Merge branch 'main' into matt/add-ltx-api-support

.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/pull_request_template.md

@@ -2,6 +2,10 @@
 
 <!-- e.g. "Fixes #000" -->
 
+## Linear ticket
+
+<!-- if you are an internal contributor, add the Linear ticket e.g. "Resolves LIT-1234" to magically link the Linear ticket to the GitHub PR -->
+
 ## Pre-Submission checklist
 
 **Please complete all items before asking a LiteLLM maintainer to review your PR**
@@ -32,6 +36,13 @@ If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slac
 - [ ] **Merge / cherry-pick CI run**  
        Links:
 
+## Screenshots / Proof of Fix
+
+<!-- Include screenshots, screen recordings, or log output demonstrating that your changes work as expected.
+     For bug fixes: show reproduction before the fix and passing behavior after.
+     For new features: show the feature working end-to-end.
+     For UI changes: include before/after screenshots. -->
+
 ## Type
 
 <!-- Select the type of Pull Request -->

.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

@@ -32,41 +32,39 @@ on:
         required: false
         type: boolean
         default: false
+      dist:
+        description: "pytest-xdist distribution mode (loadscope|load|worksteal|loadfile|no)"
+        required: false
+        type: string
+        default: "loadscope"
       artifact-name:
         description: "Unique name for the coverage artifact (must be unique per run)"
         required: false
         type: string
         default: "run"
-    secrets:
-      DATABASE_URL:
-        required: false
-      POSTGRES_USER:
-        required: false
-      POSTGRES_PASSWORD:
-        required: false
 
 permissions:
   contents: read
 
+# The postgres service container below is spawned per-job on localhost and
+# destroyed with the job. Nothing outside the runner can reach it. The
+# user/password/database here are not secrets — they're bootstrap values
+# for a throwaway container — so we hardcode them instead of attaching
+# every matrix shard to a GHA environment just to read three "secrets"
+# (which also produces a "temporarily deployed to …" notification on the
+# PR timeline per shard per push).
 jobs:
   run:
     name: Run tests
     runs-on: ubuntu-latest
     timeout-minutes: ${{ inputs.timeout-minutes }}
-    # Environment is derived from the enable-* flags, not caller-controllable.
-    # This prevents callers from passing arbitrary environment names to bypass secret scoping.
-    environment: >-
-      ${{
-        inputs.enable-postgres && 'integration-postgres' ||
-        ''
-      }}
 
     services:
       postgres:
         image: postgres@sha256:705a5d5b5836f3fcba0d02c4d281e6a7dd9ed2dd4078640f08a1e1e9896e097d # postgres:14
         env:
-          POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
-          POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}
+          POSTGRES_USER: litellm
+          POSTGRES_PASSWORD: litellm
           POSTGRES_DB: litellm_test
         ports:
           - 5432:5432
@@ -86,44 +84,37 @@ 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 }}
+          DATABASE_URL: "postgresql://litellm:litellm@localhost:5432/litellm_test"
         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:
@@ -131,10 +122,11 @@ jobs:
           MAX_FAILURES: ${{ inputs.max-failures }}
           WORKERS: ${{ inputs.workers }}
           RERUNS: ${{ inputs.reruns }}
-          DATABASE_URL: ${{ inputs.enable-postgres && secrets.DATABASE_URL || '' }}
+          DIST: ${{ inputs.dist }}
+          DATABASE_URL: ${{ inputs.enable-postgres && 'postgresql://litellm:litellm@localhost:5432/litellm_test' || '' }}
         run: |
           if [ "${WORKERS}" = "0" ]; then
-            poetry run pytest ${TEST_PATH:?} \
+            uv run --no-sync pytest ${TEST_PATH:?} \
               --tb=short -vv \
               --maxfail="${MAX_FAILURES}" \
               --reruns "${RERUNS}" \
@@ -144,13 +136,13 @@ 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 "${WORKERS}" \
               --reruns "${RERUNS}" \
               --reruns-delay 1 \
-              --dist=loadscope \
+              --dist="${DIST}" \
               --durations=20 \
               --cov=litellm \
               --cov-report=xml:coverage.xml \

.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/check-lazy-openapi-snapshot.yml

@@ -0,0 +1,75 @@
+name: Check Lazy OpenAPI Snapshot
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - "litellm_**"
+
+permissions:
+  contents: read
+  checks: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  verify:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
+      - name: Cache uv dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/uv
+            .venv
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-uv-
+
+      - name: Install dependencies
+        run: uv sync --frozen --all-groups --all-extras
+
+      - name: Regenerate snapshot to /tmp
+        id: regen
+        run: |
+          cp litellm/proxy/_lazy_openapi_snapshot.json /tmp/snapshot.committed.json
+          uv run --no-sync python -m litellm.proxy._lazy_openapi_snapshot
+          mv litellm/proxy/_lazy_openapi_snapshot.json /tmp/snapshot.fresh.json
+          mv /tmp/snapshot.committed.json litellm/proxy/_lazy_openapi_snapshot.json
+
+      - name: Compare
+        id: diff
+        continue-on-error: true
+        run: |
+          diff -q /tmp/snapshot.fresh.json litellm/proxy/_lazy_openapi_snapshot.json
+
+      - name: Mark neutral if drift
+        if: steps.diff.outcome == 'failure'
+        uses: LouisBrunner/checks-action@6b626ffbad7cc56fd58627f774b9067e6118af23 # v2.0.0
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          name: lazy-openapi-snapshot
+          conclusion: neutral
+          output: |
+            {
+              "title": "Lazy openapi snapshot is stale",
+              "summary": "Run `python -m litellm.proxy._lazy_openapi_snapshot` and commit the regenerated `litellm/proxy/_lazy_openapi_snapshot.json`. Not blocking — the snapshot will regenerate at release if not committed."
+            }

.github/workflows/check_duplicate_issues.yml

@@ -39,7 +39,7 @@ jobs:
         if: github.event.action == 'opened'
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
-          python-version: "3.11"
+          python-version: "3.12"
 
       - name: Auto-close if high-confidence duplicate
         if: github.event.action == 'opened'

.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/create-release-branch.yml

@@ -0,0 +1,65 @@
+name: Create Release Branch
+
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Release tag (e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, 1.84.0.post1; legacy v1.83.10-stable still accepted) — branch will be named release/<tag>"
+        required: true
+        type: string
+      commit_hash:
+        description: "Full 40-char commit SHA the branch should point to"
+        required: true
+        type: string
+  workflow_call:
+    inputs:
+      tag:
+        description: "Release tag (e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, 1.84.0.post1; legacy v1.83.10-stable still accepted)"
+        required: true
+        type: string
+      commit_hash:
+        description: "Full 40-char commit SHA the branch should point to"
+        required: true
+        type: string
+
+permissions: {}
+
+jobs:
+  create-branch:
+    name: Create Release Branch
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Validate inputs
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        run: |
+          if ! echo "${COMMIT_HASH}" | grep -qE '^[0-9a-f]{40}$'; then
+            echo "::error::commit_hash must be a full 40-character commit SHA"
+            exit 1
+          fi
+          if ! echo "${TAG}" | grep -qE '^v?[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::tag must start with X.Y.Z (optional leading v), e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, or v1.83.10-stable"
+            exit 1
+          fi
+
+      - name: Create release branch
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const tag = process.env.TAG;
+            const commitHash = process.env.COMMIT_HASH;
+            const branchName = `release/${tag}`;
+
+            await github.rest.git.createRef({
+              owner: context.repo.owner,
+              repo: context.repo.repo,
+              ref: `refs/heads/${branchName}`,
+              sha: commitHash,
+            });
+            core.info(`Created branch ${branchName} at ${commitHash}`);

.github/workflows/create-release.yml

@@ -4,7 +4,7 @@ on:
   workflow_dispatch:
     inputs:
       tag:
-        description: "Release tag (e.g. v1.83.0-stable)"
+        description: "Release tag (e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, 1.84.0.post1; legacy v1.83.10-stable still accepted)"
         required: true
         type: string
       commit_hash:
@@ -30,8 +30,8 @@ jobs:
             echo "::error::commit_hash must be a full 40-character commit SHA"
             exit 1
           fi
-          if ! echo "${TAG}" | grep -qE '^v[0-9]+\.[0-9]+\.[0-9]+'; then
-            echo "::error::tag must start with vX.Y.Z"
+          if ! echo "${TAG}" | grep -qE '^v?[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::tag must start with X.Y.Z (optional leading v), e.g. 1.84.0, 1.84.0rc1, 1.84.0.dev42, or v1.83.10-stable"
             exit 1
           fi
 
@@ -45,6 +45,11 @@ jobs:
             const tag = process.env.TAG;
             const commitHash = process.env.COMMIT_HASH;
 
+            // Mark RC / dev / nightly / alpha / beta tags as GitHub pre-releases.
+            // PEP 440 post-releases (e.g. `1.84.0.post1`) and legacy `-stable[.patch.N]`
+            // are stable maintenance releases, not pre-releases.
+            const isPrerelease = /(?:rc|nightly|alpha|beta|\.dev)/i.test(tag);
+
             const cosignSection = [
               `## Verify Docker Image Signature`,
               ``,
@@ -89,7 +94,7 @@ jobs:
                 target_commitish: commitHash,
                 name: tag,
                 owner: context.repo.owner,
-                prerelease: false,
+                prerelease: isPrerelease,
                 repo: context.repo.repo,
                 tag_name: tag,
               });
@@ -102,6 +107,17 @@ jobs:
                 body: updatedBody,
                 draft: false,
               });
+
             } catch (error) {
               core.setFailed(error.message);
             }
+
+  create-branch:
+    name: Create Release Branch
+    needs: release
+    permissions:
+      contents: write
+    uses: ./.github/workflows/create-release-branch.yml
+    with:
+      tag: ${{ inputs.tag }}
+      commit_hash: ${{ inputs.commit_hash }}

.github/workflows/guard-fork-dependencies.yml

@@ -0,0 +1,140 @@
+name: Guard fork dependency changes
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+    paths:
+      - "uv.lock"
+      - "pyproject.toml"
+      - "litellm-proxy-extras/pyproject.toml"
+      - "enterprise/pyproject.toml"
+
+permissions: {}
+
+jobs:
+  guard:
+    name: Block fork dependency changes
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    if: github.event.pull_request.head.repo.full_name != github.repository
+    steps:
+      - name: Checkout base branch
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          ref: ${{ github.base_ref }}
+          persist-credentials: false
+          path: base
+
+      - name: Checkout PR head (read-only)
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+          path: pr
+
+      - name: Reject uv.lock changes
+        run: |
+          if ! diff -q base/uv.lock pr/uv.lock >/dev/null 2>&1; then
+            echo "::error::Fork PRs must not modify uv.lock. Dependency lockfile changes must come from a branch in the canonical repository."
+            exit 1
+          fi
+          echo "uv.lock is unchanged."
+
+      - name: Reject new dependencies in pyproject.toml files
+        shell: bash
+        run: |
+          set -euo pipefail
+
+          # Write the checker script to a temp file to avoid shell quoting issues.
+          cat > /tmp/extract_deps.py << 'SCRIPT'
+          import re
+          import sys
+          import tomllib
+
+
+          def normalize(name: str) -> str:
+              return re.sub(r"[-_.]+", "-", name).lower()
+
+
+          def extract_dep_names(path: str) -> set[str]:
+              with open(path, "rb") as f:
+                  data = tomllib.load(f)
+
+              deps: set[str] = set()
+              pep508 = re.compile(r"^([A-Za-z0-9](?:[A-Za-z0-9._-]*[A-Za-z0-9])?)")
+
+              # [project].dependencies
+              for spec in data.get("project", {}).get("dependencies", []):
+                  m = pep508.match(spec)
+                  if m:
+                      deps.add(normalize(m.group(1)))
+
+              # [project.optional-dependencies]
+              for group in data.get("project", {}).get("optional-dependencies", {}).values():
+                  for spec in group:
+                      m = pep508.match(spec)
+                      if m:
+                          deps.add(normalize(m.group(1)))
+
+              # [dependency-groups]
+              for group in data.get("dependency-groups", {}).values():
+                  for item in group:
+                      if isinstance(item, str):
+                          m = pep508.match(item)
+                          if m:
+                              deps.add(normalize(m.group(1)))
+
+              return deps
+
+
+          if __name__ == "__main__":
+              for name in sorted(extract_dep_names(sys.argv[1])):
+                  print(name)
+          SCRIPT
+
+          had_error=0
+
+          check_deps() {
+            local base_file="$1"
+            local pr_file="$2"
+            local label="$3"
+
+            if [ ! -f "$base_file" ] && [ ! -f "$pr_file" ]; then
+              return 0
+            fi
+
+            if [ ! -f "$base_file" ] && [ -f "$pr_file" ]; then
+              echo "::error::Fork PR introduces a new $label that does not exist on the base branch."
+              return 1
+            fi
+
+            base_deps=$(python3 /tmp/extract_deps.py "$base_file")
+            pr_deps=$(python3 /tmp/extract_deps.py "$pr_file")
+
+            new_deps=$(comm -13 <(echo "$base_deps") <(echo "$pr_deps"))
+
+            if [ -n "$new_deps" ]; then
+              echo "::error::Fork PR adds new dependencies in $label: $(echo $new_deps | tr '\n' ', ')"
+              echo "New packages detected:"
+              echo "$new_deps"
+              return 1
+            fi
+
+            echo "$label: no new dependencies."
+            return 0
+          }
+
+          check_deps base/pyproject.toml pr/pyproject.toml "pyproject.toml" || had_error=1
+          check_deps base/litellm-proxy-extras/pyproject.toml pr/litellm-proxy-extras/pyproject.toml "litellm-proxy-extras/pyproject.toml" || had_error=1
+          check_deps base/enterprise/pyproject.toml pr/enterprise/pyproject.toml "enterprise/pyproject.toml" || had_error=1
+
+          if [ "$had_error" -ne 0 ]; then
+            echo ""
+            echo "::error::Fork PRs must not add new dependencies. Please open an issue or coordinate with a maintainer to update dependencies from within the canonical repository."
+            exit 1
+          fi
+
+          echo "All pyproject.toml files passed dependency check."

.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

@@ -29,28 +29,27 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
-          python-version: "3.11"
+          python-version: "3.12"
 
-      - 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/scan_duplicate_issues.yml

@@ -29,7 +29,7 @@ jobs:
       - name: Set up Python
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
-          python-version: "3.13"
+          python-version: "3.12"
 
       - name: Scan for duplicate issues
         env:

.github/workflows/test-code-quality.yml

@@ -0,0 +1,128 @@
+name: Code Quality Checks
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  code-quality:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Checkout litellm-docs into docs/my-website (for documentation_tests)
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          repository: BerriAI/litellm-docs
+          path: docs/my-website
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
+      - name: Cache uv dependencies
+        uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4.3.0
+        with:
+          path: |
+            ~/.cache/uv
+            .venv
+          key: ${{ runner.os }}-uv-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-uv-
+
+      - name: Install dependencies
+        run: uv sync --frozen --all-groups --all-extras
+
+      - name: check_licenses
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_licenses.py
+
+      - name: check_provider_folders_documented
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_provider_folders_documented.py
+
+      - name: router_code_coverage
+        run: uv run --no-sync python ./tests/code_coverage_tests/router_code_coverage.py
+
+      - name: test_chat_completion_imports
+        run: uv run --no-sync python ./tests/code_coverage_tests/test_chat_completion_imports.py
+
+      - name: info_log_check
+        run: uv run --no-sync python ./tests/code_coverage_tests/info_log_check.py
+
+      - name: check_guardrail_apply_decorator
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_guardrail_apply_decorator.py
+
+      - name: test_ban_set_verbose
+        run: uv run --no-sync python ./tests/code_coverage_tests/test_ban_set_verbose.py
+
+      - name: code_qa_check_tests
+        run: uv run --no-sync python ./tests/code_coverage_tests/code_qa_check_tests.py
+
+      - name: check_get_model_cost_key_performance
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_get_model_cost_key_performance.py
+
+      - name: test_proxy_types_import
+        run: uv run --no-sync python ./tests/code_coverage_tests/test_proxy_types_import.py
+
+      - name: callback_manager_test
+        run: uv run --no-sync python ./tests/code_coverage_tests/callback_manager_test.py
+
+      - name: recursive_detector
+        run: uv run --no-sync python ./tests/code_coverage_tests/recursive_detector.py
+
+      - name: test_router_strategy_async
+        run: uv run --no-sync python ./tests/code_coverage_tests/test_router_strategy_async.py
+
+      - name: litellm_logging_code_coverage
+        run: uv run --no-sync python ./tests/code_coverage_tests/litellm_logging_code_coverage.py
+
+      - name: ensure_async_clients_test
+        run: uv run --no-sync python ./tests/code_coverage_tests/ensure_async_clients_test.py
+
+      - name: enforce_llms_folder_style
+        run: uv run --no-sync python ./tests/code_coverage_tests/enforce_llms_folder_style.py
+
+      - name: prevent_key_leaks_in_exceptions
+        run: uv run --no-sync python ./tests/code_coverage_tests/prevent_key_leaks_in_exceptions.py
+
+      - name: check_unsafe_enterprise_import
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_unsafe_enterprise_import.py
+
+      - name: ban_copy_deepcopy_kwargs
+        run: uv run --no-sync python ./tests/code_coverage_tests/ban_copy_deepcopy_kwargs.py
+
+      - name: check_fastuuid_usage
+        run: uv run --no-sync python ./tests/code_coverage_tests/check_fastuuid_usage.py
+
+      - name: memory_test
+        run: uv run --no-sync python ./tests/code_coverage_tests/memory_test.py
+
+      - name: documentation_test_env_keys
+        run: uv run --no-sync python ./tests/documentation_tests/test_env_keys.py
+
+      - name: documentation_test_router_settings
+        run: uv run --no-sync python ./tests/documentation_tests/test_router_settings.py
+
+      - name: documentation_test_api_docs
+        run: uv run --no-sync python ./tests/documentation_tests/test_api_docs.py

.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-semgrep.yml

@@ -0,0 +1,39 @@
+name: Semgrep
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  semgrep:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+
+      - name: Run Semgrep (custom rules)
+        run: uv tool run --from 'semgrep==1.157.0' semgrep scan --config .semgrep/rules . --error

