Merge litellm_internal_staging into litellm_ishaan_fix_prom_metrics_2

Resolves conflict in prometheus.py: keep newer _inc_labeled_counter pattern from staging.

.circleci/requirements.txt

@@ -1,21 +0,0 @@
-# used by CI/CD testing
-openai==1.100.1
-python-dotenv
-tiktoken
-importlib_metadata
-cohere
-redis==5.2.1
-redisvl==0.4.1
-anthropic
-orjson==3.10.15 # fast /embedding responses
-pydantic==2.12.5
-google-cloud-aiplatform==1.133.0
-google-cloud-iam==2.19.1
-fastapi-sso==0.16.0 
-uvloop==0.21.0
-mcp==1.26.0    # for MCP server
-semantic_router==0.1.10 # for auto-routing with litellm
-fastuuid==0.14.0
-responses==0.25.7  # for proxy client tests
-pytest-retry==1.6.3  # for automatic test retries
-litellm-proxy-extras  # for prisma migrations

.devcontainer/post-create.sh

@@ -1,17 +1,17 @@
 #!/usr/bin/env bash
 set -e
 
-echo "[post-create] Installing poetry via pip"
-python -m pip install --upgrade pip
-python -m pip install poetry
+echo "[post-create] Installing uv"
+curl -LsSf https://astral.sh/uv/0.10.9/install.sh | env UV_NO_MODIFY_PATH=1 sh
+export PATH="$HOME/.local/bin:$PATH"
 
-echo "[post-create] Installing Python dependencies (poetry)"
-poetry install --with dev --extras proxy
+echo "[post-create] Installing Python dependencies (uv)"
+uv sync --frozen --group proxy-dev --extra proxy
 
 echo "[post-create] Generating Prisma client"
-poetry run prisma generate
+uv run --no-sync prisma generate
 
 echo "[post-create] Installing npm dependencies"
 cd ui/litellm-dashboard && npm ci
 
-echo "[post-create] Done"
+echo "[post-create] Done"

.gitguardian.yaml

@@ -37,7 +37,7 @@ secret:
     - "docs/**"
     - "**/*.md"
     - "**/*.lock"
-    - "poetry.lock"
+    - "uv.lock"
     - "package-lock.json"
 
   # Ignore security incidents with the SHA256 of the occurrence (false positives)

.github/scripts/close_duplicate_issues.py

@@ -42,7 +42,9 @@ def gh(*args: str) -> str:
 def fetch_open_issues(repo: str | None) -> list[dict]:
     """Fetch all open issues (excluding PRs) via gh api --paginate."""
     if repo:
-        endpoint = f"repos/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
+        endpoint = (
+            f"repos/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
+        )
     else:
         endpoint = "repos/{owner}/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
     cmd = ["api", "--paginate", endpoint]
@@ -71,7 +73,9 @@ def close_as_duplicate(
     repo_args = ["--repo", repo] if repo else []
 
     if dry_run:
-        print(f"  [DRY RUN] Would close #{issue_number} as duplicate of #{duplicate_of}")
+        print(
+            f"  [DRY RUN] Would close #{issue_number} as duplicate of #{duplicate_of}"
+        )
         return
 
     # Add comment
@@ -115,7 +119,9 @@ def find_duplicate(
     return None
 
 
-def scan_all(issues: list[dict], threshold: float, repo: str | None, dry_run: bool) -> int:
+def scan_all(
+    issues: list[dict], threshold: float, repo: str | None, dry_run: bool
+) -> int:
     """Compare every issue against all older issues. Returns count of duplicates found."""
     # Sort oldest first
     issues.sort(key=lambda i: i["number"])
@@ -144,7 +150,11 @@ def scan_all(issues: list[dict], threshold: float, repo: str | None, dry_run: bo
 
 
 def check_single(
-    issue_number: int, issues: list[dict], threshold: float, repo: str | None, dry_run: bool
+    issue_number: int,
+    issues: list[dict],
+    threshold: float,
+    repo: str | None,
+    dry_run: bool,
 ) -> bool:
     """Check a single issue against all older open issues. Returns True if duplicate found."""
     target = None
@@ -178,13 +188,23 @@ def check_single(
 
 
 def main() -> None:
-    parser = argparse.ArgumentParser(description="Detect and close duplicate GitHub issues")
+    parser = argparse.ArgumentParser(
+        description="Detect and close duplicate GitHub issues"
+    )
     mode = parser.add_mutually_exclusive_group(required=True)
     mode.add_argument("--scan", action="store_true", help="Scan all open issues")
     mode.add_argument("--issue-number", type=int, help="Check a single issue number")
-    parser.add_argument("--threshold", type=float, default=0.85, help="Similarity threshold (0-1)")
-    parser.add_argument("--close", action="store_true", help="Actually close duplicates (default is dry-run)")
-    parser.add_argument("--repo", type=str, help="Repository (owner/repo). Auto-detected if omitted.")
+    parser.add_argument(
+        "--threshold", type=float, default=0.85, help="Similarity threshold (0-1)"
+    )
+    parser.add_argument(
+        "--close",
+        action="store_true",
+        help="Actually close duplicates (default is dry-run)",
+    )
+    parser.add_argument(
+        "--repo", type=str, help="Repository (owner/repo). Auto-detected if omitted."
+    )
     args = parser.parse_args()
 
     dry_run = not args.close
@@ -200,7 +220,9 @@ def main() -> None:
         count = scan_all(issues, args.threshold, args.repo, dry_run)
         print(f"\nTotal duplicates {'found' if dry_run else 'closed'}: {count}")
     else:
-        found = check_single(args.issue_number, issues, args.threshold, args.repo, dry_run)
+        found = check_single(
+            args.issue_number, issues, args.threshold, args.repo, dry_run
+        )
         sys.exit(0 if found else 0)  # Always exit 0; finding no dup is not an error
 
 

.github/scripts/scan_keywords.py

@@ -67,14 +67,13 @@ def send_webhook(webhook_url: str, payload: dict) -> None:
 def _excerpt(text: str, max_len: int = 400) -> str:
     if not text:
         return ""
-    
+
     # Keep original formatting
     if len(text) <= max_len:
         return text
     return text[: max_len - 1] + "…"
 
 
-
 def main() -> int:
     event = read_event_payload()
     if not event:
@@ -87,8 +86,19 @@ def main() -> int:
 
     # Keywords from env or defaults
     keywords_env = os.environ.get("KEYWORDS", "")
-    default_keywords = ["azure", "openai", "bedrock", "vertexai", "vertex ai", "anthropic"]
-    keywords = [k.strip() for k in keywords_env.split(",")] if keywords_env else default_keywords
+    default_keywords = [
+        "azure",
+        "openai",
+        "bedrock",
+        "vertexai",
+        "vertex ai",
+        "anthropic",
+    ]
+    keywords = (
+        [k.strip() for k in keywords_env.split(",")]
+        if keywords_env
+        else default_keywords
+    )
 
     matches = detect_keywords(combined_text, keywords)
     found = bool(matches)
@@ -129,5 +139,3 @@ def main() -> int:
 
 if __name__ == "__main__":
     raise SystemExit(main())
-
-

.github/workflows/_test-unit-base.yml

@@ -51,37 +51,30 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
-      - name: Cache Poetry dependencies
+      - name: Cache uv dependencies
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
+            ~/.cache/uv
             .venv
-          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
           restore-keys: |
-            ${{ runner.os }}-poetry-
+            ${{ runner.os }}-uv-
 
       - name: Install dependencies
         run: |
-          poetry config virtualenvs.in-project true
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install google-genai==1.22.0 \
-            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
-
-      - name: Setup litellm-enterprise
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
       - name: Generate Prisma client
         env:
           PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
-          poetry run pip install nodejs-wheel-binaries==24.13.1
-          poetry run prisma generate --schema litellm/proxy/schema.prisma
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Run tests
         env:
@@ -90,7 +83,7 @@ jobs:
           WORKERS: ${{ inputs.workers }}
           RERUNS: ${{ inputs.reruns }}
         run: |
-          poetry run pytest ${TEST_PATH:?} \
+          uv run --no-sync pytest ${TEST_PATH:?} \
             --tb=short -vv \
             --maxfail="${MAX_FAILURES}" \
             -n "${WORKERS}" \

.github/workflows/_test-unit-services-base.yml

@@ -86,44 +86,37 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
-      - name: Cache Poetry dependencies
+      - name: Cache uv dependencies
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
+            ~/.cache/uv
             .venv
-          key: ${{ runner.os }}-poetry-services-${{ hashFiles('poetry.lock') }}
+          key: ${{ runner.os }}-uv-services-${{ hashFiles('uv.lock') }}
           restore-keys: |
-            ${{ runner.os }}-poetry-services-
+            ${{ runner.os }}-uv-services-
 
       - name: Install dependencies
         run: |
-          poetry config virtualenvs.in-project true
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install google-genai==1.22.0 \
-            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
-
-      - name: Setup litellm-enterprise
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
       - name: Generate Prisma client
         env:
           PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
-          poetry run pip install nodejs-wheel-binaries==24.13.1
-          poetry run prisma generate --schema litellm/proxy/schema.prisma
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Run Prisma migrations
         if: ${{ inputs.enable-postgres }}
         env:
           DATABASE_URL: ${{ secrets.DATABASE_URL }}
         run: |
-          poetry run prisma db push --schema litellm/proxy/schema.prisma --accept-data-loss
+          uv run --no-sync prisma db push --schema litellm/proxy/schema.prisma --accept-data-loss
 
       - name: Run tests
         env:
@@ -134,7 +127,7 @@ jobs:
           DATABASE_URL: ${{ inputs.enable-postgres && secrets.DATABASE_URL || '' }}
         run: |
           if [ "${WORKERS}" = "0" ]; then
-            poetry run pytest ${TEST_PATH:?} \
+            uv run --no-sync pytest ${TEST_PATH:?} \
               --tb=short -vv \
               --maxfail="${MAX_FAILURES}" \
               --reruns "${RERUNS}" \
@@ -144,7 +137,7 @@ jobs:
               --cov-report=xml:coverage.xml \
               --cov-config=pyproject.toml
           else
-            poetry run pytest ${TEST_PATH:?} \
+            uv run --no-sync pytest ${TEST_PATH:?} \
               --tb=short -vv \
               --maxfail="${MAX_FAILURES}" \
               -n "${WORKERS}" \

.github/workflows/auto_update_price_and_context_window.yml

@@ -17,12 +17,13 @@ jobs:
       - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
         with:
           persist-credentials: false
-      - name: Install Dependencies
-        run: |
-          pip install 'aiohttp==3.13.3'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
       - name: Update JSON Data
         run: |
-          python ".github/workflows/auto_update_price_and_context_window_file.py"
+          uv run --frozen --with 'aiohttp==3.13.3' python ".github/workflows/auto_update_price_and_context_window_file.py"
       - name: Create Pull Request
         run: |
           git add model_prices_and_context_window.json 

.github/workflows/codspeed.yml

@@ -34,13 +34,21 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install dependencies
-        run: |
-          pip install -e "."
-          pip install pytest pytest-codspeed==4.3.0
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
       - name: Run benchmarks
         uses: CodSpeedHQ/action@1c8ae4843586d3ba879736b7f6b7b0c990757fab # v4.12.1
         with:
           mode: simulation
-          run: pytest tests/benchmarks/ --codspeed
+          run: >
+            env PYTEST_DISABLE_PLUGIN_AUTOLOAD=1
+            uv run --frozen --no-default-groups
+            --with pytest==8.3.5
+            --with pytest-codspeed==4.3.0
+            pytest
+            -p pytest_codspeed.plugin
+            tests/benchmarks/
+            --codspeed

.github/workflows/guard-main-branch.yml

@@ -0,0 +1,42 @@
+name: Guard main branch
+
+on:
+  pull_request:
+    branches:
+      - main
+  merge_group:
+
+permissions: {}
+
+# DO NOT RENAME the job's `name:` — it is referenced by GitHub branch
+# protection as a required status check on `main`. Renaming silently
+# breaks the gate.
+jobs:
+  guard:
+    name: Verify PR source branch
+    runs-on: ubuntu-latest
+    timeout-minutes: 2
+    steps:
+      - name: Reject merge_group events
+        if: github.event_name == 'merge_group'
+        run: |
+          echo "::error::Merge queue is not supported for main. Disable merge queue or update this guard."
+          exit 1
+      - name: Check head branch name
+        env:
+          HEAD_REF: ${{ github.head_ref }}
+          HEAD_REPO: ${{ github.event.pull_request.head.repo.full_name }}
+          BASE_REPO: ${{ github.repository }}
+        run: |
+          echo "PR head repo: $HEAD_REPO"
+          echo "PR head branch: $HEAD_REF"
+          if [ "$HEAD_REPO" != "$BASE_REPO" ]; then
+            echo "::error::PRs to main must originate from the canonical repository ($BASE_REPO), not a fork ($HEAD_REPO). External contributors should open PRs against the 'litellm_oss_branch' branch instead."
+            exit 1
+          fi
+          if [ "$HEAD_REF" = "litellm_internal_staging" ] || [[ "$HEAD_REF" == litellm_hotfix_?* ]]; then
+            echo "Allowed source branch."
+            exit 0
+          fi
+          echo "::error::PRs to main must originate from 'litellm_internal_staging' or a 'litellm_hotfix_*' branch. Got: '$HEAD_REF'. If this is a contribution, retarget the PR against 'litellm_oss_branch' instead."
+          exit 1

.github/workflows/llm-translation-testing.yml

@@ -31,26 +31,25 @@ jobs:
         with:
           python-version: "3.11"
 
-      - name: Install Poetry
-        run: |
-          pip install 'poetry==2.3.2'
-          poetry config virtualenvs.create true
-          poetry config virtualenvs.in-project true
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+          enable-cache: false
 
-      - name: Restore Poetry dependencies cache
-        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.0.0
+      - name: Restore uv dependencies cache
+        uses: actions/cache/restore@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
-            ~/.cache/pypoetry
+            ~/.cache/uv
             .venv
-          key: ${{ runner.os }}-poetry-${{ hashFiles('**/poetry.lock') }}
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
           restore-keys: |
-            ${{ runner.os }}-poetry-
+            ${{ runner.os }}-uv-
 
       - name: Install dependencies
         run: |
-          poetry install --with dev
-          poetry run pip install 'pytest-xdist==3.8.0' 'pytest-timeout==2.4.0'
+          uv sync --frozen
 
       - name: Create test results directory
         run: mkdir -p test-results

.github/workflows/publish_to_pypi.yml

@@ -24,10 +24,22 @@ jobs:
         with:
           python-version: "3.12"
 
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+          enable-cache: false
+
       - name: Check litellm version on PyPI
         id: check-litellm
         run: |
-          VERSION=$(grep -m1 '^version' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
+          VERSION=$(python - <<'PY'
+          import tomllib
+
+          with open("pyproject.toml", "rb") as f:
+              print(tomllib.load(f)["project"]["version"])
+          PY
+          )
           echo "version=$VERSION" >> "$GITHUB_OUTPUT"
           echo "Checking if litellm $VERSION exists on PyPI..."
 
@@ -42,43 +54,46 @@ jobs:
 
       - name: Sanity check proxy-extras version
         run: |
-          # Read pinned version from requirements.txt
-          REQ_VERSION=$(grep -oP 'litellm-proxy-extras==\K[0-9.]+' requirements.txt)
-          if [ -z "$REQ_VERSION" ]; then
-            echo "::error::Could not find litellm-proxy-extras version in requirements.txt"
-            exit 1
-          fi
-          echo "requirements.txt pins litellm-proxy-extras==$REQ_VERSION"
+          # Read pinned version from project optional dependencies
+          PYPROJECT_VERSION=$(python3 - <<'PY'
+          import sys
+          import tomllib
 
-          # Read pinned version from pyproject.toml dependency
-          PYPROJECT_VERSION=$(python3 -c "
-          import re
-          with open('pyproject.toml') as f:
-              content = f.read()
-          match = re.search(r'litellm-proxy-extras\s*=\s*\{version\s*=\s*\"([^\"]+)\"', content)
-          if match:
-              print(match.group(1).lstrip('^~>='))
-          else:
-              import sys
-              print('::error::Could not find litellm-proxy-extras dependency in pyproject.toml', file=sys.stderr)
+          with open("pyproject.toml", "rb") as f:
+              proxy_requirements = tomllib.load(f)["project"]["optional-dependencies"]["proxy"]
+
+          version = None
+          for requirement in proxy_requirements:
+              normalized = requirement.split(";", 1)[0].strip()
+              if not normalized.startswith("litellm-proxy-extras"):
+                  continue
+              parts = normalized.split("==", 1)
+              if len(parts) == 2 and parts[0].strip() == "litellm-proxy-extras":
+                  candidate = parts[1].strip()
+                  if candidate:
+                      version = candidate
+                      break
+
+          if version is None:
+              print(
+                  "::error::Could not find an exact litellm-proxy-extras pin in project.optional-dependencies.proxy",
+                  file=sys.stderr,
+              )
               sys.exit(1)
-          ")
+
+          print(version)
+          PY
+          )
           echo "pyproject.toml pins litellm-proxy-extras version: $PYPROJECT_VERSION"
 
-          # Check that both pinned versions match
-          if [ "$REQ_VERSION" != "$PYPROJECT_VERSION" ]; then
-            echo "::error::Version mismatch: requirements.txt has $REQ_VERSION but pyproject.toml has $PYPROJECT_VERSION"
-            exit 1
-          fi
-
           # Check that the pinned version exists on PyPI
-          echo "Checking if litellm-proxy-extras $REQ_VERSION exists on PyPI..."
-          HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://pypi.org/pypi/litellm-proxy-extras/$REQ_VERSION/json")
+          echo "Checking if litellm-proxy-extras $PYPROJECT_VERSION exists on PyPI..."
+          HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://pypi.org/pypi/litellm-proxy-extras/$PYPROJECT_VERSION/json")
           if [ "$HTTP_STATUS" != "200" ]; then
-            echo "::error::litellm-proxy-extras $REQ_VERSION is not published on PyPI yet. Publish it before releasing litellm."
+            echo "::error::litellm-proxy-extras $PYPROJECT_VERSION is not published on PyPI yet. Publish it before releasing litellm."
             exit 1
           fi
-          echo "litellm-proxy-extras $REQ_VERSION exists on PyPI. Sanity check passed."
+          echo "litellm-proxy-extras $PYPROJECT_VERSION exists on PyPI. Sanity check passed."
 
   publish-litellm:
     name: Publish litellm to PyPI
@@ -100,16 +115,19 @@ jobs:
         with:
           python-version: "3.12"
 
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+          enable-cache: false
+
       - name: Copy model prices backup
         run: cp model_prices_and_context_window.json litellm/model_prices_and_context_window_backup.json
 
-      - name: Install build tools
-        run: python -m pip install --upgrade pip build==1.4.2
-
       - name: Build package
         run: |
           rm -rf build dist
-          python -m build
+          uv build
 
       - name: Verify build artifacts
         env:
@@ -129,8 +147,7 @@ jobs:
 
       - name: Validate package metadata
         run: |
-          pip install twine==6.2.0
-          twine check dist/*
+          uv tool run --from 'twine==6.2.0' twine check dist/*
 
       - name: Publish to PyPI
         uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e # v1.13.0

.github/workflows/run_llm_translation_tests.py

@@ -325,7 +325,7 @@ def run_tests(test_path: str = "tests/llm_translation/",
     
     # Run pytest
     cmd = [
-        "poetry", "run", "pytest", test_path,
+        "uv", "run", "--no-sync", "pytest", test_path,
         f"--junitxml={junit_xml}",
         "-v",
         "--tb=short",
@@ -335,7 +335,7 @@ def run_tests(test_path: str = "tests/llm_translation/",
     
     # Add timeout if pytest-timeout is installed
     try:
-        subprocess.run(["poetry", "run", "python", "-c", "import pytest_timeout"], 
+        subprocess.run(["uv", "run", "--no-sync", "python", "-c", "import pytest_timeout"], 
                       capture_output=True, check=True)
         cmd.extend(["--timeout=300"])
     except:
@@ -436,4 +436,4 @@ if __name__ == "__main__":
         commit=args.commit
     )
     
-    sys.exit(exit_code)
+    sys.exit(exit_code)

.github/workflows/test-linting.yml

@@ -2,7 +2,11 @@ name: LiteLLM Linting
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read
@@ -24,26 +28,28 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
       - name: Clean Python cache
         run: |
           find . -type d -name "__pycache__" -exec rm -rf {} + || true
           find . -name "*.pyc" -delete || true
 
-      - name: Check poetry.lock is up to date
+      - name: Check uv.lock is up to date
         run: |
-          poetry check --lock || (echo "❌ poetry.lock is out of sync with pyproject.toml. Run 'poetry lock' locally and commit the result." && exit 1)
+          uv lock --check || (echo "❌ uv.lock is out of sync with pyproject.toml. Run 'uv lock' locally and commit the result." && exit 1)
 
       - name: Install dependencies
         run: |
-          poetry install --with dev
+          uv sync --frozen
 
       - name: Check Black formatting
         run: |
           cd litellm
-          poetry run black --check --exclude '/enterprise/' .
+          uv run --no-sync black --check --exclude '/enterprise/' .
           cd ..
 
       - name: Debug - Check file state
@@ -58,28 +64,28 @@ jobs:
       - name: Run Ruff linting
         run: |
           cd litellm
-          poetry run ruff check .
+          uv run --no-sync ruff check .
           cd ..
 
       - name: Print OpenAI version
         run: |
-          poetry run python -c "import openai; print(f'OpenAI version: {openai.__version__}')"
+          uv run --no-sync python -c "import openai; print(f'OpenAI version: {openai.__version__}')"
 
       - name: Run MyPy type checking
         run: |
           cd litellm
-          poetry run mypy . 
+          uv run --no-sync mypy .
           cd ..
 
       - name: Check for circular imports
         run: |
           cd litellm
-          poetry run python ../tests/documentation_tests/test_circular_imports.py
+          uv run --no-sync python ../tests/documentation_tests/test_circular_imports.py
           cd ..
 
