Merge branch 'main' into main

.circleci/requirements.txt

@@ -1,20 +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==3.10.12 # fast /embedding responses
-pydantic==2.11.0
-google-cloud-aiplatform==1.43.0
-google-cloud-iam==2.19.1
-fastapi-sso==0.16.0 
-uvloop==0.21.0
-mcp==1.25.0    # for MCP server  
-semantic_router==0.1.10 # for auto-routing with litellm
-fastuuid==0.12.0
-responses==0.25.7  # for proxy client tests
-pytest-retry==1.6.3  # for automatic test retries

.claude/settings.json

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

.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 install --no-audit --no-fund
+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/ISSUE_TEMPLATE/config.yml

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

.github/actions/helm-oci-chart-releaser/action.yml

@@ -41,32 +41,54 @@ runs:
   using: composite
   steps:
     - name: Helm | Setup
-      uses: azure/setup-helm@v4
+      uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
       with:
         version: v3.20.0
 
     - name: Helm | Login
       shell: bash
-      run: echo ${{ inputs.registry_password }} | helm registry login -u ${{ inputs.registry_username }} --password-stdin ${{ inputs.registry }}
+      env:
+        REGISTRY_PASSWORD: ${{ inputs.registry_password }}
+        REGISTRY_USERNAME: ${{ inputs.registry_username }}
+        REGISTRY: ${{ inputs.registry }}
+      run: echo "$REGISTRY_PASSWORD" | helm registry login -u "$REGISTRY_USERNAME" --password-stdin "$REGISTRY"
 
     - name: Helm | Dependency
       if: inputs.update_dependencies == 'true'
       shell: bash
-      run: helm dependency update ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+      env:
+        CHART_PATH: ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+      run: helm dependency update "$CHART_PATH"
 
     - name: Helm | Package
       shell: bash
-      run: helm package ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }} --version ${{ inputs.tag }} --app-version ${{ inputs.app_version }}
+      env:
+        CHART_PATH: ${{ inputs.path == null && format('{0}/{1}', 'charts', inputs.name) || inputs.path }}
+        TAG: ${{ inputs.tag }}
+        APP_VERSION: ${{ inputs.app_version }}
+      run: helm package "$CHART_PATH" --version "$TAG" --app-version "$APP_VERSION"
 
     - name: Helm | Push
       shell: bash
-      run: helm push ${{ inputs.name }}-${{ inputs.tag }}.tgz oci://${{ inputs.registry }}/${{ inputs.repository }}
+      env:
+        NAME: ${{ inputs.name }}
+        TAG: ${{ inputs.tag }}
+        REGISTRY: ${{ inputs.registry }}
+        REPOSITORY: ${{ inputs.repository }}
+      run: helm push "${NAME}-${TAG}.tgz" "oci://${REGISTRY}/${REPOSITORY}"
 
     - name: Helm | Logout
       shell: bash
-      run: helm registry logout ${{ inputs.registry }}
+      env:
+        REGISTRY: ${{ inputs.registry }}
+      run: helm registry logout "$REGISTRY"
 
     - name: Helm | Output
       id: output
       shell: bash
-      run: echo "image=${{ inputs.registry }}/${{ inputs.repository }}/${{ inputs.name }}:${{ inputs.tag }}" >> $GITHUB_OUTPUT
+      env:
+        REGISTRY: ${{ inputs.registry }}
+        REPOSITORY: ${{ inputs.repository }}
+        NAME: ${{ inputs.name }}
+        TAG: ${{ inputs.tag }}
+      run: echo "image=${REGISTRY}/${REPOSITORY}/${NAME}:${TAG}" >> $GITHUB_OUTPUT

.github/codeql/codeql-config.yml

@@ -0,0 +1,21 @@
+name: "LiteLLM CodeQL config"
+
+queries:
+  - uses: security-and-quality
+
+# Known OOM queries on large Python codebases:
+# CodeQL builds a full data flow graph in memory. These two queries trace
+# sensitive data through every log call / regex pattern, causing combinatorial
+# path explosion on codebases with extensive logging like LiteLLM (>2 GiB
+# result sets). This is a known CodeQL scaling limitation, not a code issue.
+# Re-test periodically as CodeQL improves or the codebase refactors logging.
+query-filters:
+  - exclude:
+      id: py/clear-text-logging-sensitive-data  # CWE-312
+  - exclude:
+      id: py/polynomial-redos                   # CWE-730
+
+paths-ignore:
+  - tests
+  - docs
+  - "**/*.md"

.github/dependabot.yaml

@@ -4,6 +4,9 @@ updates:
     directory: "/"
     schedule:
       interval: "daily"
+    cooldown:
+      default-days: 7
+      semver-major-days: 14
     groups:
       github-actions:
         patterns:

.github/observatory/litellm_config.yaml

@@ -0,0 +1,19 @@
+# LiteLLM Observatory Test Configuration
+# This config is used by CI to spin up a temporary LiteLLM instance
+# for running observatory tests against RC/stable releases.
+#
+# Add model definitions for the providers you want to test.
+# Provider API keys are injected via environment variables in CI.
+
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: azure/gpt-4o
+      api_key: os.environ/AZURE_API_KEY
+      api_base: os.environ/AZURE_API_BASE
+
+  - model_name: gpt-4o-mini
+    litellm_params:
+      model: azure/gpt-4o-mini
+      api_key: os.environ/AZURE_API_KEY
+      api_base: os.environ/AZURE_API_BASE

.github/pull_request_template.md

@@ -2,15 +2,23 @@
 
 <!-- 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**
 
-- [ ] I have Added testing in the [`tests/litellm/`](https://github.com/BerriAI/litellm/tree/main/tests/litellm) directory, **Adding at least 1 test is a hard requirement** - [see details](https://docs.litellm.ai/docs/extras/contributing_code)
+- [ ] I have Added testing in the [`tests/test_litellm/`](https://github.com/BerriAI/litellm/tree/main/tests/test_litellm) directory, **Adding at least 1 test is a hard requirement** - [see details](https://docs.litellm.ai/docs/extras/contributing_code)
 - [ ] My PR passes all unit tests on [`make test-unit`](https://docs.litellm.ai/docs/extras/contributing_code)
 - [ ] My PR's scope is as isolated as possible, it only solves 1 specific problem
 - [ ] I have requested a Greptile review by commenting `@greptileai` and received a **Confidence Score of at least 4/5** before requesting a maintainer review
 
+## Delays in PR merge?
+
+If you're seeing a delay in your PR being merged, ping the LiteLLM Team on [Slack (#pr-review)](https://join.slack.com/t/litellmossslack/shared_invite/zt-3o7nkuyfr-p_kbNJj8taRfXGgQI1~YyA).
+
 ## CI (LiteLLM team)
 
 > **CI status guideline:**
@@ -28,6 +36,13 @@
 - [ ] **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

