reach out to the LiteLLM team directly
For real-time updates, follow [LiteLLM (YC W23) on X](https://x.com/LiteLLM).

2
docs/my-website/docs/data_security.md
View file

@ -128,8 +128,6 @@ We'll review all reports promptly. Note that we don't currently offer a bug boun
Legal Entity Name: Berrie AI Incorporated
Company Phone Number: 7708783106
Point of contact email address for security incidents: krrish@berri.ai
Point of contact email address for general security-related questions: krrish@berri.ai

2
docs/my-website/docs/debugging/local_debugging.md
View file

@ -67,6 +67,6 @@ response = completion("command-nightly", messages, logger_fn=my_custom_logging_f
## Still Seeing Issues?
Text us @ +17708783106 or Join the [Discord](https://discord.com/invite/wuPM9dRgDw).
Join the [Discord](https://discord.com/invite/wuPM9dRgDw).
We promise to help you in `lite`ning speed ❤️

6
docs/my-website/docs/enterprise.md
View file

@ -4,7 +4,7 @@ import Image from '@theme/IdealImage';
:::info
- ✨ SSO is free for up to 5 users. After that, an enterprise license is required. [Get Started with Enterprise here](https://www.litellm.ai/enterprise)
- Who is Enterprise for? Companies giving access to 100+ users **OR** 10+ AI use-cases. If you're not sure, [get in touch with us](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions) to discuss your needs.
- Who is Enterprise for? Companies giving access to 100+ users **OR** 10+ AI use-cases. If you're not sure, [get in touch with us](https://enterprise.litellm.ai/demo) to discuss your needs.
:::
For companies that need SSO, user management and professional support for LiteLLM Proxy
@ -36,7 +36,7 @@ Manage Yourself - you can deploy our Docker Image or build a custom image from o
### What’s the cost of the Self-Managed Enterprise edition?
Self-Managed Enterprise deployments require our team to understand your exact needs. [Get in touch with us to learn more](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
Self-Managed Enterprise deployments require our team to understand your exact needs. [Get in touch with us to learn more](https://enterprise.litellm.ai/demo)
### How does deployment with Enterprise License work?
@ -106,7 +106,7 @@ Professional Support can assist with LLM/Provider integrations, deployment, upgr
Pricing is based on usage. We can figure out a price that works for your team, on the call.
[**Contact Us to learn more**](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[**Contact Us to learn more**](https://enterprise.litellm.ai/demo)

2
docs/my-website/docs/fine_tuning.md
View file

@ -6,7 +6,7 @@ import TabItem from '@theme/TabItem';
:::info
This is an Enterprise only endpoint [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
This is an Enterprise only endpoint [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::

3
docs/my-website/docs/migration.md
View file

@ -31,5 +31,4 @@ When we have breaking changes (i.e. going from 1.x.x to 2.x.x), we will document
**How can we communicate changes better?**
Tell us
- [Discord](https://discord.com/invite/wuPM9dRgDw)
- Email (krrish@berri.ai/ishaan@berri.ai)
- Text us (+17708783106)
- Email (support@berri.ai)

1
docs/my-website/docs/observability/arize_integration.md
View file

@ -194,5 +194,4 @@ print(response)
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

3
docs/my-website/docs/observability/gcs_bucket_integration.md
View file

@ -6,7 +6,7 @@ Log LLM Logs to [Google Cloud Storage Buckets](https://cloud.google.com/storage?
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::
@ -79,5 +79,4 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/langfuse_integration.md
View file

@ -342,5 +342,4 @@ Be aware that if you are continuing an existing trace, and you set `update_trace
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/langsmith_integration.md
View file

@ -225,5 +225,4 @@ environment_variables:
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/logfire_integration.md
View file

@ -63,5 +63,4 @@ response = litellm.completion(
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/lunary_integration.md
View file

@ -176,5 +176,4 @@ You can find more details about the different ways of making requests to the Lit
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/opik_integration.md
View file

@ -261,5 +261,4 @@ All requests made with this key will automatically be tracked in the "TestProjec
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/phoenix_integration.md
View file

@ -127,5 +127,4 @@ Depending on which Phoenix Cloud version or deployment you are using, you should
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/promptlayer_integration.md
View file