       - name: Check import safety
         run: |
-          poetry run python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
+          uv run --no-sync python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
 
   secret-scan:
     runs-on: ubuntu-latest
@@ -98,18 +104,21 @@ jobs:
         with:
           python-version: "3.12"
 
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
       - name: Run secret scan test
         run: |
-          pip install 'pytest==9.0.2'
-          pytest tests/litellm/test_no_hardcoded_secrets.py -v
+          uv run --frozen --with 'pytest==9.0.2' pytest tests/litellm/test_no_hardcoded_secrets.py -v
 
       - name: Run ggshield secret scan
         env:
           GITGUARDIAN_API_KEY: ${{ secrets.GITGUARDIAN_API_KEY }}
         run: |
           if [ -n "$GITGUARDIAN_API_KEY" ]; then
-            pip install 'ggshield==1.48.0'
-            ggshield secret scan repo .
+            uv tool run --from 'ggshield==1.48.0' ggshield secret scan repo .
           else
             echo "GITGUARDIAN_API_KEY not set, skipping ggshield scan"
           fi

.github/workflows/test-litellm-ui-build.yml

@@ -4,7 +4,11 @@ permissions:
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 jobs:
   build-ui:

.github/workflows/test-litellm.yml

@@ -31,23 +31,15 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
       - name: Install dependencies
         run: |
-          poetry lock
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install "pytest-retry==1.6.3"
-          poetry run pip install 'pytest-xdist==3.8.0'
-          poetry run pip install "google-genai==1.22.0"
-          poetry run pip install "google-cloud-aiplatform==1.115.0"
-          poetry run pip install "fastapi-offline==1.7.3"
-          poetry run pip install "python-multipart==0.0.22"
-          poetry run pip install "openapi-core==0.23.0"
-      - name: Setup litellm-enterprise as local package
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv lock --check
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
       - name: Run tests
         run: |
-          poetry run pytest tests/test_litellm --tb=short -vv --maxfail=10 -n 4 --durations=50
+          uv run --no-sync pytest tests/test_litellm --tb=short -vv --maxfail=10 -n 4 --durations=50

.github/workflows/test-mcp.yml

@@ -2,7 +2,11 @@ name: LiteLLM MCP Tests (folder - tests/mcp_tests)
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read
@@ -27,26 +31,16 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
       - name: Install dependencies
         run: |
-          poetry lock
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install "pytest==7.3.1"
-          poetry run pip install "pytest-retry==1.6.3"
-          poetry run pip install "pytest-cov==5.0.0"
-          poetry run pip install "pytest-asyncio==0.21.1"
-          poetry run pip install "respx==0.22.0"
-          poetry run pip install "pydantic==2.11.0"
-          poetry run pip install "mcp==1.25.0"
-          poetry run pip install 'pytest-xdist==3.8.0'
-
-      - name: Setup litellm-enterprise as local package
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv lock --check
+          uv sync --frozen --group proxy-dev --extra proxy --extra semantic-router
 
       - name: Run MCP tests
         run: |
-          poetry run pytest tests/mcp_tests -x -vv -n 4 --cov=litellm --cov-report=xml --durations=5
+          uv run --no-sync pytest tests/mcp_tests -x -vv -n 4 --cov=litellm --cov-report=xml --durations=5

.github/workflows/test-model-map.yaml

@@ -2,7 +2,11 @@ name: Validate model_prices_and_context_window.json
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-core-utils.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Core Utilities"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-documentation.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Documentation Validation"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read
@@ -26,42 +30,35 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
-      - name: Cache Poetry dependencies
+      - name: Cache uv dependencies
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
+            ~/.cache/uv
             .venv
-          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
           restore-keys: |
-            ${{ runner.os }}-poetry-
+            ${{ runner.os }}-uv-
 
       - name: Install dependencies
         run: |
-          poetry config virtualenvs.in-project true
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install google-genai==1.22.0 \
-            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
-
-      - name: Setup litellm-enterprise
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
       - name: Generate Prisma client
         env:
           PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
-          poetry run pip install nodejs-wheel-binaries==24.13.1
-          poetry run prisma generate --schema litellm/proxy/schema.prisma
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       # Run the same documentation tests that CircleCI ran (as direct Python scripts)
       - name: Run documentation validation tests
         run: |
-          poetry run python ./tests/documentation_tests/test_env_keys.py
-          poetry run python ./tests/documentation_tests/test_router_settings.py
-          poetry run python ./tests/documentation_tests/test_api_docs.py
-          poetry run python ./tests/documentation_tests/test_circular_imports.py
+          uv run --no-sync python ./tests/documentation_tests/test_env_keys.py
+          uv run --no-sync python ./tests/documentation_tests/test_router_settings.py
+          uv run --no-sync python ./tests/documentation_tests/test_api_docs.py
+          uv run --no-sync python ./tests/documentation_tests/test_circular_imports.py

.github/workflows/test-unit-enterprise-routing.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Enterprise, Google GenAI & Routing"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-integrations.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Integrations (Callbacks & Logging)"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-llm-providers.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: LLM Provider Transformations"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-misc.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: MCP, Secrets, Containers & Misc"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-proxy-auth.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Proxy Auth & Key Management"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-proxy-db.yml

@@ -3,7 +3,7 @@ name: "Unit Tests: Proxy DB Operations"
 # Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
 on:
   push:
-    branches: [main, "litellm_*"]
+    branches: [main, "litellm_**"]
 
 permissions:
   contents: read
@@ -34,7 +34,7 @@ jobs:
           - test-group: remaining
             test-path: "tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py"
             workers: 8
-            timeout: 20
+            timeout: 30
     uses: ./.github/workflows/_test-unit-services-base.yml
     with:
       test-path: ${{ matrix.test-path }}

.github/workflows/test-unit-proxy-endpoints.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Proxy API Endpoints"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-proxy-infra.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Proxy Infrastructure"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-proxy-legacy.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Proxy Legacy Tests"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read
@@ -50,43 +54,36 @@ jobs:
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
 
-      - name: Cache Poetry dependencies
+      - name: Cache uv dependencies
         uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
         with:
           path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
+            ~/.cache/uv
             .venv
-          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
           restore-keys: |
-            ${{ runner.os }}-poetry-
+            ${{ runner.os }}-uv-
 
       - name: Install dependencies
         run: |
-          poetry config virtualenvs.in-project true
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install google-genai==1.22.0 \
-            google-cloud-aiplatform==1.115.0 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core==0.23.0
-
-      - name: Setup litellm-enterprise
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
 
       - name: Generate Prisma client
         env:
           PRISMA_BINARY_CACHE_DIR: ${{ runner.temp }}/prisma-cache
         run: |
-          poetry run pip install nodejs-wheel-binaries==24.13.1
-          poetry run prisma generate --schema litellm/proxy/schema.prisma
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
 
       - name: Run tests - ${{ matrix.test-group.name }}
         env:
           TEST_PATH: ${{ matrix.test-group.path }}
         run: |
-          poetry run pytest ${TEST_PATH} \
+          uv run --no-sync pytest ${TEST_PATH} \
             --tb=short -vv \
             --maxfail=10 \
             -n 2 \

.github/workflows/test-unit-responses-caching-types.yml

@@ -2,7 +2,11 @@ name: "Unit Tests: Responses, Caching & Types"
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 permissions:
   contents: read

.github/workflows/test-unit-security.yml

@@ -3,7 +3,7 @@ name: "Unit Tests: Security"
 # Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
 on:
   push:
-    branches: [main, "litellm_*"]
+    branches: [main, "litellm_**"]
 
 permissions:
   contents: read

.github/workflows/test_server_root_path.yml

@@ -4,12 +4,16 @@ permissions:
 
 on:
   pull_request:
-    branches: [main]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
 
 jobs:
   test-server-root-path:
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    timeout-minutes: 30
 
     strategy:
       matrix:
@@ -21,6 +25,12 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Free up disk space
+        run: |
+          sudo rm -rf /usr/local/lib/android /usr/share/dotnet /opt/ghc /usr/local/share/boost
+          sudo apt-get clean
+          df -h /
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12
 

AGENTS.md

@@ -51,7 +51,9 @@ LiteLLM is a unified interface for 100+ LLMs that:
 
 ### MAKING CODE CHANGES FOR THE UI (IGNORE FOR BACKEND)
 
-1. **Tremor is DEPRECATED, do not use Tremor components in new features/changes**
+1. **Always use `antd` for new UI components — Tremor is DEPRECATED**
+   - We are migrating off of `@tremor/react`. Do not introduce new `Badge`, `Text`, `Card`, `Grid`, `Title`, or other imports from `@tremor/react` in any new or modified file.
+   - Use `antd` equivalents: `Tag` for labels, plain `<span>`/`<div>` with Tailwind classes (or `Typography.Text`) for text, `Card` from `antd`, etc. Note that `antd` has no `"yellow"` Tag color — use `"gold"` for amber/yellow.
    - The only exception is the Tremor Table component and its required Tremor Table sub components.
 
 2. **Use Common Components as much as possible**:
@@ -121,7 +123,7 @@ LiteLLM supports MCP for agent workflows:
 
 ## RUNNING SCRIPTS
 
-Use `poetry run python script.py` to run Python scripts in the project environment (for non-test files).
+Use `uv run python script.py` to run Python scripts in the project environment (for non-test files).
 
 ## GITHUB TEMPLATES
 
@@ -232,16 +234,16 @@ When opening issues or pull requests, follow these templates:
 
 ### Environment
 
-- Poetry is installed in `~/.local/bin`; the update script ensures it is on `PATH`.
+- uv is installed in `~/.local/bin`; the update script ensures it is on `PATH`.
 - Python 3.12, Node 22 are pre-installed.
-- The virtual environment lives under `~/.cache/pypoetry/virtualenvs/`.
+- The project virtual environment lives under `.venv/`.
 
 ### Running the proxy server
 
 Start the proxy with a config file:
 
 ```bash
-poetry run litellm --config dev_config.yaml --port 4000
+uv run litellm --config dev_config.yaml --port 4000
 ```
 
 The proxy takes ~15-20 seconds to fully start (it runs Prisma migrations on boot). Wait for `/health` to return before sending requests. Without a PostgreSQL `DATABASE_URL`, the proxy connects to a default Neon dev database embedded in the `litellm-proxy-extras` package.
@@ -250,17 +252,16 @@ The proxy takes ~15-20 seconds to fully start (it runs Prisma migrations on boot
 
 See `CLAUDE.md` and the `Makefile` for standard commands. Key notes:
 
-- `psycopg-binary` must be installed (`poetry run pip install psycopg-binary`) because the pytest-postgresql plugin requires it and the lock file only includes `psycopg` (no binary).
-- `openapi-core` must be installed (`poetry run pip install openapi-core`) for the OpenAPI compliance tests in `tests/test_litellm/interactions/`.
+- `uv sync --group proxy-dev --extra proxy` installs the Prisma and proxy-side test dependencies used by the standard local workflow.
 - The `--timeout` pytest flag is NOT available; don't pass it.
-- Unit tests: `poetry run pytest tests/test_litellm/ -x -vv -n 4`
-- **Before committing, always run `poetry run black .` to format your code.** Black formatting is enforced in CI.
-- If `poetry install` fails with "pyproject.toml changed significantly since poetry.lock was last generated", run `poetry lock` first to regenerate the lock file.
+- Unit tests: `uv run pytest tests/test_litellm/ -x -vv -n 4`
+- **Before committing, always run `uv run black .` to format your code.** Black formatting is enforced in CI.
+- If `uv sync` fails because the lockfile is outdated, run `uv lock` and retry.
 
 ### Lint
 
 ```bash
-cd litellm && poetry run ruff check .
+cd litellm && uv run ruff check .
 ```
 
 Ruff is the primary fast linter. For the full lint suite (including mypy, black, circular imports), run `make lint` per `CLAUDE.md`.
@@ -271,4 +272,4 @@ Ruff is the primary fast linter. For the full lint suite (including mypy, black,
 - The proxy at port 4000 serves a **pre-built** static UI from `litellm/proxy/_experimental/out/`. After making UI code changes, you must run `npm run build` in the dashboard directory and copy the output: `cp -r ui/litellm-dashboard/out/* litellm/proxy/_experimental/out/` for the proxy to serve the updated UI.
 - SVGs used as provider logos (loaded via `<img>` tags) must NOT use `fill="currentColor"` — replace with an explicit color like `#000000` or use the `-color` variant from lobehub icons, since CSS color inheritance does not work inside `<img>` elements.
 - Provider logos live in `ui/litellm-dashboard/public/assets/logos/` (source) and `litellm/proxy/_experimental/out/assets/logos/` (pre-built). Both locations must have the file for it to work in dev and proxy-served modes.
-- UI Vitest tests: `cd ui/litellm-dashboard && npx vitest run`
+- UI Vitest tests: `cd ui/litellm-dashboard && npx vitest run`

CLAUDE.md

@@ -7,7 +7,7 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 ### Installation
 - `make install-dev` - Install core development dependencies
 - `make install-proxy-dev` - Install proxy development dependencies with full feature set
-- `make install-test-deps` - Install all test dependencies
+- `make install-test-deps` - Install the full local test environment and generate the Prisma client
 
 ### Testing
 - `make test` - Run all tests
@@ -20,14 +20,14 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 - `make format` - Apply Black code formatting
 - `make lint-ruff` - Run Ruff linting only
 - `make lint-mypy` - Run MyPy type checking only
-- **Before committing, always run `poetry run black .` to format your code.** Black formatting is enforced in CI.
+- **Before committing, always run `uv run black .` to format your code.** Black formatting is enforced in CI.
 
 ### Single Test Files
-- `poetry run pytest tests/path/to/test_file.py -v` - Run specific test file
-- `poetry run pytest tests/path/to/test_file.py::test_function -v` - Run specific test
+- `uv run pytest tests/path/to/test_file.py -v` - Run specific test file
+- `uv run pytest tests/path/to/test_file.py::test_function -v` - Run specific test
 
 ### Running Scripts
-- `poetry run python script.py` - Run Python scripts (use for non-test files)
+- `uv run python script.py` - Run Python scripts (use for non-test files)
 
 ### GitHub Issue & PR Templates
 When contributing to the project, use the appropriate templates:
@@ -109,6 +109,9 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 ### UI / Backend Consistency
 - When wiring a new UI entity type to an existing backend endpoint, verify the backend API contract (single value vs. array, required vs. optional params) and ensure the UI controls match — e.g., use a single-select dropdown when the backend accepts a single value, not a multi-select
 
+### UI Component Library
+- **Always use `antd` for new UI components** — we are migrating off of `@tremor/react`. Do not introduce new `Badge`, `Text`, `Card`, `Grid`, `Title`, or other imports from `@tremor/react` in any new or modified file. Use `antd` equivalents: `Tag` for labels, `Typography.Text` / `Typography.Title` / `Typography.Paragraph` for textual content (avoid plain text-only `<span>`, `<p>`, `<h*>` when Typography fits), and `Card` from `antd`. Note that `antd` has no `"yellow"` Tag color — use `"gold"` for amber/yellow.
+
 ### MCP OAuth / OpenAPI Transport Mapping
 - `TRANSPORT.OPENAPI` is a UI-only concept. The backend only accepts `"http"`, `"sse"`, or `"stdio"`. Always map it to `"http"` before any API call (including pre-OAuth temp-session calls).
 - FastAPI validation errors return `detail` as an array of `{loc, msg, type}` objects. Error extractors must handle: array (map `.msg`), string, nested `{error: string}`, and fallback.
@@ -151,6 +154,14 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 - Optional features enabled via environment variables
 - Separate licensing and authentication for enterprise features
 
+### CI Supply-Chain Safety
+- **Never pipe a remote script into a shell** (`curl ... | bash`, `wget ... | sh`). Download the artifact to a file, verify its SHA-256 checksum, then install.
+- **Pin every external tool to a specific version** with a full URL (not `latest` or `stable`). Unversioned downloads silently change under you.
+- **Verify checksums for all downloaded binaries.** Use the provider's official `.sha256` / `.sha256sum` sidecar file when available; otherwise compute and hardcode the digest.
+- **Prefer reusable CircleCI commands** (`commands:` section) so a tool is installed and verified in exactly one place, then referenced everywhere with `- install_<tool>` or `- wait_for_service`.
+- **Don't add tools just because they were there before.** Audit whether an external dependency is still needed. If it can be replaced with a shell one-liner or a tool already in the image, remove it.
+- These rules apply to every download in CI: binaries, install scripts, language version managers, package repos. No exceptions.
+
 ### HTTP Client Cache Safety
 - **Never close HTTP/SDK clients on cache eviction.** `LLMClientCache._remove_key()` must not call `close()`/`aclose()` on evicted clients — they may still be used by in-flight requests. Doing so causes `RuntimeError: Cannot send a request, as the client has been closed.` after the 1-hour TTL expires. Cleanup happens at shutdown via `close_litellm_async_clients()`.
 

CONTRIBUTING.md

@@ -122,9 +122,17 @@ Run all unit tests (uses parallel execution for speed):
 make test-unit
 ```
 
+If you're running broader test suites, proxy tests, or anything that touches PostgreSQL-backed fixtures/plugins, install the full local test environment first:
+
+```bash
+make install-test-deps
+```
+
+This syncs the locked test environment used across the repo, including `psycopg` v3 plus `psycopg-binary` (used by `pytest-postgresql`), `psycopg2-binary` (used by some proxy E2E tests), and a generated Prisma client for DB-backed proxy tests, so pytest startup matches CI without manual package installs.
+
 Run specific test files:
 ```bash
-poetry run pytest tests/test_litellm/test_your_file.py -v
+uv run pytest tests/test_litellm/test_your_file.py -v
 ```
 
 ### Running Linting and Formatting Checks
@@ -185,7 +193,7 @@ Run `make help` to see all available commands:
 make help                       # Show all available commands
 make install-dev               # Install development dependencies
 make install-proxy-dev         # Install proxy development dependencies
-make install-test-deps         # Install test dependencies (for running tests)
+make install-test-deps         # Install the full local test environment
 make format                    # Apply Black code formatting
 make format-check              # Check Black formatting (matches CI)
 make lint                      # Run all linting checks
@@ -247,7 +255,7 @@ To run the proxy server locally:
 make install-proxy-dev
 
 # Start the proxy server
-poetry run litellm --config your_config.yaml
+uv run litellm --config your_config.yaml
 ```
 
 ### Docker Development
@@ -332,4 +340,4 @@ Looking for ideas? Check out:
 - 🧪 Test coverage improvements
 - 🔌 New LLM provider integrations
 
-Thank you for contributing to LiteLLM! 🚀 
+Thank you for contributing to LiteLLM! 🚀 

Dockerfile

@@ -3,57 +3,75 @@ ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+
+FROM $UV_IMAGE AS uvbin
 
 # Builder stage
 FROM $LITELLM_BUILD_IMAGE AS builder
 
-# Set the working directory to /app
 WORKDIR /app
-
 USER root
 
-# Install build dependencies
-RUN apk add --no-cache bash gcc py3-pip python3 python3-dev openssl openssl-dev
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
 
-RUN python -m pip install build==1.4.2
+RUN apk add --no-cache \
+    bash \
+    gcc \
+    python3 \
+    python3-dev \
+    openssl \
+    openssl-dev \
+    nodejs \
+    npm \
+    libsndfile
 
-# Copy the current directory contents into the container at /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
+
+# Copy dependency metadata first for layer caching
+COPY pyproject.toml uv.lock ./
+COPY enterprise/pyproject.toml enterprise/
+COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
+
+# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
+RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
+
+# Copy full source tree
 COPY . .
 
-# Build Admin UI
-# Convert Windows line endings to Unix and make executable
+# Build Admin UI before final sync
 RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
 
-# Build the package
-RUN rm -rf dist/* && python -m build
+# Install project and workspace packages (fast - deps already cached)
+RUN uv sync --frozen --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
 
-# There should be only one wheel file now, assume the build only creates one
-RUN ls -1 dist/*.whl | head -1
+RUN prisma generate --schema=./schema.prisma
 
-# Install the package
-RUN pip install dist/*.whl
-
-# install dependencies as wheels
-RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
-
-# ensure pyjwt is used, not jwt
-RUN pip uninstall jwt -y
-RUN pip uninstall PyJWT -y
-RUN pip install PyJWT==2.12.0 --no-cache-dir
+RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
 
 # Runtime stage
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
-# Ensure runtime stage runs as root
 USER root
 
-# Install runtime dependencies (libsndfile needed for audio processing on ARM64)
-RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile && \
+RUN apk add --no-cache bash openssl tzdata nodejs npm python3 libsndfile supervisor && \
     npm install -g npm@11.12.1 tar@7.5.11 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
-    # SECURITY FIX: npm bundles tar, glob, and brace-expansion at multiple nested
-    # levels inside its dependency tree. `npm install -g <pkg>` only creates a
-    # SEPARATE global package, it does NOT replace npm's internal copies.
-    # We must find and replace EVERY copy inside npm's directory.
     GLOBAL="$(npm root -g)" && \
     find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
         rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
@@ -70,73 +88,24 @@ RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile
     find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
         rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
     done && \
-    # SECURITY FIX: patch npm's own package.json metadata so scanners see the
-    # actual installed versions instead of the stale declared dependencies.
     find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
         sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null && \
     npm cache clean --force && \
-    # Remove the apk-tracked npm so its stale SBOM metadata (tar 7.5.9) is
-    # no longer visible to image scanners.  The globally installed npm@latest
-    # at /usr/local/lib/node_modules/npm/ remains fully functional.
     { apk del --no-cache npm 2>/dev/null || true; }
 
 WORKDIR /app
-# Copy the current directory contents into the container at /app
-COPY . .
-RUN ls -la /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Copy the built wheel from the builder stage to the runtime stage; assumes only one wheel file is present
-COPY --from=builder /app/dist/*.whl .
-COPY --from=builder /wheels/ /wheels/
+COPY --from=builder /app /app
 
-# Install the built wheel using pip; again using a wildcard if it's the only file
-RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ --no-deps && rm -f *.whl && rm -rf /wheels
-
-# Replace the nodejs-wheel-binaries bundled node with the system node (fixes CVE-2025-55130)
-RUN NODEJS_WHEEL_NODE=$(find /usr/lib -path "*/nodejs_wheel/bin/node" 2>/dev/null) && \
-    if [ -n "$NODEJS_WHEEL_NODE" ]; then cp /usr/bin/node "$NODEJS_WHEEL_NODE"; fi
-
-# Remove test files and keys from dependencies
-RUN find /usr/lib -type f -path "*/tornado/test/*" -delete && \
-    find /usr/lib -type d -path "*/tornado/test" -delete
-
-# SECURITY FIX: nodejs-wheel-binaries (pip package used by Prisma) bundles a complete
-# npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
-# Patch every copy of tar, glob, and brace-expansion inside that tree.
-RUN GLOBAL="$(npm root -g)" && \
-    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
-    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-    done && \
-    find /usr/lib -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-    done && \
-    find /usr/lib -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-    done && \
-    find /usr/lib -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
-    done && \
-    find /usr/lib -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
-    done
-
-# Install semantic_router and aurelio-sdk using script
-# Convert Windows line endings to Unix and make executable
-RUN sed -i 's/\r$//' docker/install_auto_router.sh && chmod +x docker/install_auto_router.sh && ./docker/install_auto_router.sh
-
-# Generate prisma client using the correct schema
-RUN prisma generate --schema=./litellm/proxy/schema.prisma
-# Convert Windows line endings to Unix for entrypoint scripts
-RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh
-RUN sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
+RUN find /app/.venv -type f -path "*/tornado/test/*" -delete && \
+    find /app/.venv -type d -path "*/tornado/test" -delete
 
 EXPOSE 4000/tcp
 
-RUN apk add --no-cache supervisor
 COPY docker/supervisord.conf /etc/supervisord.conf
 
 ENTRYPOINT ["docker/prod_entrypoint.sh"]
-
-# Append "--detailed_debug" to the end of CMD to view detailed debug logs
 CMD ["--port", "4000"]

GEMINI.md

@@ -22,11 +22,11 @@ This file provides guidance to Gemini when working with code in this repository.
 - `make lint-mypy` - Run MyPy type checking only
 
 ### Single Test Files
-- `poetry run pytest tests/path/to/test_file.py -v` - Run specific test file
-- `poetry run pytest tests/path/to/test_file.py::test_function -v` - Run specific test
+- `uv run pytest tests/path/to/test_file.py -v` - Run specific test file
+- `uv run pytest tests/path/to/test_file.py::test_function -v` - Run specific test
 
 ### Running Scripts
-- `poetry run python script.py` - Run Python scripts (use for non-test files)
+- `uv run python script.py` - Run Python scripts (use for non-test files)
 
 ### GitHub Issue & PR Templates
 When contributing to the project, use the appropriate templates:
@@ -105,4 +105,4 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 ### Enterprise Features
 - Enterprise-specific code in `enterprise/` directory
 - Optional features enabled via environment variables
-- Separate licensing and authentication for enterprise features
+- Separate licensing and authentication for enterprise features

Makefile

@@ -15,7 +15,7 @@ help:
 	@echo "  make install-proxy-dev  - Install proxy development dependencies"
 	@echo "  make install-dev-ci     - Install dev dependencies (CI-compatible, pins OpenAI)"
 	@echo "  make install-proxy-dev-ci - Install proxy dev dependencies (CI-compatible)"
-	@echo "  make install-test-deps  - Install test dependencies"
+	@echo "  make install-test-deps  - Install the full local test environment"
 	@echo "  make install-helm-unittest - Install helm unittest plugin"
 	@echo "  make format             - Apply Black code formatting"
 	@echo "  make format-check       - Check Black code formatting (matches CI)"
@@ -40,49 +40,44 @@ help:
 	@echo "  make test-integration   - Run integration tests"
 	@echo "  make test-unit-helm     - Run helm unit tests"
 
-# Keep PIP simple for edge cases:
-PIP := $(shell command -v pip > /dev/null 2>&1 && echo "pip" || echo "python3 -m pip")
+UV := uv
+UV_RUN := $(UV) run --no-sync
 
 # Show info
 info:
-	@echo "PIP: $(PIP)"
+	@echo "UV: $(UV)"
 
 # Installation targets
 install-dev:
-	poetry install --with dev
+	$(UV) sync --frozen
 
 install-proxy-dev:
-	poetry install --with dev,proxy-dev --extras proxy
+	$(UV) sync --frozen --group proxy-dev --extra proxy
 
 # CI-compatible installations (matches GitHub workflows exactly)
 install-dev-ci:
-	$(PIP) install openai==2.8.0
-	poetry install --with dev
-	$(PIP) install openai==2.8.0
+	$(UV) sync --frozen
 
 install-proxy-dev-ci:
-	poetry install --with dev,proxy-dev --extras proxy
-	$(PIP) install openai==2.8.0
+	$(UV) sync --frozen --group proxy-dev --extra proxy
 
 install-test-deps: install-proxy-dev
-	poetry run $(PIP) install "pytest-retry==1.6.3"
-	poetry run $(PIP) install pytest-xdist
-	poetry run $(PIP) install openapi-core
-	cd enterprise && poetry run $(PIP) install -e . && cd ..
+	$(UV) sync --frozen --all-groups --all-extras
+	$(UV_RUN) prisma generate --schema litellm/proxy/schema.prisma
 
 install-helm-unittest:
 	helm plugin install https://github.com/helm-unittest/helm-unittest --version v0.4.4 || echo "ignore error if plugin exists"
 
 # Formatting
 format: install-dev
-	cd litellm && poetry run black . && cd ..
+	cd litellm && $(UV_RUN) black . && cd ..
 
 format-check: install-dev
-	cd litellm && poetry run black --check . && cd ..
+	cd litellm && $(UV_RUN) black --check . && cd ..
 
 # Linting targets
 lint-ruff: install-dev
-	cd litellm && poetry run ruff check . && cd ..
+	cd litellm && $(UV_RUN) ruff check . && cd ..
 