@@ -0,0 +1,230 @@
+#!/usr/bin/env python3
+"""
+Detect and close duplicate GitHub issues using title similarity.
+
+Modes:
+  --scan           Compare all open issues against each other (batch)
+  --issue-number N Check a single issue against older open issues
+
+Requires the `gh` CLI to be authenticated.
+"""
+
+import argparse
+import difflib
+import json
+import re
+import subprocess
+import sys
+
+
+def normalize_title(title: str) -> str:
+    """Strip common prefixes, lowercase, and collapse whitespace."""
+    title = re.sub(
+        r"^\[?(bug|feature request|enhancement|question|docs)[:\]]?\s*",
+        "",
+        title,
+        flags=re.IGNORECASE,
+    )
+    return " ".join(title.lower().split())
+
+
+def gh(*args: str) -> str:
+    """Run a gh CLI command and return stdout."""
+    result = subprocess.run(
+        ["gh", *args],
+        capture_output=True,
+        text=True,
+        check=True,
+    )
+    return result.stdout
+
+
+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"
+        )
+    else:
+        endpoint = "repos/{owner}/{repo}/issues?state=open&per_page=100&sort=created&direction=asc"
+    cmd = ["api", "--paginate", endpoint]
+
+    raw = gh(*cmd)
+    # gh --paginate concatenates JSON arrays, so we may get multiple arrays
+    issues = []
+    for line in raw.strip().splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        parsed = json.loads(line)
+        if isinstance(parsed, list):
+            issues.extend(parsed)
+        else:
+            issues.append(parsed)
+
+    # Filter out pull requests (they also appear in the issues endpoint)
+    return [i for i in issues if "pull_request" not in i]
+
+
+def close_as_duplicate(
+    issue_number: int, duplicate_of: int, repo: str | None, dry_run: bool
+) -> None:
+    """Close an issue as duplicate of another, adding a comment and label."""
+    repo_args = ["--repo", repo] if repo else []
+
+    if dry_run:
+        print(
+            f"  [DRY RUN] Would close #{issue_number} as duplicate of #{duplicate_of}"
+        )
+        return
+
+    # Add comment
+    comment_body = (
+        f"Closing as duplicate of #{duplicate_of}.\n\n"
+        "If you believe this is not a duplicate, please reopen and add context "
+        "explaining how this differs."
+    )
+    gh("issue", "comment", str(issue_number), "--body", comment_body, *repo_args)
+
+    # Add label
+    gh("issue", "edit", str(issue_number), "--add-label", "duplicate", *repo_args)
+
+    # Close with not_planned reason
+    gh(
+        "api",
+        f"repos/{repo or '{owner}/{repo}'}/issues/{issue_number}",
+        "-X",
+        "PATCH",
+        "-f",
+        "state=closed",
+        "-f",
+        "state_reason=not_planned",
+    )
+
+    print(f"  Closed #{issue_number} as duplicate of #{duplicate_of}")
+
+
+def find_duplicate(
+    issue: dict, candidates: list[dict], threshold: float
+) -> dict | None:
+    """Return the first candidate whose normalized title is above threshold."""
+    norm = normalize_title(issue["title"])
+    for candidate in candidates:
+        if candidate["number"] == issue["number"]:
+            continue
+        cand_norm = normalize_title(candidate["title"])
+        ratio = difflib.SequenceMatcher(None, norm, cand_norm).ratio()
+        if ratio >= threshold:
+            return candidate
+    return None
+
+
+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"])
+    closed_count = 0
+
+    for idx, issue in enumerate(issues):
+        older = issues[:idx]
+        if not older:
+            continue
+        dup = find_duplicate(issue, older, threshold)
+        if dup:
+            ratio = difflib.SequenceMatcher(
+                None,
+                normalize_title(issue["title"]),
+                normalize_title(dup["title"]),
+            ).ratio()
+            print(
+                f"#{issue['number']}: \"{issue['title']}\"\n"
+                f"  -> duplicate of #{dup['number']}: \"{dup['title']}\" "
+                f"({ratio:.0%} similar)"
+            )
+            close_as_duplicate(issue["number"], dup["number"], repo, dry_run)
+            closed_count += 1
+
+    return closed_count
+
+
+def check_single(
+    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
+    for i in issues:
+        if i["number"] == issue_number:
+            target = i
+            break
+
+    if target is None:
+        print(f"Issue #{issue_number} not found among open issues.")
+        return False
+
+    older = [i for i in issues if i["number"] < issue_number]
+    dup = find_duplicate(target, older, threshold)
+    if dup:
+        ratio = difflib.SequenceMatcher(
+            None,
+            normalize_title(target["title"]),
+            normalize_title(dup["title"]),
+        ).ratio()
+        print(
+            f"#{target['number']}: \"{target['title']}\"\n"
+            f"  -> duplicate of #{dup['number']}: \"{dup['title']}\" "
+            f"({ratio:.0%} similar)"
+        )
+        close_as_duplicate(issue_number, dup["number"], repo, dry_run)
+        return True
+
+    print(f"#{issue_number}: no duplicate found above threshold {threshold}")
+    return False
+
+
+def main() -> None:
+    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."
+    )
+    args = parser.parse_args()
+
+    dry_run = not args.close
+
+    if dry_run:
+        print("=== DRY RUN MODE (pass --close to actually close issues) ===\n")
+
+    print("Fetching open issues...")
+    issues = fetch_open_issues(args.repo)
+    print(f"Found {len(issues)} open issues.\n")
+
+    if args.scan:
+        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
+        )
+        sys.exit(0 if found else 0)  # Always exit 0; finding no dup is not an error
+
+
+if __name__ == "__main__":
+    main()

.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

@@ -0,0 +1,135 @@
+name: _Unit Test Base (Reusable)
+
+on:
+  workflow_call:
+    inputs:
+      test-path:
+        description: "Pytest path(s) to run"
+        required: true
+        type: string
+      workers:
+        description: "Number of pytest-xdist workers"
+        required: false
+        type: number
+        default: 2
+      reruns:
+        description: "Number of reruns for flaky tests"
+        required: false
+        type: number
+        default: 2
+      timeout-minutes:
+        description: "Job timeout in minutes"
+        required: false
+        type: number
+        default: 20
+      max-failures:
+        description: "Stop after this many failures"
+        required: false
+        type: number
+        default: 10
+      artifact-name:
+        description: "Unique name for the coverage artifact (must be unique per run)"
+        required: true
+        type: string
+
+permissions:
+  contents: read
+
+jobs:
+  run:
+    name: Run tests
+    runs-on: ubuntu-latest
+    timeout-minutes: ${{ inputs.timeout-minutes }}
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: 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 --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: |
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Run tests
+        env:
+          TEST_PATH: ${{ inputs.test-path }}
+          MAX_FAILURES: ${{ inputs.max-failures }}
+          WORKERS: ${{ inputs.workers }}
+          RERUNS: ${{ inputs.reruns }}
+        run: |
+          uv run --no-sync pytest ${TEST_PATH:?} \
+            --tb=short -vv \
+            --maxfail="${MAX_FAILURES}" \
+            -n "${WORKERS}" \
+            --reruns "${RERUNS}" \
+            --reruns-delay 1 \
+            --dist=loadscope \
+            --durations=20 \
+            --cov=litellm \
+            --cov-report=xml:coverage.xml \
+            --cov-config=pyproject.toml
+
+      - name: Save coverage report
+        if: always()
+        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
+        with:
+          name: coverage-${{ inputs.artifact-name }}-${{ github.run_id }}-${{ github.run_attempt }}
+          path: coverage.xml
+          retention-days: 1
+
+  upload-coverage:
+    name: Upload coverage to Codecov
+    needs: run
+    if: always()
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Download coverage report
+        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
+        with:
+          pattern: coverage-${{ inputs.artifact-name }}-${{ github.run_id }}-${{ github.run_attempt }}
+          path: coverage-reports
+          merge-multiple: true
+
+      - name: Upload to Codecov
+        uses: codecov/codecov-action@75cd11691c0faa626561e295848008c8a7dddffe # v5.5.4
+        with:
+          use_oidc: true
+          directory: coverage-reports
+          root_dir: ${{ github.workspace }}
+          fail_ci_if_error: false