.github/workflows/test-unit-caching-redis.yml

@@ -0,0 +1,38 @@
+name: "Unit Tests: Caching (Redis)"
+
+# Uses cloud Redis credentials — only runs on trusted branches, not PRs.
+# This prevents external PRs from accessing Redis credentials.
+on:
+  push:
+    branches: [main, "litellm_*"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  caching-redis:
+    uses: ./.github/workflows/_test-unit-services-base.yml
+    with:
+      # Redis-only tests that do NOT require provider API keys.
+      # Tests needing API keys (test_caching.py, test_caching_ssl.py, test_prometheus_service.py,
+      # test_router_caching.py) are in Phase 3 integration workflows.
+      test-path: >-
+        tests/local_testing/test_dual_cache.py
+        tests/local_testing/test_redis_batch_optimizations.py
+        tests/local_testing/test_router_utils.py
+      workers: 2
+      reruns: 2
+      timeout-minutes: 20
+      enable-redis: true
+      enable-postgres: false
+    secrets:
+      REDIS_HOST: ${{ secrets.REDIS_HOST }}
+      REDIS_PORT: ${{ secrets.REDIS_PORT }}
+      REDIS_PASSWORD: ${{ secrets.REDIS_PASSWORD }}
+      DATABASE_URL: ${{ secrets.DATABASE_URL }}
+      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
+      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}

.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
@@ -21,47 +25,47 @@ jobs:
         with:
           persist-credentials: false
 
+      - name: Checkout litellm-docs into docs/my-website (for documentation_tests)
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          repository: BerriAI/litellm-docs
+          path: docs/my-website
+          persist-credentials: false
+
       - name: Set up Python
         uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
           python-version: "3.12"
 
-      - name: Install Poetry
-        run: pip install 'poetry==2.3.2'
+      - name: 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
@@ -12,8 +12,74 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+# Semantic matrix: each shard groups tests by concern (auth, server, logging, …)
+# rather than alphabetical letter ranges. Adding a new test file means adding it
+# to whichever group it belongs to, not reshuffling slices.
+#
+# Design targets:
+#   * Every shard runs in <= 7 minutes of wall-clock on the default runner.
+#     Most of a shard's time is pytest plugin load + xdist worker imports +
+#     pytest-cov instrumentation, not the tests themselves. Keeping per-shard
+#     work low and matching worker count to runner cores is what controls it.
+#   * workers: 4 matches the 4-core ubuntu-latest runner. -n 8 on 4 cores
+#     oversubscribes 2x and workers fight for CPU during their cold-start
+#     imports (measured ~441% CPU for -n 8 locally, i.e. ~55% effective).
+#   * test_key_generate_prisma.py stays serial (workers=0) — it has event-loop
+#     conflicts with the logging worker when run in parallel.
+#   * test_proxy_utils.py runs as a single shard with --dist=worksteal so
+#     xdist balances its 188 parametrized cases across workers instead of
+#     pinning the whole file to one worker (the default --dist=loadscope
+#     behavior for single-file targets).
+#   * test_db_schema_migration.py is isolated because one test in it
+#     (test_aaaasschema_migration_check) takes ~170s — by itself it
+#     determines the shard's wall-clock floor.
 jobs:
+  # Fast guard — fails the workflow if a test_*.py file under
+  # tests/proxy_unit_tests/ is not referenced by any matrix entry below.
+  # The semantic-shard design (no catch-all "remaining" bucket) relies on
+  # every test file being explicitly assigned; this guard prevents a new
+  # file from silently dropping out of CI.
+  assert-shard-coverage:
+    runs-on: ubuntu-latest
+    timeout-minutes: 2
+    permissions:
+      contents: read
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+      - name: Assert every test_*.py is in a matrix shard
+        run: |
+          python3 - <<'PY'
+          import pathlib, sys, yaml
+          wf = yaml.safe_load(open(".github/workflows/test-unit-proxy-db.yml"))
+          matrix = wf["jobs"]["proxy-db"]["strategy"]["matrix"]["include"]
+          referenced = set()
+          for entry in matrix:
+              for token in entry["test-path"].split():
+                  if token.startswith("tests/proxy_unit_tests/"):
+                      referenced.add(pathlib.PurePosixPath(token).name)
+          actual = {p.name for p in pathlib.Path("tests/proxy_unit_tests").iterdir()
+                    if p.name.startswith("test_") and (p.suffix == ".py" or p.is_dir())
+                    and p.name != "test_configs"}
+          orphans = sorted(actual - referenced)
+          if orphans:
+              print("ERROR: the following files/dirs under tests/proxy_unit_tests/")
+              print("       are not assigned to any shard in test-unit-proxy-db.yml:")
+              for o in orphans:
+                  print(f"  - {o}")
+              print()
+              print("Add each to whichever semantic shard it belongs to.")
+              sys.exit(1)
+          print(f"OK: all {len(actual)} files assigned to a shard.")
+          PY
+
   proxy-db:
+    needs: assert-shard-coverage
+    # Display only the semantic shard name in the checks UI instead of GHA's
+    # default "proxy-db (key-generation, tests/proxy_unit_tests/…, 0, loadscope, 20)"
+    # which includes every matrix field and gets truncated past the test-path.
+    name: ${{ matrix.test-group }}
     permissions:
       contents: read
       id-token: write
@@ -22,19 +88,145 @@ jobs:
       fail-fast: false
       matrix:
         include:
-          # Key generation tests must NOT run in parallel (event loop conflicts with logging worker)
+          # Must run serially — event-loop conflict with the logging worker.
           - test-group: key-generation
             test-path: "tests/proxy_unit_tests/test_key_generate_prisma.py"
             workers: 0
-            timeout: 30
+            dist: loadscope
+            timeout: 20
+
+          # ---- auth: split into 2 shards ----
           - test-group: auth-checks
-            test-path: "tests/proxy_unit_tests/test_auth_checks.py tests/proxy_unit_tests/test_user_api_key_auth.py"
-            workers: 8
-            timeout: 20
-          - test-group: remaining
-            test-path: "tests/proxy_unit_tests --ignore=tests/proxy_unit_tests/test_key_generate_prisma.py --ignore=tests/proxy_unit_tests/test_auth_checks.py --ignore=tests/proxy_unit_tests/test_user_api_key_auth.py"
-            workers: 8
-            timeout: 20
+            test-path: >-
+              tests/proxy_unit_tests/test_auth_checks.py
+              tests/proxy_unit_tests/test_user_api_key_auth.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+          - test-group: jwt-and-keys
+            test-path: >-
+              tests/proxy_unit_tests/test_jwt.py
+              tests/proxy_unit_tests/test_jwt_key_mapping.py
+              tests/proxy_unit_tests/test_proxy_custom_auth.py
+              tests/proxy_unit_tests/test_key_generate_dynamodb.py
+              tests/proxy_unit_tests/test_deployed_proxy_keygen.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+
+          # ---- test_proxy_utils.py, single shard, worksteal distribution ----
+          - test-group: proxy-utils
+            test-path: "tests/proxy_unit_tests/test_proxy_utils.py"
+            workers: 4
+            dist: worksteal
+            timeout: 15
+
+          # ---- proxy server: split into 2 shards ----
+          - test-group: proxy-server-core
+            test-path: >-
+              tests/proxy_unit_tests/test_proxy_server.py
+              tests/proxy_unit_tests/test_proxy_server_keys.py
+              tests/proxy_unit_tests/test_proxy_server_caching.py
+              tests/proxy_unit_tests/test_proxy_server_langfuse.py
+              tests/proxy_unit_tests/test_proxy_server_spend.py
+              tests/proxy_unit_tests/test_aproxy_startup.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+          - test-group: proxy-runtime
+            test-path: >-
+              tests/proxy_unit_tests/test_proxy_config_unit_test.py
+              tests/proxy_unit_tests/test_proxy_routes.py
+              tests/proxy_unit_tests/test_proxy_gunicorn.py
+              tests/proxy_unit_tests/test_server_root_path.py
+              tests/proxy_unit_tests/test_proxy_pass_user_config.py
+              tests/proxy_unit_tests/test_proxy_token_counter.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+
+          # ---- logging: split into 2 shards ----
+          - test-group: custom-logging
+            test-path: >-
+              tests/proxy_unit_tests/test_custom_callback_input.py
+              tests/proxy_unit_tests/test_custom_logger_s3_gcs.py
+              tests/proxy_unit_tests/test_proxy_custom_logger.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+          - test-group: logging-misc
+            test-path: >-
+              tests/proxy_unit_tests/test_proxy_reject_logging.py
+              tests/proxy_unit_tests/test_audit_logs_proxy.py
+              tests/proxy_unit_tests/test_search_api_logging.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+
+          # ---- db-and-spend: isolate the 170s schema-migration test ----
+          # test_db_schema_migration.py has exactly one test, and that test
+          # is mostly waiting on `prisma migrate deploy` / `prisma migrate
+          # diff` subprocesses (~170s). It does no CPU-bound Python work
+          # inside the test. Running with workers=0 (serial, no xdist)
+          # skips the 4-worker cold-start cost we'd otherwise pay for a
+          # single test, saving ~4 minutes of wall-clock.
+          - test-group: schema-migration
+            test-path: "tests/proxy_unit_tests/test_db_schema_migration.py"
+            workers: 0
+            dist: loadscope
+            timeout: 15
+          - test-group: db-and-spend
+            test-path: >-
+              tests/proxy_unit_tests/test_prisma_client_backoff_retry.py
+              tests/proxy_unit_tests/test_db_schema_changes.py
+              tests/proxy_unit_tests/test_e2e_pod_lock_manager.py
+              tests/proxy_unit_tests/test_skills_db.py
+              tests/proxy_unit_tests/test_update_daily_tag_spend.py
+              tests/proxy_unit_tests/test_update_spend.py
+              tests/proxy_unit_tests/test_proxy_encrypt_decrypt.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+
+          # ---- guardrails + budget + hooks: split into 2 ----
+          - test-group: guardrails-hooks
+            test-path: >-
+              tests/proxy_unit_tests/test_proxy_setting_guardrails.py
+              tests/proxy_unit_tests/test_banned_keyword_list.py
+              tests/proxy_unit_tests/test_unit_test_proxy_hooks.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+          - test-group: budgets
+            test-path: >-
+              tests/proxy_unit_tests/test_default_end_user_budget_simple.py
+              tests/proxy_unit_tests/test_unit_test_max_model_budget_limiter.py
+              tests/proxy_unit_tests/test_zero_cost_model_budget_bypass.py
+            workers: 4
+            dist: loadscope
+            timeout: 15
+
+          - test-group: endpoints-and-responses
+            test-path: >-
+              tests/proxy_unit_tests/test_blog_posts_endpoint.py
+              tests/proxy_unit_tests/test_models_fallback_endpoint.py
+              tests/proxy_unit_tests/test_google_endpoint_routing.py
+              tests/proxy_unit_tests/test_google_gemini_proxy_request.py
+              tests/proxy_unit_tests/test_get_favicon.py
+              tests/proxy_unit_tests/test_get_image.py
+              tests/proxy_unit_tests/test_ui_path_detection.py
+              tests/proxy_unit_tests/test_prompt_test_endpoint.py
+              tests/proxy_unit_tests/test_check_batch_cost.py
+              tests/proxy_unit_tests/test_check_responses_cost.py
+              tests/proxy_unit_tests/test_response_polling_handler.py
+              tests/proxy_unit_tests/test_response_polling_pre_call_checks.py
+              tests/proxy_unit_tests/test_realtime_cache.py
+              tests/proxy_unit_tests/test_proxy_exception_mapping.py
+              tests/proxy_unit_tests/test_custom_tokenizer_bug.py
+              tests/proxy_unit_tests/test_model_response_typing
+            workers: 4
+            dist: loadscope
+            timeout: 15
     uses: ./.github/workflows/_test-unit-services-base.yml
     with:
       test-path: ${{ matrix.test-path }}
@@ -42,8 +234,5 @@ jobs:
       reruns: 2
       timeout-minutes: ${{ matrix.timeout }}
       enable-postgres: true
+      dist: ${{ matrix.dist }}
       artifact-name: proxy-db-${{ matrix.test-group }}
-    secrets:
-      DATABASE_URL: ${{ secrets.DATABASE_URL }}
-      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
-      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}

.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
@@ -32,6 +36,8 @@ jobs:
         tests/test_litellm/proxy/health_endpoints
         tests/test_litellm/proxy/public_endpoints
         tests/test_litellm/proxy/prompts
+        tests/test_litellm/proxy/rag_endpoints
+        tests/test_litellm/proxy/realtime_endpoints
         tests/test_litellm/proxy/ui_crud_endpoints
       workers: 2
       reruns: 2

.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
@@ -24,7 +28,7 @@ jobs:
           - name: "key-generation"
             path: "tests/proxy_unit_tests/test_[k-o]*.py"
           - name: "proxy-config"
-            path: "tests/proxy_unit_tests/test_prisma*.py tests/proxy_unit_tests/test_project*.py tests/proxy_unit_tests/test_prompt*.py tests/proxy_unit_tests/test_proxy_[c-r]*.py"
+            path: "tests/proxy_unit_tests/test_prisma*.py tests/proxy_unit_tests/test_prompt*.py tests/proxy_unit_tests/test_proxy_[c-r]*.py"
           - name: "proxy-server"
             path: "tests/proxy_unit_tests/test_proxy_server.py"
           - name: "proxy-server-extras"
@@ -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

@@ -1,9 +1,11 @@
 name: "Unit Tests: Security"
 
-# Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
+# Kept push-only (was previously required by DATABASE_URL secret scoping;
+# now the postgres credentials are ephemeral localhost values but the
+# push-trigger stays to match the proxy-db workflow cadence).
 on:
   push:
-    branches: [main, "litellm_*"]
+    branches: [main, "litellm_**"]
 
 permissions:
   contents: read
@@ -24,7 +26,3 @@ jobs:
       timeout-minutes: 20
       enable-postgres: true
       artifact-name: security
-    secrets:
-      DATABASE_URL: ${{ secrets.DATABASE_URL }}
-      POSTGRES_USER: ${{ secrets.POSTGRES_USER }}
-      POSTGRES_PASSWORD: ${{ secrets.POSTGRES_PASSWORD }}

.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
 

.npmrc

@@ -2,4 +2,4 @@
 # Packages needing lifecycle scripts: npm rebuild <pkg>
 ignore-scripts=true
 # Protects local npm install only — npm ci (used in CI) ignores this
-min-release-age=3d
+min-release-age=3

AGENTS.md

@@ -23,10 +23,11 @@ LiteLLM is a unified interface for 100+ LLMs that:
 
 ### Key Directories
 - `tests/` - Comprehensive test suites
-- `docs/my-website/` - Documentation website
 - `ui/litellm-dashboard/` - Admin dashboard UI
 - `enterprise/` - Enterprise-specific features
 
+Documentation lives in the separate [BerriAI/litellm-docs](https://github.com/BerriAI/litellm-docs) repository and is served at [docs.litellm.ai](https://docs.litellm.ai).
+
 ## DEVELOPMENT GUIDELINES
 
 ### MAKING CODE CHANGES
@@ -51,7 +52,9 @@ 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 +124,7 @@ 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
 
@@ -216,8 +219,8 @@ When opening issues or pull requests, follow these templates:
 
 ## HELPFUL RESOURCES
 
-- Main documentation: https://docs.litellm.ai/
-- Provider-specific docs in `docs/my-website/docs/providers/`
+- Main documentation: https://docs.litellm.ai/ (source: [BerriAI/litellm-docs](https://github.com/BerriAI/litellm-docs))
+- Provider-specific docs: https://docs.litellm.ai/docs/providers/
 - Admin UI for testing proxy features
 
 ## WHEN IN DOUBT
@@ -232,16 +235,16 @@ 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 +253,16 @@ 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 +273,4 @@ 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

@@ -2,12 +2,16 @@
 
 This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
 
+## Documentation
+
+Documentation lives in a separate repository: [BerriAI/litellm-docs](https://github.com/BerriAI/litellm-docs). It is served at [docs.litellm.ai](https://docs.litellm.ai). Do not create or edit documentation files in this repository — open doc PRs against `BerriAI/litellm-docs` instead.
+
 ## Development Commands
 
 ### 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 +24,14 @@ 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 +113,9 @@ 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 +158,14 @@ 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

@@ -1,142 +1,101 @@
 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
 
 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+
+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 UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    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 && \
-    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.
+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@13.0.6 @isaacs/brace-expansion@5.0.1 brace-expansion@5.0.5 minimatch@10.2.4 diff@8.0.3 picomatch@4.0.4 && \
     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" "$d"; \
+    for pkg in tar glob @isaacs/brace-expansion brace-expansion minimatch diff picomatch; do \
+        name="${pkg##*/}"; \
+        find "$GLOBAL/npm" -type d -name "$name" -path "*/node_modules/$pkg" | while read d; do \
+            rm -rf "$d" && cp -rL "$GLOBAL/$pkg" "$d"; \
+        done; \
     done && \
-    find "$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 && \
-    # 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 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
+# Prisma binaries live in $HOME/.cache (default prisma-python location),
+# which is /root/.cache here. Copy them from the builder so they survive
+# deployments that volume-mount /app/.cache (e.g. readOnlyRootFilesystem
+# + emptyDir) — otherwise the mount would shadow the baked-in query engine.
+COPY --from=builder /root/.cache /root/.cache
 
-# 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
@@ -464,6 +484,8 @@ make format-check   # Check formatting only
 
 For detailed contributing guidelines, see [CONTRIBUTING.md](CONTRIBUTING.md).
 