 # faster linter for developing ...
 # inspiration from:
@@ -96,37 +91,36 @@ lint-format-changed: install-dev
 			$$start = $$1; $$count = $$2 || 1; $$end = $$start + $$count - 1; \
 			print "$$file:$$start:1-$$end:999\n"; \
 		}' | \
-	while read range; do \
-		file="$${range%%:*}"; \
-		lines="$${range#*:}"; \
-		echo "Formatting $$file (lines $$lines)"; \
-		poetry run ruff format --range "$$lines" "$$file"; \
-	done
+		while read range; do \
+			file="$${range%%:*}"; \
+			lines="$${range#*:}"; \
+			echo "Formatting $$file (lines $$lines)"; \
+			$(UV_RUN) ruff format --range "$$lines" "$$file"; \
+		done
 
 lint-ruff-dev: install-dev
 	@tmpfile=$$(mktemp /tmp/ruff-dev.XXXXXX) && \
 	cd litellm && \
-	(poetry run ruff check . --output-format=pylint || true) > "$$tmpfile" && \
-	poetry run diff-quality --violations=pylint "$$tmpfile" --compare-branch=origin/main && \
+	($(UV_RUN) ruff check . --output-format=pylint || true) > "$$tmpfile" && \
+	$(UV_RUN) diff-quality --violations=pylint "$$tmpfile" --compare-branch=origin/main && \
 	cd .. ; \
 	rm -f "$$tmpfile"
 
 lint-ruff-FULL-dev: install-dev
 	@files=$$(git diff --name-only origin/main -- '*.py'); \
-	if [ -n "$$files" ]; then echo "$$files" | xargs poetry run ruff check; \
+	if [ -n "$$files" ]; then echo "$$files" | xargs $(UV_RUN) ruff check; \
 	else echo "No changed .py files to check."; fi
 
 lint-mypy: install-dev
-	poetry run $(PIP) install types-requests types-setuptools types-redis types-PyYAML
-	cd litellm && poetry run mypy . --ignore-missing-imports && cd ..
+	cd litellm && $(UV_RUN) mypy . --ignore-missing-imports && cd ..
 
 lint-black: format-check
 
 check-circular-imports: install-dev
-	cd litellm && poetry run python ../tests/documentation_tests/test_circular_imports.py && cd ..
+	cd litellm && $(UV_RUN) python ../tests/documentation_tests/test_circular_imports.py && cd ..
 
 check-import-safety: install-dev
-	@poetry run python -c "from litellm import *; print('[from litellm import *] OK! no issues!');" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
+	@$(UV_RUN) python -c "from litellm import *; print('[from litellm import *] OK! no issues!');" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
 
 # Combined linting (matches test-linting.yml workflow)
 lint: format-check lint-ruff lint-mypy check-circular-imports check-import-safety
@@ -135,46 +129,46 @@ lint: format-check lint-ruff lint-mypy check-circular-imports check-import-safet
 lint-dev: lint-format-changed lint-mypy check-circular-imports check-import-safety
 
 # Testing targets
-test:
-	poetry run pytest tests/
+test: install-test-deps
+	$(UV_RUN) pytest tests/
 
 test-unit: install-test-deps
-	poetry run pytest tests/test_litellm -x -vv -n 4
+	$(UV_RUN) pytest tests/test_litellm -x -vv -n 4
 
 # Matrix test targets (matching CI workflow groups)
 test-unit-llms: install-test-deps
-	poetry run pytest tests/test_litellm/llms --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/llms --tb=short -vv -n 4 --durations=20
 
 test-unit-proxy-guardrails: install-test-deps
-	poetry run pytest tests/test_litellm/proxy/guardrails tests/test_litellm/proxy/management_endpoints tests/test_litellm/proxy/management_helpers --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/proxy/guardrails tests/test_litellm/proxy/management_endpoints tests/test_litellm/proxy/management_helpers --tb=short -vv -n 4 --durations=20
 
 test-unit-proxy-core: install-test-deps
-	poetry run pytest tests/test_litellm/proxy/auth tests/test_litellm/proxy/client tests/test_litellm/proxy/db tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/proxy/auth tests/test_litellm/proxy/client tests/test_litellm/proxy/db tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine --tb=short -vv -n 4 --durations=20
 
 test-unit-proxy-misc: install-test-deps
-	poetry run pytest tests/test_litellm/proxy/_experimental tests/test_litellm/proxy/agent_endpoints tests/test_litellm/proxy/anthropic_endpoints tests/test_litellm/proxy/common_utils tests/test_litellm/proxy/discovery_endpoints tests/test_litellm/proxy/experimental tests/test_litellm/proxy/google_endpoints tests/test_litellm/proxy/health_endpoints tests/test_litellm/proxy/image_endpoints tests/test_litellm/proxy/middleware tests/test_litellm/proxy/openai_files_endpoint tests/test_litellm/proxy/pass_through_endpoints tests/test_litellm/proxy/prompts tests/test_litellm/proxy/public_endpoints tests/test_litellm/proxy/response_api_endpoints tests/test_litellm/proxy/spend_tracking tests/test_litellm/proxy/ui_crud_endpoints tests/test_litellm/proxy/vector_store_endpoints tests/test_litellm/proxy/test_*.py --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/proxy/_experimental tests/test_litellm/proxy/agent_endpoints tests/test_litellm/proxy/anthropic_endpoints tests/test_litellm/proxy/common_utils tests/test_litellm/proxy/discovery_endpoints tests/test_litellm/proxy/experimental tests/test_litellm/proxy/google_endpoints tests/test_litellm/proxy/health_endpoints tests/test_litellm/proxy/image_endpoints tests/test_litellm/proxy/middleware tests/test_litellm/proxy/openai_files_endpoint tests/test_litellm/proxy/pass_through_endpoints tests/test_litellm/proxy/prompts tests/test_litellm/proxy/public_endpoints tests/test_litellm/proxy/response_api_endpoints tests/test_litellm/proxy/spend_tracking tests/test_litellm/proxy/ui_crud_endpoints tests/test_litellm/proxy/vector_store_endpoints tests/test_litellm/proxy/test_*.py --tb=short -vv -n 4 --durations=20
 
 test-unit-integrations: install-test-deps
-	poetry run pytest tests/test_litellm/integrations --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/integrations --tb=short -vv -n 4 --durations=20
 
 test-unit-core-utils: install-test-deps
-	poetry run pytest tests/test_litellm/litellm_core_utils --tb=short -vv -n 2 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/litellm_core_utils --tb=short -vv -n 2 --durations=20
 
 test-unit-other: install-test-deps
-	poetry run pytest tests/test_litellm/caching tests/test_litellm/responses tests/test_litellm/secret_managers tests/test_litellm/vector_stores tests/test_litellm/a2a_protocol tests/test_litellm/anthropic_interface tests/test_litellm/completion_extras tests/test_litellm/containers tests/test_litellm/enterprise tests/test_litellm/experimental_mcp_client tests/test_litellm/google_genai tests/test_litellm/images tests/test_litellm/interactions tests/test_litellm/passthrough tests/test_litellm/router_strategy tests/test_litellm/router_utils tests/test_litellm/types --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/caching tests/test_litellm/responses tests/test_litellm/secret_managers tests/test_litellm/vector_stores tests/test_litellm/a2a_protocol tests/test_litellm/anthropic_interface tests/test_litellm/completion_extras tests/test_litellm/containers tests/test_litellm/enterprise tests/test_litellm/experimental_mcp_client tests/test_litellm/google_genai tests/test_litellm/images tests/test_litellm/interactions tests/test_litellm/passthrough tests/test_litellm/router_strategy tests/test_litellm/router_utils tests/test_litellm/types --tb=short -vv -n 4 --durations=20
 
 test-unit-root: install-test-deps
-	poetry run pytest tests/test_litellm/test_*.py --tb=short -vv -n 4 --durations=20
+	$(UV_RUN) pytest tests/test_litellm/test_*.py --tb=short -vv -n 4 --durations=20
 
 # Proxy unit tests (tests/proxy_unit_tests split alphabetically)
 test-proxy-unit-a: install-test-deps
-	poetry run pytest tests/proxy_unit_tests/test_[a-o]*.py --tb=short -vv -n 2 --durations=20
+	$(UV_RUN) pytest tests/proxy_unit_tests/test_[a-o]*.py --tb=short -vv -n 2 --durations=20
 
 test-proxy-unit-b: install-test-deps
-	poetry run pytest tests/proxy_unit_tests/test_[p-z]*.py --tb=short -vv -n 2 --durations=20
+	$(UV_RUN) pytest tests/proxy_unit_tests/test_[p-z]*.py --tb=short -vv -n 2 --durations=20
 
-test-integration:
-	poetry run pytest tests/ -k "not test_litellm"
+test-integration: install-test-deps
+	$(UV_RUN) pytest tests/ -k "not test_litellm"
 
 test-unit-helm: install-helm-unittest
 	helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm
@@ -188,6 +182,6 @@ test-llm-translation-single: install-test-deps
 	@echo "Running single LLM translation test file..."
 	@if [ -z "$(FILE)" ]; then echo "Usage: make test-llm-translation-single FILE=test_filename.py"; exit 1; fi
 	@mkdir -p test-results
-	poetry run pytest tests/llm_translation/$(FILE) \
+	$(UV_RUN) pytest tests/llm_translation/$(FILE) \
 		--junitxml=test-results/junit.xml \
 		-v --tb=short --maxfail=100 --timeout=300

README.md

@@ -12,7 +12,7 @@
         </a>
         </p>
     </p>
-<h4 align="center"><a href="https://docs.litellm.ai/docs/simple_proxy" target="_blank">LiteLLM Proxy Server (AI Gateway)</a> | <a href="https://docs.litellm.ai/docs/enterprise#hosted-litellm-proxy" target="_blank"> Hosted Proxy</a> | <a href="https://litellm.ai/enterprise"target="_blank">Enterprise Tier</a> | <a href="https://litellm.ai/" target="_blank">Website</a></h4>
+<h4 align="center"><a href="https://docs.litellm.ai/docs/simple_proxy" target="_blank">LiteLLM Proxy Server (AI Gateway)</a> | <a href="https://docs.litellm.ai/docs/enterprise#hosted-litellm-proxy" target="_blank"> Hosted Proxy</a> | <a href="https://litellm.ai/enterprise"target="_blank">Enterprise Tier</a> | <a href="https://www.litellm.ai/ai-gateway" target="_blank">Website</a></h4>
 <h4 align="center">
     <a href="https://pypi.org/project/litellm/" target="_blank">
         <img src="https://img.shields.io/pypi/v/litellm.svg" alt="PyPI Version">
@@ -39,8 +39,45 @@
 
 <img width="2688" height="1600" alt="Group 7154 (1)" src="https://github.com/user-attachments/assets/c5ee0412-6fb5-4fb6-ab5b-bafae4209ca6" />
 
+---
 
-## Use LiteLLM for
+## What is LiteLLM
+
+LiteLLM is an open source AI Gateway that gives you a single, unified interface to call 100+ LLM providers — OpenAI, Anthropic, Gemini, Bedrock, Azure, and more — using the OpenAI format.
+
+Use it as a **Python SDK** for direct library integration, or deploy the **AI Gateway (Proxy Server)** as a centralized service for your team or organization.
+
+[**Jump to LiteLLM Proxy (LLM Gateway) Docs**](https://docs.litellm.ai/docs/simple_proxy) <br>
+[**Jump to Supported LLM Providers**](https://docs.litellm.ai/docs/providers)
+
+---
+
+## Why LiteLLM
+
+Managing LLM calls across providers gets complicated fast — different SDKs, auth patterns, request formats, and error types for every model. LiteLLM removes that friction:
+
+- **Unified API** — one interface for 100+ LLMs, no provider-specific SDK juggling
+- **Drop-in OpenAI compatibility** — swap providers without rewriting your code
+- **Production-ready gateway** — virtual keys, spend tracking, guardrails, load balancing, and an admin dashboard out of the box
+- **8ms P95 latency** at 1k RPS ([benchmarks](https://docs.litellm.ai/docs/benchmarks))
+
+### OSS Adopters
+
+<table>
+  <tr>
+    <td><img height="60" alt="Stripe" src="https://github.com/user-attachments/assets/f7296d4f-9fbd-460d-9d05-e4df31697c4b" /></td>
+    <td><img height="60" alt="image" src="https://github.com/user-attachments/assets/436fca71-988b-40bb-b5fe-8450c80fdbd0" /></td>
+    <td><img height="60" alt="Google ADK" src="https://github.com/user-attachments/assets/caf270a2-5aee-45c4-8222-41a2070c4f19" /></td>
+    <td><img height="60" alt="Greptile" src="https://github.com/user-attachments/assets/0be4bd8a-7cfa-48d3-9090-f415fe948280" /></td>
+    <td><img height="60" alt="OpenHands" src="https://github.com/user-attachments/assets/a6150c4c-149e-4cae-888b-8b92be6e003f" /></td>
+    <td><h2>Netflix</h2></td>
+    <td><img height="60" alt="OpenAI Agents SDK" src="https://github.com/user-attachments/assets/c02f7be0-8c2e-4d27-aea7-7c024bfaebc0" /></td>
+  </tr>
+</table>
+
+---
+
+## Features
 
 <details open>
 <summary><b>LLMs</b> - Call 100+ LLMs (Python SDK + AI Gateway)</summary>
@@ -50,7 +87,7 @@
 ### Python SDK
 
 ```shell
-pip install litellm
+uv add litellm
 ```
 
 ```python
@@ -72,7 +109,7 @@ response = completion(model="anthropic/claude-sonnet-4-20250514", messages=[{"ro
 [**Getting Started - E2E Tutorial**](https://docs.litellm.ai/docs/proxy/docker_quick_start) - Setup virtual keys, make your first request
 
 ```shell
-pip install 'litellm[proxy]'
+uv tool install 'litellm[proxy]'
 litellm --model gpt-4o
 ```
 
@@ -223,63 +260,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
 
 </details>
 
----
-
-## How to use LiteLLM
-
-You can use LiteLLM through either the Proxy Server or Python SDK. Both gives you a unified interface to access multiple LLMs (100+ LLMs). Choose the option that best fits your needs:
-
-<table style={{width: '100%', tableLayout: 'fixed'}}>
-<thead>
-<tr>
-<th style={{width: '14%'}}></th>
-<th style={{width: '43%'}}><strong><a href="https://docs.litellm.ai/docs/simple_proxy">LiteLLM AI Gateway</a></strong></th>
-<th style={{width: '43%'}}><strong><a href="https://docs.litellm.ai/docs/">LiteLLM Python SDK</a></strong></th>
-</tr>
-</thead>
-<tbody>
-<tr>
-<td style={{width: '14%'}}><strong>Use Case</strong></td>
-<td style={{width: '43%'}}>Central service (LLM Gateway) to access multiple LLMs</td>
-<td style={{width: '43%'}}>Use LiteLLM directly in your Python code</td>
-</tr>
-<tr>
-<td style={{width: '14%'}}><strong>Who Uses It?</strong></td>
-<td style={{width: '43%'}}>Gen AI Enablement / ML Platform Teams</td>
-<td style={{width: '43%'}}>Developers building LLM projects</td>
-</tr>
-<tr>
-<td style={{width: '14%'}}><strong>Key Features</strong></td>
-<td style={{width: '43%'}}>Centralized API gateway with authentication and authorization, multi-tenant cost tracking and spend management per project/user, per-project customization (logging, guardrails, caching), virtual keys for secure access control, admin dashboard UI for monitoring and management</td>
-<td style={{width: '43%'}}>Direct Python library integration in your codebase, Router with retry/fallback logic across multiple deployments (e.g. Azure/OpenAI) - <a href="https://docs.litellm.ai/docs/routing">Router</a>, application-level load balancing and cost tracking, exception handling with OpenAI-compatible errors, observability callbacks (Lunary, MLflow, Langfuse, etc.)</td>
-</tr>
-</tbody>
-</table>
-
-LiteLLM Performance: **8ms P95 latency** at 1k RPS (See benchmarks [here](https://docs.litellm.ai/docs/benchmarks))
-
-[**Jump to LiteLLM Proxy (LLM Gateway) Docs**](https://docs.litellm.ai/docs/simple_proxy) <br>
-[**Jump to Supported LLM Providers**](https://docs.litellm.ai/docs/providers)
-
-**Stable Release:** Use docker images with the `-stable` tag. These have undergone 12 hour load tests, before being published. [More information about the release cycle here](https://docs.litellm.ai/docs/proxy/release_cycle)
-
-Support for more providers. Missing a provider or LLM Platform, raise a [feature request](https://github.com/BerriAI/litellm/issues/new?assignees=&labels=enhancement&projects=&template=feature_request.yml&title=%5BFeature%5D%3A+).
-
-## OSS Adopters 
-
-<table>
-  <tr>
-    <td><img height="60" alt="Stripe" src="https://github.com/user-attachments/assets/f7296d4f-9fbd-460d-9d05-e4df31697c4b" /></td>
-    <td><img height="60" alt="image" src="https://github.com/user-attachments/assets/436fca71-988b-40bb-b5fe-8450c80fdbd0" /></td>
-    <td><img height="60" alt="Google ADK" src="https://github.com/user-attachments/assets/caf270a2-5aee-45c4-8222-41a2070c4f19" /></td>
-    <td><img height="60" alt="Greptile" src="https://github.com/user-attachments/assets/0be4bd8a-7cfa-48d3-9090-f415fe948280" /></td>
-    <td><img height="60" alt="OpenHands" src="https://github.com/user-attachments/assets/a6150c4c-149e-4cae-888b-8b92be6e003f" /></td>
-    <td><h2>Netflix</h2></td>
-    <td><img height="60" alt="OpenAI Agents SDK" src="https://github.com/user-attachments/assets/c02f7be0-8c2e-4d27-aea7-7c024bfaebc0" /></td>
-  </tr>
-</table>
-
-## Supported Providers ([Website Supported Models](https://models.litellm.ai/) | [Docs](https://docs.litellm.ai/docs/providers))
+### Supported Providers ([Website Supported Models](https://models.litellm.ai/) | [Docs](https://docs.litellm.ai/docs/providers))
 
 | Provider                                                                            | `/chat/completions` | `/messages` | `/responses` | `/embeddings` | `/image/generations` | `/audio/transcriptions` | `/audio/speech` | `/moderations` | `/batches` | `/rerank` |
 |-------------------------------------------------------------------------------------|---------------------|-------------|--------------|---------------|----------------------|-------------------------|-----------------|----------------|-----------|-----------|
@@ -386,25 +367,62 @@ Support for more providers. Missing a provider or LLM Platform, raise a [feature
 
 [**Read the Docs**](https://docs.litellm.ai/docs/)
 
-## Run in Developer mode
-### Services
+---
+
+## Get Started
+
+You can use LiteLLM through either the Proxy Server or Python SDK. Both give you a unified interface to access multiple LLMs (100+ LLMs). Choose the option that best fits your needs:
+
+<table style={{width: '100%', tableLayout: 'fixed'}}>
+<thead>
+<tr>
+<th style={{width: '14%'}}></th>
+<th style={{width: '43%'}}><strong><a href="https://docs.litellm.ai/docs/simple_proxy">LiteLLM AI Gateway</a></strong></th>
+<th style={{width: '43%'}}><strong><a href="https://docs.litellm.ai/docs/">LiteLLM Python SDK</a></strong></th>
+</tr>
+</thead>
+<tbody>
+<tr>
+<td style={{width: '14%'}}><strong>Use Case</strong></td>
+<td style={{width: '43%'}}>Central service (LLM Gateway) to access multiple LLMs</td>
+<td style={{width: '43%'}}>Use LiteLLM directly in your Python code</td>
+</tr>
+<tr>
+<td style={{width: '14%'}}><strong>Who Uses It?</strong></td>
+<td style={{width: '43%'}}>Gen AI Enablement / ML Platform Teams</td>
+<td style={{width: '43%'}}>Developers building LLM projects</td>
+</tr>
+<tr>
+<td style={{width: '14%'}}><strong>Key Features</strong></td>
+<td style={{width: '43%'}}>Centralized API gateway with authentication and authorization, multi-tenant cost tracking and spend management per project/user, per-project customization (logging, guardrails, caching), virtual keys for secure access control, admin dashboard UI for monitoring and management</td>
+<td style={{width: '43%'}}>Direct Python library integration in your codebase, Router with retry/fallback logic across multiple deployments (e.g. Azure/OpenAI) - <a href="https://docs.litellm.ai/docs/routing">Router</a>, application-level load balancing and cost tracking, exception handling with OpenAI-compatible errors, observability callbacks (Lunary, MLflow, Langfuse, etc.)</td>
+</tr>
+</tbody>
+</table>
+
+**Stable Release:** Use docker images with the `-stable` tag. These have undergone 12 hour load tests, before being published. [More information about the release cycle here](https://docs.litellm.ai/docs/proxy/release_cycle)
+
+Support for more providers. Missing a provider or LLM Platform, raise a [feature request](https://github.com/BerriAI/litellm/issues/new?assignees=&labels=enhancement&projects=&template=feature_request.yml&title=%5BFeature%5D%3A+).
+
+### Run in Developer Mode
+#### Services
 1. Setup .env file in root
 2. Run dependant services `docker-compose up db prometheus`
 
-### Backend
+#### Backend
 1. (In root) create virtual environment `python -m venv .venv`
 2. Activate virtual environment `source .venv/bin/activate`
-3. Install dependencies `pip install -e ".[all]"`
-4. `pip install prisma`
+3. Install dependencies `uv sync --all-extras --group proxy-dev`
+4. `uv run prisma generate`
 5. `prisma generate`
 6. Start proxy backend `python litellm/proxy/proxy_cli.py`
 
-### Frontend
+#### Frontend
 1. Navigate to `ui/litellm-dashboard`
 2. Install dependencies `npm install`
 3. Run `npm run dev` to start the dashboard
 
-# Verify Docker Image Signatures
+### Verify Docker Image Signatures
 
 All LiteLLM Docker images published to GHCR are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit `0112e53`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).
 
@@ -430,6 +448,8 @@ cosign verify \
 
 Replace `<release-tag>` with the version you are deploying (e.g. `v1.83.0-stable`).
 
+---
+
 # Enterprise
 For companies that need better security, user management and professional support
 
@@ -450,7 +470,7 @@ We welcome contributions to LiteLLM! Whether you're fixing bugs, adding features
 
 ## Quick Start for Contributors
 
-This requires poetry to be installed.
+This requires uv to be installed.
 