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

@@ -0,0 +1,189 @@
+name: _Unit Test Services Base (Reusable)
+
+on:
+  workflow_call:
+    inputs:
+      test-path:
+        description: "Pytest path(s) to run"
+        required: true
+        type: string
+      workers:
+        description: "Number of pytest-xdist workers (0 = no parallelism)"
+        required: false
+        type: number
+        default: 2
+      reruns:
+        description: "Number of reruns for flaky tests"
+        required: false
+        type: number
+        default: 2
+      timeout-minutes:
+        description: "Job timeout in minutes"
+        required: false
+        type: number
+        default: 20
+      max-failures:
+        description: "Stop after this many failures"
+        required: false
+        type: number
+        default: 10
+      enable-postgres:
+        description: "Start a local Postgres service container and run Prisma migrations"
+        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"
+
+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 }}
+
+    services:
+      postgres:
+        image: postgres@sha256:705a5d5b5836f3fcba0d02c4d281e6a7dd9ed2dd4078640f08a1e1e9896e097d # postgres:14
+        env:
+          POSTGRES_USER: litellm
+          POSTGRES_PASSWORD: litellm
+          POSTGRES_DB: litellm_test
+        ports:
+          - 5432:5432
+        options: >-
+          --health-cmd "pg_isready"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: 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: ${{ runner.os }}-uv-services-${{ hashFiles('uv.lock') }}
+          restore-keys: |
+            ${{ runner.os }}-uv-services-
+
+      - name: Install dependencies
+        run: |
+          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: |
+          uv run --no-sync prisma generate --schema litellm/proxy/schema.prisma
+
+      - name: Run Prisma migrations
+        if: ${{ inputs.enable-postgres }}
+        env:
+          DATABASE_URL: "postgresql://litellm:litellm@localhost:5432/litellm_test"
+        run: |
+          uv run --no-sync prisma db push --schema litellm/proxy/schema.prisma --accept-data-loss
+
+      - name: Run tests
+        env:
+          TEST_PATH: ${{ inputs.test-path }}
+          MAX_FAILURES: ${{ inputs.max-failures }}
+          WORKERS: ${{ inputs.workers }}
+          RERUNS: ${{ inputs.reruns }}
+          DIST: ${{ inputs.dist }}
+          DATABASE_URL: ${{ inputs.enable-postgres && 'postgresql://litellm:litellm@localhost:5432/litellm_test' || '' }}
+        run: |
+          if [ "${WORKERS}" = "0" ]; then
+            uv run --no-sync pytest ${TEST_PATH:?} \
+              --tb=short -vv \
+              --maxfail="${MAX_FAILURES}" \
+              --reruns "${RERUNS}" \
+              --reruns-delay 1 \
+              --durations=20 \
+              --cov=litellm \
+              --cov-report=xml:coverage.xml \
+              --cov-config=pyproject.toml
+          else
+            uv run --no-sync pytest ${TEST_PATH:?} \
+              --tb=short -vv \
+              --maxfail="${MAX_FAILURES}" \
+              -n "${WORKERS}" \
+              --reruns "${RERUNS}" \
+              --reruns-delay 1 \
+              --dist="${DIST}" \
+              --durations=20 \
+              --cov=litellm \
+              --cov-report=xml:coverage.xml \
+              --cov-config=pyproject.toml
+          fi
+
+      - name: Save coverage report
+        if: always()
+        uses: actions/upload-artifact@4cec3d8aa04e39d1a68397de0c4cd6fb9dce8ec1 # v4.6.1
+        with:
+          name: coverage-${{ inputs.artifact-name }}-${{ github.run_id }}-${{ github.run_attempt }}
+          path: coverage.xml
+          retention-days: 1
+
+  upload-coverage:
+    name: Upload coverage to Codecov
+    needs: run
+    if: always()
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Download coverage report
+        uses: actions/download-artifact@95815c38cf2ff2164869cbab79da8d1f422bc89e # v4.2.1
+        with:
+          pattern: coverage-${{ inputs.artifact-name }}-${{ github.run_id }}-${{ github.run_attempt }}
+          path: coverage-reports
+          merge-multiple: true
+
+      - name: Upload to Codecov
+        uses: codecov/codecov-action@75cd11691c0faa626561e295848008c8a7dddffe # v5.5.4
+        with:
+          use_oidc: true
+          directory: coverage-reports
+          root_dir: ${{ github.workspace }}
+          fail_ci_if_error: false

.github/workflows/auto_update_price_and_context_window.yml

@@ -2,20 +2,28 @@ name: Updates model_prices_and_context_window.json and Create Pull Request
 
 on:
   schedule:
-    - cron: "0 0 * * 0"  # Run every Sundays at midnight
+    - cron: "0 0 * * 0" # Run every Sundays at midnight
     #- cron: "0 0 * * *" # Run daily at midnight
 
+permissions:
+  contents: write
+  pull-requests: write
+
 jobs:
   auto_update_price_and_context_window:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
-      - name: Install Dependencies
-        run: |
-          pip install aiohttp
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+      - 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 
@@ -25,4 +33,4 @@ jobs:
             --head auto-update-price-and-context-window-$(date +'%Y-%m-%d') \
             --base main
         env:
-          GH_TOKEN: ${{ secrets.GH_TOKEN }}
+          GH_TOKEN: ${{ secrets.GH_TOKEN }}

.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-schema-sync.yml

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

.github/workflows/check_duplicate_issues.yml

@@ -2,47 +2,52 @@ name: Check Duplicate Issues
 
 on:
   issues:
-    types: [opened]
+    types: [opened, edited]
 
 jobs:
-  check-duplicates:
-    if: github.event.action == 'opened'
+  check-duplicate:
     runs-on: ubuntu-latest
     permissions:
-      contents: read
       issues: write
+      contents: read
     steps:
-      - name: Install Claude Code
-        run: npm install -g @anthropic-ai/claude-code
-
-      - name: Check duplicates
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.LITELLM_VIRTUAL_KEY }}
-          ANTHROPIC_BASE_URL: ${{ secrets.LITELLM_BASE_URL }}
+      - name: Check for potential duplicates
+        uses: wow-actions/potential-duplicates@4d4ea0352e0383859279938e255179dd1dbb67b5 # v1.1.0
+        with:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PROMPT: |
-            A new issue has been created in the ${{ github.repository }} repository.
+          label: potential-duplicate
+          threshold: 0.6
+          reaction: eyes
+          comment: |
+            **⚠️ Potential duplicate detected**
 
-            Issue number: ${{ github.event.issue.number }}
+            This issue appears similar to existing issue(s):
+            {{#issues}}
+            - [#{{number}}]({{html_url}}) - {{title}} ({{accuracy}}% similar)
+            {{/issues}}
 
-            Lookup this issue with gh issue view ${{ github.event.issue.number }} --repo ${{ github.repository }}.
+            Please review the linked issue(s) to see if they address your concern. If this is not a duplicate, please provide additional context to help us understand the difference.
 