+> **📖 Contributing to documentation?** The LiteLLM docs have moved to a separate repository: [BerriAI/litellm-docs](https://github.com/BerriAI/litellm-docs). Please open doc PRs there. Docs are served at [docs.litellm.ai](https://docs.litellm.ai).
+
 ## Code Quality / Linting
 
 LiteLLM follows the [Google Python Style Guide](https://google.github.io/styleguide/pyguide.html).
@@ -486,10 +508,6 @@ 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 +522,3 @@ 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

@@ -1,23 +1,234 @@
+import argparse
 import os
-import subprocess
-from pathlib import Path
-from datetime import datetime
-import testing.postgresql
+import re
 import shutil
+import subprocess
+import sys
+from datetime import datetime
+from pathlib import Path
+
+import testing.postgresql
 
 
-def create_migration(migration_name: str = None):
+DESTRUCTIVE_PATTERN = re.compile(r"\bDROP\s+(COLUMN|TABLE|INDEX)\b", re.IGNORECASE)
+DEFAULT_BASE_BRANCH = "litellm_internal_staging"
+
+
+def _find_destructive_statements(sql: str) -> list:
+    """Return SQL lines containing DROP COLUMN, DROP TABLE, or DROP INDEX."""
+    return [
+        line.strip() for line in sql.splitlines() if DESTRUCTIVE_PATTERN.search(line)
+    ]
+
+
+def _print_freshness_failure(
+    base_branch: str, reason: str, stderr_text: str = ""
+) -> None:
+    """Loudly refuse to run when the freshness check can't be completed."""
+    banner = "=" * 72
+    out = sys.stderr
+    print(banner, file=out)
+    print(f"  FRESHNESS CHECK FAILED — COULD NOT VERIFY origin/{base_branch}", file=out)
+    print(banner, file=out)
+    print("", file=out)
+    print(f"Reason: {reason}", file=out)
+    if stderr_text:
+        print("", file=out)
+        print("git stderr:", file=out)
+        for line in stderr_text.rstrip().splitlines():
+            print(f"    {line}", file=out)
+    print("", file=out)
+    print("Common causes:", file=out)
+    print("  - No network access (offline)", file=out)
+    print("  - 'origin' remote not configured, or base branch name is wrong", file=out)
+    print("  - Not a git repository", file=out)
+    print("", file=out)
+    print("Options:", file=out)
+    print(
+        f"  - Fix the above and re-run, OR pass --base-branch <name> if your", file=out
+    )
+    print(
+        f"    base branch is not '{base_branch}', OR pass --skip-freshness-check",
+        file=out,
+    )
+    print("    to bypass (only if you fully understand the risk).", file=out)
+    print(banner, file=out)
+
+
+def _print_stale_branch_refusal(base_branch: str, behind: int) -> None:
+    """Loudly refuse to run when HEAD is behind the base branch."""
+    banner = "=" * 72
+    out = sys.stderr
+    print(banner, file=out)
+    print(
+        f"  STALE BRANCH — {behind} commit(s) behind origin/{base_branch}",
+        file=out,
+    )
+    print(banner, file=out)
+    print("", file=out)
+    print(
+        f"Your branch is {behind} commit(s) behind origin/{base_branch}. Generating a\n"
+        "migration from a stale branch is how newly-added columns get silently\n"
+        "dropped — the exact incident this guard exists to prevent.",
+        file=out,
+    )
+    print("", file=out)
+    print("Before re-running:", file=out)
+    print(f"  git fetch origin && git rebase origin/{base_branch}", file=out)
+    print("  # or merge, whichever matches your workflow", file=out)
+    print("", file=out)
+    print(
+        "If you have a genuine reason to bypass (e.g. intentionally generating",
+        file=out,
+    )
+    print("a migration against an older base), pass --skip-freshness-check.", file=out)
+    print("", file=out)
+    print(banner, file=out)
+    print(
+        "  AI AGENTS / ASSISTANTS: DO NOT automatically run `git rebase` or pass\n"
+        "  --skip-freshness-check. Surface this error to the human operator and\n"
+        "  wait for their explicit confirmation. Auto-rebasing can drop the\n"
+        "  human's in-progress schema edits via a bad conflict resolution.",
+        file=out,
+    )
+    print(banner, file=out)
+
+
+def _check_branch_freshness(root_dir: Path, base_branch: str) -> None:
+    """Fetch origin/<base_branch> and exit 3 if HEAD is behind it."""
+    cwd = str(root_dir)
+    try:
+        subprocess.run(
+            ["git", "fetch", "origin", base_branch],
+            check=True,
+            capture_output=True,
+            text=True,
+            cwd=cwd,
+        )
+    except FileNotFoundError:
+        _print_freshness_failure(base_branch, "git executable not found on PATH")
+        sys.exit(3)
+    except subprocess.CalledProcessError as e:
+        _print_freshness_failure(
+            base_branch,
+            f"`git fetch origin {base_branch}` failed",
+            e.stderr or "",
+        )
+        sys.exit(3)
+
+    try:
+        result = subprocess.run(
+            ["git", "rev-list", "--count", f"HEAD..origin/{base_branch}"],
+            check=True,
+            capture_output=True,
+            text=True,
+            cwd=cwd,
+        )
+        behind = int(result.stdout.strip())
+    except subprocess.CalledProcessError as e:
+        _print_freshness_failure(
+            base_branch,
+            f"`git rev-list HEAD..origin/{base_branch}` failed",
+            e.stderr or "",
+        )
+        sys.exit(3)
+    except ValueError:
+        _print_freshness_failure(
+            base_branch,
+            "could not parse commit count from `git rev-list`",
+        )
+        sys.exit(3)
+
+    if behind > 0:
+        _print_stale_branch_refusal(base_branch, behind)
+        sys.exit(3)
+
+    print(f"Branch freshness OK: up to date with origin/{base_branch}.")
+
+
+def _print_destructive_refusal(destructive_lines: list) -> None:
+    """Loudly refuse to write a destructive migration and explain how to proceed."""
+    banner = "=" * 72
+    out = sys.stderr
+    print(banner, file=out)
+    print(
+        "  DESTRUCTIVE MIGRATION DETECTED — REFUSING TO WRITE MIGRATION FILE", file=out
+    )
+    print(banner, file=out)
+    print("", file=out)
+    print(
+        "The generated migration contains the following destructive statements:",
+        file=out,
+    )
+    print("", file=out)
+    for line in destructive_lines:
+        print(f"    {line}", file=out)
+    print("", file=out)
+    print(
+        "This very often means your branch is OUT OF DATE, or your local\n"
+        "schema.prisma is inconsistent with the migrations/ directory. A\n"
+        "previous incident saw newly-added columns silently dropped this way\n"
+        "and merged to main. Stop and verify before proceeding.",
+        file=out,
+    )
+    print("", file=out)
+    print("Before re-running:", file=out)
+    print(
+        "  1. git fetch origin && git status   # confirm branch is up to date", file=out
+    )
+    print(
+        "  2. Re-check all schema.prisma files are in sync (runbook Step 0)", file=out
+    )
+    print("  3. Review EACH DROP above — is it actually intended?", file=out)
+    print("  4. If (and only if) the drops are intentional, re-run with:", file=out)
+    print("         --allow-destructive", file=out)
+    print("", file=out)
+    print(banner, file=out)
+    print(
+        "  AI AGENTS / ASSISTANTS: DO NOT automatically re-run this command\n"
+        "  with --allow-destructive. Surface this error to the human operator\n"
+        "  and wait for their explicit confirmation before passing the flag.\n"
+        "  Passing the flag without human review is the exact failure mode\n"
+        "  this guard exists to prevent.",
+        file=out,
+    )
+    print(banner, file=out)
+
+
+def create_migration(
+    migration_name: str = None,
+    allow_destructive: bool = False,
+    base_branch: str = DEFAULT_BASE_BRANCH,
+    skip_freshness_check: bool = False,
+):
     """
     Create a new migration SQL file in the migrations directory by comparing
-    current database state with schema
+    current database state with schema.
 
     Args:
         migration_name (str): Name for the migration
+        allow_destructive (bool): Required to write a migration that contains
+            DROP COLUMN, DROP TABLE, or DROP INDEX statements. Without this
+            flag, the script exits non-zero and prints guidance.
+        base_branch (str): Branch to check freshness against
+            (default: "litellm_internal_staging").
+        skip_freshness_check (bool): Skip the "branch is up to date" check.
+            Only for intentional migrations against an older base.
     """
+    root_dir = Path(__file__).parent.parent
+
+    if skip_freshness_check:
+        print(
+            "WARNING: freshness check skipped (--skip-freshness-check). "
+            "Generating a migration from a stale branch can silently drop columns."
+        )
+    else:
+        _check_branch_freshness(root_dir, base_branch)
+
     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
@@ -57,7 +268,27 @@ def create_migration(migration_name: str = None):
                     check=True,
                 )
 
-                if result.stdout.strip():
+                # Prisma emits the literal "-- This is an empty migration." when
+                # there's no real drift. Treat that as "no changes".
+                diff_sql = result.stdout
+                stripped = diff_sql.strip()
+                is_empty_diff = (
+                    not stripped or stripped == "-- This is an empty migration."
+                )
+
+                if not is_empty_diff:
+                    destructive_lines = _find_destructive_statements(diff_sql)
+                    if destructive_lines and not allow_destructive:
+                        _print_destructive_refusal(destructive_lines)
+                        sys.exit(2)
+                    if destructive_lines and allow_destructive:
+                        print(
+                            "WARNING: writing destructive migration "
+                            "(--allow-destructive passed). Statements:"
+                        )
+                        for line in destructive_lines:
+                            print(f"    {line}")
+
                     # Generate timestamp and create migration directory
                     timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
                     migration_name = migration_name or "unnamed_migration"
@@ -66,7 +297,7 @@ def create_migration(migration_name: str = None):
 
                     # Write the SQL to migration.sql
                     migration_file = migration_dir / "migration.sql"
-                    migration_file.write_text(result.stdout)
+                    migration_file.write_text(diff_sql)
 
                     print(f"Created migration in {migration_dir}")
                     return True
@@ -88,8 +319,48 @@ def create_migration(migration_name: str = None):
 
 
 if __name__ == "__main__":
-    # If running directly, can optionally pass migration name as argument
-    import sys
-
-    migration_name = sys.argv[1] if len(sys.argv) > 1 else None
-    create_migration(migration_name)
+    parser = argparse.ArgumentParser(
+        description=(
+            "Generate a Prisma migration by diffing the temp DB "
+            "(existing migrations applied) against schema.prisma."
+        )
+    )
+    parser.add_argument(
+        "migration_name",
+        nargs="?",
+        default=None,
+        help="Name for the migration (used in the generated directory name).",
+    )
+    parser.add_argument(
+        "--allow-destructive",
+        action="store_true",
+        help=(
+            "Required to write a migration that contains DROP COLUMN, "
+            "DROP TABLE, or DROP INDEX. Without this flag, destructive "
+            "diffs are refused."
+        ),
+    )
+    parser.add_argument(
+        "--base-branch",
+        default=DEFAULT_BASE_BRANCH,
+        help=(
+            f"Branch to check freshness against (default: {DEFAULT_BASE_BRANCH}). "
+            "The script fetches origin/<base-branch> and refuses to run if HEAD "
+            "is behind it."
+        ),
+    )
+    parser.add_argument(
+        "--skip-freshness-check",
+        action="store_true",
+        help=(
+            "Bypass the 'branch is up to date' check. Only for intentional "
+            "migrations against an older base. Pairs poorly with automation."
+        ),
+    )
+    args = parser.parse_args()
+    create_migration(
+        args.migration_name,
+        allow_destructive=args.allow_destructive,
+        base_branch=args.base_branch,
+        skip_freshness_check=args.skip_freshness_check,
+    )

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")

deploy/charts/litellm-helm/templates/deployment.yaml

@@ -47,7 +47,7 @@ spec:
         {{- toYaml .Values.podSecurityContext | nindent 8 }}
       {{- with .Values.extraInitContainers }}
       initContainers:
-        {{- toYaml . | nindent 8 }}
+        {{- tpl (toYaml .) $ | nindent 8 }}
       {{- end }}
       containers:
         - name: {{ include "litellm.name" . }}
@@ -212,7 +212,7 @@ spec:
             {{- toYaml . | nindent 12 }}
           {{- end }}
       {{- with .Values.extraContainers }}
-        {{- toYaml . | nindent 8 }}
+        {{- tpl (toYaml .) $ | nindent 8 }}
       {{- end }}
       volumes:
         {{ if .Values.securityContext.readOnlyRootFilesystem }}

deploy/charts/litellm-helm/templates/migrations-job.yaml

@@ -37,7 +37,7 @@ spec:
       serviceAccountName: {{ include "litellm.migrationServiceAccountName" . }}
       {{- with .Values.migrationJob.extraInitContainers }}
       initContainers:
-        {{- toYaml . | nindent 8 }}
+        {{- tpl (toYaml .) $ | nindent 8 }}
       {{- end }} 
       containers:
         - name: prisma-migrations
@@ -96,7 +96,7 @@ spec:
             {{- toYaml . | nindent 12 }}
           {{- end }}
       {{- with .Values.migrationJob.extraContainers }}
-        {{- toYaml . | nindent 8 }}
+        {{- tpl (toYaml .) $ | nindent 8 }}
       {{- end }}
       {{- with .Values.volumes }}
       volumes:

deploy/charts/litellm-helm/tests/deployment_tests.yaml

@@ -319,3 +319,61 @@ tests:
     asserts:
       - notExists:
           path: spec.minReadySeconds
+  - it: should work with extraInitContainers
+    template: deployment.yaml
+    set:
+      extraInitContainers:
+        - name: init-test
+          image: busybox:latest
+          command: ["echo", "hello"]
+    asserts:
+      - contains:
+          path: spec.template.spec.initContainers
+          content:
+            name: init-test
+            image: busybox:latest
+            command: ["echo", "hello"]
+  - it: should support tpl in extraInitContainers
+    template: deployment.yaml
+    set:
+      image:
+        repository: ghcr.io/berriai/litellm-database
+        tag: test
+      extraInitContainers:
+        - name: init-tpl
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+          command: ["echo", "hello"]
+    asserts:
+      - contains:
+          path: spec.template.spec.initContainers
+          content:
+            name: init-tpl
+            image: "ghcr.io/berriai/litellm-database:test"
+            command: ["echo", "hello"]
+  - it: should work with extraContainers
+    template: deployment.yaml
+    set:
+      extraContainers:
+        - name: sidecar
+          image: busybox:latest
+    asserts:
+      - contains:
+          path: spec.template.spec.containers
+          content:
+            name: sidecar
+            image: busybox:latest
+  - it: should support tpl in extraContainers
+    template: deployment.yaml
+    set:
+      image:
+        repository: ghcr.io/berriai/litellm-database
+        tag: test
+      extraContainers:
+        - name: sidecar-tpl
+          image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+    asserts:
+      - contains:
+          path: spec.template.spec.containers
+          content:
+            name: sidecar-tpl
+            image: "ghcr.io/berriai/litellm-database:test"

deploy/charts/litellm-helm/tests/migrations-job_tests.yaml

@@ -188,3 +188,69 @@ tests:
       - equal:
           path: spec.template.spec.serviceAccountName
           value: pre-existing-sa
+  - it: should work with extraInitContainers
+    template: migrations-job.yaml
+    set:
+      migrationJob:
+        enabled: true
+        extraInitContainers:
+          - name: init-test
+            image: busybox:latest
+            command: ["echo", "hello"]
+    asserts:
+      - contains:
+          path: spec.template.spec.initContainers
+          content:
+            name: init-test
+            image: busybox:latest
+            command: ["echo", "hello"]
+  - it: should support tpl in extraInitContainers
+    template: migrations-job.yaml
+    set:
+      image:
+        repository: ghcr.io/berriai/litellm-database
+        tag: test
+      migrationJob:
+        enabled: true
+        extraInitContainers:
+          - name: init-tpl
+            image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+            command: ["echo", "hello"]
+    asserts:
+      - contains:
+          path: spec.template.spec.initContainers
+          content:
+            name: init-tpl
+            image: "ghcr.io/berriai/litellm-database:test"
+            command: ["echo", "hello"]
+  - it: should work with extraContainers
+    template: migrations-job.yaml
+    set:
+      migrationJob:
+        enabled: true
+        extraContainers:
+          - name: sidecar
+            image: busybox:latest
+    asserts:
+      - contains:
+          path: spec.template.spec.containers
+          content:
+            name: sidecar
+            image: busybox:latest
+  - it: should support tpl in extraContainers
+    template: migrations-job.yaml
+    set:
+      image:
+        repository: ghcr.io/berriai/litellm-database
+        tag: test
+      migrationJob:
+        enabled: true
+        extraContainers:
+          - name: sidecar-tpl
+            image: "{{ .Values.image.repository }}:{{ .Values.image.tag }}"
+    asserts:
+      - contains:
+          path: spec.template.spec.containers
+          content:
+            name: sidecar-tpl
+            image: "ghcr.io/berriai/litellm-database:test"

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:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+
+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

@@ -1,55 +1,72 @@
 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
 
 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
-# Builder stage
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+
+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 UV_PROJECT_ENVIRONMENT=/app/.venv \
+    UV_LINK_MODE=copy \
+    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 \
@@ -67,72 +84,25 @@ 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 && \
-    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; }
 
 WORKDIR /app
-# Copy the current directory contents into the container at /app
-COPY . .
-RUN ls -la /app
+ENV 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
+# Prisma binaries live in $HOME/.cache (default prisma-python location),
+# which is /root/.cache here. Copy them from the builder so they survive
+# deployments that volume-mount /app/.cache (e.g. readOnlyRootFilesystem
+# + emptyDir) — otherwise the mount would shadow the baked-in query engine.
+COPY --from=builder /root/.cache /root/.cache
 
-# 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:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+
+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:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+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

@@ -1,67 +1,66 @@
 # Base images
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:a5a619c1793039dcf92f02178f37c94bb3d6001403716da59d6092dfe8d9b502
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
+ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
 ARG PROXY_EXTRAS_SOURCE=published
+ARG UV_IMAGE=ghcr.io/astral-sh/uv:0.11.7@sha256:733b4042187702f832f7fdecb3aff14a61b288c4ca37af188bb5715c1caebaf8
+
+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
+      apk add --no-cache \
+        python3 \
+        python3-dev \
+        gcc \
+        bash \
+        coreutils \
+        curl \
+        openssl \
+        libsndfile \
+        nodejs && 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 \
+    PATH="/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 --mount=type=cache,target=/app/.cache/uv,id=litellm-uv-cache \
+    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
-# 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 && \
-    ([ -f /app/.npmrc ] && mv /app/.npmrc /app/.npmrc.bak || true) && \
-    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" && \
-    npm cache clean --force && \
-    cd /app/ui/litellm-dashboard && \
-    if [ -f "/app/enterprise/enterprise_ui/enterprise_colors.json" ]; then \
-      cp /app/enterprise/enterprise_ui/enterprise_colors.json ./ui_colors.json; \
-    fi && \
-    ([ -f .npmrc ] && mv .npmrc .npmrc.bak || true) && \
-    npm ci && \
-    ([ -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 && \
+# Stage the pre-built Admin UI from the checked-in Next.js static export.
+# _experimental/out/ is regenerated as part of the release runbook.
+# Restructure extensionless routes (foo.html -> foo/index.html) to match the layout
+# proxy_server.py expects, and drop a readiness marker.
+RUN mkdir -p /var/lib/litellm/ui /var/lib/litellm/assets && \
+    cp -r /app/litellm/proxy/_experimental/out/. /var/lib/litellm/ui/ && \
     cp /app/litellm/proxy/logo.jpg /var/lib/litellm/assets/logo.jpg && \
     ( cd /var/lib/litellm/ui && \
       for html_file in *.html; do \
@@ -71,178 +70,79 @@ RUN mkdir -p /var/lib/litellm/ui && \
           mv "$html_file" "$folder_name/index.html"; \
         fi; \
       done && \
-      touch .litellm_ui_ready ) && \
-    cd /app/ui/litellm-dashboard && rm -rf ./out
+      touch .litellm_ui_ready )
 