 ```bash
 git clone https://github.com/BerriAI/litellm.git
@@ -486,10 +506,6 @@ All these checks must pass before your PR can be merged.
 - [Community Slack 💭](https://www.litellm.ai/support)
 - Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
 
-# Why did we build this
-
-- **Need for simplicity**: Our code started to get extremely complicated managing & translating calls between Azure, OpenAI and Cohere.
-
 # Contributors
 
 <!-- ALL-CONTRIBUTORS-LIST:START - Do not remove or modify this section -->
@@ -504,4 +520,3 @@ All these checks must pass before your PR can be merged.
 <a href="https://github.com/BerriAI/litellm/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=BerriAI/litellm" />
 </a>
-

ci_cd/run_migration.py

@@ -17,7 +17,9 @@ def create_migration(migration_name: str = None):
     try:
         # Get paths
         root_dir = Path(__file__).parent.parent
-        migrations_dir = root_dir / "litellm-proxy-extras" / "litellm_proxy_extras" / "migrations"
+        migrations_dir = (
+            root_dir / "litellm-proxy-extras" / "litellm_proxy_extras" / "migrations"
+        )
         schema_path = root_dir / "schema.prisma"
 
         # Create temporary PostgreSQL database

cookbook/anthropic_agent_sdk/agent_with_mcp.py

@@ -24,24 +24,26 @@ async def interactive_chat_with_mcp():
     Interactive CLI chat with the agent and MCP server
     """
     config = Config()
-    
+
     # Configure Anthropic SDK to point to LiteLLM gateway
     litellm_base_url = setup_litellm_env(config)
-    
+
     # Fetch available models from proxy
-    available_models = await fetch_available_models(litellm_base_url, config.LITELLM_API_KEY)
-    
+    available_models = await fetch_available_models(
+        litellm_base_url, config.LITELLM_API_KEY
+    )
+
     current_model = config.LITELLM_MODEL
-    
+
     # MCP server configuration
     mcp_server_url = f"{litellm_base_url}/mcp/deepwiki2"
     use_mcp = os.getenv("USE_MCP", "true").lower() == "true"
-    
+
     if not use_mcp:
         print("⚠️  MCP disabled via USE_MCP=false")
-    
+
     print_header(litellm_base_url, current_model, has_mcp=use_mcp)
-    
+
     while True:
         # Configure agent options
         if use_mcp:
@@ -58,7 +60,7 @@ async def interactive_chat_with_mcp():
                             "url": mcp_server_url,
                             "headers": {
                                 "Authorization": f"Bearer {config.LITELLM_API_KEY}"
-                            }
+                            },
                         }
                     },
                 )
@@ -78,12 +80,12 @@ async def interactive_chat_with_mcp():
                 model=current_model,
                 max_turns=50,
             )
-        
+
         # Create agent client
         try:
             async with ClaudeSDKClient(options=options) as client:
                 conversation_active = True
-                
+
                 while conversation_active:
                     # Get user input
                     try:
@@ -91,34 +93,36 @@ async def interactive_chat_with_mcp():
                     except (EOFError, KeyboardInterrupt):
                         print("\n\n👋 Goodbye!")
                         return
-                    
+
                     # Handle commands
-                    if user_input.lower() in ['quit', 'exit']:
+                    if user_input.lower() in ["quit", "exit"]:
                         print("\n👋 Goodbye!")
                         return
-                    
-                    if user_input.lower() == 'clear':
+
+                    if user_input.lower() == "clear":
                         print("\n🔄 Starting new conversation...\n")
                         conversation_active = False
                         continue
-                    
-                    if user_input.lower() == 'models':
+
+                    if user_input.lower() == "models":
                         handle_model_list(available_models, current_model)
                         continue
-                    
-                    if user_input.lower() == 'model':
-                        new_model, should_restart = handle_model_switch(available_models, current_model)
+
+                    if user_input.lower() == "model":
+                        new_model, should_restart = handle_model_switch(
+                            available_models, current_model
+                        )
                         if should_restart:
                             current_model = new_model
                             conversation_active = False
                         continue
-                    
+
                     if not user_input:
                         continue
-                    
+
                     # Stream response from agent
                     await stream_response(client, user_input)
-        
+
         except Exception as e:
             print(f"\n❌ Error creating agent client: {e}")
             print("This might be an MCP configuration issue. Try running without MCP:")

cookbook/anthropic_agent_sdk/common.py

@@ -8,13 +8,13 @@ import httpx
 
 class Config:
     """Configuration for LiteLLM Gateway connection"""
-    
+
     # LiteLLM proxy URL (default to local instance)
     LITELLM_PROXY_URL = os.getenv("LITELLM_PROXY_URL", "http://localhost:4000")
-    
+
     # LiteLLM API key (master key or virtual key)
     LITELLM_API_KEY = os.getenv("LITELLM_API_KEY", "sk-1234")
-    
+
     # Model name as configured in LiteLLM (e.g., "bedrock-claude-sonnet-4", "gpt-4", etc.)
     LITELLM_MODEL = os.getenv("LITELLM_MODEL", "bedrock-claude-sonnet-4.5")
 
@@ -28,7 +28,7 @@ async def fetch_available_models(base_url: str, api_key: str) -> list[str]:
             response = await client.get(
                 f"{base_url}/models",
                 headers={"Authorization": f"Bearer {api_key}"},
-                timeout=10.0
+                timeout=10.0,
             )
             response.raise_for_status()
             data = response.json()
@@ -50,7 +50,7 @@ def setup_litellm_env(config: Config):
     """
     Configure environment variables to point Agent SDK to LiteLLM
     """
-    litellm_base_url = config.LITELLM_PROXY_URL.rstrip('/')
+    litellm_base_url = config.LITELLM_PROXY_URL.rstrip("/")
     os.environ["ANTHROPIC_BASE_URL"] = litellm_base_url
     os.environ["ANTHROPIC_API_KEY"] = config.LITELLM_API_KEY
     return litellm_base_url
@@ -87,10 +87,12 @@ def handle_model_list(available_models: list[str], current_model: str):
         print(f"  {marker} {i}. {model}")
 
 
-def handle_model_switch(available_models: list[str], current_model: str) -> tuple[str, bool]:
+def handle_model_switch(
+    available_models: list[str], current_model: str
+) -> tuple[str, bool]:
     """
     Handle model switching
-    
+
     Returns:
         tuple: (new_model, should_restart_conversation)
     """
@@ -98,7 +100,7 @@ def handle_model_switch(available_models: list[str], current_model: str) -> tupl
     for i, model in enumerate(available_models, 1):
         marker = "✓" if model == current_model else " "
         print(f"  {marker} {i}. {model}")
-    
+
     try:
         choice = input("\nEnter number (or press Enter to cancel): ").strip()
         if choice:
@@ -112,7 +114,7 @@ def handle_model_switch(available_models: list[str], current_model: str) -> tupl
                 print("❌ Invalid choice")
     except (ValueError, IndexError):
         print("❌ Invalid input")
-    
+
     return current_model, False
 
 
@@ -120,41 +122,43 @@ async def stream_response(client, user_input: str):
     """
     Stream response from the agent
     """
-    print("\n🤖 Assistant: ", end='', flush=True)
-    
+    print("\n🤖 Assistant: ", end="", flush=True)
+
     try:
         await client.query(user_input)
-        
+
         # Show loading indicator
-        print("⏳ thinking...", end='', flush=True)
-        
+        print("⏳ thinking...", end="", flush=True)
+
         # Stream the response
         first_chunk = True
         async for msg in client.receive_response():
             # Clear loading indicator on first message
             if first_chunk:
-                print("\r🤖 Assistant: ", end='', flush=True)
+                print("\r🤖 Assistant: ", end="", flush=True)
                 first_chunk = False
-            
+
             # Handle different message types
-            if hasattr(msg, 'type'):
-                if msg.type == 'content_block_delta':
+            if hasattr(msg, "type"):
+                if msg.type == "content_block_delta":
                     # Streaming text delta
-                    if hasattr(msg, 'delta') and hasattr(msg.delta, 'text'):
-                        print(msg.delta.text, end='', flush=True)
-                elif msg.type == 'content_block_start':
+                    if hasattr(msg, "delta") and hasattr(msg.delta, "text"):
+                        print(msg.delta.text, end="", flush=True)
+                elif msg.type == "content_block_start":
                     # Start of content block
-                    if hasattr(msg, 'content_block') and hasattr(msg.content_block, 'text'):
-                        print(msg.content_block.text, end='', flush=True)
-            
+                    if hasattr(msg, "content_block") and hasattr(
+                        msg.content_block, "text"
+                    ):
+                        print(msg.content_block.text, end="", flush=True)
+
             # Fallback to original content handling
-            if hasattr(msg, 'content'):
+            if hasattr(msg, "content"):
                 for content_block in msg.content:
-                    if hasattr(content_block, 'text'):
-                        print(content_block.text, end='', flush=True)
-        
+                    if hasattr(content_block, "text"):
+                        print(content_block.text, end="", flush=True)
+
         print()  # New line after response
-        
+
     except Exception as e:
         print(f"\r\n❌ Error: {e}")
         print("Please check your LiteLLM gateway is running and configured correctly.")

cookbook/anthropic_agent_sdk/main.py

@@ -24,17 +24,19 @@ async def interactive_chat():
     Interactive CLI chat with the agent
     """
     config = Config()
-    
+
     # Configure Anthropic SDK to point to LiteLLM gateway
     litellm_base_url = setup_litellm_env(config)
-    
+
     # Fetch available models from proxy
-    available_models = await fetch_available_models(litellm_base_url, config.LITELLM_API_KEY)
-    
+    available_models = await fetch_available_models(
+        litellm_base_url, config.LITELLM_API_KEY
+    )
+
     current_model = config.LITELLM_MODEL
-    
+
     print_header(litellm_base_url, current_model)
-    
+
     while True:
         # Configure agent options for each conversation
         options = ClaudeAgentOptions(
@@ -42,11 +44,11 @@ async def interactive_chat():
             model=current_model,
             max_turns=50,
         )
-        
+
         # Create agent client
         async with ClaudeSDKClient(options=options) as client:
             conversation_active = True
-            
+
             while conversation_active:
                 # Get user input
                 try:
@@ -54,31 +56,33 @@ async def interactive_chat():
                 except (EOFError, KeyboardInterrupt):
                     print("\n\n👋 Goodbye!")
                     return
-                
+
                 # Handle commands
-                if user_input.lower() in ['quit', 'exit']:
+                if user_input.lower() in ["quit", "exit"]:
                     print("\n👋 Goodbye!")
                     return
-                
-                if user_input.lower() == 'clear':
+
+                if user_input.lower() == "clear":
                     print("\n🔄 Starting new conversation...\n")
                     conversation_active = False
                     continue
-                
-                if user_input.lower() == 'models':
+
+                if user_input.lower() == "models":
                     handle_model_list(available_models, current_model)
                     continue
-                
-                if user_input.lower() == 'model':
-                    new_model, should_restart = handle_model_switch(available_models, current_model)
+
+                if user_input.lower() == "model":
+                    new_model, should_restart = handle_model_switch(
+                        available_models, current_model
+                    )
                     if should_restart:
                         current_model = new_model
                         conversation_active = False
                     continue
-                
+
                 if not user_input:
                     continue
-                
+
                 # Stream response from agent
                 await stream_response(client, user_input)
 

cookbook/litellm-ollama-docker-image/requirements.txt

@@ -1 +1 @@
-litellm==1.61.15
+litellm==1.83.5

cookbook/litellm_proxy_server/batch_api/bedrock/bedrock.py

@@ -11,15 +11,15 @@ BEDROCK_BATCH_MODEL = "bedrock/batch-anthropic.claude-3-5-sonnet-20240620-v1:0"
 batch_input_file = client.files.create(
     file=open("./bedrock_batch_completions.jsonl", "rb"),
     purpose="batch",
-    extra_body={"target_model_names": BEDROCK_BATCH_MODEL}
+    extra_body={"target_model_names": BEDROCK_BATCH_MODEL},
 )
 print(batch_input_file)
 
 # Create batch
-batch = client.batches.create( 
+batch = client.batches.create(
     input_file_id=batch_input_file.id,
     endpoint="/v1/chat/completions",
     completion_window="24h",
     metadata={"description": "Test batch job"},
 )
-print(batch)
+print(batch)

cookbook/litellm_proxy_server/cli_token_usage.py

@@ -8,6 +8,7 @@ in your Python scripts after running `litellm-proxy login`.
 
 from textwrap import indent
 import litellm
+
 LITELLM_BASE_URL = "http://localhost:4000/"
 
 
@@ -15,38 +16,38 @@ def main():
     """Using CLI token with LiteLLM SDK"""
     print("🚀 Using CLI Token with LiteLLM SDK")
     print("=" * 40)
-    #litellm._turn_on_debug()
-    
+    # litellm._turn_on_debug()
+
     # Get the CLI token
     api_key = litellm.get_litellm_gateway_api_key()
-    
+
     if not api_key:
         print("❌ No CLI token found. Please run 'litellm-proxy login' first.")
         return
-    
+
     print("✅ Found CLI token.")
 
     available_models = litellm.get_valid_models(
         check_provider_endpoint=True,
         custom_llm_provider="litellm_proxy",
         api_key=api_key,
-        api_base=LITELLM_BASE_URL
+        api_base=LITELLM_BASE_URL,
     )
-    
+
     print("✅ Available models:")
     if available_models:
         for i, model in enumerate(available_models, 1):
             print(f"   {i:2d}. {model}")
     else:
         print("   No models available")
-    
+
     # Use with LiteLLM
     try:
         response = litellm.completion(
             model="litellm_proxy/gemini/gemini-2.5-flash",
             messages=[{"role": "user", "content": "Hello from CLI token!"}],
             api_key=api_key,
-            base_url=LITELLM_BASE_URL
+            base_url=LITELLM_BASE_URL,
         )
         print(f"✅ LLM Response: {response.model_dump_json(indent=4)}")
     except Exception as e:
@@ -55,7 +56,7 @@ def main():
 
 if __name__ == "__main__":
     main()
-    
+
     print("\n💡 Tips:")
     print("1. Run 'litellm-proxy login' to authenticate first")
     print("2. Replace 'https://your-proxy.com' with your actual proxy URL")

cookbook/litellm_proxy_server/mcp/mcp_with_litellm_proxy.py

@@ -3,11 +3,12 @@ Use LiteLLM Proxy MCP Gateway to call MCP tools.
 
 When using LiteLLM Proxy, you can use the same MCP tools across all your LLM providers.
 """
+
 import openai
 
 client = openai.OpenAI(
-    api_key="sk-1234", # paste your litellm proxy api key here
-    base_url="http://localhost:4000" # paste your litellm proxy base url here
+    api_key="sk-1234",  # paste your litellm proxy api key here
+    base_url="http://localhost:4000",  # paste your litellm proxy base url here
 )
 print("Making API request to Responses API with MCP tools")
 
@@ -17,7 +18,7 @@ response = client.responses.create(
         {
             "role": "user",
             "content": "give me TLDR of what BerriAI/litellm repo is about",
-            "type": "message"
+            "type": "message",
         }
     ],
     tools=[
@@ -25,11 +26,11 @@ response = client.responses.create(
             "type": "mcp",
             "server_label": "litellm",
             "server_url": "litellm_proxy",
-            "require_approval": "never"
+            "require_approval": "never",
         }
     ],
     stream=True,
-    tool_choice="required"
+    tool_choice="required",
 )
 
 for chunk in response:

cookbook/litellm_proxy_server/secret_manager/my_secret_manager.py

@@ -40,8 +40,10 @@ class InMemorySecretManager(CustomSecretManager):
     ) -> Optional[str]:
         """Read secret synchronously"""
         from litellm._logging import verbose_proxy_logger
-        
-        verbose_proxy_logger.info(f"CUSTOM SECRET MANAGER: LOOKING FOR SECRET: {secret_name}")
+
+        verbose_proxy_logger.info(
+            f"CUSTOM SECRET MANAGER: LOOKING FOR SECRET: {secret_name}"
+        )
         value = self.secrets.get(secret_name)
         verbose_proxy_logger.info(f"CUSTOM SECRET MANAGER: READ SECRET: {value}")
         return value
@@ -76,4 +78,3 @@ class InMemorySecretManager(CustomSecretManager):
             del self.secrets[secret_name]
             return {"status": "deleted", "secret_name": secret_name}
         return {"status": "not_found", "secret_name": secret_name}
-

cookbook/livekit_agent_sdk/main.py

@@ -5,6 +5,7 @@ This example shows how to use LiveKit's xAI realtime plugin through LiteLLM prox
 LiteLLM acts as a unified interface, allowing you to switch between xAI, OpenAI, 
 and Azure realtime APIs without changing your agent code.
 """
+
 import asyncio
 import json
 import os
@@ -23,71 +24,79 @@ async def run_voice_agent():
     2. Sends a user message
     3. Streams back the response
     """
-    
+
     url = f"ws://{PROXY_URL.replace('http://', '').replace('https://', '')}/v1/realtime?model={MODEL}"
     headers = {"Authorization": f"Bearer {API_KEY}"}
-    
+
     print(f"🎙️  Connecting to voice agent...")
     print(f"   Model: {MODEL}")
     print(f"   Proxy: {PROXY_URL}")
     print()
-    
+
     async with websockets.connect(url, additional_headers=headers) as ws:
         # Receive initial connection event
         initial = json.loads(await ws.recv())
         print(f"✅ Connected! Event: {initial['type']}\n")
-        
+
         # Get user input
         user_message = input("💬 Your message: ").strip()
         if not user_message:
             user_message = "Tell me a fun fact about AI!"
-        
+
         print(f"\n🤖 Sending to {MODEL}...\n")
-        
+
         # Send user message
-        await ws.send(json.dumps({
-            "type": "conversation.item.create",
-            "item": {
-                "type": "message",
-                "role": "user",
-                "content": [{"type": "input_text", "text": user_message}]
-            }
-        }))
-        
+        await ws.send(
+            json.dumps(
+                {
+                    "type": "conversation.item.create",
+                    "item": {
+                        "type": "message",
+                        "role": "user",
+                        "content": [{"type": "input_text", "text": user_message}],
+                    },
+                }
+            )
+        )
+
         # Request response
-        await ws.send(json.dumps({
-            "type": "response.create",
-            "response": {"modalities": ["text", "audio"]}
-        }))
-        
+        await ws.send(
+            json.dumps(
+                {
+                    "type": "response.create",
+                    "response": {"modalities": ["text", "audio"]},
+                }
+            )
+        )
+
         # Stream response
-        print("🎤 Response: ", end='', flush=True)
+        print("🎤 Response: ", end="", flush=True)
         transcript = []
-        
+
         try:
             while True:
                 msg = await asyncio.wait_for(ws.recv(), timeout=15.0)
                 event = json.loads(msg)
-                
+
                 # Capture transcript deltas
-                if event['type'] == 'response.output_audio_transcript.delta':
-                    delta = event.get('delta', '')
+                if event["type"] == "response.output_audio_transcript.delta":
+                    delta = event.get("delta", "")
                     if delta:
-                        print(delta, end='', flush=True)
+                        print(delta, end="", flush=True)
                         transcript.append(delta)
-                
+
                 # Done when response completes
-                elif event['type'] == 'response.done':
+                elif event["type"] == "response.done":
                     break
-        
+
         except asyncio.TimeoutError:
             pass
-        
+
         print("\n")
-        
+
         if transcript:
             print(f"✅ Complete response: {''.join(transcript)}")
-        
+
         await ws.close()
 
 
@@ -97,7 +106,7 @@ def main():
     print("LiveKit xAI Voice Agent via LiteLLM Proxy")
     print("=" * 70)
     print()
-    
+
     try:
         asyncio.run(run_voice_agent())
     except KeyboardInterrupt:

cookbook/misc/RELEASE_NOTES_GENERATION_INSTRUCTIONS.md

@@ -9,6 +9,32 @@ This document provides comprehensive instructions for AI agents to generate rele
 3. **Previous Version Commit Hash** - To compare model pricing changes
 4. **Reference Release Notes** - Use recent stable releases (v1.76.3-stable, v1.77.2-stable) as templates for consistent formatting
 
+### Resolving Staging PRs
+
+The GitHub release page (e.g. `https://github.com/BerriAI/litellm/releases/tag/v1.83.3-stable`) does **not** list the real changelog directly. The "What's Changed" section contains **staging PRs** that each bundle many individual commits/PRs. For example:
+
+- `Litellm oss staging 03 14 2026 by @RheagalFire in #23686`
+- `Litellm ryan march 16 by @ryan-crabbe in #23822`
+
+To get the real changelog, you MUST click into each staging PR (e.g. `#23686`, `#23822`), open its **Commits** tab, and extract every underlying commit/PR (look for the `(#NNNNN)` suffix on commit titles). Those underlying PRs — not the staging PRs — are what get categorized in the release notes. Never treat a staging PR title as a single changelog entry.
+
+**IMPORTANT — staging PRs are not the complete source.** Some PRs land on the release branch *before* the staging PRs and are therefore not reachable via `gh api /pulls/<staging>/commits`. GitHub's auto-generated "What's Changed" on the release page also misses these. To catch every PR in the release, you MUST additionally walk the full git log range between the previous release's commit and this release's commit:
+
+```bash
+git fetch origin --tags
+git log <prev_release_commit>..<this_release_commit> --oneline | grep -oE '#[0-9]+' | sort -u
+```
+
+Union the PR set from the staging-PR walk with the PR set from `git log`. Any PR in `git log` but missing from your staging-expanded set is almost certainly a content PR that merged directly to the release branch — fetch its title/body with `gh pr view <N>` and categorize it. Do not trust the GH release body or the staging PRs alone as the authoritative list.
+
+**Sanity check for new contributors.** The GH release body's "New Contributors" list is a *floor*, not authoritative. For every PR author who appears in the release (including underlying PRs from staging and PRs found only via `git log`), verify whether they are a first-time contributor by running:
+
+```bash
+gh api "search/issues?q=is:pr+author:<login>+repo:BerriAI/litellm+is:merged&sort=created&order=asc" --jq '.items[0] | {n:.number, merged:.closed_at}'
+```
+
+If the author's earliest merged PR number matches a PR in this release window, they are a new contributor. If their earliest merged PR predates the previous release tag, they are not. Do not copy the GH release body's list blindly — it can both miss contributors (PRs that merged via an older dev branch) and falsely include contributors whose "first" PR in this window was not actually their first ever.
+
 ## Step-by-Step Process
 
 ### 1. Initial Setup and Analysis

cookbook/misc/test_responses_api.py

@@ -1,10 +1,9 @@
 import base64
 from openai import OpenAI
 import time
-client = OpenAI(
-    base_url="http://0.0.0.0:4001",
-    api_key="sk-1234"
-)
+
+client = OpenAI(base_url="http://0.0.0.0:4001", api_key="sk-1234")
+
 
 # Function to encode the image
 def encode_image(image_path):
@@ -25,7 +24,7 @@ response = client.responses.create(
         {
             "role": "user",
             "content": [
-                { "type": "input_text", "text": "what color is the image"},
+                {"type": "input_text", "text": "what color is the image"},
                 {
                     "type": "input_image",
                     "image_url": f"data:image/jpeg;base64,{base64_image}",
@@ -36,7 +35,6 @@ response = client.responses.create(
 )
 
 
-
 print(response.output_text)
 print("response1 id===", response.id)
 print("sleeping for 20 seconds...")
@@ -45,9 +43,7 @@ print("making follow up request for existing id")
 response2 = client.responses.create(
     model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0",
     previous_response_id=response.id,
-    input="ok, and what objects are in the image?"
+    input="ok, and what objects are in the image?",
 )
 
 print(response2.output_text)
-
-

cookbook/nova_sonic_realtime.py

@@ -52,11 +52,11 @@ class RealtimeClient:
     async def connect(self):
         """Connect to LiteLLM proxy realtime endpoint."""
         print(f"Connecting to {self.url}...")
-        
+
         headers = {}
         if self.api_key:
             headers["Authorization"] = f"Bearer {self.api_key}"
-        
+
         self.ws = await websockets.connect(
             self.url,
             additional_headers=headers,
@@ -175,7 +175,9 @@ class RealtimeClient:
 
         try:
             while self.is_active:
-                audio_data = self.input_stream.read(CHUNK_SIZE, exception_on_overflow=False)
+                audio_data = self.input_stream.read(
+                    CHUNK_SIZE, exception_on_overflow=False
+                )
                 await self.send_audio_chunk(audio_data)
                 await asyncio.sleep(0.01)  # Small delay to prevent overwhelming
         except Exception as e:
@@ -270,6 +272,7 @@ async def main():
     except Exception as e:
         print(f"\n❌ Error: {e}")
         import traceback
+
         traceback.print_exc()
     finally:
         await client.close()
@@ -281,7 +284,7 @@ if __name__ == "__main__":
     print("2. Bedrock is configured in proxy_server_config.yaml")
     print("3. AWS credentials are set")
     print()
-    
+
     try:
         asyncio.run(main())
     except KeyboardInterrupt:

cookbook/veo_video_generation.py

@@ -21,49 +21,45 @@ from typing import Optional
 
 class VeoVideoGenerator:
     """Complete Veo video generation client using LiteLLM proxy."""
-    
-    def __init__(self, base_url: str = "http://localhost:4000/gemini/v1beta", 
-                 api_key: str = "sk-1234"):
+
+    def __init__(
+        self,
+        base_url: str = "http://localhost:4000/gemini/v1beta",
+        api_key: str = "sk-1234",
+    ):
         """
         Initialize the Veo video generator.
-        
+
         Args:
             base_url: Base URL for the LiteLLM proxy with Gemini pass-through
             api_key: API key for LiteLLM proxy authentication
         """
         self.base_url = base_url
         self.api_key = api_key
-        self.headers = {
-            "x-goog-api-key": api_key,
-            "Content-Type": "application/json"
-        }
-    
+        self.headers = {"x-goog-api-key": api_key, "Content-Type": "application/json"}
+
     def generate_video(self, prompt: str) -> Optional[str]:
         """
         Initiate video generation with Veo.
-        
+
         Args:
             prompt: Text description of the video to generate
-            
+
         Returns:
             Operation name if successful, None otherwise
         """
         print(f"🎬 Generating video with prompt: '{prompt}'")
-        
+
         url = f"{self.base_url}/models/veo-3.0-generate-preview:predictLongRunning"
-        payload = {
-            "instances": [{
-                "prompt": prompt
-            }]
-        }
-        
+        payload = {"instances": [{"prompt": prompt}]}
+
         try:
             response = requests.post(url, headers=self.headers, json=payload)
             response.raise_for_status()
-            
+
             data = response.json()
             operation_name = data.get("name")
-            
+
             if operation_name:
                 print(f"✅ Video generation started: {operation_name}")
                 return operation_name
@@ -71,58 +67,64 @@ class VeoVideoGenerator:
                 print("❌ No operation name returned")
                 print(f"Response: {json.dumps(data, indent=2)}")
                 return None
-                
+
         except requests.RequestException as e:
             print(f"❌ Failed to start video generation: {e}")
-            if hasattr(e, 'response') and e.response is not None:
+            if hasattr(e, "response") and e.response is not None:
                 try:
                     error_data = e.response.json()
                     print(f"Error details: {json.dumps(error_data, indent=2)}")
                 except:
                     print(f"Error response: {e.response.text}")
             return None
-    
-    def wait_for_completion(self, operation_name: str, max_wait_time: int = 600) -> Optional[str]:
+
+    def wait_for_completion(
+        self, operation_name: str, max_wait_time: int = 600
+    ) -> Optional[str]:
         """
         Poll operation status until video generation is complete.
-        
+
         Args:
             operation_name: Name of the operation to monitor
             max_wait_time: Maximum time to wait in seconds (default: 10 minutes)
-            
+
         Returns:
             Video URI if successful, None otherwise
         """
         print("⏳ Waiting for video generation to complete...")
-        
+
         operation_url = f"{self.base_url}/{operation_name}"
         start_time = time.time()
         poll_interval = 10  # Start with 10 seconds
-        
+
         while time.time() - start_time < max_wait_time:
             try:
-                print(f"🔍 Polling status... ({int(time.time() - start_time)}s elapsed)")
-                
+                print(
+                    f"🔍 Polling status... ({int(time.time() - start_time)}s elapsed)"
+                )
+
                 response = requests.get(operation_url, headers=self.headers)
                 response.raise_for_status()
-                
+
                 data = response.json()
-                
+
                 # Check for errors
                 if "error" in data:
                     print("❌ Error in video generation:")
                     print(json.dumps(data["error"], indent=2))
                     return None
-                
+
                 # Check if operation is complete
                 is_done = data.get("done", False)
-                
+
                 if is_done:
                     print("🎉 Video generation complete!")
-                    
+
                     try:
                         # Extract video URI from nested response
-                        video_uri = data["response"]["generateVideoResponse"]["generatedSamples"][0]["video"]["uri"]
+                        video_uri = data["response"]["generateVideoResponse"][
+                            "generatedSamples"
+                        ][0]["video"]["uri"]
                         print(f"📹 Video URI: {video_uri}")
                         return video_uri
                     except KeyError as e:
@@ -130,64 +132,68 @@ class VeoVideoGenerator:
                         print("Full response:")
                         print(json.dumps(data, indent=2))
                         return None
-                
+
                 # Wait before next poll, with exponential backoff
                 time.sleep(poll_interval)
                 poll_interval = min(poll_interval * 1.2, 30)  # Cap at 30 seconds
-                
+
             except requests.RequestException as e:
                 print(f"❌ Error polling operation status: {e}")
                 time.sleep(poll_interval)
-        
+
         print(f"⏰ Timeout after {max_wait_time} seconds")
         return None
-    
-    def download_video(self, video_uri: str, output_filename: str = "generated_video.mp4") -> bool:
+
+    def download_video(
+        self, video_uri: str, output_filename: str = "generated_video.mp4"
+    ) -> bool:
         """
         Download the generated video file.
-        
+
         Args:
             video_uri: URI of the video to download (from Google's response)
             output_filename: Local filename to save the video
-            
+
         Returns:
             True if download successful, False otherwise
         """
         print(f"⬇️  Downloading video...")
         print(f"Original URI: {video_uri}")
-        
+
         # Convert Google URI to LiteLLM proxy URI
         # Example: files/abc123 -> /gemini/v1beta/files/abc123:download?alt=media
         if video_uri.startswith("files/"):
             download_path = f"{video_uri}:download?alt=media"
         else:
             download_path = video_uri
-            
+
         litellm_download_url = f"{self.base_url}/{download_path}"
         print(f"Download URL: {litellm_download_url}")
-        
+
         try:
             # Download with streaming and redirect handling
             response = requests.get(
-                litellm_download_url, 
-                headers=self.headers, 
+                litellm_download_url,
+                headers=self.headers,
                 stream=True,
-                allow_redirects=True  # Handle redirects automatically
+                allow_redirects=True,  # Handle redirects automatically
             )
             response.raise_for_status()
-            
+
             # Save video file
-            with open(output_filename, 'wb') as f:
+            with open(output_filename, "wb") as f:
                 downloaded_size = 0
                 for chunk in response.iter_content(chunk_size=8192):
                     if chunk:
                         f.write(chunk)
                         downloaded_size += len(chunk)
-                        
+
                         # Progress indicator for large files
                         if downloaded_size % (1024 * 1024) == 0:  # Every MB
-                            print(f"📦 Downloaded {downloaded_size / (1024*1024):.1f} MB...")
-            
+                            print(
+                                f"📦 Downloaded {downloaded_size / (1024*1024):.1f} MB..."
+                            )
+
             # Verify file was created and has content
             if os.path.exists(output_filename):
                 file_size = os.path.getsize(output_filename)
@@ -203,48 +209,52 @@ class VeoVideoGenerator:
             else:
                 print("❌ File was not created")
                 return False
-                
+
         except requests.RequestException as e:
             print(f"❌ Download failed: {e}")
-            if hasattr(e, 'response') and e.response is not None:
+            if hasattr(e, "response") and e.response is not None:
                 print(f"Status code: {e.response.status_code}")
                 print(f"Response headers: {dict(e.response.headers)}")
             return False
-    
+
     def generate_and_download(self, prompt: str, output_filename: str = None) -> bool:
         """
         Complete workflow: generate video and download it.
-        
+
         Args:
             prompt: Text description for video generation
             output_filename: Output filename (auto-generated if None)
-            
+
         Returns:
             True if successful, False otherwise
         """
         # Auto-generate filename if not provided
         if output_filename is None:
             timestamp = int(time.time())
-            safe_prompt = "".join(c for c in prompt[:30] if c.isalnum() or c in (' ', '-', '_')).rstrip()
-            output_filename = f"veo_video_{safe_prompt.replace(' ', '_')}_{timestamp}.mp4"
-        
+            safe_prompt = "".join(
+                c for c in prompt[:30] if c.isalnum() or c in (" ", "-", "_")
+            ).rstrip()
+            output_filename = (
+                f"veo_video_{safe_prompt.replace(' ', '_')}_{timestamp}.mp4"
+            )
+
         print("=" * 60)
         print("🎬 VEO VIDEO GENERATION WORKFLOW")
         print("=" * 60)
-        
+
         # Step 1: Generate video
         operation_name = self.generate_video(prompt)
         if not operation_name:
             return False
-        
+
         # Step 2: Wait for completion
         video_uri = self.wait_for_completion(operation_name)
         if not video_uri:
             return False
-        
+
         # Step 3: Download video
         success = self.download_video(video_uri, output_filename)
-        
+
         if success:
             print("=" * 60)
             print("🎉 SUCCESS! Video generation complete!")
@@ -254,51 +264,51 @@ class VeoVideoGenerator:
             print("=" * 60)
             print("❌ FAILED! Video generation or download failed")
             print("=" * 60)
-        
+
         return success
 
 
 def main():
     """
     Example usage of the VeoVideoGenerator.
-    
+
     Configure these environment variables:
     - LITELLM_BASE_URL: Your LiteLLM proxy URL (default: http://localhost:4000/gemini/v1beta)
     - LITELLM_API_KEY: Your LiteLLM API key (default: sk-1234)
     """
-    
+
     # Configuration from environment or defaults
     base_url = os.getenv("LITELLM_BASE_URL", "http://localhost:4000/gemini/v1beta")
     api_key = os.getenv("LITELLM_API_KEY", "sk-1234")
-    
+
     print("🚀 Starting Veo Video Generation Example")
     print(f"📡 Using LiteLLM proxy at: {base_url}")
-    
+
     # Initialize generator
     generator = VeoVideoGenerator(base_url=base_url, api_key=api_key)
-    
+
     # Example prompts - try different ones!
     example_prompts = [
         "A cat playing with a ball of yarn in a sunny garden",
         "Ocean waves crashing against rocky cliffs at sunset",
         "A bustling city street with people walking and cars passing by",
-        "A peaceful forest with sunlight filtering through the trees"
+        "A peaceful forest with sunlight filtering through the trees",
     ]
-    
+
     # Use first example or get from user
     prompt = example_prompts[0]
     print(f"🎬 Using prompt: '{prompt}'")
-    
+
     # Generate and download video
     success = generator.generate_and_download(prompt)
-    
+
     if success:
         print("\n✅ Example completed successfully!")
         print("💡 Try modifying the prompt in the script for different videos!")
     else:
         print("\n❌ Example failed!")
         print("🔧 Check your LiteLLM proxy configuration and Google AI Studio API key")
-        
+
         # Troubleshooting tips
         print("\n🔍 Troubleshooting:")
         print("1. Ensure LiteLLM proxy is running with Google AI Studio pass-through")

docker/Dockerfile.alpine

@@ -3,55 +3,66 @@ ARG LITELLM_BUILD_IMAGE=python:3.11-alpine@sha256:f07e2ace46f560f09a6eeec7b4913b
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=python:3.11-alpine@sha256:f07e2ace46f560f09a6eeec7b4913b80ee99546e749ef82342a419a326620856
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+
+FROM $UV_IMAGE AS uvbin
 
-# Builder stage
 FROM $LITELLM_BUILD_IMAGE AS builder
 
-# Set the working directory to /app
 WORKDIR /app
 
-# Install build dependencies
-RUN apk add --no-cache gcc python3-dev musl-dev
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
 
-RUN pip install --upgrade pip==26.0.1 && \
-    pip install build==1.4.2
+RUN apk add --no-cache gcc python3-dev musl-dev nodejs npm libsndfile
 
-# Copy the current directory contents into the container at /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
+
+# Copy dependency metadata first for layer caching
+COPY pyproject.toml uv.lock ./
+COPY enterprise/pyproject.toml enterprise/
+COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
+
+# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
+RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
+
+# Copy full source tree
 COPY . .
 
-# Build the package
-RUN rm -rf dist/* && python -m build
+# Install project and workspace packages (fast - deps already cached)
+RUN uv sync --frozen --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
 
-# There should be only one wheel file now, assume the build only creates one
-RUN ls -1 dist/*.whl | head -1
+RUN prisma generate --schema=./schema.prisma
 
-# Install the package
-RUN pip install dist/*.whl
+RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
 
-# install dependencies as wheels
-RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
-
-# Runtime stage
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
-# Update dependencies and clean up, install libsndfile for audio processing
-RUN apk upgrade --no-cache && apk add --no-cache libsndfile
+RUN apk upgrade --no-cache && apk add --no-cache libsndfile nodejs npm
 
 WORKDIR /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Copy the built wheel from the builder stage to the runtime stage; assumes only one wheel file is present
-COPY --from=builder /app/dist/*.whl .
-COPY --from=builder /wheels/ /wheels/
-
-# Install the built wheel using pip; again using a wildcard if it's the only file
-RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ --no-deps && rm -f *.whl && rm -rf /wheels
-
-# Convert Windows line endings to Unix for entrypoint scripts
-RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh
-RUN sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
+COPY --from=builder /app /app
 
 EXPOSE 4000/tcp
 
-# Set your entrypoint and command
 ENTRYPOINT ["docker/prod_entrypoint.sh"]
 CMD ["--port", "4000"]

docker/Dockerfile.database

@@ -3,53 +3,72 @@ ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
-# Builder stage
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+
+FROM $UV_IMAGE AS uvbin
+
 FROM $LITELLM_BUILD_IMAGE AS builder
 
-# Set the working directory to /app
 WORKDIR /app
-
 USER root
 
-# Install build dependencies
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
+
 RUN apk add --no-cache \
     bash \
     gcc \
-    py3-pip \
     python3 \
     python3-dev \
     openssl \
-    openssl-dev
+    openssl-dev \
+    nodejs \
+    npm \
+    libsndfile
 
-RUN python -m pip install build==1.4.2
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Copy the current directory contents into the container at /app
+# Copy dependency metadata first for layer caching
+COPY pyproject.toml uv.lock ./
+COPY enterprise/pyproject.toml enterprise/
+COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
+
+# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
+RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
+
+# Copy full source tree
 COPY . .
 
-# Build Admin UI
-# Convert Windows line endings to Unix and make executable
+# Build Admin UI before final sync
 RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
 
-# Build the package
-RUN rm -rf dist/* && python -m build
+# Install project and workspace packages (fast - deps already cached)
+RUN uv sync --frozen --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
 
-# There should be only one wheel file now, assume the build only creates one
-RUN ls -1 dist/*.whl | head -1
+RUN prisma generate --schema=./schema.prisma
 
-# Install the package
-RUN pip install dist/*.whl
+RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
 
-# install dependencies as wheels
-RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
-
-# Runtime stage
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
-# Ensure runtime stage runs as root
 USER root
 
-# Install runtime dependencies
-RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile && \
+RUN apk add --no-cache bash openssl tzdata nodejs npm python3 libsndfile supervisor && \
     npm install -g npm@11.12.1 tar@7.5.11 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
     GLOBAL="$(npm root -g)" && \
     find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
@@ -73,66 +92,18 @@ RUN apk add --no-cache bash openssl tzdata nodejs npm python3 py3-pip libsndfile
     { apk del --no-cache npm 2>/dev/null || true; }
 
 WORKDIR /app
-# Copy the current directory contents into the container at /app
-COPY . .
-RUN ls -la /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Copy the built wheel from the builder stage to the runtime stage; assumes only one wheel file is present
-COPY --from=builder /app/dist/*.whl .
-COPY --from=builder /wheels/ /wheels/
+COPY --from=builder /app /app
 
-# Install the built wheel using pip; again using a wildcard if it's the only file
-RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ --no-deps && rm -f *.whl && rm -rf /wheels
+RUN find /app/.venv -type f -path "*/tornado/test/*" -delete && \
+    find /app/.venv -type d -path "*/tornado/test" -delete
 
-# SECURITY FIX: nodejs-wheel-binaries (pip package used by Prisma) bundles a complete
-# npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
-# Patch every copy of tar, glob, and brace-expansion inside that tree.
-RUN GLOBAL="$(npm root -g)" && \
-    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
-    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-    done && \
-    find /usr/lib -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-    done && \
-    find /usr/lib -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-    done && \
-    find /usr/lib -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
-    done && \
-    find /usr/lib -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
-    done
-
-# Install semantic_router and aurelio-sdk using script
-# Convert Windows line endings to Unix and make executable
-RUN sed -i 's/\r$//' docker/install_auto_router.sh && chmod +x docker/install_auto_router.sh && ./docker/install_auto_router.sh
-
-# ensure pyjwt is used, not jwt
-RUN pip uninstall jwt -y
-RUN pip uninstall PyJWT -y
-RUN pip install PyJWT==2.12.0 --no-cache-dir
-
-# Build Admin UI (runtime stage)
-# Convert Windows line endings to Unix and make executable
-RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
-
-# Generate prisma client
-RUN prisma generate
-# Convert Windows line endings to Unix for entrypoint scripts
-RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh
-RUN sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
 EXPOSE 4000/tcp
 
-RUN apk add --no-cache supervisor
 COPY docker/supervisord.conf /etc/supervisord.conf
 
-# # Set your entrypoint and command
-
-
 ENTRYPOINT ["docker/prod_entrypoint.sh"]
-
-# Append "--detailed_debug" to the end of CMD to view detailed debug logs 
-# CMD ["--port", "4000", "--detailed_debug"]
 CMD ["--port", "4000"]

docker/Dockerfile.dev

@@ -3,60 +3,70 @@ ARG LITELLM_BUILD_IMAGE=python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973a
 
 # Runtime image
 ARG LITELLM_RUNTIME_IMAGE=python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973afcbd606dbf021a589cab77d6b00b579d
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+
+FROM $UV_IMAGE AS uvbin
 
-# Builder stage
 FROM $LITELLM_BUILD_IMAGE AS builder
 
-# Set the working directory to /app
 WORKDIR /app
-
 USER root
 
-# Install build dependencies in one layer
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
+
 RUN apt-get update && apt-get install -y --no-install-recommends \
     gcc \
     g++ \
     python3-dev \
     libssl-dev \
     pkg-config \
-    && rm -rf /var/lib/apt/lists/* \
-    && pip install --upgrade pip==26.0.1 build==1.4.2
+    nodejs \
+    npm \
+    && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better layer caching
-COPY requirements.txt .
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Install Python dependencies with cache mount for faster rebuilds
-RUN --mount=type=cache,target=/root/.cache/pip \
-    pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
+# Copy dependency metadata first for layer caching
+COPY pyproject.toml uv.lock ./
+COPY enterprise/pyproject.toml enterprise/
+COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
 
-# Fix JWT dependency conflicts early
-RUN pip uninstall jwt -y || true && \
-    pip uninstall PyJWT -y || true && \
-    pip install PyJWT==2.12.0 --no-cache-dir
+# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
+RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python
 
-# Copy only necessary files for build
-COPY pyproject.toml README.md schema.prisma poetry.lock ./
-COPY litellm/ ./litellm/
-COPY enterprise/ ./enterprise/
-COPY docker/ ./docker/
+# Copy full source tree
+COPY . .
 
-# Build Admin UI once
-# Convert Windows line endings to Unix and make executable
+# Build Admin UI before final sync
 RUN sed -i 's/\r$//' docker/build_admin_ui.sh && chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
 
-# Build the package
-RUN rm -rf dist/* && python -m build
+# Install project and workspace packages (fast - deps already cached)
+RUN uv sync --frozen --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python
 
-# Install the built package
-RUN pip install dist/*.whl
+RUN prisma generate --schema=./schema.prisma
+
+RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
 
-# Runtime stage
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
-# Ensure runtime stage runs as root
 USER root
 
-# Install only runtime dependencies
 RUN apt-get update && apt-get upgrade -y \
         libxml2 \
         libexpat1 \
@@ -72,9 +82,9 @@ RUN apt-get update && apt-get upgrade -y \
         libc6 \
     && apt-get install -y --no-install-recommends \
         libssl3 \
-    libatomic1 \
-    nodejs \
-    npm \
+        libatomic1 \
+        nodejs \
+        npm \
     && rm -rf /var/lib/apt/lists/* \
     && npm install -g npm@11.12.1 tar@7.5.11 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 \
     && GLOBAL="$(npm root -g)" \
@@ -99,53 +109,13 @@ RUN apt-get update && apt-get upgrade -y \
     && apt-get purge -y npm
 
 WORKDIR /app
+ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    XDG_CACHE_HOME=/app/.cache \
+    PATH="/app/.venv/bin:${PATH}"
 
-# Copy only necessary runtime files
-COPY docker/entrypoint.sh docker/prod_entrypoint.sh ./docker/
-COPY litellm/ ./litellm/
-COPY pyproject.toml README.md schema.prisma poetry.lock ./
-
-# Copy pre-built wheels and install everything at once
-COPY --from=builder /wheels/ /wheels/
-COPY --from=builder /app/dist/*.whl .
-
-# Install all dependencies in one step with no-cache for smaller image
-RUN pip install --no-cache-dir *.whl /wheels/* --no-index --find-links=/wheels/ --no-deps && \
-    rm -f *.whl && \
-    rm -rf /wheels
-
-# SECURITY FIX: nodejs-wheel-binaries (pip package used by Prisma) bundles a complete
-# npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
-# Patch every copy of tar, glob, and brace-expansion inside that tree.
-RUN GLOBAL="$(npm root -g)" && \
-    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
-    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-    done && \
-    find /usr/lib -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-    done && \
-    find /usr/lib -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-    done && \
-    find /usr/lib -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
-    done && \
-    find /usr/lib -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
-    done
-
-# Generate prisma client and set permissions
-# Convert Windows line endings to Unix for entrypoint scripts
-RUN prisma generate && \
-    sed -i 's/\r$//' docker/entrypoint.sh && \
-    sed -i 's/\r$//' docker/prod_entrypoint.sh && \
-    chmod +x docker/entrypoint.sh && \
-    chmod +x docker/prod_entrypoint.sh
+COPY --from=builder /app /app
 
 EXPOSE 4000/tcp
 
 ENTRYPOINT ["docker/prod_entrypoint.sh"]
-
-# Append "--detailed_debug" to the end of CMD to view detailed debug logs 
-CMD ["--port", "4000"]
+CMD ["--port", "4000"]

docker/Dockerfile.health_check

@@ -1,16 +1,22 @@
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+FROM $UV_IMAGE AS uvbin
+
 FROM python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973afcbd606dbf021a589cab77d6b00b579d
 
 WORKDIR /app
 
-# Copy health check script and requirements
+# Copy the uv binary and the health check script.
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY pyproject.toml uv.lock /app/
 COPY scripts/health_check/health_check_client.py /app/health_check_client.py
-COPY scripts/health_check/health_check_requirements.txt /app/requirements.txt
 
-# Install dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Make script executable
-RUN chmod +x /app/health_check_client.py
+# Resolve and install the health-check dependencies from the project lockfile
+# so the runtime image stays self-contained and reproducible.
+RUN uv export --frozen --no-default-groups --only-group healthcheck --no-emit-project --no-hashes --output-file /tmp/health-check-requirements.txt \
+  && uv pip install --system -r /tmp/health-check-requirements.txt \
+  && rm /tmp/health-check-requirements.txt \
+  && rm /app/pyproject.toml /app/uv.lock \
+  && chmod +x /app/health_check_client.py
 
 # Run as non-root user
 RUN groupadd --gid 1000 appuser && useradd --uid 1000 --gid 1000 --no-create-home appuser

docker/Dockerfile.non_root

@@ -2,51 +2,84 @@
 ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
 ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
 ARG PROXY_EXTRAS_SOURCE=published
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+
+FROM $UV_IMAGE AS uvbin
 
-# -----------------
-# Builder Stage
-# -----------------
 FROM $LITELLM_BUILD_IMAGE AS builder
 ARG PROXY_EXTRAS_SOURCE
 WORKDIR /app
 USER root
 
-# Install build dependencies with retry logic (includes node for UI build)
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
+
 RUN for i in 1 2 3; do \
     apk add --no-cache \
-    python3 \
-    python3-dev \
-    py3-pip \
-    clang \
-    llvm \
-    lld \
-    gcc \
-    linux-headers \
-    build-base \
-    bash \
-    nodejs \
-    npm && break || sleep 5; \
-    done \
-  && pip install --no-cache-dir --upgrade pip==26.0.1 build==1.4.2
+      python3 \
+      python3-dev \
+      clang \
+      llvm \
+      lld \
+      gcc \
+      linux-headers \
+      build-base \
+      bash \
+      coreutils \
+      curl \
+      openssl \
+      openssl-dev \
+      nodejs \
+      npm \
+      libsndfile && break || sleep 5; \
+    done
 
-# Cache Python dependencies
-COPY requirements.txt .
-RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt \
-  && pip wheel --no-cache-dir --wheel-dir=/wheels/ "semantic_router==0.1.11" "aurelio-sdk==0.0.19" "PyJWT==2.12.0"
+ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    NVM_DIR=/root/.nvm \
+    PATH="/root/.nvm/versions/node/v20.20.2/bin:/app/.venv/bin:${PATH}" \
+    LITELLM_NON_ROOT=true \
+    PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+    PRISMA_CLI_BINARY_TARGETS="debian-openssl-3.0.x" \
+    XDG_CACHE_HOME=/app/.cache
 
-# Copy source after dependency layers
+# Copy dependency metadata first for layer caching
+COPY pyproject.toml uv.lock ./
+COPY enterprise/pyproject.toml enterprise/
+COPY litellm-proxy-extras/pyproject.toml litellm-proxy-extras/
+
+# Install third-party dependencies (cached unless pyproject.toml/uv.lock change)
+RUN uv sync --frozen --no-install-project --no-install-workspace --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python3
+
+# Copy full source tree
 COPY . .
 