-            Search through existing issues (excluding #${{ github.event.issue.number }}) to find potential duplicates.
+      - name: Checkout close script
+        if: github.event.action == 'opened'
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          sparse-checkout: .github/scripts
+          persist-credentials: false
 
-            Use gh issue list --repo ${{ github.repository }} with relevant search terms from the new issue's title and description. Try multiple keyword combinations to search broadly. Check both open and recently closed issues.
+      - name: Set up Python
+        if: github.event.action == 'opened'
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
 
-            Consider:
-            1. Similar titles or descriptions
-            2. Same error messages or symptoms
-            3. Related functionality or components
-            4. Similar feature requests
-
-            If you find potential duplicates, post a SINGLE comment on issue #${{ github.event.issue.number }} using gh issue comment ${{ github.event.issue.number }} --repo ${{ github.repository }} with this format:
-
-            _This comment was generated by an LLM and may be inaccurate._
-
-            This issue might be a duplicate of existing issues. Please check:
-            - #[issue_number]: [brief description of similarity]
-
-            If you find NO duplicates, do NOT post any comment. Stay silent.
-        run: claude -p "$PROMPT" --model sonnet --max-turns 10 --allowedTools "Bash(gh issue *)"
+      - name: Auto-close if high-confidence duplicate
+        if: github.event.action == 'opened'
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          python3 .github/scripts/close_duplicate_issues.py \
+            --issue-number ${{ github.event.issue.number }} \
+            --repo ${{ github.repository }} \
+            --threshold 0.85 \
+            --close

.github/workflows/check_duplicate_prs.yml

@@ -1,52 +0,0 @@
-name: Check Duplicate PRs
-
-on:
-  pull_request_target:
-    types: [opened]
-
-jobs:
-  check-duplicates:
-    if: |
-      github.event.pull_request.user.login != 'ishaan-jaff' &&
-      github.event.pull_request.user.login != 'krrishdholakia' &&
-      github.event.pull_request.user.login != 'actions-user' &&
-      !endsWith(github.event.pull_request.user.login, '[bot]')
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      pull-requests: write
-    steps:
-      - name: Install Claude Code
-        run: npm install -g @anthropic-ai/claude-code
-
-      - name: Check duplicates
-        env:
-          ANTHROPIC_API_KEY: ${{ secrets.LITELLM_VIRTUAL_KEY }}
-          ANTHROPIC_BASE_URL: ${{ secrets.LITELLM_BASE_URL }}
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          PROMPT: |
-            A new PR has been opened in the ${{ github.repository }} repository.
-
-            PR number: ${{ github.event.pull_request.number }}
-
-            Lookup this PR with gh pr view ${{ github.event.pull_request.number }} --repo ${{ github.repository }}.
-
-            Search through existing open PRs (excluding #${{ github.event.pull_request.number }}) to find potential duplicates.
-
-            Use gh pr list --repo ${{ github.repository }} with relevant search terms from the new PR's title and description. Try multiple keyword combinations to search broadly. Check both open and recently closed PRs.
-
-            Consider:
-            1. Similar titles or descriptions
-            2. Same bug fix or feature being implemented
-            3. Related functionality or components
-            4. Overlapping code changes (same files or areas)
-
-            If you find potential duplicates, post a SINGLE comment on PR #${{ github.event.pull_request.number }} using gh pr comment ${{ github.event.pull_request.number }} --repo ${{ github.repository }} with this format:
-
-            _This comment was generated by an LLM and may be inaccurate._
-
-            This PR might be a duplicate of existing PRs. Please check:
-            - #[pr_number]: [brief description of similarity]
-
-            If you find NO duplicates, do NOT post any comment. Stay silent.
-        run: claude -p "$PROMPT" --model sonnet --max-turns 10 --allowedTools "Bash(gh pr *)"

.github/workflows/codeql.yml

@@ -0,0 +1,55 @@
+name: "CodeQL"
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+  schedule:
+    # Run daily at 04:00 UTC
+    - cron: "0 4 * * *"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ github.event_name == 'pull_request' }}
+
+jobs:
+  analyze:
+    if: github.event_name != 'schedule' || github.repository == 'BerriAI/litellm'
+    name: Analyze (${{ matrix.language }})
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    permissions:
+      security-events: write
+      packages: read
+      actions: read
+      contents: read
+
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          - language: actions
+            build-mode: none
+          - language: javascript-typescript
+            build-mode: none
+          - language: python
+            build-mode: none
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Initialize CodeQL
+        uses: github/codeql-action/init@ebcb5b36ded6beda4ceefea6a8bc4cc885255bb3 # v3
+        with:
+          languages: ${{ matrix.language }}
+          build-mode: ${{ matrix.build-mode }}
+          config-file: ./.github/codeql/codeql-config.yml
+
+      - name: Perform CodeQL Analysis
+        uses: github/codeql-action/analyze@ebcb5b36ded6beda4ceefea6a8bc4cc885255bb3 # v3
+        with:
+          category: "/language:${{ matrix.language }}"

.github/workflows/codspeed.yml

@@ -0,0 +1,54 @@
+name: CodSpeed Benchmarks
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    branches:
+      - main
+  # Allow CodSpeed to trigger backtest performance analysis
+  # in order to generate initial data
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  id-token: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  benchmarks:
+    runs-on: ubuntu-latest
+    timeout-minutes: 15
+
+    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 benchmarks
+        uses: CodSpeedHQ/action@1c8ae4843586d3ba879736b7f6b7b0c990757fab # v4.12.1
+        with:
+          mode: simulation
+          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

@@ -0,0 +1,123 @@
+name: Create Release
+
+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)"
+        required: true
+        type: string
+      commit_hash:
+        description: "Full 40-char commit SHA to target"
+        required: true
+        type: string
+
+permissions: {}
+
+jobs:
+  release:
+    name: Create Release
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Validate inputs
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        run: |
+          if ! echo "${COMMIT_HASH}" | grep -qE '^[0-9a-f]{40}$'; then
+            echo "::error::commit_hash must be a full 40-character commit SHA"
+            exit 1
+          fi
+          if ! echo "${TAG}" | grep -qE '^v?[0-9]+\.[0-9]+\.[0-9]+'; then
+            echo "::error::tag must start with 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
+        env:
+          TAG: ${{ inputs.tag }}
+          COMMIT_HASH: ${{ inputs.commit_hash }}
+        uses: actions/github-script@60a0d83039c74a4aee543508d2ffcb1c3799cdea # v7.0.1
+        with:
+          script: |
+            const tag = process.env.TAG;
+            const commitHash = process.env.COMMIT_HASH;
+
+            // Mark RC / dev / nightly / alpha / beta tags as GitHub pre-releases.
+            // PEP 440 post-releases (e.g. `1.84.0.post1`) and legacy `-stable[.patch.N]`
+            // are stable maintenance releases, not pre-releases.
+            const isPrerelease = /(?:rc|nightly|alpha|beta|\.dev)/i.test(tag);
+
+            const cosignSection = [
+              `## Verify Docker Image Signature`,
+              ``,
+              `All LiteLLM Docker images are signed with [cosign](https://docs.sigstore.dev/cosign/overview/). Every release is signed with the same key introduced in [commit \`0112e53\`](https://github.com/BerriAI/litellm/commit/0112e53046018d726492c814b3644b7d376029d0).`,
+              ``,
+              `**Verify using the pinned commit hash (recommended):**`,
+              ``,
+              `A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the original signing key:`,
+              ``,
+              '```bash',
+              `cosign verify \\`,
+              `  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \\`,
+              `  ghcr.io/berriai/litellm:${tag}`,
+              '```',
+              ``,
+              `**Verify using the 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/${tag}/cosign.pub \\`,
+              `  ghcr.io/berriai/litellm:${tag}`,
+              '```',
+              ``,
+              `Expected output:`,
+              ``,
+              '```',
+              `The following checks were performed on each of these signatures:`,
+              `  - The cosign claims were validated`,
+              `  - The signatures were verified against the specified public key`,
+              '```',
+              ``,
+              `---`,
+              ``,
+            ].join('\n');
+
+            try {
+              const response = await github.rest.repos.createRelease({
+                draft: true,
+                generate_release_notes: true,
+                target_commitish: commitHash,
+                name: tag,
+                owner: context.repo.owner,
+                prerelease: isPrerelease,
+                repo: context.repo.repo,
+                tag_name: tag,
+              });
+
+              const updatedBody = cosignSection + (response.data.body ?? '');
+              await github.rest.repos.updateRelease({
+                owner: context.repo.owner,
+                repo: context.repo.repo,
+                release_id: response.data.id,
+                body: updatedBody,
+                draft: false,
+              });
+
+            } catch (error) {
+              core.setFailed(error.message);
+            }
+
+  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/create_daily_staging_branch.yml