@ -84,5 +84,4 @@ Credits to [Nick Bradford](https://github.com/nsbradford), from [Vim-GPT](https:
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/slack_integration.md
View file

@ -101,5 +101,4 @@ response = litellm.completion(
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/sumologic_integration.md
View file

@ -328,5 +328,4 @@ If you get authentication errors, regenerate the HTTP Source URL in Sumo Logic:
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/supabase_integration.md
View file

@ -105,5 +105,4 @@ litellm.modify_integration("supabase",{"table_name": "litellm_logs"})
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/observability/wandb_integration.md
View file

@ -57,5 +57,4 @@ response = litellm.completion(
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

2
docs/my-website/docs/proxy/config_settings.md
View file

@ -206,7 +206,7 @@ router_settings:
| Name | Type | Description |
|------|------|-------------|
| completion_model | string | The default model to use for completions when `model` is not specified in the request |
| completion_model | string | The model to use for all completions, overriding any `model` specified in the request |
| disable_spend_logs | boolean | If true, turns off writing each transaction to the database |
| disable_spend_updates | boolean | If true, turns off all spend updates to the DB. Including key/user/team spend updates. |
| disable_master_key_return | boolean | If true, turns off returning master key on UI. (checked on '/user/info' endpoint) |

2
docs/my-website/docs/proxy/cost_tracking.md
View file

@ -163,7 +163,7 @@ Use this when you want non-proxy admins to access `/spend` endpoints
:::info
Schedule a [meeting with us to get your Enterprise License](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
Schedule a [meeting with us to get your Enterprise License](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/email.md
View file

@ -203,7 +203,7 @@ After regenerating the key, the user will receive an email notification with:
:::info
Customizing Email Branding is an Enterprise Feature [Get in touch with us for a Free Trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
Customizing Email Branding is an Enterprise Feature [Get in touch with us for a Free Trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/enterprise.md
View file

@ -5,7 +5,7 @@ import TabItem from '@theme/TabItem';
# ✨ Enterprise Features
:::tip
To get a license, get in touch with us [here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
To get a license, get in touch with us [here](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/guardrails/aporia_api.md
View file

@ -139,7 +139,7 @@ curl -i http://localhost:4000/v1/chat/completions \
:::info
✨ This is an Enterprise only feature [Contact us to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Contact us to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/guardrails/custom_guardrail.md
View file

@ -417,7 +417,7 @@ curl -i -X POST http://localhost:4000/v1/chat/completions \
:::info
✨ This is an Enterprise only feature [Contact us to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Contact us to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/guardrails/guardrails_ai.md
View file

@ -59,7 +59,7 @@ curl -i http://localhost:4000/v1/chat/completions \
:::info
✨ This is an Enterprise only feature [Contact us to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Contact us to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/ip_address.md
View file

@ -3,7 +3,7 @@
:::info
You need a LiteLLM License to unlock this feature. [Grab time](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions), to get one today!
You need a LiteLLM License to unlock this feature. [Grab time](https://enterprise.litellm.ai/demo), to get one today!
:::

6
docs/my-website/docs/proxy/logging.md
View file

@ -1109,7 +1109,7 @@ Log LLM Logs to [Google Cloud Storage Buckets](https://cloud.google.com/storage?
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::
@ -1194,7 +1194,7 @@ Log LLM Logs/SpendLogs to [Google Cloud Storage PubSub Topic](https://cloud.goog
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::
@ -1497,7 +1497,7 @@ Log LLM Logs to [Azure Data Lake Storage](https://learn.microsoft.com/en-us/azur
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::