 # Set non-root flag for build time consistency
 ENV LITELLM_NON_ROOT=true
 
-# Build Admin UI using the upstream command order while keeping a single RUN layer
+# Build Admin UI once and stage the static output for the runtime image.
 # NOTE: .npmrc files (which may set ignore-scripts=true and min-release-age=3d)
 # are temporarily renamed during npm install/ci so they don't block lifecycle
 # scripts needed by the build. This is safe because npm ci installs from
 # package-lock.json with pinned versions + integrity hashes.
-RUN mkdir -p /var/lib/litellm/ui && \
+RUN mkdir -p /var/lib/litellm/ui /var/lib/litellm/assets && \
     ([ -f /app/.npmrc ] && mv /app/.npmrc /app/.npmrc.bak || true) && \
+    NVM_VERSION="v0.40.4" && \
+    NVM_CHECKSUM="4b7412c49960c7d31e8df72da90c1fb5b8cccb419ac99537b737028d497aba4f" && \
+    NODE_VERSION="v20.20.2" && \
+    NVM_SCRIPT="/tmp/install-nvm.sh" && \
+    curl -fsSL "https://raw.githubusercontent.com/nvm-sh/nvm/${NVM_VERSION}/install.sh" -o "$NVM_SCRIPT" && \
+    echo "${NVM_CHECKSUM}  ${NVM_SCRIPT}" | sha256sum -c - && \
+    bash "$NVM_SCRIPT" && \
+    export NVM_DIR="$HOME/.nvm" && \
+    . "$NVM_DIR/nvm.sh" && \
+    nvm install "${NODE_VERSION}" && \
+    nvm use "${NODE_VERSION}" && \
     npm install -g npm@11.12.1 && \
     npm install -g node-gyp@12.2.0 && \
     ln -sf "$(npm root -g)/node-gyp" "$(npm root -g)/npm/node_modules/node-gyp" && \
@@ -56,12 +89,11 @@ RUN mkdir -p /var/lib/litellm/ui && \
       cp /app/enterprise/enterprise_ui/enterprise_colors.json ./ui_colors.json; \
     fi && \
     ([ -f .npmrc ] && mv .npmrc .npmrc.bak || true) && \
-    npm ci && \
+    npm ci --no-audit --no-fund && \
     ([ -f .npmrc.bak ] && mv .npmrc.bak .npmrc || true) && \
     ([ -f /app/.npmrc.bak ] && mv /app/.npmrc.bak /app/.npmrc || true) && \
     npm run build && \
     cp -r /app/ui/litellm-dashboard/out/* /var/lib/litellm/ui/ && \
-    mkdir -p /var/lib/litellm/assets && \
     cp /app/litellm/proxy/logo.jpg /var/lib/litellm/assets/logo.jpg && \
     ( cd /var/lib/litellm/ui && \
       for html_file in *.html; do \
@@ -74,175 +106,106 @@ RUN mkdir -p /var/lib/litellm/ui && \
       touch .litellm_ui_ready ) && \
     cd /app/ui/litellm-dashboard && rm -rf ./out
 
-# Build litellm wheel and place it in wheels dir (replace any PyPI wheels)
-RUN rm -rf dist/* && python -m build && \
-  rm -f /wheels/litellm-*.whl && \
-  cp dist/*.whl /wheels/
-
-# Optionally build local litellm-proxy-extras wheel
-RUN if [ "$PROXY_EXTRAS_SOURCE" = "local" ]; then \
-      cd /app/litellm-proxy-extras && rm -rf dist && python -m build && \
-      cp dist/*.whl /wheels/; \
+RUN if [ "$PROXY_EXTRAS_SOURCE" = "published" ]; then \
+      uv sync --frozen --no-default-groups --no-editable \
+        --extra proxy \
+        --extra proxy-runtime \
+        --extra extra_proxy \
+        --extra semantic-router \
+        --python python3 \
+        --no-sources-package litellm-proxy-extras; \
+    else \
+      uv sync --frozen --no-default-groups --no-editable \
+        --extra proxy \
+        --extra proxy-runtime \
+        --extra extra_proxy \
+        --extra semantic-router \
+        --python python3; \
     fi
 
-# Pre-cache Prisma binaries in the builder stage
-ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
-    PRISMA_CLI_BINARY_TARGETS="debian-openssl-3.0.x" \
-    XDG_CACHE_HOME=/app/.cache \
-    PATH="/usr/lib/python3.13/site-packages/nodejs/bin:${PATH}"
-
-RUN pip install --no-cache-dir prisma==0.11.0 nodejs-wheel-binaries==24.13.1 \
-    && mkdir -p /app/.cache/npm
-
-RUN NPM_CONFIG_CACHE=/app/.cache/npm \
-    python -c "import prisma.cli.prisma as p; p.ensure_cached()"
-
-RUN prisma generate && \
+RUN mkdir -p /app/.cache/npm && \
+    prisma generate --schema=./schema.prisma && \
     prisma --version && \
     prisma migrate diff --from-empty --to-schema-datamodel ./schema.prisma --script > /dev/null 2>&1 || true
 
-# -----------------
-# Runtime Stage
-# -----------------
+RUN sed -i 's/\r$//' docker/entrypoint.sh && chmod +x docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && chmod +x docker/prod_entrypoint.sh
+
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 ARG PROXY_EXTRAS_SOURCE
 WORKDIR /app
 USER root
 
-# Install runtime dependencies with retry
 RUN for i in 1 2 3; do \
     apk upgrade --no-cache && break || sleep 5; \
-    done \
-  && for i in 1 2 3; do \
-    apk add --no-cache python3 py3-pip bash openssl tzdata nodejs npm supervisor && break || sleep 5; \
-    done \
-  && apk upgrade --no-cache nodejs \
-  && npm install -g npm@11.12.1 tar@7.5.11 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 \
-  && GLOBAL="$(npm root -g)" \
-  && find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-     done \
-  && find "$GLOBAL/npm" -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-     done \
-  && find "$GLOBAL/npm" -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-     done \
-  && find "$GLOBAL/npm" -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
-     done \
-  && find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
-     done \
-  && find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
-        sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null \
-  && npm cache clean --force \
-  && { apk del --no-cache npm 2>/dev/null || true; }
+    done && \
+    for i in 1 2 3; do \
+      apk add --no-cache python3 bash openssl tzdata nodejs npm supervisor libsndfile && break || sleep 5; \
+    done && \
+    apk upgrade --no-cache nodejs && \
+    npm install -g npm@11.12.1 tar@7.5.11 glob@11.1.0 @isaacs/brace-expansion@5.0.1 minimatch@10.2.4 diff@8.0.3 && \
+    GLOBAL="$(npm root -g)" && \
+    find "$GLOBAL/npm" -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
+      rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
+    done && \
+    find "$GLOBAL/npm" -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
+      rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
+    done && \
+    find "$GLOBAL/npm" -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
+      rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
+    done && \
+    find "$GLOBAL/npm" -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
+      rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
+    done && \
+    find "$GLOBAL/npm" -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
+      rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
+    done && \
+    find /usr/local/lib /usr/lib -path "*/node_modules/npm/package.json" -exec \
+      sed -i 's/"tar": "\^7\.5\.[0-9]*"/"tar": "^7.5.10"/g; s/"minimatch": "\^10\.[0-9.]*"/"minimatch": "^10.2.4"/g' {} + 2>/dev/null && \
+    npm cache clean --force && \
+    { apk del --no-cache npm 2>/dev/null || true; }
 
-# Copy artifacts from builder
-COPY --from=builder /app/requirements.txt /app/requirements.txt
-COPY --from=builder /app/docker/entrypoint.sh /app/docker/prod_entrypoint.sh /app/docker/
-COPY --from=builder /app/docker/supervisord.conf /etc/supervisord.conf
-COPY --from=builder /app/schema.prisma /app/
-# Keep enterprise bridge module in runtime so `enterprise.enterprise_hooks`
-# can load and register managed enterprise hooks (e.g. managed_files).
-COPY --from=builder /app/enterprise /app/enterprise
-# Copy prisma_migration.py for Helm migrations job compatibility
-COPY --from=builder /app/litellm/proxy/prisma_migration.py /app/litellm/proxy/prisma_migration.py
-COPY --from=builder /wheels/ /wheels/
+COPY --from=builder /app /app
 COPY --from=builder /var/lib/litellm/ui /var/lib/litellm/ui
 COPY --from=builder /var/lib/litellm/assets /var/lib/litellm/assets
-COPY --from=builder /app/.cache /app/.cache
-COPY --from=builder /app/litellm-proxy-extras /app/litellm-proxy-extras
-COPY --from=builder \
-  /usr/lib/python3.13/site-packages/nodejs* \
-  /usr/lib/python3.13/site-packages/prisma* \
-  /usr/lib/python3.13/site-packages/tomlkit* \
-  /usr/lib/python3.13/site-packages/nodeenv* \
-  /usr/lib/python3.13/site-packages/
-COPY --from=builder /usr/bin/prisma /usr/bin/prisma
+COPY --from=builder /app/docker/supervisord.conf /etc/supervisord.conf
 
-# Final runtime environment configuration
-ENV PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
+ENV PATH="/app/.venv/bin:${PATH}" \
+    PRISMA_BINARY_CACHE_DIR=/app/.cache/prisma-python/binaries \
     PRISMA_CLI_BINARY_TARGETS="debian-openssl-3.0.x" \
     HOME=/app \
     LITELLM_NON_ROOT=true \
-    XDG_CACHE_HOME=/app/.cache
-
-# Install packages from wheels and optional extras without network
-RUN pip install --no-index --find-links=/wheels/ -r requirements.txt && \
-    pip install --no-index --find-links=/wheels/ /wheels/litellm-*-py3-none-any.whl && \
-    pip install --no-index --find-links=/wheels/ --no-deps semantic_router==0.1.11 && \
-    pip install --no-index --find-links=/wheels/ aurelio-sdk==0.0.19 && \
-    if [ "$PROXY_EXTRAS_SOURCE" = "local" ]; then \
-      if ls /wheels/litellm_proxy_extras-*.whl >/dev/null 2>&1; then \
-        pip install --no-index --find-links=/wheels/ /wheels/litellm_proxy_extras-*.whl; \
-      else \
-        echo "litellm_proxy_extras wheel not found; skipping local install"; \
-      fi; \
-    fi
-
-# SECURITY FIX: nodejs-wheel-binaries (pip package used by Prisma) bundles a complete
-# npm with old vulnerable deps at /usr/lib/python3.*/site-packages/nodejs_wheel/.
-# Patch every copy of tar, glob, and brace-expansion inside that tree.
-RUN GLOBAL="$(npm root -g)" && \
-    [ -n "$GLOBAL" ] || { echo "ERROR: npm root -g returned empty; aborting"; exit 1; } && \
-    find /usr/lib -type d -name "tar" -path "*/node_modules/tar" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-    done && \
-    find /usr/lib -type d -name "glob" -path "*/node_modules/glob" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-    done && \
-    find /usr/lib -type d -name "brace-expansion" -path "*/node_modules/@isaacs/brace-expansion" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-    done && \
-    find /usr/lib -type d -name "minimatch" -path "*/node_modules/minimatch" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/minimatch" "$d"; \
-    done && \
-    find /usr/lib -type d -name "diff" -path "*/node_modules/diff" | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/diff" "$d"; \
-    done
-
-# Permissions, cleanup, and Prisma prep
-# Convert Windows line endings to Unix for entrypoint scripts
-RUN sed -i 's/\r$//' docker/entrypoint.sh && \
-    sed -i 's/\r$//' docker/prod_entrypoint.sh && \
-    chmod +x docker/entrypoint.sh docker/prod_entrypoint.sh && \
-    mkdir -p /nonexistent /.npm /var/lib/litellm/assets /var/lib/litellm/ui && \
-    chown -R nobody:nogroup /app /var/lib/litellm/ui /var/lib/litellm/assets /nonexistent /.npm && \
-    pip uninstall jwt -y || true && \
-    pip uninstall PyJWT -y || true && \
-    pip install --no-index --find-links=/wheels/ PyJWT==2.12.0 --no-cache-dir && \
-    rm -rf /wheels && \
-    PRISMA_PATH=$(python -c "import os, prisma; print(os.path.dirname(prisma.__file__))") && \
-    chown -R nobody:nogroup $PRISMA_PATH && \
-    LITELLM_PKG_MIGRATIONS_PATH="$(python -c 'import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))' 2>/dev/null || echo '')/migrations" && \
-    [ -n "$LITELLM_PKG_MIGRATIONS_PATH" ] && chown -R nobody:nogroup $LITELLM_PKG_MIGRATIONS_PATH && \
-    LITELLM_PROXY_EXTRAS_PATH=$(python -c "import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))" 2>/dev/null || echo "") && \
-    chgrp -R 0 $PRISMA_PATH /var/lib/litellm/ui /var/lib/litellm/assets && \
-    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chgrp -R 0 $LITELLM_PROXY_EXTRAS_PATH || true && \
-    chmod -R g=u $PRISMA_PATH /var/lib/litellm/ui /var/lib/litellm/assets && \
-    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g=u $LITELLM_PROXY_EXTRAS_PATH || true && \
-    chmod -R g+w $PRISMA_PATH /var/lib/litellm/ui /var/lib/litellm/assets && \
-    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g+w $LITELLM_PROXY_EXTRAS_PATH || true && \
-    chmod -R g+rX $PRISMA_PATH && \
-    chmod -R g+rX /app/.cache && \
-    mkdir -p /tmp/.npm /nonexistent /.npm
-
-# Switch to non-root user for runtime
-USER nobody
-
-# Generate Prisma client as nobody user to ensure correct file ownership
-RUN prisma generate
-
-# Prisma runtime knobs for offline containers
-ENV PRISMA_SKIP_POSTINSTALL_GENERATE=1 \
+    XDG_CACHE_HOME=/app/.cache \
+    PRISMA_SKIP_POSTINSTALL_GENERATE=1 \
     PRISMA_HIDE_UPDATE_MESSAGE=1 \
     PRISMA_ENGINES_CHECKSUM_IGNORE_MISSING=1 \
     NPM_CONFIG_CACHE=/app/.cache/npm \
     NPM_CONFIG_PREFER_OFFLINE=true \
     PRISMA_OFFLINE_MODE=true
 
+RUN sed -i 's/\r$//' docker/entrypoint.sh && \
+    sed -i 's/\r$//' docker/prod_entrypoint.sh && \
+    chmod +x docker/entrypoint.sh docker/prod_entrypoint.sh && \
+    mkdir -p /nonexistent /.npm /var/lib/litellm/assets /var/lib/litellm/ui /tmp/.npm && \
+    chown -R nobody:nogroup /app /var/lib/litellm/ui /var/lib/litellm/assets /nonexistent /.npm /tmp/.npm && \
+    PRISMA_PATH=$(python -c "import os, prisma; print(os.path.dirname(prisma.__file__))") && \
+    chown -R nobody:nogroup "$PRISMA_PATH" && \
+    LITELLM_PKG_MIGRATIONS_PATH="$(python -c 'import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))' 2>/dev/null || echo '')/migrations" && \
+    [ -n "$LITELLM_PKG_MIGRATIONS_PATH" ] && chown -R nobody:nogroup "$LITELLM_PKG_MIGRATIONS_PATH" || true && \
+    LITELLM_PROXY_EXTRAS_PATH=$(python -c "import os, litellm_proxy_extras; print(os.path.dirname(litellm_proxy_extras.__file__))" 2>/dev/null || echo "") && \
+    chgrp -R 0 "$PRISMA_PATH" /var/lib/litellm/ui /var/lib/litellm/assets && \
+    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chgrp -R 0 "$LITELLM_PROXY_EXTRAS_PATH" || true && \
+    chmod -R g=u "$PRISMA_PATH" /var/lib/litellm/ui /var/lib/litellm/assets && \
+    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g=u "$LITELLM_PROXY_EXTRAS_PATH" || true && \
+    chmod -R g+w "$PRISMA_PATH" /var/lib/litellm/ui /var/lib/litellm/assets && \
+    [ -n "$LITELLM_PROXY_EXTRAS_PATH" ] && chmod -R g+w "$LITELLM_PROXY_EXTRAS_PATH" || true && \
+    chmod -R g+rX "$PRISMA_PATH" /var/lib/litellm/ui /var/lib/litellm/assets /app/.cache
+
+USER nobody
+
+RUN prisma generate --schema=./schema.prisma
+
 EXPOSE 4000/tcp
+
 ENTRYPOINT ["/app/docker/prod_entrypoint.sh"]
 CMD ["--port", "4000"]

docker/build_from_pip/Dockerfile.build_from_pip

@@ -1,27 +1,53 @@
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9@sha256:10902f58a1606787602f303954cea099626a4adb02acbac4c69920fe9d278f82
+FROM $UV_IMAGE AS uvbin
+
 FROM python:3.13-slim@sha256:739e7213785e88c0f702dcdc12c0973afcbd606dbf021a589cab77d6b00b579d
 
+ARG LITELLM_VERSION=1.83.0
+
 WORKDIR /app
 
-ENV HOME=/home/litellm
-ENV PATH="${HOME}/venv/bin:$PATH"
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
 
-# Install runtime dependencies needed for building native extensions
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends gcc libffi-dev && \
+    apt-get install -y --no-install-recommends gcc libffi-dev nodejs npm && \
     rm -rf /var/lib/apt/lists/*
 
-RUN python -m venv ${HOME}/venv
-RUN ${HOME}/venv/bin/pip install --no-cache-dir --upgrade pip==26.0.1
+ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    PATH="/app/.venv/bin:${PATH}"
 
-COPY docker/build_from_pip/requirements.txt .
-RUN --mount=type=cache,target=${HOME}/.cache/pip \
-    ${HOME}/venv/bin/pip install -r requirements.txt
-
-# Copy Prisma schema file
 COPY schema.prisma .
 
-# Generate prisma client
-RUN prisma generate
+# This image is specifically for validating/installing the published PyPI
+# artifact, not the checked-out source tree.
+# Keep the moved proxy-runtime packages explicit until the published PyPI
+# artifact includes that extra; newer releases will simply dedupe these.
+RUN uv venv --python python && \
+    uv pip install --python /app/.venv/bin/python \
+      "litellm[proxy,proxy-runtime]==${LITELLM_VERSION}" \
+      "google-cloud-aiplatform==1.133.0" \
+      "google-genai==1.37.0" \
+      "anthropic[vertex]==0.84.0" \
+      "grpcio==1.78.0" \
+      "prometheus-client==0.20.0" \
+      "langfuse==2.59.7" \
+      "opentelemetry-api==1.28.0" \
+      "opentelemetry-sdk==1.28.0" \
+      "opentelemetry-exporter-otlp==1.28.0" \
+      "ddtrace==2.19.0" \
+      "sentry-sdk==2.21.0" \
+      "mangum==0.17.0" \
+      "azure-ai-contentsafety==1.0.0" \
+      "azure-storage-file-datalake==12.20.0" \
+      "pypdf==6.7.5" \
+      "llm-sandbox==0.3.31" \
+      "detect-secrets==1.5.0" \
+      "prisma==0.11.0" \
+      "openai==2.24.0"
+
+RUN prisma generate --schema=./schema.prisma
 
 EXPOSE 4000/tcp
 

docker/build_from_pip/requirements.txt

@@ -1,6 +0,0 @@
-litellm[proxy]==1.83.0
-prometheus_client==0.20.0
-langfuse==2.59.7
-prisma==0.11.0
-openai==2.24.0
-ddtrace==2.19.0 # for advanced DD tracing / profiling

docker/entrypoint.sh

@@ -1,13 +1,16 @@
 #!/bin/bash
-echo $(pwd)
+set -euo pipefail
 
-# Run the Python migration script
-python3 litellm/proxy/prisma_migration.py
+REPO_ROOT="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd)"
+VENV_PYTHON="$REPO_ROOT/.venv/bin/python"
+MIGRATION_SCRIPT="$REPO_ROOT/litellm/proxy/prisma_migration.py"
 
-# Check if the Python script executed successfully
-if [ $? -eq 0 ]; then
-    echo "Migration script ran successfully!"
+if [ -x "$VENV_PYTHON" ]; then
+    "$VENV_PYTHON" "$MIGRATION_SCRIPT"
+elif command -v uv >/dev/null 2>&1; then
+    (cd "$REPO_ROOT" && uv run --no-sync python "$MIGRATION_SCRIPT")
 else
-    echo "Migration script failed!"
-    exit 1
+    python3 "$MIGRATION_SCRIPT"
 fi
+
+echo "Migration script ran successfully!"

docker/install_auto_router.sh

@@ -1,3 +1,4 @@
 #!/bin/bash
-pip install semantic_router==0.1.11 --no-deps
-pip install aurelio-sdk==0.0.19 --no-deps
+set -euo pipefail
+
+# semantic-router dependencies are installed via `uv sync`.

docs/my-website/Dockerfile

@@ -1,9 +1,32 @@
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.10.9
+
+FROM $UV_IMAGE AS uvbin
+
 FROM python:3.14.0a3-slim
 
+COPY --from=uvbin /uv /usr/local/bin/uv
+COPY --from=uvbin /uvx /usr/local/bin/uvx
 COPY . /app
 WORKDIR /app
-RUN pip install -r requirements.txt
+
+ENV UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    PATH="/app/.venv/bin:${PATH}"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    gcc \
+    python3-dev \
+    libssl-dev \
+    pkg-config \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN uv sync --frozen --no-default-groups --no-editable \
+    --extra proxy \
+    --extra proxy-runtime \
+    --extra extra_proxy \
+    --extra semantic-router \
+    --python python
 
 EXPOSE $PORT 
 
-CMD litellm --host 0.0.0.0 --port $PORT --workers 10 --config config.yaml
+CMD ["sh", "-c", "litellm --host 0.0.0.0 --port $PORT --workers 10 --config config.yaml"]

docs/my-website/blog/claude_opus_4_7/index.md

@@ -0,0 +1,366 @@
+---
+slug: claude_opus_4_7
+title: "Day 0 Support: Claude Opus 4.7"
+date: 2026-04-16T10:00:00
+authors:
+  - sameer
+  - ishaan-alt
+  - krrish
+description: "Day 0 support for Claude Opus 4.7 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock."
+tags: [anthropic, claude, opus 4.7]
+hide_table_of_contents: false
+---
+
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
+LiteLLM now supports [Claude Opus 4.7](https://www.anthropic.com/news/claude-opus-4-7) on Day 0. Use it across Anthropic, Azure, Vertex AI, and Bedrock through the LiteLLM AI Gateway.
+
+{/* truncate */}
+
+## Docker Image
+
+```bash
+docker pull ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.83.3-stable.opus-4.7
+```
+
+## Usage - Anthropic
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+  - model_name: claude-opus-4-7
+    litellm_params:
+      model: anthropic/claude-opus-4-7
+      api_key: os.environ/ANTHROPIC_API_KEY
+```
+
+**2. Start the proxy**
+
+```bash
+docker run -d \
+  -p 4000:4000 \
+  -e ANTHROPIC_API_KEY=$ANTHROPIC_API_KEY \
+  -v $(pwd)/config.yaml:/app/config.yaml \
+  ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.83.3-stable.opus-4.7 \
+  --config /app/config.yaml
+```
+
+**3. Test it!**
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "what llm are you"
+    }
+  ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+## Usage - Azure
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+  - model_name: claude-opus-4-7
+    litellm_params:
+      model: azure_ai/claude-opus-4-7
+      api_key: os.environ/AZURE_AI_API_KEY
+      api_base: os.environ/AZURE_AI_API_BASE  # https://<resource>.services.ai.azure.com
+```
+
+**2. Start the proxy**
+
+```bash
+docker run -d \
+  -p 4000:4000 \
+  -e AZURE_AI_API_KEY=$AZURE_AI_API_KEY \
+  -e AZURE_AI_API_BASE=$AZURE_AI_API_BASE \
+  -v $(pwd)/config.yaml:/app/config.yaml \
+  ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.83.3-stable.opus-4.7 \
+  --config /app/config.yaml
+```
+
+**3. Test it!**
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "what llm are you"
+    }
+  ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+## Usage - Vertex AI
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+  - model_name: claude-opus-4-7
+    litellm_params:
+      model: vertex_ai/claude-opus-4-7
+      vertex_project: os.environ/VERTEX_PROJECT
+      vertex_location: us-east5
+```
+
+**2. Start the proxy**
+
+```bash
+docker run -d \
+  -p 4000:4000 \
+  -e VERTEX_PROJECT=$VERTEX_PROJECT \
+  -e GOOGLE_APPLICATION_CREDENTIALS=/app/credentials.json \
+  -v $(pwd)/config.yaml:/app/config.yaml \
+  -v $(pwd)/credentials.json:/app/credentials.json \
+  ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.83.3-stable.opus-4.7 \
+  --config /app/config.yaml
+```
+
+**3. Test it!**
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "what llm are you"
+    }
+  ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+## Usage - Bedrock
+
+<Tabs>
+<TabItem value="proxy" label="LiteLLM Proxy">
+
+**1. Setup config.yaml**
+
+```yaml
+model_list:
+  - model_name: claude-opus-4-7
+    litellm_params:
+      model: bedrock/anthropic.claude-opus-4-7
+      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
+      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
+      aws_region_name: us-east-1
+```
+
+**2. Start the proxy**
+
+```bash
+docker run -d \
+  -p 4000:4000 \
+  -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
+  -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
+  -v $(pwd)/config.yaml:/app/config.yaml \
+  ghcr.io/berriai/litellm:litellm_stable_release_branch-v1.83.3-stable.opus-4.7 \
+  --config /app/config.yaml
+```
+
+**3. Test it!**
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "what llm are you"
+    }
+  ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+## Advanced Features
+
+### Adaptive Thinking
+
+:::note
+When using `reasoning_effort` with Claude Opus 4.7, all values (`low`, `medium`, `high`, `xhigh`) are mapped to `thinking: {type: "adaptive"}`. To use explicit thinking budgets with `type: "enabled"`, pass the native `thinking` parameter directly.
+:::
+
+<Tabs>
+<TabItem value="completions" label="/chat/completions">
+
+LiteLLM supports adaptive thinking through the `reasoning_effort` parameter:
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Solve this complex problem: What is the optimal strategy for..."
+    }
+  ],
+  "reasoning_effort": "high"
+}'
+```
+
+</TabItem>
+<TabItem value="messages" label="/v1/messages">
+
+Use the `thinking` parameter with `type: "adaptive"` to enable adaptive thinking mode:
+
+```bash
+curl --location 'http://0.0.0.0:4000/v1/messages' \
+--header 'x-api-key: sk-12345' \
+--header 'content-type: application/json' \
+--data '{
+    "model": "claude-opus-4-7",
+    "max_tokens": 16000,
+    "thinking": {
+        "type": "adaptive"
+    },
+    "messages": [
+        {
+            "role": "user",
+            "content": "Explain why the sum of two even numbers is always even."
+        }
+    ]
+}'
+```
+
+</TabItem>
+</Tabs>
+
+### Effort Levels
+
+Claude Opus 4.7 supports four effort levels: `low`, `medium`, `high` (default), and `xhigh`. These give you finer-grained control over how much reasoning the model applies to a task. Pass the effort level via the `output_config` parameter.
+
+`xhigh` is a new effort level introduced with Opus 4.7 that sits above `high`. The `max` effort level is Claude Opus 4.6 only and is not available on 4.7.
+
+<Tabs>
+<TabItem value="completions" label="/chat/completions">
+
+```bash
+curl --location 'http://0.0.0.0:4000/chat/completions' \
+--header 'Content-Type: application/json' \
+--header 'Authorization: Bearer $LITELLM_KEY' \
+--data '{
+  "model": "claude-opus-4-7",
+  "messages": [
+    {
+      "role": "user",
+      "content": "Explain quantum computing"
+    }
+  ],
+  "output_config": {
+    "effort": "xhigh"
+  }
+}'
+```
+
+**Using OpenAI SDK:**
+
+```python
+import openai
+
+client = openai.OpenAI(
+    api_key="your-litellm-key",
+    base_url="http://0.0.0.0:4000"
+)
+
+response = client.chat.completions.create(
+    model="claude-opus-4-7",
+    messages=[{"role": "user", "content": "Explain quantum computing"}],
+    extra_body={"output_config": {"effort": "xhigh"}}
+)
+```
+
+**Using LiteLLM SDK:**
+
+```python
+from litellm import completion
+
+response = completion(
+    model="anthropic/claude-opus-4-7",
+    messages=[{"role": "user", "content": "Explain quantum computing"}],
+    output_config={"effort": "xhigh"},
+)
+```
+
+You can combine `reasoning_effort` with `output_config` for even more fine-grained control over the model's behavior.
+
+</TabItem>
+<TabItem value="messages" label="/v1/messages">
+
+```bash
+curl --location 'http://0.0.0.0:4000/v1/messages' \
+--header 'x-api-key: sk-12345' \
+--header 'content-type: application/json' \
+--data '{
+    "model": "claude-opus-4-7",
+    "max_tokens": 4096,
+    "messages": [
+        {
+            "role": "user",
+            "content": "Explain quantum computing"
+        }
+    ],
+    "output_config": {
+        "effort": "xhigh"
+    }
+}'
+```
+
+</TabItem>
+</Tabs>
+
+**Effort level guide:**
+
+| Effort | When to use |
+|--------|-------------|
+| `low` | Short, fast responses — simple lookups, formatting, classification |
+| `medium` | Balanced tradeoff for everyday Q&A and light reasoning |
+| `high` (default) | Complex reasoning, code generation, analysis |
+| `xhigh` | Hardest problems — multi-step math, deep research, agentic planning |
+