@@ -2,18 +2,22 @@ name: Create Daily Staging Branch
 
 on:
   schedule:
-    - cron: '0 0,12 * * *'  # Runs every 12 hours at midnight and noon UTC
-  workflow_dispatch:  # Allow manual trigger
+    - cron: "0 0,12 * * *" # Runs every 12 hours at midnight and noon UTC
+  workflow_dispatch: # Allow manual trigger
 
 jobs:
   create-staging-branch:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
+    permissions:
+      contents: write
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v3
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
         with:
           fetch-depth: 0
+          persist-credentials: false
 
       - name: Create daily staging branch
         env:
@@ -41,3 +45,43 @@ jobs:
             git push origin $BRANCH_NAME
             echo "Successfully created and pushed branch: $BRANCH_NAME"
           fi
+
+  create-internal-dev-branch:
+    if: github.repository == 'BerriAI/litellm'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Create internal dev branch
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+        run: |
+          # Configure Git user
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+
+          # Generate branch name with MM_DD_YYYY format
+          BRANCH_NAME="litellm_internal_dev_$(date +'%m_%d_%Y')"
+          echo "Creating branch: $BRANCH_NAME"
+
+          # Fetch all branches
+          git fetch --all
+
+          # Check if the branch already exists
+          if git show-ref --verify --quiet refs/remotes/origin/$BRANCH_NAME; then
+            echo "Branch $BRANCH_NAME already exists. Skipping creation."
+          else
+            echo "Creating new branch: $BRANCH_NAME"
+            # Create the new branch from main
+            git checkout -b $BRANCH_NAME origin/main
+            # Push the new branch
+            git push origin $BRANCH_NAME
+            echo "Successfully created and pushed branch: $BRANCH_NAME"
+          fi

.github/workflows/ghcr_deploy.yml

@@ -1,434 +0,0 @@
-# this workflow is triggered by an API call when there is a new PyPI release of LiteLLM
-name: Build, Publish LiteLLM Docker Image. New Release
-on:
-  workflow_dispatch:
-    inputs:
-      tag:
-        description: "The tag version you want to build"
-        required: true
-      release_type:
-        description: "The release type you want to build. Can be 'latest', 'stable', 'dev', 'rc'"
-        type: string
-        default: "latest"
-      commit_hash:
-        description: "Commit hash"
-        required: true
-
-# Defines two custom environment variables for the workflow. Used for the Container registry domain, and a name for the Docker image that this workflow builds.
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
-  CHART_NAME: litellm-helm
-
-# There is a single job in this workflow. It's configured to run on the latest available version of Ubuntu.
-jobs:
-  # print commit hash, tag, and release type
-  print:
-    runs-on: ubuntu-latest
-    steps:
-      - run: |
-          echo "Commit hash: ${{ github.event.inputs.commit_hash }}"
-          echo "Tag: ${{ github.event.inputs.tag }}"
-          echo "Release type: ${{ github.event.inputs.release_type }}"
-  docker-hub-deploy:
-    if: github.repository == 'BerriAI/litellm'
-    runs-on: ubuntu-latest
-    steps:
-      -
-        name: Checkout
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-      -
-        name: Set up QEMU
-        uses: docker/setup-qemu-action@v3
-      -
-        name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-      -
-        name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-      -
-        name: Build and push
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          tags: litellm/litellm:${{ github.event.inputs.tag || 'latest' }} 
-      -
-        name: Build and push litellm-database image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          file: ./docker/Dockerfile.database
-          tags: litellm/litellm-database:${{ github.event.inputs.tag || 'latest' }}
-      -
-        name: Build and push litellm-spend-logs image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          file: ./litellm-js/spend-logs/Dockerfile
-          tags: litellm/litellm-spend_logs:${{ github.event.inputs.tag || 'latest' }}
-      -
-        name: Build and push litellm-non_root image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          push: true
-          file: ./docker/Dockerfile.non_root
-          tags: litellm/litellm-non_root:${{ github.event.inputs.tag || 'latest' }}
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    # Sets the permissions granted to the `GITHUB_TOKEN` for the actions in this job.
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-      # Uses the `docker/login-action` action to log in to the Container registry registry using the account and password that will publish the packages. Once published, the packages are scoped to the account defined here.
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
-      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
-      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
-      - name: Build and push Docker image
-        uses: docker/build-push-action@4976231911ebf5f32aad765192d35f942aa48cb8
-        with:
-          context: .
-          push: true
-          tags: |
-            ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm:main-stable', env.REGISTRY) || '' }},
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm:{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-          labels: ${{ steps.meta.outputs.labels }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-  
-  build-and-push-image-ee:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for EE Dockerfile
-        id: meta-ee
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-ee
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push EE Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: Dockerfile
-          push: true
-          tags: |
-            ${{ steps.meta-ee.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-ee.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-ee:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-ee:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta-ee.outputs.labels }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-   
-  build-and-push-image-database:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for database Dockerfile
-        id: meta-database
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-database
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push Database Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./docker/Dockerfile.database
-          push: true
-          tags: |
-            ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-database.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-database:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-database:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta-database.outputs.labels }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-            
-  build-and-push-image-non_root:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for non_root Dockerfile
-        id: meta-non_root
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-non_root
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push non_root Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./docker/Dockerfile.non_root
-          push: true
-          tags: |
-            ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-non_root.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-non_root:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-non_root:main-stable', env.REGISTRY) || '' }}
-          labels: ${{ steps.meta-non_root.outputs.labels }} 
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-  
-  build-and-push-image-spend-logs:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          ref: ${{ github.event.inputs.commit_hash }}
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: Extract metadata (tags, labels) for spend-logs Dockerfile
-        id: meta-spend-logs
-        uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}-spend_logs
-      # Configure multi platform Docker builds
-      - name: Set up QEMU
-        uses: docker/setup-qemu-action@e0e4588fad221d38ee467c0bffd91115366dc0c5
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@edfb0fe6204400c56fbfd3feba3fe9ad1adfa345
-
-      - name: Build and push Database Docker image
-        uses: docker/build-push-action@f2a1d5e99d037542a71f64918e516c093c6f3fc4
-        with:
-          context: .
-          file: ./litellm-js/spend-logs/Dockerfile
-          push: true
-          tags: |
-            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.tag || 'latest' }},
-            ${{ steps.meta-spend-logs.outputs.tags }}-${{ github.event.inputs.release_type }}
-            ${{ (github.event.inputs.release_type == 'stable'  || github.event.inputs.release_type == 'rc') && format('{0}/berriai/litellm-spend_logs:main-{1}', env.REGISTRY, github.event.inputs.tag) || '' }},
-            ${{ github.event.inputs.release_type == 'stable' && format('{0}/berriai/litellm-spend_logs:main-stable', env.REGISTRY) || '' }}
-          platforms: local,linux/amd64,linux/arm64,linux/arm64/v8
-
-  build-and-push-helm-chart:
-    if: github.event.inputs.release_type  != 'dev'
-    needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-        with:
-          fetch-depth: 0
-
-      - name: Log in to the Container registry
-        uses: docker/login-action@65b78e6e13532edd9afa3aa52ac7964289d1a9c1
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-
-      - name: lowercase github.repository_owner
-        run: |
-          echo "REPO_OWNER=`echo ${{github.repository_owner}} | tr '[:upper:]' '[:lower:]'`" >>${GITHUB_ENV}
-    
-      # Sync Helm chart version with LiteLLM release version (1-1 versioning)
-      # This allows users to easily map Helm chart versions to LiteLLM versions
-      # See: https://codefresh.io/docs/docs/ci-cd-guides/helm-best-practices/
-      - name: Calculate chart and app versions
-        id: chart_version
-        shell: bash
-        run: |
-          INPUT_TAG="${{ github.event.inputs.tag }}"
-          RELEASE_TYPE="${{ github.event.inputs.release_type }}"
-
-          # Chart version = LiteLLM version without 'v' prefix (Helm semver convention)
-          # v1.81.0 -> 1.81.0, v1.81.0.rc.1 -> 1.81.0.rc.1
-          CHART_VERSION="${INPUT_TAG#v}"
-
-          # Add suffix for 'latest' releases (rc already has suffix in tag)
-          if [ "$RELEASE_TYPE" = "latest" ]; then
-            CHART_VERSION="${CHART_VERSION}-latest"
-          fi
-
-          # App version = Docker tag (keeps 'v' prefix to match Docker image tags)
-          APP_VERSION="${INPUT_TAG}"
-
-          echo "version=${CHART_VERSION}" | tee -a $GITHUB_OUTPUT
-          echo "app_version=${APP_VERSION}" | tee -a $GITHUB_OUTPUT
-
-      - uses: ./.github/actions/helm-oci-chart-releaser
-        with:
-          name: ${{ env.CHART_NAME }}
-          repository: ${{ env.REPO_OWNER }}
-          tag: ${{ steps.chart_version.outputs.version }}
-          app_version: ${{ steps.chart_version.outputs.app_version }}
-          path: deploy/charts/${{ env.CHART_NAME }}
-          registry: ${{ env.REGISTRY }}
-          registry_username: ${{ github.actor }}
-          registry_password: ${{ secrets.GITHUB_TOKEN }}
-          update_dependencies: true
-
-  release:
-    name: "New LiteLLM Release"
-    needs: [docker-hub-deploy, build-and-push-image, build-and-push-image-database]
-
-    runs-on: "ubuntu-latest"
-   
-    steps:
-      - name: Display version
-        run: echo "Current version is ${{ github.event.inputs.tag }}"
-      - name: "Set Release Tag"
-        run: echo "RELEASE_TAG=${{ github.event.inputs.tag }}" >> $GITHUB_ENV
-      - name: Display release tag
-        run: echo "RELEASE_TAG is $RELEASE_TAG"
-      - name: "Create release"
-        uses: "actions/github-script@v6"
-        with:
-          github-token: "${{ secrets.GITHUB_TOKEN }}"
-          script: |
-            const commitHash = "${{ github.event.inputs.commit_hash}}";
-            console.log("Commit Hash:", commitHash); // Add this line for debugging
-            try {
-              const response = await github.rest.repos.createRelease({
-                draft: false,
-                generate_release_notes: true,
-                target_commitish: commitHash,
-                name: process.env.RELEASE_TAG,
-                owner: context.repo.owner,
-                prerelease: false,
-                repo: context.repo.repo,
-                tag_name: process.env.RELEASE_TAG,
-              });
-      
-              core.exportVariable('RELEASE_ID', response.data.id);
-              core.exportVariable('RELEASE_UPLOAD_URL', response.data.upload_url);
-            } catch (error) {
-              core.setFailed(error.message);
-            }
-      - name: Fetch Release Notes
-        id: release-notes
-        uses: actions/github-script@v6
-        with:
-          github-token: "${{ secrets.GITHUB_TOKEN }}"
-          script: |
-            try {
-              const response = await github.rest.repos.getRelease({
-                owner: context.repo.owner,
-                repo: context.repo.repo,
-                release_id: process.env.RELEASE_ID,
-              });
-              const formattedBody = JSON.stringify(response.data.body).slice(1, -1);
-              return formattedBody;
-            } catch (error) {
-              core.setFailed(error.message);
-            }
-        env:
-          RELEASE_ID: ${{ env.RELEASE_ID }}
-      - name: Github Releases To Discord
-        env:
-          WEBHOOK_URL: ${{ secrets.WEBHOOK_URL }}
-          REALEASE_TAG: ${{ env.RELEASE_TAG }}
-          RELEASE_NOTES: ${{ steps.release-notes.outputs.result }}
-        run: |
-          curl -H "Content-Type: application/json" -X POST -d '{
-            "content": "New LiteLLM release '"${RELEASE_TAG}"'",
-            "username": "Release Changelog",
-            "avatar_url": "https://cdn.discordapp.com/avatars/487431320314576937/bd64361e4ba6313d561d54e78c9e7171.png",
-            "embeds": [
-              {
-                "title": "Changelog for LiteLLM '"${RELEASE_TAG}"'",
-                "description": "'"${RELEASE_NOTES}"'",
-                "color": 2105893
-              }
-            ]
-          }' $WEBHOOK_URL
-