-# 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 [ "$PROXY_EXTRAS_SOURCE" = "local" ]; then \
-      cd /app/litellm-proxy-extras && rm -rf dist && python -m build && \
-      cp dist/*.whl /wheels/; \
+RUN --mount=type=cache,target=/app/.cache/uv,id=litellm-uv-cache \
+    if [ "$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 prisma generate --schema=./schema.prisma
 
-RUN pip install --no-cache-dir prisma==0.11.0 nodejs-wheel-binaries==24.13.1 \
-    && mkdir -p /app/.cache/npm
+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
 
-RUN NPM_CONFIG_CACHE=/app/.cache/npm \
-    python -c "import prisma.cli.prisma as p; p.ensure_cached()"
-
-RUN prisma generate && \
-    prisma --version && \
-    prisma migrate diff --from-empty --to-schema-datamodel ./schema.prisma --script > /dev/null 2>&1 || true
-
-# -----------------
-# Runtime Stage
-# -----------------
 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; }
+      apk upgrade --no-cache && break || sleep 5; \
+    done && \
+    for i in 1 2 3; do \
+      apk add --no-cache python3 bash openssl tzdata supervisor libsndfile nodejs && break || sleep 5; \
+    done
 
-# 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 mkdir -p /nonexistent /var/lib/litellm/assets /var/lib/litellm/ui && \
+    chown -R nobody:nogroup /app /var/lib/litellm/ui /var/lib/litellm/assets /nonexistent && \
+    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 65534
+
+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`.

docker/tests/nonroot.yaml

@@ -2,7 +2,7 @@ schemaVersion: 2.0.0
 
 metadataTest:
   entrypoint: ["docker/prod_entrypoint.sh"]
-  user: "nobody"
+  user: "65534"
   workdir: "/app"
 
 fileExistenceTests:

docs/my-website/.gitignore

@@ -1,23 +0,0 @@
-# Dependencies
-/node_modules
-
-# Production
-/build
-
-# Generated files
-.docusaurus
-.cache-loader
-
-# Misc
-.DS_Store
-.env
-.env.local
-.env.development.local
-.env.test.local
-.env.production.local
-
-npm-debug.log*
-yarn-debug.log*
-yarn-error.log*
-yarn.lock
-pnpm-lock.yaml

docs/my-website/Dockerfile

@@ -1,9 +0,0 @@
-FROM python:3.14.0a3-slim
-
-COPY . /app
-WORKDIR /app
-RUN pip install -r requirements.txt
-
-EXPOSE $PORT 
-
-CMD litellm --host 0.0.0.0 --port $PORT --workers 10 --config config.yaml

docs/my-website/README.md

@@ -1,41 +0,0 @@
-# Website
-
-This website is built using [Docusaurus 2](https://docusaurus.io/), a modern static website generator.
-
-### Installation
-
-```
-$ yarn
-```
-
-### Local Development
-
-```
-$ yarn start
-```
-
-This command starts a local development server and opens up a browser window. Most changes are reflected live without having to restart the server.
-
-### Build
-
-```
-$ yarn build
-```
-
-This command generates static content into the `build` directory and can be served using any static contents hosting service.
-
-### Deployment
-
-Using SSH:
-
-```
-$ USE_SSH=true yarn deploy
-```
-
-Not using SSH:
-
-```
-$ GIT_USER=<Your GitHub username> yarn deploy
-```
-
-If you are using GitHub pages for hosting, this command is a convenient way to build the website and push to the `gh-pages` branch.

docs/my-website/babel.config.js

@@ -1,3 +0,0 @@
-module.exports = {
-  presets: [require.resolve('@docusaurus/core/lib/babel/preset')],
-};

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

@@ -1,138 +0,0 @@
----
-slug: anthropic-wildcard-model-access-incident
-title: "Incident Report: Wildcard Blocking New Models After Cost Map Reload"
-date: 2026-02-23T10:00:00
-authors:
-  - sameer
-  - krrish
-  - ishaan-alt
-tags: [incident-report, proxy, auth, model-access]
-hide_table_of_contents: false
----
-
-**Date:** Feb 23, 2026  
-**Duration:** ~3 hours  
-**Severity:** High (for users with provider wildcard access rules)  
-**Status:** Resolved
-
-## Summary
-
-When a new Anthropic model (e.g. `claude-sonnet-4-6`) was added to the LiteLLM model cost map and a cost map reload was triggered, requests to the new model were rejected with:
-
-```
-key not allowed to access model. This key can only access models=['anthropic/*']. Tried to access claude-sonnet-4-6.
-```
-
-The reload updated `litellm.model_cost` correctly but never re-ran `add_known_models()`, so `litellm.anthropic_models` (the in-memory set used by the wildcard resolver) remained stale. The new model was invisible to the `anthropic/*` wildcard even though the cost map knew about it.
-
-- **LLM calls:** All requests to newly-added Anthropic models were blocked with a 401.
-- **Existing models:** Unaffected — only models missing from the stale provider set were impacted.
-- **Other providers:** Same bug class existed for any provider wildcard (e.g. `openai/*`, `gemini/*`).
-
-{/* truncate */}
-
----
-
-## Background
-
-LiteLLM supports provider-level wildcard access rules. When an admin configures a key or team with `models=['anthropic/*']`, any model whose provider resolves to `anthropic` should be allowed. The resolution happens in `_model_custom_llm_provider_matches_wildcard_pattern`:
-
-```mermaid
-flowchart TD
-    A["1. Request arrives for claude-sonnet-4-6"] --> B["2. Auth check: can this key call this model?
-    proxy/auth/auth_checks.py"]
-    B --> C["3. Key has models=['anthropic/*']
-    → wildcard match attempted"]
-    C --> D["4. get_llm_provider('claude-sonnet-4-6')
-    checks litellm.anthropic_models set"]
-    D -->|"model IN set"| E["5a. ✅ Provider = 'anthropic'
-    → 'anthropic/claude-sonnet-4-6' matches 'anthropic/*'"]
-    D -->|"model NOT IN set"| F["5b. ❌ Provider unknown
-    → exception raised → wildcard returns False"]
-    E --> G["6. Request allowed"]
-    F --> H["6. 401: key not allowed to access model"]
-
-    style E fill:#d4edda,stroke:#28a745
-    style F fill:#f8d7da,stroke:#dc3545
-    style H fill:#f8d7da,stroke:#dc3545
-    style D fill:#fff3cd,stroke:#ffc107
-```
-
-`litellm.anthropic_models` is a Python `set` populated at import time by `add_known_models()`. It is the source `get_llm_provider()` consults to map a bare model name like `claude-sonnet-4-6` to the provider string `"anthropic"`.
-
----
-
-## Root Cause
-
-`add_known_models()` is called **once** at module import time. Both reload paths in `proxy_server.py` updated `litellm.model_cost` with the fresh map but never called `add_known_models()` again:
-
-```python
-# Before the fix — both reload paths looked like this:
-new_model_cost_map = get_model_cost_map(url=model_cost_map_url)
-litellm.model_cost = new_model_cost_map          # ✅ cost map updated
-_invalidate_model_cost_lowercase_map()           # ✅ cache cleared
-# ❌ add_known_models() never called
-#    → litellm.anthropic_models still has the old set
-#    → new model not in the set
-#    → get_llm_provider() raises for the new model
-#    → wildcard match returns False
-#    → 401 for every request to the new model
-```
-
-The gap existed in two places:
-1. `_check_and_reload_model_cost_map` — the periodic automatic reload (every 10 s)
-2. The `/reload/model_cost_map` admin endpoint — the manual reload
-
-**Timeline:**
-
-1. New model (`claude-sonnet-4-6`) added to `model_prices_and_context_window.json`
-2. Admin triggers cost map reload via UI → `litellm.model_cost` updated
-3. Users with `anthropic/*` wildcard keys attempt requests to `claude-sonnet-4-6`
-4. `get_llm_provider('claude-sonnet-4-6')` raises → wildcard returns False → 401
-5. Admin reloads cost map again — same result (root cause not addressed)
-6. ~3 hours of investigation → root cause identified → fix deployed
-
----
-
-## The Fix
-
-After each reload, `add_known_models()` is called with the freshly fetched map passed explicitly. Passing the map directly (rather than relying on the module-level reference) removes any ambiguity about which dict is iterated:
-
-```python
-# After the fix — both reload paths now do:
-new_model_cost_map = get_model_cost_map(url=model_cost_map_url)
-litellm.model_cost = new_model_cost_map
-_invalidate_model_cost_lowercase_map()
-litellm.add_known_models(model_cost_map=new_model_cost_map)  # ✅ sets repopulated
-```
-
-`add_known_models()` was also updated to accept an optional explicit map so callers cannot accidentally iterate a stale module-level reference:
-
-```python
-# Before
-def add_known_models():
-    for key, value in model_cost.items():   # reads module global — ambiguous after reload
-        ...
-
-# After
-def add_known_models(model_cost_map: Optional[Dict] = None):
-    _map = model_cost_map if model_cost_map is not None else model_cost
-    for key, value in _map.items():         # always iterates the map you just fetched
-        ...
-```
-
-After the fix, the provider sets (`anthropic_models`, `open_ai_chat_completion_models`, etc.) are always consistent with `litellm.model_cost` immediately after every reload. New models become accessible via wildcard rules without any proxy restart.
-
----
-
-## Remediation
-
-| # | Action | Status | Code |
-|---|---|---|---|
-| 1 | Call `add_known_models(model_cost_map=...)` in the periodic reload path | ✅ Done | [`proxy_server.py#L4393`](https://github.com/BerriAI/litellm/blob/main/litellm/proxy/proxy_server.py#L4393) |
-| 2 | Call `add_known_models(model_cost_map=...)` in the `/reload/model_cost_map` endpoint | ✅ Done | [`proxy_server.py#L11904`](https://github.com/BerriAI/litellm/blob/main/litellm/proxy/proxy_server.py#L11904) |
-| 3 | Update `add_known_models()` to accept an explicit map parameter | ✅ Done | [`__init__.py#L617`](https://github.com/BerriAI/litellm/blob/main/litellm/__init__.py#L617) |
-| 4 | Regression test: `add_known_models(model_cost_map=...)` populates provider sets | ✅ Done | [`test_auth_checks.py`](https://github.com/BerriAI/litellm/blob/main/tests/proxy_unit_tests/test_auth_checks.py) |
-| 5 | Regression test: `anthropic/*` wildcard grants/denies access correctly after reload | ✅ Done | [`test_auth_checks.py`](https://github.com/BerriAI/litellm/blob/main/tests/proxy_unit_tests/test_auth_checks.py) |
-
----

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

@@ -1,39 +0,0 @@
----
-slug: april-townhall-announcement
-title: "April Townhall: Security + Product Roadmap"
-date: 2026-04-02T07:30:00
-authors:
-  - krrish
-description: "Join the LiteLLM April townhall on Friday, 10 April at 7:30 AM to learn about LiteLLM's security and product roadmap."
-tags: [announcement, townhall]
-hide_table_of_contents: true
----
-
-import Image from '@theme/IdealImage';
-
-We are hosting our April townhall on **Friday, 10 April at 7:30 AM PST**.
-
-<Image
-  img={require('../../img/april_townhall_banner.png')}
-  style={{width: '900px', height: 'auto', display: 'block'}}
-/>
-
-{/* truncate */}
-
-## Agenda
-
-- Product updates and roadmap progress
-- Reliability and security updates
-- Open Q&A with the team
-
-## How to contribute
-
-Add your thoughts to this [ticket](https://github.com/BerriAI/litellm/issues/24825) to help us shape the agenda.
-
-## Register
-
-Register here: [LiteLLM April Townhall Form](https://forms.gle/hvyVXwbFjzJQE7dEA)
-
-We will hold the townhall from **7:30 AM to 8:30 AM PST on Zoom**.
-
-For security, attendance is restricted to corporate emails. If you register with a non-corporate email, we will share the townhall slides and accompanying blog post after the event.

docs/my-website/blog/authors.yml

@@ -1,48 +0,0 @@
-litellm:
-  name: LiteLLM Team
-  title: LiteLLM Core Team
-  url: https://github.com/BerriAI/litellm
-  image_url: https://github.com/BerriAI.png
-
-sameer:
-  name: Sameer Kankute
-  title: SWE @ LiteLLM (LLM Translation)
-  url: https://www.linkedin.com/in/sameer-kankute/
-  image_url: https://pbs.twimg.com/profile_images/2001352686994907136/ONgNuSk5_400x400.jpg
-
-krrish:
-  name: Krrish Dholakia
-  title: CEO, LiteLLM
-  url: https://www.linkedin.com/in/krish-d/
-  image_url: https://pbs.twimg.com/profile_images/1298587542745358340/DZv3Oj-h_400x400.jpg
-
-ishaan:
-  name: Ishaan Jaffer
-  title: CTO, LiteLLM
-  url: https://www.linkedin.com/in/reffajnaahsi/
-  image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-
-# Alias for typo in name
-ishaan-alt:
-  name: Ishaan Jaff
-  title: CTO, LiteLLM
-  url: https://www.linkedin.com/in/reffajnaahsi/
-  image_url: https://pbs.twimg.com/profile_images/1613813310264340481/lz54oEiB_400x400.jpg
-
-ryan:
-  name: Ryan Crabbe
-  title: Performance Engineer, LiteLLM
-  url: https://www.linkedin.com/in/ryan-crabbe-0b9687214
-  image_url: https://media.licdn.com/dms/image/v2/D5603AQHt1t9Z4BJ6Gw/profile-displayphoto-shrink_400_400/profile-displayphoto-shrink_400_400/0/1724453682340?e=1772064000&v=beta&t=VXdmr13rsNB05wyA2F1TENOB5UuDHUZ0FCHTolNyR5M
-
-alexsander:
-  name: Alexsander Hamir
-  title: Performance Engineer, LiteLLM
-  url: https://www.linkedin.com/in/alexsander-baptista/
-  image_url: https://github.com/AlexsanderHamir.png
-
-yuneng:
-  name: Yuneng Jiang
-  title: SWE @ LiteLLM (Full Stack)
-  url: https://www.linkedin.com/in/yuneng-david-jiang-455676139/
-  image_url: https://avatars.githubusercontent.com/u/171294688?v=4

docs/my-website/blog/ci_cd_v2_improvements/index.md

@@ -1,90 +0,0 @@
----
-slug: ci-cd-v2-improvements
-title: "Announcing CI/CD v2 for LiteLLM"
-date: 2026-03-30T21:30:00
-authors:
-  - krrish
-description: "CI/CD v2 introduces isolated environments, stronger security gates, and safer release separation for LiteLLM."
-tags: [engineering, ci-cd, security]
-hide_table_of_contents: false
----
-
-import Image from '@theme/IdealImage';
-
-The CI/CD v2 is now live for LiteLLM.
-
-<Image
-  img={require('../../img/ci_cd_architecture.png')}
-  style={{width: '700px', height: 'auto', display: 'block'}}
-/>
-
-<br/>
-Building on the roadmap from our [security incident](https://docs.litellm.ai/blog/security-townhall-updates#roadmap), CI/CD v2 introduces isolated environments, stronger security gates, and safer release separation for LiteLLM.
-
-## What changed
-
-- Security scans and unit tests run in isolated environments.
-- Validation and release are separated into different repositories, making it harder for an attacker to reach release credentials.
-- Trusted Publishing for PyPI releases - this means no long-lived credentials are used to publish releases.
-- Immutable Docker release tags - this means no tampering of Docker release tags after they are published [Learn more](https://docs.docker.com/docker-hub/repos/manage/hub-images/immutable-tags/). Note: work for GHCR docker releases is planned as well.
-- Docker image signing with [Cosign](https://github.com/sigstore/cosign) - all release images are signed so users can independently verify they came from us.
-
-## Verify Docker image signatures
-
-Starting from `v1.83.0-nightly`, 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).
-
-**Verify using the pinned commit hash (recommended):**
-
-A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:
-
-```bash
-cosign verify \
-  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
-  ghcr.io/berriai/litellm:<release-tag>
-```
-
-**Verify using a release tag (convenience):**
-
-Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:
-
-```bash
-cosign verify \
-  --key https://raw.githubusercontent.com/BerriAI/litellm/<release-tag>/cosign.pub \
-  ghcr.io/berriai/litellm:<release-tag>
-```
-
-Replace `<release-tag>` with the version you are deploying (e.g. `v1.83.0-stable`).
-
-Expected output:
-
-```
-The following checks were performed on each of these signatures:
-  - The cosign claims were validated
-  - The signatures were verified against the specified public key
-```
-
-## What's next
-
-Moving forward, we plan on:
-- Adopting OpenSSF (this is a set of security criteria that projects should meet to demonstrate a strong security posture - [Learn more](https://baseline.openssf.org/versions/2026-02-19.html))
-  - We've added Scorecard and Allstar to our Github
-
-- Adding SLSA Build Provenance to our CI/CD pipeline - this means we allow users to independently verify that a release came from us and prevent silent modifications of releases after they are published.
-
-
-We hope that this will mean you can be confident that the releases you are using are safe and from us.
-
-
-## The principle
-
-The new CI/CD pipeline reflects the principles, outlined below, and is designed to be more secure and reliable:
-
-- **Limit** what each package can access
-- **Reduce** the number of sensitive environment variables
-- **Avoid** compromised packages
-- **Prevent** release tampering
-
-
-## How to help: 
-
-Help us plan April's stability sprint - https://github.com/BerriAI/litellm/issues/24825