docs/my-website/blog/redis_circuit_breaker/diagrams.js

@@ -0,0 +1,159 @@
+import React from 'react';
+
+const s = {
+  fig: {margin: '2.5rem 0', fontFamily: 'inherit'},
+  box: {borderRadius: 12, border: '1px solid #e5e7eb', background: '#fff', padding: '2rem 2.5rem'},
+  label: {fontSize: 11, fontWeight: 700, textTransform: 'uppercase', letterSpacing: '0.12em', color: '#9ca3af', textAlign: 'center', marginBottom: '1.5rem'},
+  caption: {textAlign: 'center', fontSize: 12, color: '#9ca3af', marginTop: 12},
+  node: (border='#d1d5db', bg='#f9fafb') => ({
+    border: `1px solid ${border}`, borderRadius: 6, padding: '8px 20px',
+    fontSize: 13, background: bg, display: 'inline-block',
+  }),
+  arrow: {display: 'flex', flexDirection: 'column', alignItems: 'center'},
+};
+
+const SmallArrow = ({color='#9ca3af'}) => (
+  <svg width="2" height="28" style={{display:'block'}}>
+    <line x1="1" y1="0" x2="1" y2="22" stroke={color} strokeWidth="1.5"/>
+    <polygon points="1,28 -2,21 4,21" fill={color}/>
+  </svg>
+);
+
+export function CascadeFailure() {
+  return (
+    <figure style={s.fig}>
+      <div style={s.box}>
+        <p style={s.label}>Without circuit breaker — cascade failure</p>
+        <div style={{display:'flex', flexDirection:'column', alignItems:'center', gap:0}}>
+          <div style={s.node()}>LiteLLM Pod (×100)</div>
+          <SmallArrow />
+          <div style={s.node()}>Rate limit / cache check</div>
+          <div style={{position:'relative', display:'flex', flexDirection:'column', alignItems:'center'}}>
+            <SmallArrow color="#f87171"/>
+            <span style={{position:'absolute', left:8, top:4, fontSize:11, color:'#f87171', whiteSpace:'nowrap'}}>hangs 30s per request</span>
+          </div>
+          <div style={s.node('#fca5a5','#fef2f2')}><span style={{color:'#b91c1c', fontWeight:600}}>Redis — degraded, timing out</span></div>
+          <SmallArrow color="#fb923c"/>
+          <div style={s.node('#fdba74','#fff7ed')}><span style={{color:'#c2410c', fontWeight:600}}>Postgres — 100× normal read load</span></div>
+          <SmallArrow />
+          <div style={{...s.node('#111827','#111827'), color:'#fff', fontWeight:600}}>Total outage — gateway down</div>
+        </div>
+      </div>
+      <figcaption style={s.caption}>Slow Redis → every auth check times out → database overwhelmed → full cascade</figcaption>
+    </figure>
+  );
+}
+
+export function CircuitBreakerStates() {
+  const circle = (border, color, label, sub) => (
+    <div style={{display:'flex', flexDirection:'column', alignItems:'center', width: 140}}>
+      <div style={{width:88, height:88, borderRadius:'50%', border:`2px solid ${border}`, background:'#fff', display:'flex', flexDirection:'column', alignItems:'center', justifyContent:'center'}}>
+        <span style={{fontSize:11, fontWeight:700, color, letterSpacing:'0.06em'}}>{label}</span>
+        <span style={{fontSize:10, color:'#9ca3af', marginTop:2}}>{sub}</span>
+      </div>
+      <p style={{fontSize:11, color:'#6b7280', textAlign:'center', marginTop:10, lineHeight:1.5}}>{'\u00a0'}</p>
+    </div>
+  );
+  const arrow = (label) => (
+    <div style={{display:'flex', flexDirection:'column', alignItems:'center', marginTop:36, marginLeft:4, marginRight:4}}>
+      <span style={{fontSize:10, color:'#6b7280', marginBottom:4}}>{label}</span>
+      <div style={{display:'flex', alignItems:'center'}}>
+        <div style={{height:1, width:48, background:'#9ca3af'}}/>
+        <svg width="8" height="8" style={{marginLeft:-1}}><polygon points="0,0 8,4 0,8" fill="#6b7280"/></svg>
+      </div>
+    </div>
+  );
+  return (
+    <figure style={s.fig}>
+      <div style={s.box}>
+        <p style={s.label}>Circuit breaker state machine</p>
+        <div style={{display:'flex', justifyContent:'center', alignItems:'flex-start'}}>
+          {circle('#1f2937','#111827','CLOSED','normal')}
+          {arrow('5 failures')}
+          {circle('#f87171','#dc2626','OPEN','fast-fail')}
+          {arrow('60s timeout')}
+          {circle('#fbbf24','#b45309','HALF-OPEN','probing')}
+        </div>
+        <div style={{display:'flex', justifyContent:'center', gap:32, marginTop:24}}>
+          <div style={{display:'flex', flexDirection:'column', alignItems:'center', gap:4}}>
+            <div style={{display:'flex', alignItems:'center', gap:4}}>
+              <svg width="8" height="8"><polygon points="8,0 0,4 8,8" fill="#16a34a"/></svg>
+              <div style={{height:1, width:100, background:'#16a34a'}}/>
+            </div>
+            <span style={{fontSize:10, color:'#16a34a'}}>probe success → CLOSED</span>
+          </div>
+          <div style={{display:'flex', flexDirection:'column', alignItems:'center', gap:4}}>
+            <div style={{display:'flex', alignItems:'center', gap:4}}>
+              <svg width="8" height="8"><polygon points="8,0 0,4 8,8" fill="#ef4444"/></svg>
+              <div style={{height:1, width:100, borderTop:'2px dashed #f87171'}}/>
+            </div>
+            <span style={{fontSize:10, color:'#ef4444'}}>probe failure → OPEN again</span>
+          </div>
+        </div>
+      </div>
+    </figure>
+  );
+}
+
+export function CircuitBreakerFlow() {
+  return (
+    <figure style={s.fig}>
+      <div style={s.box}>
+        <p style={s.label}>With circuit breaker — graceful degradation</p>
+        <div style={{display:'flex', flexDirection:'column', alignItems:'center'}}>
+          <div style={s.node()}>Incoming request</div>
+          <SmallArrow />
+          <div style={{...s.node('#111827'), border:'2px solid #111827', fontWeight:600}}>Circuit Breaker</div>
+          <div style={{display:'flex', gap:80, marginTop:20, alignItems:'flex-start'}}>
+            <div style={{display:'flex', flexDirection:'column', alignItems:'center', gap:8}}>
+              <SmallArrow />
+              <span style={{fontSize:10, fontWeight:700, textTransform:'uppercase', letterSpacing:'0.06em', color:'#6b7280', border:'1px solid #e5e7eb', borderRadius:4, padding:'2px 8px'}}>Closed</span>
+              <div style={{...s.node(), textAlign:'center', fontSize:13}}>Redis call<br/><span style={{fontSize:11, color:'#9ca3af'}}>normal latency</span></div>
+            </div>
+            <div style={{display:'flex', flexDirection:'column', alignItems:'center', gap:8}}>
+              <SmallArrow />
+              <span style={{fontSize:10, fontWeight:700, textTransform:'uppercase', letterSpacing:'0.06em', color:'#ef4444', border:'1px solid #fca5a5', borderRadius:4, padding:'2px 8px'}}>Open</span>
+              <div style={{...s.node('#fca5a5'), textAlign:'center', fontSize:13}}>Fast-fail — 0ms<br/><span style={{fontSize:11, color:'#9ca3af'}}>no network call</span></div>
+              <SmallArrow />
+              <div style={{...s.node(), textAlign:'center', fontSize:13}}>DB fallback<br/><span style={{fontSize:11, color:'#9ca3af'}}>bounded load</span></div>
+            </div>
+          </div>
+          <div style={{...s.node('#111827','#111827'), color:'#fff', fontWeight:600, marginTop:24}}>Request completes — gateway stays up</div>
+        </div>
+      </div>
+      <figcaption style={s.caption}>Redis down → circuit opens → 0ms rejection → DB absorbs bounded fallback traffic</figcaption>
+    </figure>
+  );
+}
+
+export function IncidentTimeline() {
+  const row = (color, text) => (
+    <div style={{display:'flex', alignItems:'flex-start', gap:10, marginBottom:12}}>
+      <div style={{marginTop:5, width:6, height:6, borderRadius:'50%', background:color, flexShrink:0}}/>
+      <p style={{fontSize:13, color:'#4b5563', margin:0, lineHeight:1.5}}>{text}</p>
+    </div>
+  );
+  return (
+    <figure style={s.fig}>
+      <div style={s.box}>
+        <p style={s.label}>Redis degrades — before vs. after</p>
+        <div style={{display:'grid', gridTemplateColumns:'1fr 1fr', gap:20}}>
+          <div style={{border:'1px solid #e5e7eb', borderRadius:8, padding:20}}>
+            <p style={{fontSize:10, fontWeight:700, textTransform:'uppercase', letterSpacing:'0.1em', color:'#9ca3af', marginBottom:16}}>Without circuit breaker</p>
+            {row('#f87171','All 100 pods hang for 30s on each auth check')}
+            {row('#f87171','Threadpools fill up, requests queue')}
+            {row('#f87171','100× simultaneous DB fallbacks overwhelm Postgres')}
+            {row('#f87171','Requires manual intervention to recover')}
+          </div>
+          <div style={{border:'1px solid #111827', borderRadius:8, padding:20}}>
+            <p style={{fontSize:10, fontWeight:700, textTransform:'uppercase', letterSpacing:'0.1em', color:'#9ca3af', marginBottom:16}}>With circuit breaker</p>
+            {row('#111827','Circuit opens after 5 failures — 0ms fast-fail')}
+            {row('#111827','Auth falls back to DB — bounded, not 100× load')}
+            {row('#111827','Cache miss rate temporarily elevated — gateway stays up')}
+            {row('#111827','Auto-recovers when Redis comes back — no intervention needed')}
+          </div>
+        </div>
+      </div>
+    </figure>
+  );
+}

docs/my-website/blog/redis_circuit_breaker/index.md

@@ -0,0 +1,141 @@
+---
+slug: redis-circuit-breaker
+title: "Making the AI Gateway Resilient to Redis Failures"
+date: 2026-04-11T09:00:00
+authors:
+  - ishaan
+description: "How LiteLLM's production AI Gateway handles Redis degradation at scale without cascading failures — circuit breaker pattern, 0ms fast-fail, automatic recovery."
+tags: [reliability, redis, infrastructure, engineering, ai-gateway]
+hide_table_of_contents: true
+---
+
+import { CascadeFailure, CircuitBreakerStates, CircuitBreakerFlow, IncidentTimeline } from './diagrams';
+
+*Last Updated: April 2026*
+
+Enterprise AI Gateway deployments put Redis in the hot path for nearly every request: rate limiting, cache lookups, spend tracking. When Redis is healthy, the latency contribution is single-digit milliseconds — invisible to end users. When it degrades, a production AI Gateway needs to stay up regardless.
+
+Running LiteLLM at scale across 100+ pods means designing for failure modes before they appear. The easy case is Redis going fully down: fail fast, fall through to the database, continue serving requests. The hard case — the one that takes down gateways — is a *slow* Redis: still accepting connections, still responding, but timing out after 20-30 seconds per operation.
+
+{/* truncate */}
+
+## Why slow Redis is harder than a full outage
+
+<CascadeFailure />
+
+With 100 pods each hanging 30 seconds on every auth check, threadpools fill up and requests queue. By the time Redis times out and falls through to Postgres, the database receives 100× its normal load from simultaneous fallbacks. A slow Redis becomes a database outage becomes a full gateway outage. A production-grade AI Gateway cannot allow one degraded dependency to cascade into total failure.
+
+## The fix: circuit breaker pattern
+
+The circuit breaker pattern tracks consecutive failures and cuts off the unhealthy dependency before it cascades. Instead of hanging 30 seconds on each Redis call, the circuit opens after 5 consecutive failures and fast-fails at 0ms — no network call, no wait.
+
+<CircuitBreakerStates />
+
+Three states:
+
+- **CLOSED** — normal. All Redis calls pass through.
+- **OPEN** — Redis is unhealthy. Every call fast-fails instantly. Requests continue with degraded-but-functional behavior: auth and rate limiting fall back to the database.
+- **HALF-OPEN** — after 60 seconds, one probe request tests recovery. Success closes the circuit; failure resets the timer.
+
+This is how a reliable AI Gateway handles infrastructure degradation: stay up, degrade gracefully, recover automatically.
+
+## How requests flow through the AI Gateway
+
+<CircuitBreakerFlow />
+
+When the circuit is open, the gateway does not stall. Auth checks fall back to Postgres — slower, but bounded. The database absorbs the load because it receives *some* requests via DB fallback, not *all* 100 pods simultaneously dumping their queued requests after a 30-second timeout.
+
+The difference between a resilient AI Gateway and a fragile one: controlled degradation vs. uncontrolled cascade.
+
+## The implementation
+
+```python
+class RedisCircuitBreaker:
+    def __init__(self, failure_threshold: int, recovery_timeout: int):
+        self.failure_threshold = failure_threshold  # default: 5
+        self.recovery_timeout = recovery_timeout    # default: 60s
+        self._failure_count = 0
+        self._state = self.CLOSED
+
+    def is_open(self) -> bool:
+        if self._state == self.OPEN:
+            if time.time() - self._opened_at > self.recovery_timeout:
+                self._state = self.HALF_OPEN
+                return False  # this caller is the recovery probe
+            return True       # fast-fail
+        return False
+
+    def record_failure(self):
+        self._failure_count += 1
+        self._opened_at = time.time()
+        if self._failure_count >= self.failure_threshold:
+            self._state = self.OPEN  # open the circuit
+
+    def record_success(self):
+        self._failure_count = 0
+        self._state = self.CLOSED   # Redis recovered
+```
+
+Every async Redis operation goes through a decorator that checks the breaker before touching the network. When open, it raises immediately:
+
+```python
+@_redis_circuit_breaker_guard
+async def async_get_cache(self, key: str):
+    ...
+```
+
+The decorator handles all bookkeeping — success resets nothing, failures increment the counter, exceptions trigger `record_failure()`. The caller sees a clean exception and falls through to its normal non-Redis path. No changes required in calling code.
+
+## AI Gateway resilience in production
+
+<IncidentTimeline />
+
+Redis degradation events no longer cascade in production. The observable symptom during a Redis slowdown is a temporary bump in cache miss rate — the right failure mode for a resilient AI Gateway. Auth still works. Rate limiting still works. Spend tracking still works, at slightly higher DB cost. Recovery is fully automatic when Redis comes back.
+
+```bash
+# configure via environment variables
+REDIS_CIRCUIT_BREAKER_FAILURE_THRESHOLD=5   # failures before opening
+REDIS_CIRCUIT_BREAKER_RECOVERY_TIMEOUT=60  # seconds before probe
+```
+
+The circuit breaker ships on by default in all LiteLLM versions since `v1.82.0`. No configuration needed for most deployments.
+
+## Key Takeaways
+
+- A slow Redis is more dangerous than a downed one: 30-second timeouts across 100+ pods overwhelm Postgres at 100× normal load
+- LiteLLM's AI Gateway uses a circuit breaker that fast-fails Redis calls at 0ms after 5 consecutive failures
+- Three states: CLOSED (normal), OPEN (fast-fail + DB fallback), HALF-OPEN (probe recovery)
+- Auth, rate limiting, and spend tracking continue working during Redis outages
+- Resilient, production-grade behavior — enabled by default since `v1.82.0`, no configuration required
+
+---
+
+### Frequently Asked Questions
+
+### Does the circuit breaker affect normal Redis performance?
+
+No. When Redis is healthy (circuit CLOSED), every call passes through with zero overhead. The breaker only activates after 5 consecutive failures — transparent under normal conditions.
+
+### What happens to rate limiting when the circuit is open?
+
+Rate limiting falls back to Postgres with bounded load. Limits remain enforced at slightly higher DB cost until Redis recovers and the circuit closes automatically.
+
+### How is this different from basic Redis retry logic?
+
+Retry logic still waits for each timeout (30s × retries). The circuit breaker cuts the connection immediately at 0ms after the failure threshold, preventing threadpool exhaustion across all pods simultaneously. Retries make slow-Redis worse; the circuit breaker contains it.
+
+### Is this available in LiteLLM OSS?
+
+Yes. The circuit breaker ships in LiteLLM OSS (Apache 2.0) by default since `v1.82.0`. [LiteLLM Enterprise](https://litellm.ai/enterprise) adds SSO/SCIM, air-gapped deployment, 24/7 SLA support, and advanced guardrails on top of the OSS foundation.
+
+---
+
+## Conclusion
+
+Redis resilience is one layer of what makes LiteLLM a production-grade, reliable AI Gateway at scale. The circuit breaker pattern ensures infrastructure degradation stays contained — the right failure mode is a temporary cache miss rate bump, not a full outage. This is how AI Gateway infrastructure should behave under pressure: degrade gracefully, recover automatically, keep serving traffic. For teams with strict uptime and compliance requirements, [LiteLLM Enterprise](https://litellm.ai/enterprise) provides the additional controls needed for regulated production environments.
+
+## Recommended Reading
+
+- [LiteLLM AI Gateway — full feature overview](https://docs.litellm.ai/docs/simple_proxy)
+- [Load balancing and routing across 100+ LLM providers](https://docs.litellm.ai/docs/routing)
+- [Spend tracking and budget controls](https://docs.litellm.ai/docs/proxy/cost_tracking)

docs/my-website/docs/adding_provider/generic_prompt_management_api.md

@@ -378,7 +378,7 @@ if __name__ == "__main__":
 
 1. Install dependencies:
 ```bash
-pip install fastapi uvicorn
+uv add fastapi uvicorn
 ```
 
 2. Save the code above to `prompt_server.py`

docs/my-website/docs/benchmarks.md

@@ -5,6 +5,55 @@ import Image from '@theme/IdealImage';
 
 Benchmarks for LiteLLM Gateway (Proxy Server) tested against a fake OpenAI endpoint.
 
+
+LiteLLM Gateway has **8ms P95 latency** at 1k RPS (See benchmarks [here](#4-instances))
+
+## Machine Spec used for testing
+
+Each machine deploying LiteLLM had the following specs:
+
+- 4 CPU
+- 8GB RAM
+
+## Configuration
+
+- Database: PostgreSQL
+- Redis: Not used
+
+
+### 2 Instance LiteLLM Proxy
+
+In these tests the baseline latency characteristics are measured against a fake-openai-endpoint.
+
+#### Performance Metrics
+
+| **Type** | **Name** | **Median (ms)** | **95%ile (ms)** | **99%ile (ms)** | **Average (ms)** | **Current RPS** |
+| --- | --- | --- | --- | --- | --- | --- |
+| POST | /chat/completions | 200 | 630 | 1200 | 262.46 | 1035.7 |
+| Custom | LiteLLM Overhead Duration (ms) | 12 | 29 | 43 | 14.74 | 1035.7 |
+|  | Aggregated | 100 | 430 | 930 | 138.6 | 2071.4 |
+
+<!-- <Image img={require('../img/1_instance_proxy.png')} /> -->
+
+<!-- ## **Horizontal Scaling - 10K RPS**
+
+<Image img={require('../img/instances_vs_rps.png')} /> -->
+
+
+### 4 Instances
+
+| **Type** | **Name** | **Median (ms)** | **95%ile (ms)** | **99%ile (ms)** | **Average (ms)** | **Current RPS** |
+| --- | --- | --- | --- | --- | --- | --- |
+| POST | /chat/completions | 100 | 150 | 240 | 111.73 | 1170 |
+| Custom | LiteLLM Overhead Duration (ms) | 2 | 8 | 13 | 3.32 | 1170 |
+|  | Aggregated | 77 | 130 | 180 | 57.53 | 2340 |
+
+#### Key Findings
+- Doubling from 2 to 4 LiteLLM instances halves median latency: 200 ms → 100 ms.
+- High-percentile latencies drop significantly: P95 630 ms → 150 ms, P99 1,200 ms → 240 ms.
+- Setting workers equal to CPU count gives optimal performance.
+
+
 ## Setting Up Benchmarking with Network Mock
 
 The fastest way to benchmark proxy overhead is using `network_mock` mode. This intercepts outbound requests at the httpx transport layer and returns canned responses, no need for setting up a mock provider. 
@@ -41,6 +90,8 @@ litellm --config benchmark_config.yaml --port 4000 --num_workers 8
 python scripts/benchmark_mock.py --requests 2000 --max-concurrent 200 --runs 3
 ```
 
+Get the benchmarking script [here](https://github.com/BerriAI/litellm/blob/main/scripts/benchmark_mock.py)
+
 This measures pure proxy overhead on the hot path without any network latency to a real or fake provider.
 
 ## Setting Up a Fake OpenAI Endpoint
@@ -61,38 +112,6 @@ model_list:
       api_key: "test"
 ```
 
-### 2 Instance LiteLLM Proxy
-
-In these tests the baseline latency characteristics are measured against a fake-openai-endpoint.
-
-#### Performance Metrics
-
-| **Type** | **Name** | **Median (ms)** | **95%ile (ms)** | **99%ile (ms)** | **Average (ms)** | **Current RPS** |
-| --- | --- | --- | --- | --- | --- | --- |
-| POST | /chat/completions | 200 | 630 | 1200 | 262.46 | 1035.7 |
-| Custom | LiteLLM Overhead Duration (ms) | 12 | 29 | 43 | 14.74 | 1035.7 |
-|  | Aggregated | 100 | 430 | 930 | 138.6 | 2071.4 |
-
-<!-- <Image img={require('../img/1_instance_proxy.png')} /> -->
-
-<!-- ## **Horizontal Scaling - 10K RPS**
-
-<Image img={require('../img/instances_vs_rps.png')} /> -->
-
-
-### 4 Instances
-
-| **Type** | **Name** | **Median (ms)** | **95%ile (ms)** | **99%ile (ms)** | **Average (ms)** | **Current RPS** |
-| --- | --- | --- | --- | --- | --- | --- |
-| POST | /chat/completions | 100 | 150 | 240 | 111.73 | 1170 |
-| Custom | LiteLLM Overhead Duration (ms) | 2 | 8 | 13 | 3.32 | 1170 |
-|  | Aggregated | 77 | 130 | 180 | 57.53 | 2340 |
-
-#### Key Findings
-- Doubling from 2 to 4 LiteLLM instances halves median latency: 200 ms → 100 ms.
-- High-percentile latencies drop significantly: P95 630 ms → 150 ms, P99 1,200 ms → 240 ms.
-- Setting workers equal to CPU count gives optimal performance.
-
 ## `/realtime` API Benchmarks
 
 End-to-end latency benchmarks for the `/realtime` endpoint tested against a fake realtime endpoint.
@@ -115,17 +134,6 @@ End-to-end latency benchmarks for the `/realtime` endpoint tested against a fake
 | **System** | 4 vCPUs, 8 GB RAM, 4 workers, 4 instances |
 | **Database** | PostgreSQL (Redis unused) |
 
-## Machine Spec used for testing
-
-Each machine deploying LiteLLM had the following specs:
-
-- 4 CPU
-- 8GB RAM
-
-## Configuration
-
-- Database: PostgreSQL
-- Redis: Not used
 
 ## Infrastructure Recommendations
 

docs/my-website/docs/caching/all_caches.md

@@ -23,7 +23,7 @@ import TabItem from '@theme/TabItem';
 
 Install redis
 ```shell
-pip install redis
+uv add redis
 ```
 
 For the hosted version you can setup your own Redis DB here: https://redis.io/try-free/
@@ -55,7 +55,7 @@ response2 = completion(
 For GCP Memorystore Redis with IAM authentication:
 
 ```shell
-pip install google-cloud-iam
+uv add google-cloud-iam
 ```
 
 ```python
@@ -150,7 +150,7 @@ response2 = completion(
 
 Install boto3
 ```shell
-pip install boto3
+uv add boto3
 ```
 
 Set AWS environment variables
@@ -187,7 +187,7 @@ response2 = completion(
 
 Install azure-storage-blob and azure-identity
 ```shell
-pip install azure-storage-blob azure-identity
+uv add azure-storage-blob azure-identity
 ```
 
 ```python
@@ -219,7 +219,7 @@ response2 = completion(
 
 Install redisvl client
 ```shell
-pip install redisvl==0.4.1
+uv add redisvl==0.4.1
 ```
 
 For the hosted version you can setup your own Redis DB here: https://redis.io/try-free/
@@ -366,7 +366,7 @@ response2 = completion(
 Install the disk caching extra:
 
 ```shell
-pip install "litellm[caching]"
+uv add "litellm[caching]"
 ```
 