36
docs/my-website/docs/proxy/multiple_admins.md
View file

@ -20,7 +20,7 @@ LiteLLM tracks changes to the following entities and actions:
:::tip
Requires Enterprise License, Get in touch with us [here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
Requires Enterprise License, Get in touch with us [here](https://enterprise.litellm.ai/demo)
:::
@ -56,6 +56,40 @@ On the LiteLLM UI, navigate to Logs -> Audit Logs. You should see the audit log
/>
## Export Audit Logs to External Storage
You can export audit logs to an external storage backend (e.g. S3) in addition to storing them in the database. Logs are batched and uploaded asynchronously, so they do not block your proxy requests.
### S3 Example
Add `audit_log_callbacks` and `s3_callback_params` to your `litellm_settings`:
```yaml
litellm_settings:
store_audit_logs: true
audit_log_callbacks: ["s3_v2"]
s3_callback_params:
s3_bucket_name: my-audit-logs-bucket # AWS Bucket Name
s3_region_name: us-west-2 # AWS Region
s3_aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
s3_aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
s3_path: litellm-audit # [OPTIONAL] prefix path in the bucket
```
Audit logs are written as JSON files to:
```
s3://<bucket>/audit_logs/<YYYY-MM-DD>/<HH-MM-SS>_<audit-log-id>.json
# or, when s3_path is set:
s3://<bucket>/<s3_path>/audit_logs/<YYYY-MM-DD>/<HH-MM-SS>_<audit-log-id>.json
```
:::info
Both `store_audit_logs: true` and `audit_log_callbacks` must be set. If `store_audit_logs` is not enabled, the callbacks will not fire.
:::
## Advanced
### Attribute Management changes to Users

2
docs/my-website/docs/proxy/oauth2.md
View file

@ -4,7 +4,7 @@ Use this if you want to use an Oauth2.0 token to make `/chat`, `/embeddings` req
:::info
This is an Enterprise Feature - [get in touch with us if you want a free trial to test if this feature meets your needs]((https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions))
This is an Enterprise Feature - [get in touch with us if you want a free trial to test if this feature meets your needs]((https://enterprise.litellm.ai/demo))
:::

1
docs/my-website/docs/proxy/pass_through.md
View file

@ -422,6 +422,5 @@ general_settings:
[Community Discord 💭](https://discord.gg/wuPM9dRgDw)
Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

2
docs/my-website/docs/proxy/prod.md
View file

@ -47,7 +47,7 @@ export LITELLM_LOG="ERROR"
:::info
Need Help or want dedicated support ? Talk to a founder [here]: (https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
Need Help or want dedicated support ? Talk to a founder [here]: (https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/public_routes.md
View file

@ -5,7 +5,7 @@ import TabItem from '@theme/TabItem';
:::info
Requires a LiteLLM Enterprise License. [Get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions).
Requires a LiteLLM Enterprise License. [Get a free trial](https://enterprise.litellm.ai/demo).
:::

2
docs/my-website/docs/proxy/tag_routing.md
View file

@ -315,7 +315,7 @@ LiteLLM Proxy supports team-based tag routing, allowing you to associate specifi
:::info
This is an enterprise feature, [Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
This is an enterprise feature, [Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

4
docs/my-website/docs/proxy/team_logging.md
View file

@ -26,7 +26,7 @@ Team 3 -> Disabled Logging (for GDPR compliance)
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::
@ -248,7 +248,7 @@ Use the `/key/generate` or `/key/update` endpoints to add logging callbacks to a
:::info
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
✨ This is an Enterprise only feature [Get Started with Enterprise here](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/team_model_add.md
View file

@ -5,7 +5,7 @@
This is an Enterprise feature.
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/proxy/token_auth.md
View file

@ -11,7 +11,7 @@ Use JWT's to auth admins / users / projects into the proxy.
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

1
docs/my-website/docs/proxy_server.md
View file

@ -813,5 +813,4 @@ Thread Stats Avg Stdev Max +/- Stdev
- [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
- Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

1
docs/my-website/docs/reasoning_content.md
View file

@ -13,6 +13,7 @@ Supported Providers:
- Deepseek (`deepseek/`)
- Anthropic API (`anthropic/`)
- Bedrock (Anthropic + Deepseek + GPT-OSS) (`bedrock/`)
- OpenAI Responses API (`openai/responses/`)
- Vertex AI (Anthropic) (`vertexai/`)
- OpenRouter (`openrouter/`)
- XAI (`xai/`)

2
docs/my-website/docs/secret.md
View file

@ -6,7 +6,7 @@
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/aws_kms.md
View file

@ -6,7 +6,7 @@
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/aws_secret_manager.md
View file