.github/workflows/ghcr_helm_deploy.yml

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

.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/helm_unit_test.yml

@@ -6,22 +6,36 @@ on:
     branches:
       - main
 
+permissions:
+  contents: read
+
 jobs:
   unit-test:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout
-        uses: actions/checkout@v2
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
       - name: Set up Helm 3.11.1
-        uses: azure/setup-helm@v1
+        uses: azure/setup-helm@1a275c3b69536ee54be43f2070a358922e12c8d4 # v4.3.1
         with:
-          version: '3.11.1'
+          version: "3.11.1"
 
       - name: Install Helm Unit Test Plugin
         run: |
           helm plugin install https://github.com/helm-unittest/helm-unittest --version v0.4.4
+      - name: Verify Helm Unit Test Plugin integrity
+        run: |
+          EXPECTED_SHA="e251ba198448629678ff2168e1a469249d998155"
+          PLUGIN_DIR="$(helm env HELM_PLUGINS)/helm-unittest"
+          ACTUAL_SHA="$(git -C "$PLUGIN_DIR" rev-parse HEAD)"
+          if [ "$ACTUAL_SHA" != "$EXPECTED_SHA" ]; then
+            echo "::error::Helm unittest plugin checksum mismatch! Expected $EXPECTED_SHA but got $ACTUAL_SHA"
+            exit 1
+          fi
+          echo "Helm unittest plugin integrity verified: $ACTUAL_SHA"
 
       - name: Run unit tests
-        run:
-          helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm
+        run: helm unittest -f 'tests/*.yaml' deploy/charts/litellm-helm