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

@@ -1,168 +0,0 @@
----
-slug: claude-code-beta-headers-incident
-title: "Incident Report: Invalid beta headers with Claude Code"
-date: 2026-02-16T10:00:00
-authors:
-  - sameer
-  - ishaan-alt
-  - krrish
-tags: [incident-report, anthropic, stability]
-hide_table_of_contents: false
----
-
-**Date:** February 13, 2026
-**Duration:** ~3 hours
-**Severity:** High
-**Status:** Resolved
-
-> **Note:** This fix will be available starting from `v1.81.13-nightly` or higher of LiteLLM.
-
-## Summary
-
-Claude Code began sending unsupported Anthropic beta headers to non-Anthropic providers (Bedrock, Azure AI, Vertex AI), causing `invalid beta flag` errors. LiteLLM was forwarding all beta headers without provider-specific validation. Users experienced request failures when routing Claude Code requests through LiteLLM to these providers.
-
-- **LLM calls to Anthropic:** No impact.
-- **LLM calls to Bedrock/Azure/Vertex:** Failed with `invalid beta flag` errors when unsupported headers were present.
-- **Cost tracking and routing:** No impact.
-
-{/* truncate */}
-
----
-
-## Background
-
-Anthropic uses beta headers to enable experimental features in Claude. When Claude Code makes API requests, it includes headers like `anthropic-beta: prompt-caching-scope-2026-01-05,advanced-tool-use-2025-11-20`. However, not all providers support all Anthropic beta features.
-
-Before this incident, LiteLLM forwarded all beta headers to all providers without validation:
-
-```mermaid
-sequenceDiagram
-    participant CC as Claude Code
-    participant LP as LiteLLM (old behavior)
-    participant Provider as Provider (Bedrock/Azure/Vertex)
-
-    CC->>LP: Request with beta headers
-    Note over CC,LP: anthropic-beta: header1,header2,header3
-
-    LP->>Provider: Forward ALL headers (no validation)
-    Note over LP,Provider: anthropic-beta: header1,header2,header3
-
-    Provider-->>LP: ❌ Error: invalid beta flag
-    LP-->>CC: Request fails
-```
-
-Requests succeeded for Anthropic (native support) but failed for other providers when Claude Code sent headers those providers didn't support.
-
----
-
-## Root cause
-
-LiteLLM lacked provider-specific beta header validation. When Claude Code introduced new beta features or sent headers that specific providers didn't support, those headers were blindly forwarded, causing provider API errors.
-
----
-
-## Remediation
-
-| # | Action | Status | Code |
-|---|---|---|---|
-| 1 | Create `anthropic_beta_headers_config.json` with provider-specific mappings | ✅ Done | [`anthropic_beta_headers_config.json`](https://github.com/BerriAI/litellm/blob/main/litellm/anthropic_beta_headers_config.json) |
-| 2 | Implement strict validation: headers must be explicitly mapped to be forwarded | ✅ Done | [`litellm_logging.py`](https://github.com/BerriAI/litellm/blob/main/litellm/litellm_core_utils/litellm_logging.py) |
-| 3 | Add `/reload/anthropic_beta_headers` endpoint for dynamic config updates | ✅ Done | Proxy management endpoints |
-| 4 | Add `/schedule/anthropic_beta_headers_reload` for automatic periodic updates | ✅ Done | Proxy management endpoints |
-| 5 | Support `LITELLM_ANTHROPIC_BETA_HEADERS_URL` for custom config sources | ✅ Done | Environment configuration |
-| 6 | Support `LITELLM_LOCAL_ANTHROPIC_BETA_HEADERS` for air-gapped deployments | ✅ Done | Environment configuration |
-
-Now LiteLLM validates and transforms headers per-provider:
-
-```mermaid
-sequenceDiagram
-    participant CC as Claude Code
-    participant LP as LiteLLM (new behavior)
-    participant Config as Beta Headers Config
-    participant Provider as Provider (Bedrock/Azure/Vertex)
-
-    CC->>LP: Request with beta headers
-    Note over CC,LP: anthropic-beta: header1,header2,header3
-
-    LP->>Config: Load header mapping for provider
-    Config-->>LP: Returns mapping (header→value or null)
-
-    Note over LP: Validate & Transform:<br/>1. Check if header exists in mapping<br/>2. Filter out null values<br/>3. Map to provider-specific names
-
-    LP->>Provider: Request with filtered & mapped headers
-    Note over LP,Provider: anthropic-beta: mapped-header2<br/>(header1, header3 filtered out)
-
-    Provider-->>LP: ✅ Success response
-    LP-->>CC: Response
-```
-
----
-
-## Dynamic configuration updates
-
-A key improvement is zero-downtime configuration updates. When Anthropic releases new beta features, users can update their configuration without restarting:
-
-```bash
-# Manually trigger reload (no restart needed)
-curl -X POST "https://your-proxy-url/reload/anthropic_beta_headers" \
-  -H "Authorization: Bearer YOUR_ADMIN_TOKEN"
-
-# Or schedule automatic reloads every 24 hours
-curl -X POST "https://your-proxy-url/schedule/anthropic_beta_headers_reload?hours=24" \
-  -H "Authorization: Bearer YOUR_ADMIN_TOKEN"
-```
-
-This prevents future incidents where Claude Code introduces new headers before LiteLLM configuration is updated.
-
----
-
-## Configuration format
-
-The `anthropic_beta_headers_config.json` file maps input headers to provider-specific output headers:
-
-```json
-{
-  "description": "Mapping of Anthropic beta headers for each provider.",
-  "anthropic": {
-    "advanced-tool-use-2025-11-20": "advanced-tool-use-2025-11-20",
-    "computer-use-2025-01-24": "computer-use-2025-01-24"
-  },
-  "bedrock_converse": {
-    "advanced-tool-use-2025-11-20": null,
-    "computer-use-2025-01-24": "computer-use-2025-01-24"
-  },
-  "azure_ai": {
-    "advanced-tool-use-2025-11-20": "advanced-tool-use-2025-11-20",
-    "computer-use-2025-01-24": "computer-use-2025-01-24"
-  }
-}
-```
-
-**Validation rules:**
-1. Headers must exist in the mapping for the target provider
-2. Headers with `null` values are filtered out (unsupported)
-3. Header names can be transformed per-provider (e.g., Bedrock uses different names for some features)
-
----
-
-## Resolution steps for users
-
-For users still experiencing issues, update to the latest LiteLLM version if < v1.81.11-nightly:
-
-```bash
-pip install --upgrade litellm
-```
-
-Or manually reload the configuration without restarting:
-
-```bash
-curl -X POST "https://your-proxy-url/reload/anthropic_beta_headers" \
-  -H "Authorization: Bearer YOUR_ADMIN_TOKEN"
-```
-
----
-
-## Related documentation
-
-- [Managing Anthropic Beta Headers](../../docs/proxy/sync_anthropic_beta_headers) - Complete configuration guide
-- [`anthropic_beta_headers_config.json`](https://github.com/BerriAI/litellm/blob/main/litellm/anthropic_beta_headers_config.json) - Current configuration file

docs/my-website/blog/claude_opus_4_6/index.md

@@ -1,723 +0,0 @@
----
-slug: claude_opus_4_6
-title: "Day 0 Support: Claude Opus 4.6"
-date: 2026-02-05T10:00:00
-authors:
-  - sameer
-  - ishaan-alt
-  - krrish
-description: "Day 0 support for Claude Opus 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock."
-tags: [anthropic, claude, opus 4.6]
-hide_table_of_contents: false
----
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-LiteLLM now supports Claude Opus 4.6 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-v1.80.0-stable.opus-4-6
-```
-
-## Usage - Anthropic
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-opus-4-6
-    litellm_params:
-      model: anthropic/claude-opus-4-6
-      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-v1.80.0-stable.opus-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-opus-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Azure
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-opus-4-6
-    litellm_params:
-      model: azure_ai/claude-opus-4-6
-      api_key: os.environ/AZURE_AI_API_KEY
-      api_base: os.environ/AZURE_AI_API_BASE  # https://<resource>.services.ai.azure.com
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e AZURE_AI_API_KEY=$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-v1.80.0-stable.opus-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-opus-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Vertex AI
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-opus-4-6
-    litellm_params:
-      model: vertex_ai/claude-opus-4-6
-      vertex_project: os.environ/VERTEX_PROJECT
-      vertex_location: us-east5
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e VERTEX_PROJECT=$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-v1.80.0-stable.opus-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-opus-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Bedrock
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-opus-4-6
-    litellm_params:
-      model: bedrock/anthropic.claude-opus-4-6-v1
-      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
-      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
-      aws_region_name: us-east-1
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e AWS_ACCESS_KEY_ID=$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-v1.80.0-stable.opus-4-6 \
-  --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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-</Tabs>
-
-## Advanced Features
-
-### Compaction
-
-<Tabs>
-<TabItem value="completions" label="/chat/completions">
-
-Litellm supports enabling compaction for the new claude-opus-4-6.
-
-**Enabling Compaction**
-
-To enable compaction, add the `context_management` parameter with the `compact_20260112` edit type:
-
-```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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "What is the weather in San Francisco?"
-    }
-  ],
-  "context_management": {
-    "edits": [
-      {
-        "type": "compact_20260112"
-      }
-    ]
-  },
-  "max_tokens": 100
-}'
-```
-All the parameters supported for context_management by anthropic are supported and can be directly added. Litellm automatically adds the `compact-2026-01-12` beta header in the request.
-
-</TabItem>
-<TabItem value="messages" label="/v1/messages">
-
-Enable compaction to reduce context size while preserving key information. LiteLLM automatically adds the `compact-2026-01-12` beta header when compaction is enabled.
-
-:::info
-**Provider Support:** Compaction is supported on Anthropic, Azure AI, and Vertex AI. It is **not supported** on Bedrock (Invoke or Converse APIs).
-:::
-
-```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-4-6",
-    "max_tokens": 4096,
-    "messages": [
-        {
-            "role": "user",
-            "content": "Hi"
-        }
-    ],
-    "context_management": {
-        "edits": [
-            {
-                "type": "compact_20260112"
-            }
-        ]
-    }
-}'
-```
-
-</TabItem>
-</Tabs>
-
-
-**Response with Compaction Block**
-
-The response will include the compaction summary in `provider_specific_fields.compaction_blocks`:
-
-```json
-{
-  "id": "chatcmpl-a6c105a3-4b25-419e-9551-c800633b6cb2",
-  "created": 1770357619,
-  "model": "claude-opus-4-6",
-  "object": "chat.completion",
-  "choices": [
-    {
-      "finish_reason": "length",
-      "index": 0,
-      "message": {
-        "content": "I don't have access to real-time data, so I can't provide the current weather in San Francisco. To get up-to-date weather information, I'd recommend checking:\n\n- **Weather websites** like weather.com, accuweather.com, or wunderground.com\n- **Search engines** – just Google \"San Francisco weather\"\n- **Weather apps** on your phone (e.g., Apple Weather, Google Weather)\n- **National",
-        "role": "assistant",
-        "provider_specific_fields": {
-          "compaction_blocks": [
-            {
-              "type": "compaction",
-              "content": "Summary of the conversation: The user requested help building a web scraper..."
-            }
-          ]
-        }
-      }
-    }
-  ],
-  "usage": {
-    "completion_tokens": 100,
-    "prompt_tokens": 86,
-    "total_tokens": 186
-  }
-}
-```
-
-**Using Compaction Blocks in Follow-up Requests**
-
-To continue the conversation with compaction, include the compaction block in the assistant message's `provider_specific_fields`:
-
-```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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "How can I build a web scraper?"
-    },
-    {
-      "role": "assistant",
-      "content": [
-        {
-          "type": "text",
-          "text": "Certainly! To build a basic web scraper, you'll typically use a programming language like Python along with libraries such as `requests` (for fetching web pages) and `BeautifulSoup` (for parsing HTML). Here's a basic example:\n\n```python\nimport requests\nfrom bs4 import BeautifulSoup\n\nurl = 'https://example.com'\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.text, 'html.parser')\n\n# Extract and print all text\ntext = soup.get_text()\nprint(text)\n```\n\nLet me know what you're interested in scraping or if you need help with a specific website!"
-        }
-      ],
-      "provider_specific_fields": {
-        "compaction_blocks": [
-          {
-            "type": "compaction",
-            "content": "Summary of the conversation: The user asked how to build a web scraper, and the assistant gave an overview using Python with requests and BeautifulSoup."
-          }
-        ]
-      }
-    },
-    {
-      "role": "user",
-      "content": "How do I use it to scrape product prices?"
-    }
-  ],
-  "context_management": {
-    "edits": [
-      {
-        "type": "compact_20260112"
-      }
-    ]
-  },
-  "max_tokens": 100
-}'
-```
-
-**Streaming Support**
-
-Compaction blocks are also supported in streaming mode. You'll receive:
-- `compaction_start` event when a compaction block begins
-- `compaction_delta` events with the compaction content
-- The accumulated `compaction_blocks` in `provider_specific_fields`
-
-### Adaptive Thinking
-
-:::note
-When using `reasoning_effort` with Claude Opus 4.6, all values (`low`, `medium`, `high`) are mapped to `thinking: {type: "adaptive"}`. To use explicit thinking budgets with `type: "enabled"`, pass the native `thinking` parameter directly (see "Native thinking param" tab below).
-:::
-
-<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-4-6",
-  "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-4-6",
-    "max_tokens": 16000,
-    "thinking": {
-        "type": "adaptive"
-    },
-    "messages": [
-        {
-            "role": "user",
-            "content": "Explain why the sum of two even numbers is always even."
-        }
-    ]
-}'
-```
-
-</TabItem>
-<TabItem value="native" label="Native thinking param">
-
-Use the `thinking` parameter directly for adaptive thinking via the SDK:
-
-```python
-import litellm
-
-response = litellm.completion(
-  model="anthropic/claude-opus-4-6",
-  messages=[{"role": "user", "content": "Solve this complex problem: What is the optimal strategy for..."}],
-  thinking={"type": "adaptive"},
-)
-```
-
-</TabItem>
-</Tabs>
-
-### Effort Levels
-
-<Tabs>
-<TabItem value="completions" label="/chat/completions">
-
-Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `output_config` 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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "Explain quantum computing"
-    }
-  ],
-  "output_config": {
-        "effort": "medium"
-    }
-}'
-```
-
-You can use reasoning effort plus output_config to have more control on the model.
-
-</TabItem>
-<TabItem value="messages" label="/v1/messages">
-
-Four effort levels available: `low`, `medium`, `high` (default), and `max`. Pass directly via the `output_config` parameter:
-
-```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-4-6",
-    "max_tokens": 4096,
-    "messages": [
-        {
-            "role": "user",
-            "content": "Explain quantum computing"
-        }
-    ],
-    "output_config": {
-        "effort": "medium"
-    }
-}'
-```
-
-</TabItem>
-</Tabs>
-
-### 1M Token Context (Beta)
-
-Opus 4.6 supports 1M token context. Premium pricing applies for prompts exceeding 200k tokens ($10/$37.50 per million input/output tokens). LiteLLM supports cost calculations for 1M token contexts.
-
-<Tabs>
-<TabItem value="completions" label="/chat/completions">
-
-To use the 1M token context window, you need to forward the `anthropic-beta` header from your client to the LLM provider.
-
-**Step 1: Enable header forwarding in your config**
-
-```yaml
-general_settings:
-  forward_client_headers_to_llm_api: true
-```
-
-**Step 2: Send requests with the beta header**
-
-```bash
-curl --location 'http://0.0.0.0:4000/chat/completions' \
---header 'Content-Type: application/json' \
---header 'Authorization: Bearer $LITELLM_KEY' \
---header 'anthropic-beta: context-1m-2025-08-07' \
---data '{
-  "model": "claude-opus-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "Analyze this large document..."
-    }
-  ]
-}'
-```
-
-</TabItem>
-<TabItem value="messages" label="/v1/messages">
-
-To use the 1M token context window, you need to forward the `anthropic-beta` header from your client to the LLM provider.
-
-**Step 1: Enable header forwarding in your config**
-
-```yaml
-general_settings:
-  forward_client_headers_to_llm_api: true
-```
-
-**Step 2: Send requests with the beta header**
-
-```bash
-curl --location 'http://0.0.0.0:4000/v1/messages' \
---header 'x-api-key: sk-12345' \
---header 'anthropic-beta: context-1m-2025-08-07' \
---header 'content-type: application/json' \
---data '{
-    "model": "claude-opus-4-6",
-    "max_tokens": 16000,
-    "messages": [
-        {
-            "role": "user",
-            "content": "Analyze this large document..."
-        }
-    ]
-}'
-```
-
-:::tip
-You can combine multiple beta headers by separating them with commas:
-```bash
---header 'anthropic-beta: context-1m-2025-08-07,compact-2026-01-12'
-```
-:::
-
-</TabItem>
-</Tabs>
-
-### US-Only Inference
-
-Available at 1.1× token pricing. LiteLLM automatically tracks costs for US-only inference.
-
-<Tabs>
-<TabItem value="completions" label="/chat/completions">
-
-Use the `inference_geo` parameter to specify US-only inference:
-
-```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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "What is the capital of France?"
-    }
-  ],
-  "inference_geo": "us"
-}'
-```
-
-LiteLLM will automatically apply the 1.1× pricing multiplier for US-only inference in cost tracking.
-
-</TabItem>
-<TabItem value="messages" label="/v1/messages">
-
-Use the `inference_geo` parameter to specify US-only inference:
-
-```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-4-6",
-    "max_tokens": 4096,
-    "messages": [
-        {
-            "role": "user",
-            "content": "What is the capital of France?"
-        }
-    ],
-    "inference_geo": "us"
-}'
-```
-
-LiteLLM will automatically apply the 1.1× pricing multiplier for US-only inference in cost tracking.
-
-</TabItem>
-</Tabs>
-
-### Fast Mode
-
-:::info
-Fast mode is **only supported on the Anthropic provider** (`anthropic/claude-opus-4-6`). It is not available on Azure AI, Vertex AI, or Bedrock.
-:::
-
-**Pricing:**
-- Standard: $5 input / $25 output per MTok
-- Fast: $30 input / $150 output per MTok (6× premium)
-
-<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-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "Refactor this module..."
-    }
-  ],
-  "max_tokens": 4096,
-  "speed": "fast"
-}'
-```
-
-**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-4-6",
-    messages=[{"role": "user", "content": "Refactor this module..."}],
-    max_tokens=4096,
-    extra_body={"speed": "fast"}
-)
-```
-
-**Using LiteLLM SDK:**
-
-```python
-from litellm import completion
-
-response = completion(
-    model="anthropic/claude-opus-4-6",
-    messages=[{"role": "user", "content": "Refactor this module..."}],
-    max_tokens=4096,
-    speed="fast"
-)
-```
-
-LiteLLM automatically tracks the higher costs for fast mode in usage and cost calculations.
-
-</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-4-6",
-    "max_tokens": 4096,
-    "speed": "fast",
-    "messages": [
-        {
-            "role": "user",
-            "content": "Refactor this module..."
-        }
-    ]
-}'
-```
-
-LiteLLM automatically:
-- Adds the `fast-mode-2026-02-01` beta header
-- Tracks the 6× premium pricing in cost calculations
-
-</TabItem>
-</Tabs>