@ -9,7 +9,7 @@ import TabItem from '@theme/TabItem';
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/azure_key_vault.md
View file

@ -6,7 +6,7 @@
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/cyberark.md
View file

@ -8,7 +8,7 @@ import Image from '@theme/IdealImage';
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/google_kms.md
View file

@ -6,7 +6,7 @@
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/google_secret_manager.md
View file

@ -6,7 +6,7 @@
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/hashicorp_vault.md
View file

@ -8,7 +8,7 @@ import Image from '@theme/IdealImage';
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

2
docs/my-website/docs/secret_managers/overview.md
View file

@ -8,7 +8,7 @@ import Image from '@theme/IdealImage';
[Enterprise Pricing](https://www.litellm.ai/#pricing)
[Contact us here to get a free trial](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
[Contact us here to get a free trial](https://enterprise.litellm.ai/demo)
:::

1
docs/my-website/docs/troubleshoot.md
View file

@ -50,7 +50,6 @@ Full error logs, stack traces, and any images from service metrics (CPU, memory,
[Community Discord 💭](https://discord.gg/wuPM9dRgDw)
[Community Slack 💭](https://www.litellm.ai/support)
Our numbers 📞 +1 (770) 8783-106 / +1 (412) 618-6238
Our emails ✉️ ishaan@berri.ai / krrish@berri.ai

2
docs/my-website/docs/tutorials/compare_llms.md
View file

@ -82,7 +82,7 @@ Benchmark Results for 'When will BerriAI IPO?':
+-----------------+----------------------------------------------------------------------------------+---------------------------+------------+
```
## Support
**🤝 Schedule a 1-on-1 Session:** Book a [1-on-1 session](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions) with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.
**🤝 Schedule a 1-on-1 Session:** Book a [1-on-1 session](https://enterprise.litellm.ai/demo) with Krrish and Ishaan, the founders, to discuss any issues, provide feedback, or explore how we can improve LiteLLM for you.
<!--

27
docs/my-website/docs/tutorials/opencode_integration.md
View file

@ -253,7 +253,7 @@ model_list:
litellm_params:
model: openai/gpt-4
api_key: os.environ/OPENAI_API_KEY
- model_name: gpt-4o
litellm_params:
model: openai/gpt-4o
@ -264,7 +264,7 @@ model_list:
litellm_params:
model: anthropic/claude-3-5-sonnet-20241022
api_key: os.environ/ANTHROPIC_API_KEY
# DeepSeek models
- model_name: deepseek-chat
litellm_params:
@ -272,6 +272,19 @@ model_list:
api_key: os.environ/DEEPSEEK_API_KEY
```
### Dropping OpenCode-specific parameters
OpenCode sends a `reasoningSummary` parameter with reasoning-capable models such as `gpt-5`. This parameter is not supported by the Chat Completions API and will cause errors. Add `additional_drop_params` to every model entry in your `model_list` that will receive requests from OpenCode with reasoning enabled:
```yaml
model_list:
- model_name: gpt-5
litellm_params:
model: openai/gpt-5
api_key: os.environ/OPENAI_API_KEY
additional_drop_params: ["reasoningSummary"]
```
## Troubleshooting
**OpenCode not connecting:**
@ -294,6 +307,16 @@ model_list:
- Validate JSON syntax using a JSON validator
- Ensure the `$schema` URL is accessible
**`Unknown parameter: 'reasoningSummary'` error:**
- OpenCode sends a `reasoningSummary` parameter that is not supported by the Chat Completions API. Add `additional_drop_params: ["reasoningSummary"]` to each affected model entry in your `litellm_params`:
```yaml
- model_name: gpt-5
litellm_params:
model: openai/gpt-5
api_key: os.environ/OPENAI_API_KEY
additional_drop_params: ["reasoningSummary"]
```
## Tips
- Add more models to the config as needed - they'll appear in `/models`

BIN
docs/my-website/img/security_update_march_2026/proxy_version.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 396 KiB