.github/workflows/interpret_load_test.py

@@ -1,139 +0,0 @@
-import csv
-import os
-from github import Github
-
-
-def interpret_results(csv_file):
-    with open(csv_file, newline="") as csvfile:
-        csvreader = csv.DictReader(csvfile)
-        rows = list(csvreader)
-        """
-        in this csv reader
-        - Create 1 new column "Status"
-        - if a row has a median response time < 300 and an average response time < 300, Status = "Passed ✅"
-        - if a row has a median response time >= 300 or an average response time >= 300, Status = "Failed ❌"
-        - Order the table in this order Name, Status, Median Response Time, Average Response Time, Requests/s,Failures/s, Min Response Time, Max Response Time, all other columns
-        """
-
-        # Add a new column "Status"
-        for row in rows:
-            median_response_time = float(
-                row["Median Response Time"].strip().rstrip("ms")
-            )
-            average_response_time = float(
-                row["Average Response Time"].strip().rstrip("s")
-            )
-
-            request_count = int(row["Request Count"])
-            failure_count = int(row["Failure Count"])
-
-            failure_percent = round((failure_count / request_count) * 100, 2)
-
-            # Determine status based on conditions
-            if (
-                median_response_time < 300
-                and average_response_time < 300
-                and failure_percent < 5
-            ):
-                row["Status"] = "Passed ✅"
-            else:
-                row["Status"] = "Failed ❌"
-
-        # Construct Markdown table header
-        markdown_table = "| Name | Status | Median Response Time (ms) | Average Response Time (ms) | Requests/s | Failures/s | Request Count | Failure Count | Min Response Time (ms) | Max Response Time (ms) |"
-        markdown_table += (
-            "\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |"
-        )
-
-        # Construct Markdown table rows
-        for row in rows:
-            markdown_table += f"\n| {row['Name']} | {row['Status']} | {row['Median Response Time']} | {row['Average Response Time']} | {row['Requests/s']} | {row['Failures/s']} | {row['Request Count']} | {row['Failure Count']} | {row['Min Response Time']} | {row['Max Response Time']} |"
-    print("markdown table: ", markdown_table)
-    return markdown_table
-
-
-def _get_docker_run_command_stable_release(release_version):
-    return f"""
-\n\n
-## Docker Run LiteLLM Proxy
-
-```
-docker run \\
--e STORE_MODEL_IN_DB=True \\
--p 4000:4000 \\
-ghcr.io/berriai/litellm:litellm_stable_release_branch-{release_version}
-```
-    """
-
-
-def _get_docker_run_command(release_version):
-    return f"""
-\n\n
-## Docker Run LiteLLM Proxy
-
-```
-docker run \\
--e STORE_MODEL_IN_DB=True \\
--p 4000:4000 \\
-ghcr.io/berriai/litellm:main-{release_version}
-```
-    """
-
-
-def get_docker_run_command(release_version):
-    if "stable" in release_version:
-        return _get_docker_run_command_stable_release(release_version)
-    else:
-        return _get_docker_run_command(release_version)
-
-
-if __name__ == "__main__":
-    return
-    csv_file = "load_test_stats.csv"  # Change this to the path of your CSV file
-    markdown_table = interpret_results(csv_file)
-
-    # Update release body with interpreted results
-    github_token = os.getenv("GITHUB_TOKEN")
-    g = Github(github_token)
-    repo = g.get_repo(
-        "BerriAI/litellm"
-    )  # Replace with your repository's username and name
-    latest_release = repo.get_latest_release()
-    print("got latest release: ", latest_release)
-    print(latest_release.title)
-    print(latest_release.tag_name)
-
-    release_version = latest_release.title
-
-    print("latest release body: ", latest_release.body)
-    print("markdown table: ", markdown_table)
-
-    # check if "Load Test LiteLLM Proxy Results" exists
-    existing_release_body = latest_release.body
-    if "Load Test LiteLLM Proxy Results" in latest_release.body:
-        # find the "Load Test LiteLLM Proxy Results" section and delete it
-        start_index = latest_release.body.find("Load Test LiteLLM Proxy Results")
-        existing_release_body = latest_release.body[:start_index]
-
-    docker_run_command = get_docker_run_command(release_version)
-    print("docker run command: ", docker_run_command)
-
-    new_release_body = (
-        existing_release_body
-        + docker_run_command
-        + "\n\n"
-        + "### Don't want to maintain your internal proxy? get in touch 🎉"
-        + "\nHosted Proxy Alpha: https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions"
-        + "\n\n"
-        + "## Load Test LiteLLM Proxy Results"
-        + "\n\n"
-        + markdown_table
-    )
-    print("new release body: ", new_release_body)
-    try:
-        latest_release.update_release(
-            name=latest_release.tag_name,
-            message=new_release_body,
-        )
-    except Exception as e:
-        print(e)

.github/workflows/issue-keyword-labeler.yml

@@ -2,8 +2,8 @@ name: Issue Keyword Labeler
 
 on:
   issues:
-    types: 
-        - opened
+    types:
+      - opened
 
 jobs:
   scan-and-label:
@@ -13,7 +13,9 @@ jobs:
       contents: read
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
       - name: Scan for provider keywords
         id: scan
@@ -24,7 +26,7 @@ jobs:
 
       - name: Ensure label exists
         if: steps.scan.outputs.found == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -51,7 +53,7 @@ jobs:
 
       - name: Add label to the issue
         if: steps.scan.outputs.found == 'true'
-        uses: actions/github-script@v7
+        uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
         with:
           github-token: ${{ secrets.GITHUB_TOKEN }}
           script: |
@@ -61,4 +63,3 @@ jobs:
               issue_number: context.issue.number,
               labels: ['llm translation']
             });
-

.github/workflows/label-component.yml

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

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

@@ -4,54 +4,56 @@ on:
   workflow_dispatch:
     inputs:
       release_candidate_tag:
-        description: 'Release candidate tag/version'
+        description: "Release candidate tag/version"
         required: true
         type: string
   push:
     tags:
-      - 'v*-rc*'  # Triggers on release candidate tags like v1.0.0-rc1
-  
+      - "v*-rc*" # Triggers on release candidate tags like v1.0.0-rc1
+
+permissions:
+  contents: read
+
 jobs:
   run-llm-translation-tests:
     runs-on: ubuntu-latest
     timeout-minutes: 90
-    
+
     steps:
       - name: Checkout code
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
         with:
+          persist-credentials: false
           ref: ${{ github.event.inputs.release_candidate_tag || github.ref }}
-      
+
       - name: Set up Python
-        uses: actions/setup-python@v5
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
         with:
-          python-version: '3.11'
-      
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
         with:
-          version: latest
-          virtualenvs-create: true
-          virtualenvs-in-project: true
-      
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v3
+          version: "0.10.9"
+          enable-cache: false
+
+      - 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 pytest-timeout
-      
+          uv sync --frozen
+
       - name: Create test results directory
         run: mkdir -p test-results
-      
+
       - name: Run LLM Translation Tests
         env:
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
@@ -61,13 +63,14 @@ jobs:
           AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
           AZURE_API_BASE: ${{ secrets.AZURE_API_BASE }}
           AZURE_API_VERSION: ${{ secrets.AZURE_API_VERSION }}
-          # Add other API keys as needed
+          RC_TAG: ${{ github.event.inputs.release_candidate_tag || github.ref_name }}
+          COMMIT_SHA: ${{ github.sha }}
         run: |
           python .github/workflows/run_llm_translation_tests.py \
-            --tag "${{ github.event.inputs.release_candidate_tag || github.ref_name }}" \
-            --commit "${{ github.sha }}" \
+            --tag "$RC_TAG" \
+            --commit "$COMMIT_SHA" \
             || true  # Continue even if tests fail
-      
+
       - name: Display test summary
         if: always()
         run: |
@@ -79,9 +82,9 @@ jobs:
           else
             echo "Warning: Test report was not generated"
           fi
-      
+
       - name: Upload test artifacts
-        uses: actions/upload-artifact@v4
+        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
         if: always()
         with:
           name: LLM-Translation-Artifact-${{ github.event.inputs.release_candidate_tag || github.ref_name }}