 Then you can use the disk cache as follows.

docs/my-website/docs/completion/anthropic_advisor_tool.md

@@ -14,12 +14,48 @@ The advisor tool is in beta. Include `anthropic-beta: advisor-tool-2026-03-01` i
 
 ## Supported Providers
 
-| Provider | Chat Completions API | Messages API |
-|----------|---------------------|--------------|
-| **Anthropic API** | ✅ | ✅ |
-| **Azure Anthropic** | ❌ (coming soon) | ❌ (coming soon) |
-| **Google Cloud Vertex AI** | ❌ (coming soon) | ❌ (coming soon) |
-| **Amazon Bedrock** | ❌ (coming soon) | ❌ (coming soon) |
+| Provider | Chat Completions API | Messages API | Notes |
+|----------|---------------------|--------------|-------|
+| **Anthropic API** | ✅ | ✅ | Native — runs server-side |
+| **OpenAI / Azure OpenAI** | ✅ | ✅ | LiteLLM orchestration loop |
+| **Amazon Bedrock** | ✅ | ✅ | LiteLLM orchestration loop |
+| **Google Vertex AI** | ✅ | ✅ | LiteLLM orchestration loop |
+| **Groq / Mistral / others** | ✅ | ✅ | LiteLLM orchestration loop |
+
+## How it works (LiteLLM native orchestration)
+
+For non-Anthropic providers, LiteLLM implements the advisor loop itself. The API you call is identical — LiteLLM handles everything transparently.
+
+When a request arrives with an `advisor_20260301` tool and a non-Anthropic provider, `AdvisorOrchestrationHandler` intercepts it. It translates the advisor tool into a regular function tool the provider understands, then runs an orchestration loop:
+
+```mermaid
+flowchart TD
+    A["Your request\ntools: advisor_20260301\nmodel: e.g. openai/gpt-4.1-mini"] --> B["AdvisorOrchestrationHandler\ntranslates advisor → regular fn tool"]
+
+    B --> C["EXECUTOR CALL\nopenai / bedrock / vertex / etc."]
+
+    C --> D{"executor calls\nadvisor tool?"}
+
+    D -->|"yes — tool_use\nname=advisor"| E{"max_uses\nexceeded?"}
+
+    E -->|no| F["ADVISOR SUB-CALL\nclaude-opus-4-6\nfull transcript forwarded\nno tools"]
+
+    F --> G["Inject advice as\ntool_result into history"]
+
+    G --> C
+
+    E -->|yes| H["AdvisorMaxIterationsError"]
+
+    D -->|"no — end_turn\nor other stop reason"| I["Clean final response\nno advisor blocks in output"]
+```
+
+**What LiteLLM does for you:**
+
+- Strips `advisor_20260301` from the outgoing request — the provider only sees a standard function tool named `advisor`
+- When the executor calls it, intercepts before the result reaches you, runs the advisor sub-call, and injects the advice
+- Strips any `advisor_tool_result` / `server_tool_use` blocks from message history on re-send so non-Anthropic providers never see Anthropic-specific types
+- Wraps the final response in an SSE stream if you requested `stream=True`
+- Enforces `max_uses` as a hard cap — `AdvisorMaxIterationsError` is raised if exceeded; `max_uses=0` disables the advisor entirely
 
 ## Model Compatibility
 
@@ -305,6 +341,37 @@ response = client.beta.messages.create(
 print(response)
 ```
 
+#### Non-Anthropic Provider (LiteLLM orchestration loop)
+
+```python showLineNumbers title="Advisor Tool with OpenAI executor"
+import asyncio
+import litellm
+
+async def main():
+    # executor: openai/gpt-4.1-mini  |  advisor: claude-opus-4-6
+    # LiteLLM runs the orchestration loop automatically
+    response = await litellm.anthropic.messages.acreate(
+        model="openai/gpt-4.1-mini",
+        messages=[
+            {"role": "user", "content": "Implement a Python LRU cache with O(1) get and put."}
+        ],
+        tools=[
+            {
+                "type": "advisor_20260301",
+                "name": "advisor",
+                "model": "claude-opus-4-6",
+                "max_uses": 3,
+            }
+        ],
+        max_tokens=1024,
+        custom_llm_provider="openai",
+    )
+    # Final response is clean — no advisor tool_use blocks
+    print(response["content"][0]["text"])
+
+asyncio.run(main())
+```
+
 ---
 
 ## Response Structure

docs/my-website/docs/completion/message_sanitization.md

@@ -401,7 +401,7 @@ response = litellm.completion(
 
 3. Ensure you're using a recent version of LiteLLM:
    ```bash
-   pip install --upgrade litellm
+   uv add --upgrade-package litellm litellm
    ```
 
 ### Unexpected Dummy Tool Results

docs/my-website/docs/completion/prompt_compression.md

@@ -0,0 +1,123 @@
+# Prompt Compression (`compress()`)
+
+Use `litellm.compress()` to shrink long conversation history before calling `completion()`.
+
+The function keeps high-relevance and recent context, replaces low-relevance content with lightweight stubs, and returns a retrieval tool so the model can request full content only when needed.
+
+## Quickstart
+
+```python
+import litellm
+
+messages = [
+    {"role": "system", "content": "You are a coding assistant."},
+    {"role": "user", "content": "# auth.py\n" + "def authenticate():\n    pass\n" * 2000},
+    {"role": "user", "content": "# utils.py\n" + "def helper():\n    pass\n" * 2000},
+    {"role": "user", "content": "Fix the bug in auth.py"},
+]
+
+compressed = litellm.compress(
+    messages=messages,
+    model="gpt-4o",
+    compression_trigger=1000,
+    compression_target=500,
+)
+
+response = litellm.completion(
+    model="gpt-4o",
+    messages=compressed["messages"],
+    tools=compressed["tools"],
+)
+```
+
+## What It Returns
+
+`compress()` returns a dictionary with:
+
+- `messages`: compressed conversation messages
+- `original_tokens`: token count before compression
+- `compressed_tokens`: token count after compression
+- `compression_ratio`: fraction of tokens removed
+- `cache`: key-value mapping of stub key -> original full content
+- `tools`: retrieval tool definition (`litellm_content_retrieve`) for on-demand restoration
+
+## Parameters
+
+- `messages` (`List[dict]`, required): input conversation messages
+- `model` (`str`, required): model name used for token counting
+- `compression_trigger` (`int`, default `200000`): compress only if input token count exceeds this
+- `compression_target` (`Optional[int]`, default `70% of compression_trigger`): desired post-compression token budget
+- `embedding_model` (`Optional[str]`): if set, combines BM25 + embedding relevance scoring
+- `embedding_model_params` (`Optional[dict]`): additional kwargs passed to `litellm.embedding()`
+- `compression_cache` (`Optional[DualCache]`): optional cache used by embedding scoring
+
+## Behavior Notes
+
+- Messages below `compression_trigger` are passed through unchanged.
+- System messages, the last user message, and the last assistant message are always preserved.
+- If a relevant message does not fully fit the remaining budget, `compress()` may keep a truncated version of it.
+- Compressed-out content is never lost; it is stored in `cache` and addressable by `litellm_content_retrieve`.
+
+## Handling Retrieval Tool Calls
+
+If the model calls `litellm_content_retrieve`, look up the requested key in `compressed["cache"]` and return that value as tool output.
+
+```python
+import json
+
+tool_call = response.choices[0].message.tool_calls[0]
+args = json.loads(tool_call.function.arguments)
+full_content = compressed["cache"][args["key"]]
+```
+
+## Performance
+
+Benchmarked on [SWE-bench Lite](https://huggingface.co/datasets/princeton-nlp/SWE-bench_Lite_bm25_27K) (real GitHub issues with ~27k tokens of BM25-retrieved repo context per problem).
+
+### Claude Opus — 5 problems, trigger=10k
+
+| Metric | Baseline | Compressed | Delta |
+|---|---|---|---|
+| File overlap | 1.000 | 1.000 | +0.000 |
+| Exact file match | 100% | 100% | +0.0% |
+| Hunk overlap | 0.582 | 0.361 | -0.221 |
+| Content similarity | 0.367 | 0.373 | +0.006 |
+| Avg prompt tokens | 30,828 | 6,890 | -77.7% |
+| Avg cost/problem | $0.488 | $0.136 | **-72.0%** |
+
+**Key takeaways:**
+
+- **File-level targeting is fully preserved** — the model edits the same files with or without compression.
+- **Content similarity matches baseline** — the actual lines changed are comparable.
+- **Hunk overlap drops modestly** (-0.221) — the model targets the right files but may edit slightly different line ranges with less surrounding context.
+- **72% cost savings** with 78% token reduction.
+
+### Metrics explained
+
+| Metric | What it measures |
+|---|---|
+| **File overlap** | Fraction of gold-patch files present in the generated patch |
+| **Exact file match** | Whether the generated patch touches exactly the same set of files |
+| **Hunk overlap** | Fraction of gold hunk line ranges covered by generated hunks |
+| **Content similarity** | Jaccard similarity of changed lines (added/removed) between gold and generated patches |
+
+### Running the SWE-bench eval
+
+```bash
+# 5-problem quick check
+python tests/eval_swe_bench.py --model claude-opus-4-20250514 --problems 5
+
+# Custom trigger/target
+python tests/eval_swe_bench.py --model gpt-4o --problems 20 \
+    --compression-trigger 15000 --compression-target 10000
+
+# With embedding scoring
+python tests/eval_swe_bench.py --model gpt-4o --problems 10 \
+    --embedding-model text-embedding-3-small
+```
+
+### Running the HumanEval-style eval
+
+```bash
+python scripts/eval_compression.py --model gpt-4o --problems 5
+```

docs/my-website/docs/contributing.md

@@ -29,7 +29,7 @@ general_settings:
 Start the proxy on port 4000:
 
 ```bash
-poetry run litellm --config config.yaml --port 4000
+uv run litellm --config config.yaml --port 4000
 ```
 
 The UI comes pre-built in the repo. Access it at `http://localhost:4000/ui`

docs/my-website/docs/default_code_snippet.md

@@ -16,7 +16,7 @@ If you want to use the non-hosted version, [go here](https://docs.litellm.ai/doc
 
 
 ```
-pip install litellm
+uv add litellm
 ```
 
 <QueryParamReader/>

docs/my-website/docs/extras/contributing_code.md

@@ -41,7 +41,7 @@ git clone https://github.com/BerriAI/litellm.git
 Step 2: Install dev dependencies
 
 ```shell
-poetry install --with dev --extras proxy
+uv sync --group dev --extra proxy
 ```
 
 ### 2. Adding tests

docs/my-website/docs/index.md

@@ -9,6 +9,10 @@ import TabItem from '@theme/TabItem';
 import NavigationCards from '@site/src/components/NavigationCards';
 import Image from '@theme/IdealImage';
 
+:::note Security Update
+The Trivy supply-chain compromise has been contained :tada: . All affected packages have been deleted and current releases are free of the compromised code/component. Please refer to our [Security Townhall](/blog/security-townhall-updates) for a deeper understanding of the problem, and [CI/CD v2](/blog/ci-cd-v2-improvements) for how we're improving moving forward.
+:::
+
 <Image style={{padding: '10px', margin: '0 0 2.5rem'}} img={require('../img/hero.png')} />
 
 **LiteLLM** is an open-source library that gives you a single, unified interface to call 100+ LLMs — OpenAI, Anthropic, Vertex AI, Bedrock, and more — using the OpenAI format.
@@ -26,13 +30,13 @@ import Image from '@theme/IdealImage';
 ## Installation
 
 ```shell
-pip install litellm
+uv add litellm
 ```
 
 To run the full Proxy Server (LLM Gateway):
 
 ```shell
-pip install 'litellm[proxy]'
+uv tool install 'litellm[proxy]'
 ```
 
 ---
@@ -336,7 +340,7 @@ The proxy is a self-hosted OpenAI-compatible gateway. Any client that works with
 #### Step 1 — Start the proxy
 
 <Tabs>
-<TabItem value="pip" label="pip">
+<TabItem value="cli" label="LiteLLM CLI">
 
 ```shell
 litellm --model huggingface/bigcode/starcoder

docs/my-website/docs/integrations/letta.md

@@ -16,7 +16,7 @@ Letta allows you to build LLM agents that can:
 ## Prerequisites
 
 ```bash
-pip install letta litellm
+uv add letta litellm
 ```
 
 ## Quick Start
@@ -910,7 +910,7 @@ for model in models:
 ```
 
 ### Common SDK Issues
-- **Import errors**: Ensure `pip install litellm letta` is run
+- **Import errors**: Ensure `uv add litellm letta` is run
 - **Model format**: Use `provider/model` format (e.g., `openai/gpt-4`)
 - **API key format**: Different providers have different key formats
 - **Rate limits**: Implement exponential backoff for retries

docs/my-website/docs/langchain/langchain.md

@@ -5,7 +5,7 @@ import TabItem from '@theme/TabItem';
 
 ## Pre-Requisites
 ```shell
-!pip install litellm langchain
+!uv add litellm langchain
 ```
 ## Quick Start
 

docs/my-website/docs/learn/gateway_quickstart.md

@@ -13,7 +13,7 @@ If you need a Docker or database-first setup, use the [Docker + Database tutoria
 ## 1. Install The Gateway
 
 ```bash
-pip install 'litellm[proxy]'
+uv tool install 'litellm[proxy]'
 ```
 
 ## 2. Set One Provider Key

docs/my-website/docs/learn/sdk_quickstart.md

@@ -11,7 +11,7 @@ Use this path if you are integrating LiteLLM directly into application code.
 ## 1. Install LiteLLM
 
 ```bash
-pip install litellm==1.82.6
+uv add 'litellm==1.82.6'
 ```
 
 ## 2. Set Provider Credentials

docs/my-website/docs/load_test.md

@@ -17,7 +17,7 @@ model_list:
       api_base: https://exampleopenaiendpoint-production.up.railway.app/
 ```
 
-2. `pip install locust`
+2. `uv add locust`
 
 3. Create a file called `locustfile.py` on your local machine. Copy the contents from the litellm load test located [here](https://github.com/BerriAI/litellm/blob/main/.github/workflows/locustfile.py)
 

docs/my-website/docs/load_test_advanced.md

@@ -70,7 +70,7 @@ litellm_settings:
   callbacks: ["prometheus"] # Enterprise LiteLLM Only - use prometheus to get metrics on your load test
 ```
 
-2. `pip install locust`
+2. `uv add locust`
 
 3. Create a file called `locustfile.py` on your local machine. Copy the contents from the litellm load test located [here](https://github.com/BerriAI/litellm/blob/main/.github/workflows/locustfile.py)
 
@@ -138,7 +138,7 @@ litellm_settings:
   callbacks: ["prometheus"] # Enterprise LiteLLM Only - use prometheus to get metrics on your load test
 ```
 
-2. `pip install locust`
+2. `uv add locust`
 
 3. Create a file called `locustfile.py` on your local machine. Copy the contents from the litellm load test located [here](https://github.com/BerriAI/litellm/blob/main/.github/workflows/locustfile.py)
 

docs/my-website/docs/mcp_aws_sigv4.md

@@ -224,7 +224,7 @@ SigV4-authenticated MCP servers skip the standard health check on proxy startup.
 Install the `botocore` package:
 
 ```bash
-pip install botocore
+uv add botocore
 ```
 
 `botocore` is used for SigV4 credential handling and is required when using `aws_sigv4` auth.

docs/my-website/docs/mcp_oauth.md

@@ -205,7 +205,7 @@ sequenceDiagram
 Use [BerriAI/mock-oauth2-mcp-server](https://github.com/BerriAI/mock-oauth2-mcp-server) to test locally:
 
 ```bash title="Terminal 1 - Start mock server" showLineNumbers
-pip install fastapi uvicorn
+uv add fastapi uvicorn
 python mock_oauth2_mcp_server.py  # starts on :8765
 ```
 

docs/my-website/docs/observability/braintrust.md

@@ -9,7 +9,7 @@ import TabItem from '@theme/TabItem';
 ## Quick Start
 
 ```python
-# pip install braintrust
+# uv add braintrust
 import litellm
 import os
 

docs/my-website/docs/observability/lago.md

@@ -22,7 +22,7 @@ litellm.callbacks = ["lago"] # logs cost + usage of successful calls to lago
 <TabItem value="sdk" label="SDK">
 
 ```python
-# pip install lago 
+# uv add lago 
 import litellm
 import os
 

docs/my-website/docs/observability/langfuse_integration.md

@@ -26,9 +26,9 @@ For Langfuse v3, we recommend using the [Langfuse OTEL](./langfuse_otel_integrat
 ## Usage with LiteLLM Python SDK
 
 ### Pre-Requisites
-Ensure you have run `pip install langfuse` for this integration
+Ensure you have run `uv add langfuse` for this integration
 ```shell
-pip install langfuse==2.59.7 litellm
+uv add langfuse==2.59.7 litellm
 ```
 
 ### Quick Start
@@ -44,7 +44,7 @@ litellm.success_callback = ["langfuse"]
 litellm.failure_callback = ["langfuse"] # logs errors to langfuse
 ```
 ```python
-# pip install langfuse 
+# uv add langfuse 
 import litellm
 import os
 
@@ -335,7 +335,7 @@ Be aware that if you are continuing an existing trace, and you set `update_trace
 
 ## Troubleshooting & Errors
 ### Data not getting logged to Langfuse ? 
-- Ensure you're on the latest version of langfuse `pip install langfuse -U`. The latest version allows litellm to log JSON input/outputs to langfuse
+- Ensure you're on the latest version of langfuse `uv add langfuse -U`. The latest version allows litellm to log JSON input/outputs to langfuse
 - Follow [this checklist](https://langfuse.com/faq/all/missing-traces) if you don't see any traces in langfuse.
 
 ## Support & Talk to Founders

docs/my-website/docs/observability/langfuse_otel_integration.md

@@ -24,7 +24,7 @@ The Langfuse OpenTelemetry integration allows you to send LiteLLM traces and obs
 2. **API Keys**: Get your public and secret keys from your Langfuse project settings
 3. **Dependencies**: Install required packages:
    ```bash
-   pip install litellm opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp
+   uv add litellm opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp
    ```
 
 ## Configuration

docs/my-website/docs/observability/langsmith_integration.md

@@ -18,7 +18,7 @@ join our [discord](https://discord.gg/wuPM9dRgDw)
 
 ## Pre-Requisites
 ```shell
-pip install litellm
+uv add litellm
 ```
 
 ## Quick Start

docs/my-website/docs/observability/levo_integration.md

@@ -36,7 +36,7 @@ Send all your LLM requests and responses to Levo for monitoring and analysis usi
 **1. Install OpenTelemetry dependencies:**
 
 ```bash
-pip install opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc
+uv add opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc
 ```
 
 **2. Enable Levo callback in your LiteLLM config:**
@@ -133,7 +133,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
    ```
 
 4. **Check for initialization errors**: Look for errors in LiteLLM startup logs. Common issues:
-   - Missing OpenTelemetry packages: Install with `pip install opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc`
+   - Missing OpenTelemetry packages: Install with `uv add opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc`
    - Missing required environment variables: All four required variables must be set
    - Invalid collector URL: Ensure the URL is correct and reachable
 
@@ -150,7 +150,7 @@ curl --location 'http://0.0.0.0:4000/chat/completions' \
 - Solution: Set the `LEVOAI_COLLECTOR_URL` environment variable with your collector endpoint URL from Levo support.
 
 **Error: "No module named 'opentelemetry'"**
-- Solution: Install OpenTelemetry packages: `pip install opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc`
+- Solution: Install OpenTelemetry packages: `uv add opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp-proto-http opentelemetry-exporter-otlp-proto-grpc`
 
 ## Additional Resources
 

docs/my-website/docs/observability/literalai_integration.md

@@ -11,7 +11,7 @@ import Image from '@theme/IdealImage';
 Ensure you have the `literalai` package installed:
 
 ```shell
-pip install literalai litellm
+uv add literalai litellm
 ```
 
 ## Quick Start

docs/my-website/docs/observability/logfire_integration.md

@@ -17,11 +17,11 @@ join our [discord](https://discord.gg/wuPM9dRgDw)
 Ensure you have installed the following packages to use this integration
 
 ```shell
-pip install litellm
+uv add litellm
 
-pip install opentelemetry-api==1.25.0
-pip install opentelemetry-sdk==1.25.0
-pip install opentelemetry-exporter-otlp==1.25.0
+uv add opentelemetry-api==1.25.0
+uv add opentelemetry-sdk==1.25.0
+uv add opentelemetry-exporter-otlp==1.25.0
 ```
 
 ## Quick Start
@@ -33,7 +33,7 @@ litellm.callbacks = ["logfire"]
 ```
 
 ```python
-# pip install logfire
+# uv add logfire
 import litellm
 import os
 

docs/my-website/docs/observability/lunary_integration.md

@@ -15,7 +15,7 @@ You can reach out to us anytime by [email](mailto:hello@lunary.ai) or directly [
 ### Pre-Requisites
 
 ```shell
-pip install litellm lunary
+uv add litellm lunary
 ```
 
 ### Quick Start
@@ -124,7 +124,7 @@ my_chain("Chain input")
 ### Step1: Install dependencies and set your environment variables 
 Install the dependencies
 ```shell
-pip install litellm lunary
+uv add litellm lunary
 ```
 
 Get you Lunary public key from from https://app.lunary.ai/settings 

docs/my-website/docs/observability/mlflow.md

@@ -17,7 +17,7 @@ MLflow’s integration with LiteLLM supports advanced observability compatible w
 Install MLflow:
 
 ```shell
-pip install "litellm[mlflow]"
+uv add "litellm[mlflow]"
 ```
 
 To enable MLflow auto tracing for LiteLLM:
@@ -167,7 +167,7 @@ This approach generates a unified trace, combining your custom Python code with
 For using `mlflow` on LiteLLM Proxy Server, you need to install the `mlflow` package on your docker container.
 
 ```shell
-pip install "mlflow>=3.1.4"
+uv add "mlflow>=3.1.4"
 ```
 
 ### Configuration

docs/my-website/docs/observability/openmeter.md

@@ -28,7 +28,7 @@ litellm.callbacks = ["openmeter"] # logs cost + usage of successful calls to ope
 <TabItem value="sdk" label="SDK">
 
 ```python
-# pip install openmeter 
+# uv add openmeter 
 import litellm
 import os
 

docs/my-website/docs/observability/opentelemetry_integration.md

@@ -27,7 +27,7 @@ USE_OTEL_LITELLM_REQUEST_SPAN=true
 Install the OpenTelemetry SDK:
 
 ```
-pip install opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp
+uv add opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp
 ```
 
 Set the environment variables (different providers may require different variables):
@@ -63,7 +63,7 @@ OTEL_EXPORTER_OTLP_PROTOCOL=grpc
 OTEL_EXPORTER_OTLP_HEADERS="api-key=key,other-config-value=value"
 ```
 
-> Note: OTLP gRPC requires `grpcio`. Install via `pip install "litellm[grpc]"` (or `grpcio`).
+> Note: OTLP gRPC requires `grpcio`. Install via `uv add "litellm[grpc]"` (or `grpcio`).
 
 </TabItem>
 
@@ -75,7 +75,7 @@ OTEL_ENDPOINT="https://api.lmnr.ai:8443"
 OTEL_HEADERS="authorization=Bearer <project-api-key>"
 ```
 
-> Note: OTLP gRPC requires `grpcio`. Install via `pip install "litellm[grpc]"` (or `grpcio`).
+> Note: OTLP gRPC requires `grpcio`. Install via `uv add "litellm[grpc]"` (or `grpcio`).
 
 </TabItem>
 

docs/my-website/docs/observability/phoenix_integration.md

@@ -22,7 +22,7 @@ Use just 2 lines of code, to instantly log your responses **across all providers
 You can also use the instrumentor option instead of the callback, which you can find [here](https://docs.arize.com/phoenix/tracing/integrations-tracing/litellm).
 
 ```bash
-pip install opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp litellm[proxy]
+uv add opentelemetry-api opentelemetry-sdk opentelemetry-exporter-otlp litellm[proxy]
 ```
 ```python
 litellm.callbacks = ["arize_phoenix"]
@@ -73,7 +73,7 @@ environment_variables:
     PHOENIX_COLLECTOR_HTTP_ENDPOINT: "https://app.phoenix.arize.com/s/<space-name>/v1/traces" # OPTIONAL - For setting the HTTP endpoint
 ```
 
-> Note: If you set the gRPC endpoint, install `grpcio` via `pip install "litellm[grpc]"` (or `grpcio`).
+> Note: If you set the gRPC endpoint, install `grpcio` via `uv add "litellm[grpc]"` (or `grpcio`).
 
 2. Start the proxy
 

docs/my-website/docs/observability/qualifire_integration.md

@@ -23,7 +23,7 @@ Looking for Qualifire Guardrails? Check out the [Qualifire Guardrails Integratio
 2. Get your API key and webhook URL from the Qualifire dashboard
 
 ```bash
-pip install litellm
+uv add litellm
 ```
 
 ## Quick Start

docs/my-website/docs/observability/raw_request_response.md

@@ -12,7 +12,7 @@ See the raw request/response sent by LiteLLM in your logging provider (OTEL/Lang
 <TabItem value="sdk" label="SDK">
 
 ```python
-# pip install langfuse 
+# uv add langfuse 
 import litellm
 import os