2
enterprise/LICENSE.md
View file

@ -7,7 +7,7 @@ With regard to the BerriAI Software:
This software and associated documentation files (the "Software") may only be
used in production, if you (and any entity that you represent) have agreed to,
and are in compliance with, the BerriAI Subscription Terms of Service, available
via [call](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions) or email (info@berri.ai) (the "Enterprise Terms"), or other
via [call](https://enterprise.litellm.ai/demo) or email (info@berri.ai) (the "Enterprise Terms"), or other
agreement governing the use of the Software, as agreed by you and BerriAI,
and otherwise have a valid BerriAI Enterprise license for the
correct number of user seats. Subject to the foregoing sentence, you are free to

2
enterprise/README.md
View file

@ -4,6 +4,6 @@ Code in this folder is licensed under a commercial license. Please review the [L
**These features are covered under the LiteLLM Enterprise contract**
👉 **Using in an Enterprise / Need specific features ?** Meet with us [here](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions?month=2024-02)
👉 **Using in an Enterprise / Need specific features ?** Meet with us [here](https://enterprise.litellm.ai/demo?month=2024-02)
See all Enterprise Features here 👉 [Docs](https://docs.litellm.ai/docs/proxy/enterprise)

2
enterprise/litellm_enterprise/enterprise_callbacks/send_emails/base_email.py
View file

@ -632,7 +632,7 @@ class BaseEmailLogger(CustomLogger):
warning_msg = (
f"Email sent with default values instead of custom values for: {fields_str}. "
"This is an Enterprise feature. To use custom email fields, please upgrade to LiteLLM Enterprise. "
"Schedule a meeting here: https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions"
"Schedule a meeting here: https://enterprise.litellm.ai/demo"
)
verbose_proxy_logger.warning(f"{warning_msg}")

4
litellm/integrations/prometheus.py
View file

@ -931,10 +931,14 @@ class PrometheusLogger(CustomLogger):
user_api_key_auth_metadata: Optional[dict] = standard_logging_payload[
"metadata"
].get("user_api_key_auth_metadata")
spend_logs_metadata: Optional[dict] = standard_logging_payload["metadata"].get(
"spend_logs_metadata"
)
combined_metadata: Dict[str, Any] = {
**(_requester_metadata if _requester_metadata else {}),
**(user_api_key_auth_metadata if user_api_key_auth_metadata else {}),
**(spend_logs_metadata if spend_logs_metadata else {}),
}
if standard_logging_payload is not None and isinstance(
standard_logging_payload, dict

2
litellm/litellm_core_utils/litellm_logging.py
View file

@ -4753,6 +4753,7 @@ class StandardLoggingPayloadSetup:
user_api_key_team_id=None,
user_api_key_org_id=None,
user_api_key_project_id=None,
user_api_key_project_alias=None,
user_api_key_user_id=None,
user_api_key_team_alias=None,
user_api_key_user_email=None,
@ -5584,6 +5585,7 @@ def get_standard_logging_metadata(
user_api_key_team_id=None,
user_api_key_org_id=None,
user_api_key_project_id=None,
user_api_key_project_alias=None,
user_api_key_user_id=None,
user_api_key_user_email=None,
user_api_key_team_alias=None,

36
litellm/llms/a2a/chat/guardrail_translation/handler.py
View file

@ -111,6 +111,7 @@ class A2AGuardrailHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
user_api_key_dict: Optional["UserAPIKeyAuth"] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process A2A output response by applying guardrails to text content.
@ -166,13 +167,21 @@ class A2AGuardrailHandler(BaseTranslation):
return response
# Step 2: Apply guardrail to all texts in batch
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response_dict}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response_dict}
else:
if "response" not in request_data:
request_data["response"] = response_dict
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(user_api_key_dict)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
@ -213,6 +222,7 @@ class A2AGuardrailHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
user_api_key_dict: Optional["UserAPIKeyAuth"] = None,
request_data: Optional[dict] = None,
) -> List[Any]:
"""
Process A2A streaming output by applying guardrails to accumulated text.
@ -258,10 +268,18 @@ class A2AGuardrailHandler(BaseTranslation):
if not combined_text:
return responses_so_far
request_data: dict = {"responses_so_far": responses_so_far}
user_metadata = self.transform_user_api_key_dict_to_metadata(user_api_key_dict)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if request_data is None:
request_data = {"responses_so_far": responses_so_far}
else:
if "responses_so_far" not in request_data:
request_data["responses_so_far"] = responses_so_far
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=[combined_text])
guardrailed_inputs = await guardrail_to_apply.apply_guardrail(