docs/my-website/blog/claude_sonnet_4_6/index.md

@@ -1,279 +0,0 @@
----
-slug: claude_sonnet_4_6
-title: "Day 0 Support: Claude Sonnet 4.6"
-date: 2026-02-17T10:00:00
-authors:
-  - ishaan-alt
-  - krrish
-description: "Day 0 support for Claude Sonnet 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock."
-tags: [anthropic, claude, sonnet 4.6]
-hide_table_of_contents: false
----
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-LiteLLM now supports Claude Sonnet 4.6 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:v1.81.3-stable.sonnet-4-6
-```
-
-## Usage - Anthropic
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-sonnet-4-6
-    litellm_params:
-      model: anthropic/claude-sonnet-4-6
-      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:v1.81.3-stable.sonnet-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-sonnet-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-
-<TabItem value="sdk" label="LiteLLM SDK">
-
-```python
-from litellm import completion
-
-response = completion(
-    model="anthropic/claude-sonnet-4-6",
-    messages=[{"role": "user", "content": "what llm are you"}]
-)
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Azure
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-sonnet-4-6
-    litellm_params:
-      model: azure_ai/claude-sonnet-4-6
-      api_key: os.environ/AZURE_AI_API_KEY
-      api_base: os.environ/AZURE_AI_API_BASE  # https://<resource>.services.ai.azure.com
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e AZURE_AI_API_KEY=$AZURE_AI_API_KEY \
-  -e AZURE_AI_API_BASE=$AZURE_AI_API_BASE \
-  -v $(pwd)/config.yaml:/app/config.yaml \
-  ghcr.io/berriai/litellm:v1.81.3-stable.sonnet-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-sonnet-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-
-<TabItem value="sdk" label="LiteLLM SDK">
-
-```python
-from litellm import completion
-
-response = completion(
-    model="azure_ai/claude-sonnet-4-6",
-    api_key="your-azure-api-key",
-    api_base="https://<resource>.services.ai.azure.com",
-    messages=[{"role": "user", "content": "what llm are you"}]
-)
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Vertex AI
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-sonnet-4-6
-    litellm_params:
-      model: vertex_ai/claude-sonnet-4-6
-      vertex_project: os.environ/VERTEX_PROJECT
-      vertex_location: us-east5
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e VERTEX_PROJECT=$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:v1.81.3-stable.sonnet-4-6 \
-  --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 $LITELLM_KEY' \
---data '{
-  "model": "claude-sonnet-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-
-<TabItem value="sdk" label="LiteLLM SDK">
-
-```python
-from litellm import completion
-
-response = completion(
-    model="vertex_ai/claude-sonnet-4-6",
-    vertex_project="your-project-id",
-    vertex_location="us-east5",
-    messages=[{"role": "user", "content": "what llm are you"}]
-)
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-</Tabs>
-
-## Usage - Bedrock
-
-<Tabs>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: claude-sonnet-4-6
-    litellm_params:
-      model: bedrock/anthropic.claude-sonnet-4-6-v1
-      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
-      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
-      aws_region_name: us-east-1
-```
-
-**2. Start the proxy**
-
-```bash
-docker run -d \
-  -p 4000:4000 \
-  -e AWS_ACCESS_KEY_ID=$AWS_ACCESS_KEY_ID \
-  -e AWS_SECRET_ACCESS_KEY=$AWS_SECRET_ACCESS_KEY \
-  -v $(pwd)/config.yaml:/app/config.yaml \
-  ghcr.io/berriai/litellm:v1.81.3-stable.sonnet-4-6 \
-  --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-sonnet-4-6",
-  "messages": [
-    {
-      "role": "user",
-      "content": "what llm are you"
-    }
-  ]
-}'
-```
-
-</TabItem>
-
-<TabItem value="sdk" label="LiteLLM SDK">
-
-```python
-from litellm import completion
-
-response = completion(
-    model="bedrock/anthropic.claude-sonnet-4-6-v1",
-    aws_access_key_id="your-access-key",
-    aws_secret_access_key="your-secret-key",
-    aws_region_name="us-east-1",
-    messages=[{"role": "user", "content": "what llm are you"}]
-)
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-</Tabs>

docs/my-website/blog/fastapi_middleware_performance/index.mdx

@@ -1,211 +0,0 @@
----
-slug: fastapi-middleware-performance
-title: "Your Middleware Could Be a Bottleneck"
-date: 2026-02-07T10:00:00
-authors:
-  - krrish
-  - ishaan-alt
-  - ryan
-description: "How we improved LiteLLM proxy latency and throughput by replacing a single middleware base class"
-tags: [performance, fastapi, middleware]
-hide_table_of_contents: false
----
-
-import { BaseHTTPMiddlewareAnimation, PureASGIAnimation, BenchmarkVisualization } from '@site/src/components/MiddlewareDiagrams';
-
-> How we improved LiteLLM proxy latency and throughput by replacing a single, simple middleware base class
-
----
-
-## Our Setup
-
-The LiteLLM proxy server has two middleware layers. The first is Starlette's `CORSMiddleware` (re-exported by FastAPI), which is a pure ASGI middleware. Then we have a simple BaseHTTPMiddleware called PrometheusAuthMiddleware.
-
-The job of `PrometheusAuthMiddleware` is to authenticate requests to the `/metrics` endpoint. It's not on by default, you enable it with a flag in your proxy config:
-
-<details>
-<summary>Proxy config flag</summary>
-
-```yaml
-litellm_settings:
-    require_auth_for_metrics_endpoint: true
-```
-
-</details>
-
-The middleware checks two things: is the request hitting `/metrics`, and is auth even enabled? If both checks fail, which they do for the vast majority of requests, it just passes the request through unchanged.
-
-<details>
-<summary>PrometheusAuthMiddleware source</summary>
-
-```python
-class PrometheusAuthMiddleware(BaseHTTPMiddleware):
-    async def dispatch(self, request: Request, call_next):
-        if self._is_prometheus_metrics_endpoint(request):
-            if self._should_run_auth_on_metrics_endpoint() is True:
-                try:
-                    await user_api_key_auth(request=request, api_key=...)
-                except Exception as e:
-                    return JSONResponse(status_code=401, content=...)
-        response = await call_next(request)
-        return response
-
-    @staticmethod
-    def _is_prometheus_metrics_endpoint(request: Request):
-        if "/metrics" in request.url.path:
-            return True
-        return False
-```
-
-</details>
-
-Looks harmless. Subclass `BaseHTTPMiddleware`, implement `dispatch()`, done. This is what you will see in Starlette's documentation<sup>[1](#footnote-1)</sup>.
-
-{/* truncate */}
-
----
-
-## What BaseHTTPMiddleware Actually Does
-
-When you write a `dispatch()` method, you'd expect the request to flow straight through your function and out the other side. What actually happens is much more involved. 
-
-On every request, even a pure passthrough (meaning nothing happens), `BaseHTTPMiddleware` creates **7 intermediate objects and tasks**:
-
-<BaseHTTPMiddlewareAnimation />
-
-It wraps the request in a new object to track body state, creates a synchronization event, allocates an in-memory channel to pass messages between your middleware and the inner app, sets up a task group to manage the lifecycle, and then runs your actual route handler in a *separate background task* when you call `call_next()`. The response body then flows back through that in-memory channel, gets re-wrapped in a streaming response object, and finally reaches the caller. That's a lot.
-
-For a middleware that for us, does nothing on 99.9% of requests, paying this cost doesn't make sense.
-
-Compare that to a pure ASGI middleware, which we can have just check the request path and continue along. 
-
-<PureASGIAnimation />
-
-Our middleware is doing something really simple. For the vast majority of requests it doesn't need to do anything at all but just let the request pass through. It doesn't need task groups, memory streams, or cancel scopes. It needs a function call.
-
----
-
-## Comparing Both
-
-We replaced the `BaseHTTPMiddleware` subclass with a pure ASGI middleware. To benchmark the difference, we used Apache Bench<sup>[2](#footnote-2)</sup> to compare both configurations of LiteLLM's middleware stack: the old setup (1 pure ASGI + 1 `BaseHTTPMiddleware`) against the new setup (2 pure ASGI).
-
-A minimal FastAPI app serves `GET /health` → `PlainTextResponse("ok")`. The endpoint does zero work to isolate the middleware overhead: any difference between configs is purely the cost of the middleware plumbing itself. Both middlewares are just calling the next layer. Same work, different base class.
-
-Apache Bench (`ab`) fires requests at the server with 1,000 concurrent connections and a single uvicorn worker. One worker means one event loop, so the benchmark directly measures how each middleware design handles concurrent load on a single thread.
-
-<BenchmarkVisualization />
-
-<details>
-<summary>Try it yourself</summary>
-
-Save the script below as `benchmark_middleware.py`, then run:
-
-```bash
-# Terminal 1 — start the "before" server (1 ASGI + 1 BaseHTTPMiddleware)
-python benchmark_middleware.py --middleware mixed
-
-# Terminal 2 — benchmark it
-ab -n 50000 -c 1000 http://localhost:8000/health
-
-# Stop the server, then start the "after" server (2x pure ASGI)
-python benchmark_middleware.py --middleware asgi
-
-# Terminal 2 — benchmark again
-ab -n 50000 -c 1000 http://localhost:8000/health
-```
-
-```python
-import argparse
-import uvicorn
-from fastapi import FastAPI
-from fastapi.responses import PlainTextResponse
-from starlette.middleware.base import BaseHTTPMiddleware
-from starlette.requests import Request
-from starlette.types import ASGIApp, Receive, Scope, Send
-
-
-class NoOpBaseHTTPMiddleware(BaseHTTPMiddleware):
-    async def dispatch(self, request: Request, call_next):
-        return await call_next(request)
-
-
-class NoOpPureASGIMiddleware:
-    def __init__(self, app: ASGIApp) -> None:
-        self.app = app
-
-    async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
-        await self.app(scope, receive, send)
-
-
-def create_app(middleware_type: str | None = None, layers: int = 2) -> FastAPI:
-    app = FastAPI()
-
-    @app.get("/health")
-    async def health():
-        return PlainTextResponse("ok")
-
-    if middleware_type == "mixed":
-        app.add_middleware(NoOpBaseHTTPMiddleware)
-        app.add_middleware(NoOpPureASGIMiddleware)
-    elif middleware_type == "asgi":
-        for _ in range(layers):
-            app.add_middleware(NoOpPureASGIMiddleware)
-
-    return app
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser()
-    parser.add_argument("--middleware", choices=["asgi", "mixed"], default=None)
-    parser.add_argument("--layers", type=int, default=2)
-    parser.add_argument("--port", type=int, default=8000)
-    args = parser.parse_args()
-
-    app = create_app(middleware_type=args.middleware, layers=args.layers)
-    uvicorn.run(app, host="0.0.0.0", port=args.port, workers=1, log_level="warning")
-```
-
-</details>
-
----
-
-## Our Change
-
-Here's what we replaced it with:
-
-```python
-class PrometheusAuthMiddleware:
-    def __init__(self, app: ASGIApp) -> None:
-        self.app = app
-
-    async def __call__(self, scope: Scope, receive: Receive, send: Send) -> None:
-        if scope["type"] != "http" or "/metrics" not in scope.get("path", ""):
-            await self.app(scope, receive, send)
-            return
-
-        if litellm.require_auth_for_metrics_endpoint is True:
-            request = Request(scope, receive)
-            api_key = request.headers.get("Authorization") or ""
-            try:
-                await user_api_key_auth(request=request, api_key=api_key)
-            except Exception as e:
-                # send 401 directly via ASGI protocol
-                ...
-                return
-
-        await self.app(scope, receive, send)
-```
-
-For the 99.9% of requests that aren't hitting `/metrics`, the middleware is now one dict lookup, one string check, and one function call. No objects allocated, no tasks spawned. 
-
-It's important to evaluate if the tools you're using are the right fit for the job as your software grows and handles more responsiblity. We're now putting in a static analysis check to prevent this from happening again with any newly introduced middlewares. If we find the use case is necessary then that's okay and we'll reevalute but for everything LiteLLM needs to do at the moment it's not. 
-
-This middleware change was one part of a broader optimization effort on the LiteLLM proxy. Across all optimizations combined, we've measured about a **30% reduction in proxy overhead** over the past two weeks. 
-
----
-
-<a id="footnote-1"></a>
-<sup>1</sup> [Starlette Middleware — BaseHTTPMiddleware](https://starlette.dev/middleware/#basehttpmiddleware)
-
-<a id="footnote-2"></a>
-<sup>2</sup> [Apache HTTP server benchmarking tool (`ab`)](https://httpd.apache.org/docs/2.4/programs/ab.html)

docs/my-website/blog/gemin_3.1/index.md

@@ -1,142 +0,0 @@
----
-slug: gemini_3_1_pro
-title: "DAY 0 Support: Gemini 3.1 Pro on LiteLLM"
-date: 2026-02-19T10:00:00
-authors:
-  - sameer
-  - krrish
-  - ishaan-alt
-description: "Guide to using Gemini 3.1 Pro on LiteLLM Proxy and SDK with day 0 support."
-tags: [gemini, day 0 support, llms]
-hide_table_of_contents: false
----
-
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-# Gemini 3.1 Pro Day 0 Support 
-
-LiteLLM now supports `gemini-3.1-pro-preview` and all the new API changes along with it.
-
-{/* truncate */}
-
-## Deploy this version
-
-<Tabs>
-<TabItem value="docker" label="Docker">
-
-``` showLineNumbers title="docker run litellm"
-docker run \
--e STORE_MODEL_IN_DB=True \
--p 4000:4000 \
-ghcr.io/berriai/litellm:main-v1.81.9-stable.gemini.3.1-pro
-```
-
-</TabItem>
-
-<TabItem value="pip" label="Pip">
-
-``` showLineNumbers title="pip install litellm"
-pip install litellm==v1.81.9-stable.gemini.3.1-pro
-```
-
-</TabItem>
-</Tabs>
-
-## What's New
-
-### 1. New Thinking Levels: `thinkingLevel` with MINIMAL & MEDIUM
-
-Gemini 3.1 Pro introduces support for **medium** thinking level
-
-LiteLLM automatically maps the OpenAI `reasoning_effort` parameter to Gemini's `thinkingLevel`, so you can use familiar `reasoning_effort` values (`minimal`, `low`, `medium`, `high`) without changing your code!
-
----
-## Supported Endpoints
-
-LiteLLM provides **full end-to-end support** for Gemini 3.1 Pro on:
-
-- ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
-- ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
-- ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
-
-All endpoints support:
-- Streaming and non-streaming responses
-- Function calling with thought signatures
-- Multi-turn conversations
-- All Gemini 3-specific features
-- Conversion of provider specific thinking related param to thinkingLevel
-
-## Quick Start
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-**Basic Usage with MEDIUM thinking (NEW)**
-
-```python
-from litellm import completion
-
-# No need to make any changes to your code as we map openai reasoning param to thinkingLevel
-response = completion(
-    model="gemini/gemini-3.1-pro-preview",
-    messages=[{"role": "user", "content": "Solve this complex math problem: 25 * 4 + 10"}],
-    reasoning_effort="medium",  # NEW: MEDIUM thinking level
-)
-
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-
-<TabItem value="proxy" label="PROXY">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: gemini-3.1-pro-preview
-    litellm_params:
-      model: gemini/gemini-3.1-pro-preview
-      api_key: os.environ/GEMINI_API_KEY
-  - model_name: vertex-gemini-3.1-pro-preview
-    litellm_params:
-      model: vertex_ai/gemini-3.1-pro-preview
-```
-
-**2. Start proxy**
-
-```bash
-litellm --config /path/to/config.yaml
-```
-
-**3. Call with MEDIUM thinking**
-
-```bash
-curl -X POST http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
-  -d '{
-    "model": "gemini-3.1-pro-preview",
-    "messages": [{"role": "user", "content": "Complex reasoning task"}],
-    "reasoning_effort": "medium"
-  }'
-```
-
-</TabItem>
-</Tabs>
-
----
-
-## `reasoning_effort` Mapping for Gemini 3+
-
-| reasoning_effort | thinking_level | 
-|------------------|----------------|
-| `minimal` | `minimal` |
-| `low` | `low` |
-| `medium` | `medium` |
-| `high` | `high` |
-| `disable` | `minimal` |
-| `none` | `minimal` |

docs/my-website/blog/gemini_3/index.md

@@ -1,975 +0,0 @@
----
-slug: gemini_3
-title: "DAY 0 Support: Gemini 3 on LiteLLM"
-date: 2025-11-19T10:00:00
-authors:
-  - sameer
-  - krrish
-  - ishaan-alt
-description: "Common questions and best practices for using gemini-3-pro-preview with LiteLLM Proxy and SDK."
-tags: [gemini, day 0 support, llms]
-hide_table_of_contents: false
----
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-:::info
-
-This guide covers common questions and best practices for using `gemini-3-pro-preview` with LiteLLM Proxy and SDK.
-
-:::
-
-{/* truncate */}
-
-## Quick Start
-
-<Tabs>
-<TabItem value="sdk" label="Python SDK">
-
-```python
-from litellm import completion
-import os
-
-os.environ["GEMINI_API_KEY"] = "your-api-key"
-
-response = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "Hello!"}],
-    reasoning_effort="low"
-)
-
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-**1. Add to config.yaml:**
-
-```yaml
-model_list:
-  - model_name: gemini-3-pro-preview
-    litellm_params:
-      model: gemini/gemini-3-pro-preview
-      api_key: os.environ/GEMINI_API_KEY
-```
-
-**2. Start proxy:**
-
-```bash
-litellm --config /path/to/config.yaml
-```
-
-**3. Make request:**
-
-```bash
-curl http://0.0.0.0:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",
-    "messages": [{"role": "user", "content": "Hello!"}],
-    "reasoning_effort": "low"
-  }'
-```
-
-</TabItem>
-</Tabs>
-
-## Supported Endpoints
-
-LiteLLM provides **full end-to-end support** for Gemini 3 Pro Preview on:
-
-- ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
-- ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
-- ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](https://cloud.google.com/vertex-ai/docs/generative-ai/model-reference/gemini#rest) compatible endpoint (for code, see: `client.models.generate_content(...)`)
-
-All endpoints support:
-- Streaming and non-streaming responses
-- Function calling with thought signatures
-- Multi-turn conversations
-- All Gemini 3-specific features
-
-## Thought Signatures
-
-#### What are Thought Signatures?
-
-Thought signatures are encrypted representations of the model's internal reasoning process. They're essential for maintaining context across multi-turn conversations, especially with function calling.
-
-#### How Thought Signatures Work
-
-1. **Automatic Extraction**: When Gemini 3 returns a function call, LiteLLM automatically extracts the `thought_signature` from the response
-2. **Storage**: Thought signatures are stored in `provider_specific_fields.thought_signature` of tool calls
-3. **Automatic Preservation**: When you include the assistant's message in conversation history, LiteLLM automatically preserves and returns thought signatures to Gemini
-
-## Example: Multi-Turn Function Calling
-
-#### Streaming with Thought Signatures
-
-When using streaming mode with `stream_chunk_builder()`, thought signatures are now automatically preserved:
-
-<Tabs>
-<TabItem value="streaming" label="Streaming SDK">
-
-```python
-import os
-import litellm
-from litellm import completion
-
-os.environ["GEMINI_API_KEY"] = "your-api-key"
-
-MODEL = "gemini/gemini-3-pro-preview"
-
-messages = [
-    {"role": "system", "content": "You are a helpful assistant. Use the calculate tool."},
-    {"role": "user", "content": "What is 2+2?"},
-]
-
-tools = [{
-    "type": "function",
-    "function": {
-        "name": "calculate",
-        "description": "Calculate a mathematical expression",
-        "parameters": {
-            "type": "object",
-            "properties": {"expression": {"type": "string"}},
-            "required": ["expression"],
-        },
-    },
-}]
-
-print("Step 1: Sending request with stream=True...")
-response = completion(
-    model=MODEL,
-    messages=messages,
-    stream=True,
-    tools=tools,
-    reasoning_effort="low"
-)
-
-# Collect all chunks
-chunks = []
-for part in response:
-    chunks.append(part)
-
-# Reconstruct message using stream_chunk_builder
-# Thought signatures are now preserved automatically!
-full_response = litellm.stream_chunk_builder(chunks, messages=messages)
-print(f"Full response: {full_response}")
-
-assistant_msg = full_response.choices[0].message
-
-# ✅ Thought signature is now preserved in provider_specific_fields
-if assistant_msg.tool_calls and assistant_msg.tool_calls[0].provider_specific_fields:
-    thought_sig = assistant_msg.tool_calls[0].provider_specific_fields.get("thought_signature")
-    print(f"Thought signature preserved: {thought_sig is not None}")
-
-# Append assistant message (includes thought signatures automatically)
-messages.append(assistant_msg)
-
-# Mock tool execution
-messages.append({
-    "role": "tool",
-    "content": "4",
-    "tool_call_id": assistant_msg.tool_calls[0].id
-})
-
-print("\nStep 2: Sending tool result back to model...")
-response_2 = completion(
-    model=MODEL,
-    messages=messages,
-    stream=True,
-    tools=tools,
-    reasoning_effort="low"
-)
-
-for part in response_2:
-    if part.choices[0].delta.content:
-        print(part.choices[0].delta.content, end="")
-print()  # New line
-```
-
-**Key Points:**
-- ✅ `stream_chunk_builder()` now preserves `provider_specific_fields` including thought signatures
-- ✅ Thought signatures are automatically included when appending `assistant_msg` to conversation history
-- ✅ Multi-turn conversations work seamlessly with streaming
-
-</TabItem>
-<TabItem value="sdk" label="Non-Streaming SDK">
-
-```python
-from openai import OpenAI
-import json
-
-client = OpenAI(api_key="sk-1234", base_url="http://localhost:4000")
-
-# Define tools
-tools = [
-    {
-        "type": "function",
-        "function": {
-            "name": "get_weather",
-            "description": "Get the current weather",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "location": {"type": "string"}
-                },
-                "required": ["location"]
-            }
-        }
-    }
-]
-
-# Step 1: Initial request
-messages = [{"role": "user", "content": "What's the weather in Tokyo?"}]
-
-response = client.chat.completions.create(
-    model="gemini-3-pro-preview",
-    messages=messages,
-    tools=tools,
-    reasoning_effort="low"
-)
-
-# Step 2: Append assistant message (thought signatures automatically preserved)
-messages.append(response.choices[0].message)
-
-# Step 3: Execute tool and append result
-for tool_call in response.choices[0].message.tool_calls:
-    if tool_call.function.name == "get_weather":
-        result = {"temperature": 30, "unit": "celsius"}
-        messages.append({
-            "role": "tool",
-            "content": json.dumps(result),
-            "tool_call_id": tool_call.id
-        })
-
-# Step 4: Follow-up request (thought signatures automatically included)
-response2 = client.chat.completions.create(
-    model="gemini-3-pro-preview",
-    messages=messages,
-    tools=tools,
-    reasoning_effort="low"
-)
-
-print(response2.choices[0].message.content)
-```
-
-**Key Points:**
-- ✅ Thought signatures are automatically extracted from `response.choices[0].message.tool_calls[].provider_specific_fields.thought_signature`
-- ✅ When you append `response.choices[0].message` to your conversation history, thought signatures are automatically preserved
-- ✅ You don't need to manually extract or manage thought signatures
-
-</TabItem>
-<TabItem value="proxy" label="cURL">
-
-```bash
-# Step 1: Initial request
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",
-    "messages": [
-      {"role": "user", "content": "What'\''s the weather in Tokyo?"}
-    ],
-    "tools": [
-      {
-        "type": "function",
-        "function": {
-          "name": "get_weather",
-          "description": "Get the current weather",
-          "parameters": {
-            "type": "object",
-            "properties": {
-              "location": {"type": "string"}
-            },
-            "required": ["location"]
-          }
-        }
-      }
-    ],
-    "reasoning_effort": "low"
-  }'
-```
-
-**Response includes thought signature:**
-
-```json
-{
-  "choices": [{
-    "message": {
-      "role": "assistant",
-      "tool_calls": [{
-        "id": "call_abc123",
-        "type": "function",
-        "function": {
-          "name": "get_weather",
-          "arguments": "{\"location\": \"Tokyo\"}"
-        },
-        "provider_specific_fields": {
-          "thought_signature": "CpcHAdHtim9+q4rstcbvQC0ic4x1/vqQlCJWgE+UZ6dTLYGHMMBkF/AxqL5UmP6SY46uYC8t4BTFiXG5zkw6EMJ..."
-        }
-      }]
-    }
-  }]
-}
-```
-
-```bash
-# Step 2: Follow-up request (include assistant message with thought signature)
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",
-    "messages": [
-      {"role": "user", "content": "What'\''s the weather in Tokyo?"},
-      {
-        "role": "assistant",
-        "content": null,
-        "tool_calls": [{
-          "id": "call_abc123",
-          "type": "function",
-          "function": {
-            "name": "get_weather",
-            "arguments": "{\"location\": \"Tokyo\"}"
-          },
-          "provider_specific_fields": {
-            "thought_signature": "CpcHAdHtim9+q4rstcbvQC0ic4x1/vqQlCJWgE+UZ6dTLYGHMMBkF/AxqL5UmP6SY46uYC8t4BTFiXG5zkw6EMJ..."
-          }
-        }]
-      },
-      {
-        "role": "tool",
-        "content": "{\"temperature\": 30, \"unit\": \"celsius\"}",
-        "tool_call_id": "call_abc123"
-      }
-    ],
-    "tools": [...],
-    "reasoning_effort": "low"
-  }'
-```
-
-</TabItem>
-</Tabs>
-
-#### Important Notes on Thought Signatures
-
-1. **Automatic Handling**: LiteLLM automatically extracts and preserves thought signatures. You don't need to manually manage them.
-
-2. **Parallel Function Calls**: When the model makes parallel function calls, only the **first function call** has a thought signature.
-
-3. **Sequential Function Calls**: In multi-step function calling, each step's first function call has its own thought signature that must be preserved.
-
-4. **Required for Context**: Thought signatures are essential for maintaining reasoning context. Without them, the model may lose context of its previous reasoning.
-
-## Conversation History: Switching from Non-Gemini-3 Models
-
-#### Common Question: Will switching from a non-Gemini-3 model to Gemini-3 break conversation history?
-
-**Answer: No!** LiteLLM automatically handles this by adding dummy thought signatures when needed.
-
-#### How It Works
-
-When you switch from a model that doesn't use thought signatures (e.g., `gemini-2.5-flash`) to Gemini 3, LiteLLM:
-
-1. **Detects missing signatures**: Identifies assistant messages with tool calls that lack thought signatures
-2. **Adds dummy signature**: Automatically injects a dummy thought signature (`skip_thought_signature_validator`) for compatibility
-3. **Maintains conversation flow**: Your conversation history continues to work seamlessly
-
-#### Example: Switching Models Mid-Conversation
-
-<Tabs>
-<TabItem value="sdk" label="Python SDK">
-
-```python
-from openai import OpenAI
-
-client = OpenAI(api_key="sk-1234", base_url="http://localhost:4000")
-
-# Step 1: Start with gemini-2.5-flash (no thought signatures)
-messages = [{"role": "user", "content": "What's the weather?"}]
-
-response1 = client.chat.completions.create(
-    model="gemini-2.5-flash",
-    messages=messages,
-    tools=[...],
-    reasoning_effort="low"
-)
-
-# Append assistant message (no tool call thought signature from gemini-2.5-flash)
-messages.append(response1.choices[0].message)
-
-# Step 2: Switch to gemini-3-pro-preview
-# LiteLLM automatically adds dummy thought signature to the previous assistant message
-response2 = client.chat.completions.create(
-    model="gemini-3-pro-preview",  # 👈 Switched model
-    messages=messages,  # 👈 Same conversation history
-    tools=[...],
-    reasoning_effort="low"
-)
-
-# ✅ Works seamlessly! No errors, no breaking changes
-print(response2.choices[0].message.content)
-```
-
-</TabItem>
-<TabItem value="proxy" label="cURL">
-
-```bash
-# Step 1: Start with gemini-2.5-flash
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-2.5-flash",
-    "messages": [{"role": "user", "content": "What'\''s the weather?"}],
-    "tools": [...],
-    "reasoning_effort": "low"
-  }'
-
-# Step 2: Switch to gemini-3-pro-preview with same conversation history
-# LiteLLM automatically handles the missing thought signature
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",  # 👈 Switched model
-    "messages": [
-      {"role": "user", "content": "What'\''s the weather?"},
-      {
-        "role": "assistant",
-        "tool_calls": [...]  # 👈 No thought_signature from gemini-2.5-flash
-      }
-    ],
-    "tools": [...],
-    "reasoning_effort": "low"
-  }'
-# ✅ Works! LiteLLM adds dummy signature automatically
-```
-
-</TabItem>
-</Tabs>
-
-#### Dummy Signature Details
-
-The dummy signature used is: `base64("skip_thought_signature_validator")`
-
-This is the recommended approach by Google for handling conversation history from models that don't support thought signatures. It allows Gemini 3 to:
-- Accept the conversation history without validation errors
-- Continue the conversation seamlessly
-- Maintain context across model switches
-
-## Thinking Level Parameter
-
-#### How `reasoning_effort` Maps to `thinking_level`
-
-For Gemini 3 Pro Preview, LiteLLM automatically maps `reasoning_effort` to the new `thinking_level` parameter:
-
-| `reasoning_effort` | `thinking_level` | Notes |
-|-------------------|------------------|-------|
-| `"minimal"` | `"low"` | Maps to low thinking level |
-| `"low"` | `"low"` | Default for most use cases |
-| `"medium"` | `"high"` | Medium not available yet, maps to high |
-| `"high"` | `"high"` | Maximum reasoning depth |
-| `"disable"` | `"low"` | Gemini 3 cannot fully disable thinking |
-| `"none"` | `"low"` | Gemini 3 cannot fully disable thinking |
-
-#### Default Behavior
-
-If you don't specify `reasoning_effort`, LiteLLM automatically sets `thinking_level="low"` for Gemini 3 models, to avoid high costs. 
-
-### Example Usage
-
-<Tabs>
-<TabItem value="sdk" label="Python SDK">
-
-```python
-from litellm import completion
-
-# Low thinking level (faster, lower cost)
-response = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "What's the weather?"}],
-    reasoning_effort="low"  # Maps to thinking_level="low"
-)
-
-# High thinking level (deeper reasoning, higher cost)
-response = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "Solve this complex math problem step by step."}],
-    reasoning_effort="high"  # Maps to thinking_level="high"
-)
-```
-
-</TabItem>
-<TabItem value="proxy" label="LiteLLM Proxy">
-
-```bash
-# Low thinking level
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",
-    "messages": [{"role": "user", "content": "What'\''s the weather?"}],
-    "reasoning_effort": "low"
-  }'
-
-# High thinking level
-curl http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer sk-1234" \
-  -d '{
-    "model": "gemini-3-pro-preview",
-    "messages": [{"role": "user", "content": "Solve this complex problem."}],
-    "reasoning_effort": "high"
-  }'
-```
-
-</TabItem>
-</Tabs>
-
-## Important Notes
-
-1. **Gemini 3 Cannot Disable Thinking**: Unlike Gemini 2.5 models, Gemini 3 cannot fully disable thinking. Even when you set `reasoning_effort="none"` or `"disable"`, it maps to `thinking_level="low"`.
-
-2. **Temperature Recommendation**: For Gemini 3 models, LiteLLM defaults `temperature` to `1.0` and strongly recommends keeping it at this default. Setting `temperature < 1.0` can cause:
-   - Infinite loops
-   - Degraded reasoning performance
-   - Failure on complex tasks
-
-3. **Automatic Defaults**: If you don't specify `reasoning_effort`, LiteLLM automatically sets `thinking_level="low"` for optimal performance.
-
-## Cost Tracking: Prompt Caching & Context Window
-
-LiteLLM provides comprehensive cost tracking for Gemini 3 Pro Preview, including support for prompt caching and tiered pricing based on context window size.
-
-### Prompt Caching Cost Tracking
-
-Gemini 3 supports prompt caching, which allows you to cache frequently used prompt prefixes to reduce costs. LiteLLM automatically tracks and calculates costs for:
-
-- **Cache Hit Tokens**: Tokens that are read from cache (charged at a lower rate)
-- **Cache Creation Tokens**: Tokens that are written to cache (one-time cost)
-- **Text Tokens**: Regular prompt tokens that are processed normally
-
-#### How It Works
-
-LiteLLM extracts caching information from the `prompt_tokens_details` field in the usage object:
-
-```python
-{
-  "usage": {
-    "prompt_tokens": 50000,
-    "completion_tokens": 1000,
-    "total_tokens": 51000,
-    "prompt_tokens_details": {
-      "cached_tokens": 30000,  # Cache hit tokens
-      "cache_creation_tokens": 5000,  # Tokens written to cache
-      "text_tokens": 15000  # Regular processed tokens
-    }
-  }
-}
-```
-
-### Context Window Tiered Pricing
-
-Gemini 3 Pro Preview supports up to 1M tokens of context, with tiered pricing that automatically applies when your prompt exceeds 200k tokens.
-
-#### Automatic Tier Detection
-
-LiteLLM automatically detects when your prompt exceeds the 200k token threshold and applies the appropriate tiered pricing:
-
-```python
-from litellm import completion_cost
-
-# Example: Small prompt (< 200k tokens)
-response_small = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "Hello!"}]
-)
-# Uses base pricing: $0.000002/input token, $0.000012/output token
-
-# Example: Large prompt (> 200k tokens)
-response_large = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "..." * 250000}]  # 250k tokens
-)
-# Automatically uses tiered pricing: $0.000004/input token, $0.000018/output token
-```
-
-#### Cost Breakdown
-
-The cost calculation includes:
-
-1. **Text Processing Cost**: Regular tokens processed at base or tiered rate
-2. **Cache Read Cost**: Cached tokens read at discounted rate
-3. **Cache Creation Cost**: One-time cost for writing tokens to cache (applies tiered rate if above 200k)
-4. **Output Cost**: Generated tokens at base or tiered rate
-
-### Example: Viewing Cost Breakdown
-
-You can view the detailed cost breakdown using LiteLLM's cost tracking:
-
-```python
-from litellm import completion, completion_cost
-
-response = completion(
-    model="gemini/gemini-3-pro-preview",
-    messages=[{"role": "user", "content": "Explain prompt caching"}],
-    caching=True  # Enable prompt caching
-)
-
-# Get total cost
-total_cost = completion_cost(completion_response=response)
-print(f"Total cost: ${total_cost:.6f}")
-
-# Access usage details
-usage = response.usage
-print(f"Prompt tokens: {usage.prompt_tokens}")
-print(f"Completion tokens: {usage.completion_tokens}")
-
-# Access caching details
-if usage.prompt_tokens_details:
-    print(f"Cache hit tokens: {usage.prompt_tokens_details.cached_tokens}")
-    print(f"Cache creation tokens: {usage.prompt_tokens_details.cache_creation_tokens}")
-    print(f"Text tokens: {usage.prompt_tokens_details.text_tokens}")
-```
-
-### Cost Optimization Tips
-
-1. **Use Prompt Caching**: For repeated prompt prefixes, enable caching to reduce costs by up to 90% for cached portions
-2. **Monitor Context Size**: Be aware that prompts above 200k tokens use tiered pricing (2x for input, 1.5x for output)
-3. **Cache Management**: Cache creation tokens are charged once when writing to cache, then subsequent reads are much cheaper
-4. **Track Usage**: Use LiteLLM's built-in cost tracking to monitor spending across different token types
-
-### Integration with LiteLLM Proxy
-
-When using LiteLLM Proxy, all cost tracking is automatically logged and available through:
-
-- **Usage Logs**: Detailed token and cost breakdowns in proxy logs
-- **Budget Management**: Set budgets and alerts based on actual usage
-- **Analytics Dashboard**: View cost trends and breakdowns by token type
-
-```yaml
-# config.yaml
-model_list:
-  - model_name: gemini-3-pro-preview
-    litellm_params:
-      model: gemini/gemini-3-pro-preview
-      api_key: os.environ/GEMINI_API_KEY
-
-litellm_settings:
-  # Enable detailed cost tracking
-  success_callback: ["langfuse"]  # or your preferred logging service
-```
-
-## Using with Claude Code CLI
-
-You can use `gemini-3-pro-preview` with **Claude Code CLI** - Anthropic's command-line interface. This allows you to use Gemini 3 Pro Preview with Claude Code's native syntax and workflows.
-
-### Setup
-
-**1. Add Gemini 3 Pro Preview to your `config.yaml`:**
-
-```yaml
-model_list:
-  - model_name: gemini-3-pro-preview
-    litellm_params:
-      model: gemini/gemini-3-pro-preview
-      api_key: os.environ/GEMINI_API_KEY
-
-litellm_settings:
-  master_key: os.environ/LITELLM_MASTER_KEY
-```
-
-**2. Set environment variables:**
-
-```bash
-export GEMINI_API_KEY="your-gemini-api-key"
-export LITELLM_MASTER_KEY="sk-1234567890"  # Generate a secure key
-```
-
-**3. Start LiteLLM Proxy:**
-
-```bash
-litellm --config /path/to/config.yaml
-
-# RUNNING on http://0.0.0.0:4000
-```
-
-**4. Configure Claude Code to use LiteLLM Proxy:**
-
-```bash
-export ANTHROPIC_BASE_URL="http://0.0.0.0:4000"
-export ANTHROPIC_AUTH_TOKEN="$LITELLM_MASTER_KEY"
-```
-
-**5. Use Gemini 3 Pro Preview with Claude Code:**
-
-```bash
-# Claude Code will use gemini-3-pro-preview from your LiteLLM proxy
-claude --model gemini-3-pro-preview
-
-```
-
-### Example Usage
-
-Once configured, you can interact with Gemini 3 Pro Preview using Claude Code's native interface:
-
-```bash
-$ claude --model gemini-3-pro-preview
-> Explain how thought signatures work in multi-turn conversations.
-
-# Gemini 3 Pro Preview responds through Claude Code interface
-```
-
-### Benefits
-
-- ✅ **Native Claude Code Experience**: Use Gemini 3 Pro Preview with Claude Code's familiar CLI interface
-- ✅ **Unified Authentication**: Single API key for all models through LiteLLM proxy
-- ✅ **Cost Tracking**: All usage tracked through LiteLLM's centralized logging
-- ✅ **Seamless Model Switching**: Easily switch between Claude and Gemini models
-- ✅ **Full Feature Support**: All Gemini 3 features (thought signatures, function calling, etc.) work through Claude Code
-
-### Troubleshooting
-
-**Claude Code not finding the model:**
-- Ensure the model name in Claude Code matches exactly: `gemini-3-pro-preview`
-- Verify your proxy is running: `curl http://0.0.0.0:4000/health`
-- Check that `ANTHROPIC_BASE_URL` points to your LiteLLM proxy
-
-**Authentication errors:**
-- Verify `ANTHROPIC_AUTH_TOKEN` matches your LiteLLM master key
-- Ensure `GEMINI_API_KEY` is set correctly
-- Check LiteLLM proxy logs for detailed error messages
-
-## Responses API Support
-
-LiteLLM fully supports the OpenAI Responses API for Gemini 3 Pro Preview, including both streaming and non-streaming modes. The Responses API provides a structured way to handle multi-turn conversations with function calling, and LiteLLM automatically preserves thought signatures throughout the conversation.
-
-### Example: Using Responses API with Gemini 3
-
-<Tabs>
-<TabItem value="sdk" label="Non-Streaming">
-
-```python
-from openai import OpenAI
-import json
-
-client = OpenAI()
-
-# 1. Define a list of callable tools for the model
-tools = [
-    {
-        "type": "function",
-        "name": "get_horoscope",
-        "description": "Get today's horoscope for an astrological sign.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "sign": {
-                    "type": "string",
-                    "description": "An astrological sign like Taurus or Aquarius",
-                },
-            },
-            "required": ["sign"],
-        },
-    },
-]
-
-def get_horoscope(sign):
-    return f"{sign}: Next Tuesday you will befriend a baby otter."
-
-# Create a running input list we will add to over time
-input_list = [
-    {"role": "user", "content": "What is my horoscope? I am an Aquarius."}
-]
-
-# 2. Prompt the model with tools defined
-response = client.responses.create(
-    model="gemini-3-pro-preview",
-    tools=tools,
-    input=input_list,
-)
-
-# Save function call outputs for subsequent requests
-input_list += response.output
-
-for item in response.output:
-    if item.type == "function_call":
-        if item.name == "get_horoscope":
-            # 3. Execute the function logic for get_horoscope
-            horoscope = get_horoscope(json.loads(item.arguments))
-            
-            # 4. Provide function call results to the model
-            input_list.append({
-                "type": "function_call_output",
-                "call_id": item.call_id,
-                "output": json.dumps({
-                  "horoscope": horoscope
-                })
-            })
-
-print("Final input:")
-print(input_list)
-
-response = client.responses.create(
-    model="gemini-3-pro-preview",
-    instructions="Respond only with a horoscope generated by a tool.",
-    tools=tools,
-    input=input_list,
-)
-
-# 5. The model should be able to give a response!
-print("Final output:")
-print(response.model_dump_json(indent=2))
-print("\n" + response.output_text)
-```
-
-**Key Points:**
-- ✅ Thought signatures are automatically preserved in function calls
-- ✅ Works seamlessly with multi-turn conversations
-- ✅ All Gemini 3-specific features are fully supported
-
-</TabItem>
-<TabItem value="streaming" label="Streaming">
-
-```python
-from openai import OpenAI
-import json
-
-client = OpenAI()
-
-tools = [
-    {
-        "type": "function",
-        "name": "get_horoscope",
-        "description": "Get today's horoscope for an astrological sign.",
-        "parameters": {
-            "type": "object",
-            "properties": {
-                "sign": {
-                    "type": "string",
-                    "description": "An astrological sign like Taurus or Aquarius",
-                },
-            },
-            "required": ["sign"],
-        },
-    },
-]
-
-def get_horoscope(sign):
-    return f"{sign}: Next Tuesday you will befriend a baby otter."
-
-input_list = [
-    {"role": "user", "content": "What is my horoscope? I am an Aquarius."}
-]
-
-# Streaming mode
-response = client.responses.create(
-    model="gemini-3-pro-preview",
-    tools=tools,
-    input=input_list,
-    stream=True,
-)
-
-# Collect all chunks
-chunks = []
-for chunk in response:
-    chunks.append(chunk)
-    # Process streaming chunks as they arrive
-    print(chunk)
-
-# Thought signatures are automatically preserved in streaming mode
-```
-
-**Key Points:**
-- ✅ Streaming mode fully supported
-- ✅ Thought signatures preserved across streaming chunks
-- ✅ Real-time processing of function calls and responses
-
-</TabItem>
-</Tabs>
-
-### Responses API Benefits
-
-- ✅ **Structured Output**: Responses API provides a clear structure for handling function calls and multi-turn conversations
-- ✅ **Thought Signature Preservation**: LiteLLM automatically preserves thought signatures in both streaming and non-streaming modes
-- ✅ **Seamless Integration**: Works with existing OpenAI SDK patterns
-- ✅ **Full Feature Support**: All Gemini 3 features (thought signatures, function calling, reasoning) are fully supported
-
-
-## Best Practices
-
-#### 1. Always Include Thought Signatures in Conversation History
-
-When building multi-turn conversations with function calling:
-
-✅ **Do:**
-```python
-# Append the full assistant message (includes thought signatures)
-messages.append(response.choices[0].message)
-```
-
-❌ **Don't:**
-```python
-# Don't manually construct assistant messages without thought signatures
-messages.append({
-    "role": "assistant",
-    "tool_calls": [...]  # Missing thought signatures!
-})
-```
-
-#### 2. Use Appropriate Thinking Levels
-
-- **`reasoning_effort="low"`**: For simple queries, quick responses, cost optimization
-- **`reasoning_effort="high"`**: For complex problems requiring deep reasoning
-
-#### 3. Keep Temperature at Default
-
-For Gemini 3 models, always use `temperature=1.0` (default). Lower temperatures can cause issues.
-
-#### 4. Handle Model Switches Gracefully
-
-When switching from non-Gemini-3 to Gemini-3:
-- ✅ LiteLLM automatically handles missing thought signatures
-- ✅ No manual intervention needed
-- ✅ Conversation history continues seamlessly
-
-
-## Troubleshooting
-
-#### Issue: Missing Thought Signatures
-
-**Symptom**: Error when including assistant messages in conversation history
-
-**Solution**: Ensure you're appending the full assistant message from the response:
-```python
-messages.append(response.choices[0].message)  # ✅ Includes thought signatures
-```
-
-#### Issue: Conversation Breaks When Switching Models
-
-**Symptom**: Errors when switching from gemini-2.5-flash to gemini-3-pro-preview
-
-**Solution**: This should work automatically! LiteLLM adds dummy signatures. If you see errors, ensure you're using the latest LiteLLM version.
-
-#### Issue: Infinite Loops or Poor Performance
-
-**Symptom**: Model gets stuck or produces poor results
-
-**Solution**: 
-- Ensure `temperature=1.0` (default for Gemini 3)
-- Check that `reasoning_effort` is set appropriately
-- Verify you're using the correct model name: `gemini/gemini-3-pro-preview`
-
-## Additional Resources
-
-- [Gemini Provider Documentation](../../docs/providers/gemini)
-- [Thought Signatures Guide](../../docs/providers/gemini#thought-signatures)
-- [Reasoning Content Documentation](../../docs/reasoning_content)
-- [Function Calling Guide](../../docs/completion/function_call)