26
litellm/llms/anthropic/chat/guardrail_translation/handler.py
View file

@ -252,6 +252,7 @@ class AnthropicMessagesHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response by applying guardrails to text content and tool calls.
@ -323,15 +324,21 @@ class AnthropicMessagesHandler(BaseTranslation):
# Step 2: Apply guardrail to all texts in batch
if texts_to_check or tool_calls_to_check:
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response}
else:
if "response" not in request_data:
request_data["response"] = response
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
if images_to_check:
@ -375,6 +382,7 @@ class AnthropicMessagesHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> List[Any]:
"""
Process output streaming response by applying guardrails to text content.
@ -413,7 +421,7 @@ class AnthropicMessagesHandler(BaseTranslation):
_guardrailed_inputs = await guardrail_to_apply.apply_guardrail( # allow rejecting the response, if invalid
inputs=guardrail_inputs,
request_data={},
request_data=request_data if request_data is not None else {},
input_type="response",
logging_obj=litellm_logging_obj,
)
@ -426,7 +434,7 @@ class AnthropicMessagesHandler(BaseTranslation):
string_so_far = self.get_streaming_string_so_far(responses_so_far)
_guardrailed_inputs = await guardrail_to_apply.apply_guardrail( # allow rejecting the response, if invalid
inputs={"texts": [string_so_far]},
request_data={},
request_data=request_data if request_data is not None else {},
input_type="response",
logging_obj=litellm_logging_obj,
)

2
litellm/llms/base_llm/guardrail_translation/base_translation.py
View file

@ -73,6 +73,7 @@ class BaseTranslation(ABC):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
user_api_key_dict: Optional["UserAPIKeyAuth"] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response with guardrails.
@ -91,6 +92,7 @@ class BaseTranslation(ABC):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
user_api_key_dict: Optional["UserAPIKeyAuth"] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output streaming response with guardrails.

1
litellm/llms/cohere/rerank/guardrail_translation/handler.py
View file

@ -83,6 +83,7 @@ class CohereRerankHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response - not applicable for rerank.

20
litellm/llms/mistral/ocr/guardrail_translation/handler.py
View file

@ -91,6 +91,7 @@ class OCRHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process OCR output by applying guardrails to extracted page text.
@ -127,14 +128,27 @@ class OCRHandler(BaseTranslation):
if model:
inputs["model"] = model
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {}
# Add user metadata if available
if user_api_key_dict is not None:
metadata = self.transform_user_api_key_dict_to_metadata(user_api_key_dict)
inputs.update(metadata) # type: ignore
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
# Preserve original behavior: inject metadata into inputs for
# third-party guardrail providers that read it from there
inputs.update(user_metadata) # type: ignore
# Also store in request_data for the logging pipeline
if "litellm_metadata" not in request_data:
request_data["litellm_metadata"] = user_metadata
guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
inputs=inputs,
request_data={},
request_data=request_data,
input_type="response",
logging_obj=litellm_logging_obj,
)

49
litellm/llms/openai/chat/guardrail_translation/handler.py
View file

@ -86,9 +86,9 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
if tool_calls_to_check:
inputs["tool_calls"] = tool_calls_to_check # type: ignore
if messages:
inputs[
"structured_messages"
] = messages # pass the openai /chat/completions messages to the guardrail, as-is
inputs["structured_messages"] = (
messages # pass the openai /chat/completions messages to the guardrail, as-is
)
# Pass tools (function definitions) to the guardrail
tools = data.get("tools")
if tools:
@ -260,6 +260,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response by applying guardrails to text content.
@ -308,15 +309,21 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
# Step 2: Apply guardrail to all texts and tool calls in batch
if texts_to_check or tool_calls_to_check:
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response}
else:
if "response" not in request_data:
request_data["response"] = response
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
if images_to_check:
@ -364,6 +371,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> List["ModelResponseStream"]:
"""
Process output streaming responses by applying guardrails to text content.
@ -402,6 +410,7 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
guardrail_to_apply=guardrail_to_apply,
litellm_logging_obj=litellm_logging_obj,
user_api_key_dict=user_api_key_dict,
request_data=request_data,
)
return responses_so_far
@ -436,15 +445,21 @@ class OpenAIChatCompletionsHandler(BaseTranslation):
# Step 3: Apply guardrail to all combined texts in batch
if texts_to_check:
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"responses": responses_so_far}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"responses": responses_so_far}
else:
if "responses" not in request_data:
request_data["responses"] = responses_so_far
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
if images_to_check:

21
litellm/llms/openai/completion/guardrail_translation/handler.py
View file

@ -125,6 +125,7 @@ class OpenAITextCompletionHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response by applying guardrails to completion text.
@ -155,15 +156,21 @@ class OpenAITextCompletionHandler(BaseTranslation):
# Apply guardrails in batch
if texts_to_check:
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response}
else:
if "response" not in request_data:
request_data["response"] = response
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
# Include model information from the response if available

1
litellm/llms/openai/embeddings/guardrail_translation/handler.py
View file

@ -155,6 +155,7 @@ class OpenAIEmbeddingsHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response - embeddings responses contain vectors, not text.

1
litellm/llms/openai/image_generation/guardrail_translation/handler.py
View file

@ -87,6 +87,7 @@ class OpenAIImageGenerationHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response - typically not needed for image generation.

28
litellm/llms/openai/responses/guardrail_translation/handler.py
View file

@ -347,6 +347,7 @@ class OpenAIResponsesHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response by applying guardrails to text content and tool calls.
@ -402,15 +403,21 @@ class OpenAIResponsesHandler(BaseTranslation):
# Step 2: Apply guardrail to all texts in batch
if texts_to_check or tool_calls_to_check:
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response}
else:
if "response" not in request_data:
request_data["response"] = response
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=texts_to_check)
if images_to_check:
@ -454,6 +461,7 @@ class OpenAIResponsesHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> List[Any]:
"""
Process output streaming response by applying guardrails to text content.
@ -481,7 +489,7 @@ class OpenAIResponsesHandler(BaseTranslation):
inputs["model"] = model_response_stream.model
_guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
inputs=inputs,
request_data={},
request_data=request_data if request_data is not None else {},
input_type="response",
logging_obj=litellm_logging_obj,
)
@ -512,7 +520,7 @@ class OpenAIResponsesHandler(BaseTranslation):
if tool_calls or text:
_guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
inputs=guardrail_inputs,
request_data={},
request_data=request_data if request_data is not None else {},
input_type="response",
logging_obj=litellm_logging_obj,
)
@ -537,7 +545,7 @@ class OpenAIResponsesHandler(BaseTranslation):
inputs["model"] = response_model
_guardrailed_inputs = await guardrail_to_apply.apply_guardrail(
inputs=inputs,
request_data={},
request_data=request_data if request_data is not None else {},
input_type="response",
logging_obj=litellm_logging_obj,
)

1
litellm/llms/openai/speech/guardrail_translation/handler.py
View file

@ -85,6 +85,7 @@ class OpenAITextToSpeechHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output - not applicable for text-to-speech.

21
litellm/llms/openai/transcriptions/guardrail_translation/handler.py
View file

@ -58,6 +58,7 @@ class OpenAIAudioTranscriptionHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output transcription by applying guardrails to transcribed text.
@ -79,15 +80,21 @@ class OpenAIAudioTranscriptionHandler(BaseTranslation):
if isinstance(response.text, str):
original_text = response.text
# Create a request_data dict with response info and user API key metadata
request_data: dict = {"response": response}
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = {"response": response}
else:
if "response" not in request_data:
request_data["response"] = response
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
inputs = GenericGuardrailAPIInputs(texts=[original_text])
# Include model information from the response if available

29
litellm/llms/pass_through/guardrail_translation/handler.py
View file

@ -139,6 +139,7 @@ class PassThroughEndpointHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional["LiteLLMLoggingObj"] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
"""
Process output response by applying guardrails to targeted fields.
@ -171,17 +172,27 @@ class PassThroughEndpointHandler(BaseTranslation):
if not text_to_check:
return response
# Create a request_data dict with response info and user API key metadata
request_data: dict = (
{"response": response}
if not isinstance(response, dict)
else response.copy()
)
# Use the real request_data if provided (proxy path), otherwise
# create a standalone dict (SDK / direct-call path).
if request_data is None:
request_data = (
{"response": response}
if not isinstance(response, dict)
else response.copy()
)
else:
if "response" not in request_data:
request_data["response"] = (
response if not isinstance(response, dict) else response.copy()
)
# Add user API key metadata with prefixed keys
user_metadata = self.transform_user_api_key_dict_to_metadata(user_api_key_dict)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
if "litellm_metadata" not in request_data:
user_metadata = self.transform_user_api_key_dict_to_metadata(
user_api_key_dict
)
if user_metadata:
request_data["litellm_metadata"] = user_metadata
# Apply guardrail (pass-through doesn't modify the text, just checks it)
inputs = GenericGuardrailAPIInputs(texts=[text_to_check])

1
litellm/proxy/_experimental/mcp_server/guardrail_translation/handler.py
View file

@ -92,6 +92,7 @@ class MCPGuardrailTranslationHandler(BaseTranslation):
guardrail_to_apply: "CustomGuardrail",
litellm_logging_obj: Optional[Any] = None,
user_api_key_dict: Optional[Any] = None,
request_data: Optional[dict] = None,
) -> Any:
verbose_proxy_logger.debug(
"MCP Guardrail: Output processing not implemented for MCP tools",

2
litellm/proxy/_types.py
View file

@ -2416,6 +2416,7 @@ class LiteLLM_VerificationTokenView(LiteLLM_VerificationToken):
organization_metadata: Optional[dict] = None
# Project Params
project_alias: Optional[str] = None
project_metadata: Optional[dict] = None
# Time stamps
@ -3228,6 +3229,7 @@ class SpendLogsMetadata(TypedDict):
user_api_key_alias: Optional[str]
user_api_key_team_id: Optional[str]
user_api_key_project_id: Optional[str]
user_api_key_project_alias: Optional[str]
user_api_key_org_id: Optional[str]
user_api_key_user_id: Optional[str]
user_api_key_team_alias: Optional[str]

3
litellm/proxy/auth/user_api_key_auth.py
View file

@ -836,6 +836,7 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
)
if _jwt_project_obj is not None:
valid_token.project_metadata = _jwt_project_obj.metadata
valid_token.project_alias = _jwt_project_obj.project_alias
# run through common checks
_ = await common_checks(
@ -1431,6 +1432,7 @@ async def _user_api_key_auth_builder( # noqa: PLR0915
)
if _project_obj is not None:
valid_token.project_metadata = _project_obj.metadata
valid_token.project_alias = _project_obj.project_alias
global_proxy_spend = None
if (
@ -1888,6 +1890,7 @@ async def _run_post_custom_auth_checks(
)
if _project_obj is not None:
valid_token.project_metadata = _project_obj.metadata
valid_token.project_alias = _project_obj.project_alias
if general_settings.get("custom_auth_run_common_checks", False):
_ = await common_checks(

16
litellm/proxy/db/create_views.py
View file

@ -27,14 +27,16 @@ async def create_missing_views(db: _db): # noqa: PLR0915
await db.execute_raw(
"""
CREATE VIEW "LiteLLM_VerificationTokenView" AS
SELECT
v.*,
t.spend AS team_spend,
t.max_budget AS team_max_budget,
t.tpm_limit AS team_tpm_limit,
t.rpm_limit AS team_rpm_limit
SELECT
v.*,
t.spend AS team_spend,
t.max_budget AS team_max_budget,
t.tpm_limit AS team_tpm_limit,
t.rpm_limit AS team_rpm_limit,
p.project_alias AS project_alias
FROM "LiteLLM_VerificationToken" v
LEFT JOIN "LiteLLM_TeamTable" t ON v.team_id = t.team_id;
LEFT JOIN "LiteLLM_TeamTable" t ON v.team_id = t.team_id
LEFT JOIN "LiteLLM_ProjectTable" p ON v.project_id = p.project_id;
"""
)

Some files were not shown because too many files have changed in this diff Show more