docs/my-website/blog/gemini_3_1_flash_lite/index.md

@@ -1,168 +0,0 @@
----
-slug: gemini_3_1_flash_lite_preview
-title: "DAY 0 Support: Gemini 3.1 Flash Lite Preview on LiteLLM"
-date: 2026-03-03T08:00:00
-authors:
-  - sameer
-  - krrish
-  - ishaan-alt
-description: "Guide to using Gemini 3.1 Flash Lite Preview on LiteLLM Proxy and SDK with day 0 support."
-tags: [gemini, day 0 support, llms, supernova]
-hide_table_of_contents: false
----
-
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-# Gemini 3.1 Flash Lite Preview Day 0 Support 
-
-LiteLLM now supports `gemini-3.1-flash-lite-preview` with full day 0 support!
-
-:::note
-If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above.
-:::
-
-{/* truncate */}
-
-## Deploy this version
-
-<Tabs>
-<TabItem value="docker" label="Docker">
-
-``` showLineNumbers title="docker run litellm"
-docker run \
--e STORE_MODEL_IN_DB=True \
--p 4000:4000 \
-ghcr.io/berriai/litellm:main-v1.80.8-stable.1
-```
-
-</TabItem>
-
-<TabItem value="pip" label="Pip">
-
-``` showLineNumbers title="pip install litellm"
-pip install litellm==v1.80.8-stable.1
-```
-
-</TabItem>
-</Tabs>
-
-## What's New
-
-Supports all four thinking levels:
-- **MINIMAL**: Ultra-fast responses with minimal reasoning
-- **LOW**: Simple instruction following
-- **MEDIUM**: Balanced reasoning for complex tasks
-- **HIGH**: Maximum reasoning depth (dynamic)
-
----
-
-## Quick Start
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-**Basic Usage**
-
-```python
-from litellm import completion
-
-response = completion(
-    model="gemini/gemini-3.1-flash-lite-preview",
-    messages=[{"role": "user", "content": "Extract key entities from this text: ..."}],
-)
-
-print(response.choices[0].message.content)
-```
-
-**With Thinking Levels**
-
-```python
-from litellm import completion
-
-# Use MEDIUM thinking for complex reasoning tasks
-response = completion(
-    model="gemini/gemini-3.1-flash-lite-preview",
-    messages=[{"role": "user", "content": "Analyze this dataset and identify patterns"}],
-    reasoning_effort="medium",  # low, medium , high
-)
-
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-
-<TabItem value="proxy" label="PROXY">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: gemini-3.1-flash-lite
-    litellm_params:
-      model: gemini/gemini-3.1-flash-lite-preview
-      api_key: os.environ/GEMINI_API_KEY
-  
-  # Or use Vertex AI
-  - model_name: vertex-gemini-3.1-flash-lite
-    litellm_params:
-      model: vertex_ai/gemini-3.1-flash-lite-preview
-      vertex_project: your-project-id
-      vertex_location: us-central1
-```
-
-**2. Start proxy**
-
-```bash
-litellm --config /path/to/config.yaml
-```
-
-**3. Make requests**
-
-```bash
-curl -X POST http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
-  -d '{
-    "model": "gemini-3.1-flash-lite",
-    "messages": [{"role": "user", "content": "Extract structured data from this text"}],
-    "reasoning_effort": "low"
-  }'
-```
-
-</TabItem>
-</Tabs>
-
----
-
-## Supported Endpoints
-
-LiteLLM provides **full end-to-end support** for Gemini 3.1 Flash Lite Preview on:
-
-- ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
-- ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
-- ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
-
-All endpoints support:
-- Streaming and non-streaming responses
-- Function calling with thought signatures
-- Multi-turn conversations
-- All Gemini 3-specific features (thinking levels, thought signatures)
-- Full multimodal support (text, image, audio, video)
-
----
-
-## `reasoning_effort` Mapping for Gemini 3.1
-
-LiteLLM automatically maps OpenAI's `reasoning_effort` parameter to Gemini's `thinkingLevel`:
-
-| reasoning_effort | thinking_level | Use Case |
-|------------------|----------------|----------|
-| `minimal` | `minimal` | Ultra-fast responses, simple queries |
-| `low` | `low` | Basic instruction following |
-| `medium` | `medium` | Balanced reasoning for moderate complexity |
-| `high` | `high` | Maximum reasoning depth, complex problems |
-| `disable` | `minimal` | Disable extended reasoning |
-| `none` | `minimal` | No extended reasoning |

docs/my-website/blog/gemini_3_flash/index.md

@@ -1,247 +0,0 @@
----
-slug: gemini_3_flash
-title: "DAY 0 Support: Gemini 3 Flash on LiteLLM"
-date: 2025-12-17T10:00:00
-authors:
-  - sameer
-  - krrish
-  - ishaan-alt
-description: "Guide to using Gemini 3 Flash on LiteLLM Proxy and SDK with day 0 support."
-tags: [gemini, day 0 support, llms]
-hide_table_of_contents: false
----
-
-
-import Tabs from '@theme/Tabs';
-import TabItem from '@theme/TabItem';
-
-# Gemini 3 Flash Day 0 Support 
-
-LiteLLM now supports `gemini-3-flash-preview` and all the new API changes along with it.
-
-:::note
-If you only want cost tracking, you need no change in your current Litellm version. But if you want the support for new features introduced along with it like thinking levels, you will need to use v1.80.8-stable.1 or above.
-:::
-
-{/* truncate */}
-
-## Deploy this version
-
-<Tabs>
-<TabItem value="docker" label="Docker">
-
-``` showLineNumbers title="docker run litellm"
-docker run \
--e STORE_MODEL_IN_DB=True \
--p 4000:4000 \
-ghcr.io/berriai/litellm:main-v1.80.8-stable.1
-```
-
-</TabItem>
-
-<TabItem value="pip" label="Pip">
-
-``` showLineNumbers title="pip install litellm"
-pip install litellm==1.80.8.post1
-```
-
-</TabItem>
-</Tabs>
-
-## What's New
-
-### 1. New Thinking Levels: `thinkingLevel` with MINIMAL & MEDIUM
-
-Gemini 3 Flash introduces granular thinking control with `thinkingLevel` instead of `thinkingBudget`.
-- **MINIMAL**: Ultra-lightweight thinking for fast responses
-- **MEDIUM**: Balanced thinking for complex reasoning  
-- **HIGH**: Maximum reasoning depth
-
-LiteLLM automatically maps the OpenAI `reasoning_effort` parameter to Gemini's `thinkingLevel`, so you can use familiar `reasoning_effort` values (`minimal`, `low`, `medium`, `high`) without changing your code!
-
-### 2. Thought Signatures
-
-Like `gemini-3-pro`, this model also includes thought signatures for tool calls. LiteLLM handles signature extraction and embedding internally. [Learn more about thought signatures](../gemini_3/index.md#thought-signatures).
-
-**Edge Case Handling**: If thought signatures are missing in the request, LiteLLM adds a dummy signature ensuring the API call doesn't break
-
----
-## Supported Endpoints
-
-LiteLLM provides **full end-to-end support** for Gemini 3 Flash on:
-
-- ✅ `/v1/chat/completions` - OpenAI-compatible chat completions endpoint
-- ✅ `/v1/responses` - OpenAI Responses API endpoint (streaming and non-streaming)
-- ✅ [`/v1/messages`](../../docs/anthropic_unified) - Anthropic-compatible messages endpoint
-- ✅ `/v1/generateContent` – [Google Gemini API](../../docs/generateContent) compatible endpoint 
-All endpoints support:
-- Streaming and non-streaming responses
-- Function calling with thought signatures
-- Multi-turn conversations
-- All Gemini 3-specific features
-- Converstion of provider specific thinking related param to thinkingLevel
-
-## Quick Start
-
-<Tabs>
-<TabItem value="sdk" label="SDK">
-
-**Basic Usage with MEDIUM thinking (NEW)**
-
-```python
-from litellm import completion
-
-# No need to make any changes to your code as we map openai reasoning param to thinkingLevel
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "Solve this complex math problem: 25 * 4 + 10"}],
-    reasoning_effort="medium",  # NEW: MEDIUM thinking level
-)
-
-print(response.choices[0].message.content)
-```
-
-</TabItem>
-
-<TabItem value="proxy" label="PROXY">
-
-**1. Setup config.yaml**
-
-```yaml
-model_list:
-  - model_name: gemini-3-flash
-    litellm_params:
-      model: gemini/gemini-3-flash-preview
-      api_key: os.environ/GEMINI_API_KEY
-```
-
-**2. Start proxy**
-
-```bash
-litellm --config /path/to/config.yaml
-```
-
-**3. Call with MEDIUM thinking**
-
-```bash
-curl -X POST http://localhost:4000/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
-  -d '{
-    "model": "gemini-3-flash",
-    "messages": [{"role": "user", "content": "Complex reasoning task"}],
-    "reasoning_effort": "medium"
-  }'
-``'
-
-</TabItem>
-</Tabs>
-
----
-
-## All `reasoning_effort` Levels
-
-<Tabs>
-<TabItem value="minimal" label="MINIMAL">
-
-**Ultra-fast, minimal reasoning**
-
-```python
-from litellm import completion
-
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "What's 2+2?"}],
-    reasoning_effort="minimal",
-)
-```
-
-</TabItem>
-
-<TabItem value="low" label="LOW">
-
-**Simple instruction following**
-
-```python
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "Write a haiku about coding"}],
-    reasoning_effort="low",
-)
-```
-
-</TabItem>
-
-<TabItem value="medium" label="MEDIUM (NEW)">
-
-**Balanced reasoning for complex tasks** ✨
-
-```python
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "Analyze this dataset and find patterns"}],
-    reasoning_effort="medium",  # NEW!
-)
-```
-
-</TabItem>
-
-<TabItem value="high" label="HIGH">
-
-**Maximum reasoning depth**
-
-```python
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "Prove this mathematical theorem"}],
-    reasoning_effort="high",
-)
-```
-
-</TabItem>
-</Tabs>
-
----
-
-## Key Features
-
-✅ **Thinking Levels**: MINIMAL, LOW, MEDIUM, HIGH  
-✅ **Thought Signatures**: Track reasoning with unique identifiers  
-✅ **Seamless Integration**: Works with existing OpenAI-compatible client  
-✅ **Backward Compatible**: Gemini 2.5 models continue using `thinkingBudget`  
-
----
-
-## Installation
-
-```bash
-pip install litellm --upgrade
-```
-
-```python
-import litellm
-from litellm import completion
-
-response = completion(
-    model="gemini/gemini-3-flash-preview",
-    messages=[{"role": "user", "content": "Your question here"}],
-    reasoning_effort="medium",  # Use MEDIUM thinking
-)
-print(response)
-```
-
-:::note
-If using this model via vertex_ai, keep the location as global as this is the only supported location as of now.
-:::
-
-
-## `reasoning_effort` Mapping for Gemini 3+
-
-| reasoning_effort | thinking_level | 
-|------------------|----------------|
-| `minimal` | `minimal` |
-| `low` | `low` |
-| `medium` | `medium` |
-| `high` | `high` |
-| `disable` | `minimal` |
-| `none` | `minimal` |