.github/workflows/load_test.yml

@@ -1,59 +0,0 @@
-name: Test Locust Load Test
-
-on:
-  workflow_run:
-    workflows: ["Build, Publish LiteLLM Docker Image. New Release"]
-    types:
-      - completed
-  workflow_dispatch:
-
-jobs:
-  build:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v1
-      - name: Setup Python
-        uses: actions/setup-python@v2
-        with:
-          python-version: '3.x'
-
-      - name: Install dependencies
-        run: |
-          python -m pip install --upgrade pip
-          pip install PyGithub
-      - name: re-deploy proxy
-        run: |
-          echo "Current working directory: $PWD"
-          ls
-          python ".github/workflows/redeploy_proxy.py"
-        env:
-          LOAD_TEST_REDEPLOY_URL1: ${{ secrets.LOAD_TEST_REDEPLOY_URL1 }}
-          LOAD_TEST_REDEPLOY_URL2: ${{ secrets.LOAD_TEST_REDEPLOY_URL2 }}
-        working-directory: ${{ github.workspace }}
-      - name: Run Load Test
-        id: locust_run
-        uses: BerriAI/locust-github-action@master
-        with:
-          LOCUSTFILE: ".github/workflows/locustfile.py"
-          URL:  "https://post-release-load-test-proxy.onrender.com/"
-          USERS: "20"
-          RATE: "20"
-          RUNTIME: "300s"
-      - name: Process Load Test Stats
-        run: |
-          echo "Current working directory: $PWD"
-          ls
-          python ".github/workflows/interpret_load_test.py"
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        working-directory: ${{ github.workspace }}
-      - name: Upload CSV as Asset to Latest Release
-        uses: xresloader/upload-to-github-release@v1
-        env:
-          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-        with:
-          file: "load_test_stats.csv;load_test.html"
-          update_latest_release: true
-          tag_name: "load-test"
-          overwrite: true

.github/workflows/locustfile.py

@@ -1,28 +0,0 @@
-from locust import HttpUser, task, between
-
-
-class MyUser(HttpUser):
-    wait_time = between(1, 5)
-
-    @task
-    def chat_completion(self):
-        headers = {
-            "Content-Type": "application/json",
-            "Authorization": "Bearer sk-8N1tLOOyH8TIxwOLahhIVg",
-            # Include any additional headers you may need for authentication, etc.
-        }
-
-        # Customize the payload with "model" and "messages" keys
-        payload = {
-            "model": "fake-openai-endpoint",
-            "messages": [
-                {"role": "system", "content": "You are a chat bot."},
-                {"role": "user", "content": "Hello, how are you?"},
-            ],
-            # Add more data as necessary
-        }
-
-        # Make a POST request to the "chat/completions" endpoint
-        response = self.client.post("chat/completions", json=payload, headers=headers)
-
-        # Print or log the response if needed

.github/workflows/main.yml

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

.github/workflows/publish-migrations.yml

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

.github/workflows/publish_to_pypi.yml

@@ -0,0 +1,153 @@
+name: Publish to PyPI
+
+on:
+  workflow_dispatch:
+
+jobs:
+  preflight-checks:
+    name: Preflight Checks
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      contents: read
+    # No environment — read-only checks, no approval needed
+    outputs:
+      needs_publish: ${{ steps.check-litellm.outputs.needs_publish }}
+      version: ${{ steps.check-litellm.outputs.version }}
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Set up uv
+        uses: astral-sh/setup-uv@37802adc94f370d6bfd71619e3f0bf239e1f3b78 # v7
+        with:
+          version: "0.10.9"
+          enable-cache: false
+
+      - name: Check litellm version on PyPI
+        id: check-litellm
+        run: |
+          VERSION=$(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 $VERSION exists on PyPI..."
+
+          HTTP_STATUS=$(curl -s -o /dev/null -w "%{http_code}" "https://pypi.org/pypi/litellm/$VERSION/json")
+          if [ "$HTTP_STATUS" = "200" ]; then
+            echo "litellm $VERSION already exists on PyPI. Skipping publish."
+            echo "needs_publish=false" >> "$GITHUB_OUTPUT"
+          else
+            echo "litellm $VERSION not found on PyPI. Publish needed."
+            echo "needs_publish=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Sanity check proxy-extras version
+        run: |
+          # Read pinned version from project optional dependencies
+          PYPROJECT_VERSION=$(python3 - <<'PY'
+          import sys
+          import tomllib
+
+          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 the pinned version exists on PyPI
+          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 $PYPROJECT_VERSION is not published on PyPI yet. Publish it before releasing litellm."
+            exit 1
+          fi
+          echo "litellm-proxy-extras $PYPROJECT_VERSION exists on PyPI. Sanity check passed."
+
+  publish-litellm:
+    name: Publish litellm to PyPI
+    needs: preflight-checks
+    if: needs.preflight-checks.outputs.needs_publish == 'true'
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    permissions:
+      id-token: write
+      contents: read
+    environment: pypi-publish
+
+    steps:
+      - name: Checkout repo
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: 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: Build package
+        run: |
+          rm -rf build dist
+          uv build
+
+      - name: Verify build artifacts
+        env:
+          EXPECTED_VERSION: ${{ needs.preflight-checks.outputs.version }}
+        run: |
+          echo "Contents of dist/:"
+          ls -la dist/
+          # Ensure we have both sdist and wheel
+          ls dist/*.tar.gz
+          ls dist/*.whl
+          # Verify built version matches expected
+          ls dist/ | grep -q "litellm-${EXPECTED_VERSION}" || {
+            echo "::error::Built artifacts do not match expected version $EXPECTED_VERSION"
+            ls dist/
+            exit 1
+          }
+
+      - name: Validate package metadata
+        run: |
+          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/read_pyproject_version.yml

@@ -3,7 +3,10 @@ name: Read Version from pyproject.toml
 on:
   push:
     branches:
-      - main  # Change this to the default branch of your repository
+      - main # Change this to the default branch of your repository
+
+permissions:
+  contents: read
 
 jobs:
   read-version:
@@ -11,20 +14,14 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v2
-
-      - name: Set up Python
-        uses: actions/setup-python@v2
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
         with:
-          python-version: 3.8  # Adjust the Python version as needed
-
-      - name: Install dependencies
-        run: pip install toml
+          persist-credentials: false
 
       - name: Read version from pyproject.toml
         id: read-version
         run: |
-          version=$(python -c 'import toml; print(toml.load("pyproject.toml")["tool"]["commitizen"]["version"])')
+          version=$(grep -m1 '^version' pyproject.toml | sed 's/version = "\(.*\)"/\1/')
           printf "LITELLM_VERSION=%s" "$version" >> $GITHUB_ENV
 
       - name: Display version

.github/workflows/redeploy_proxy.py

@@ -1,20 +0,0 @@
-"""
-
-redeploy_proxy.py
-"""
-
-import os
-import requests
-import time
-
-# send a get request to this endpoint
-deploy_hook1 = os.getenv("LOAD_TEST_REDEPLOY_URL1")
-response = requests.get(deploy_hook1, timeout=20)
-
-
-deploy_hook2 = os.getenv("LOAD_TEST_REDEPLOY_URL2")
-response = requests.get(deploy_hook2, timeout=20)
-
-print("SENT GET REQUESTS to re-deploy proxy")
-print("sleeeping.... for 60s")
-time.sleep(60)

.github/workflows/regenerate-poetry-lock.yml

@@ -1,80 +0,0 @@
-name: Regenerate poetry.lock
-
-# Runs whenever pyproject.toml is merged into main (the most common cause of
-# the "pyproject.toml changed significantly since poetry.lock was last generated"
-# CI failure).  Can also be triggered manually.
-on:
-  push:
-    branches:
-      - main
-    paths:
-      - pyproject.toml
-  workflow_dispatch:
-
-permissions:
-  contents: write       # needed to push the auto/regenerate-poetry-lock-* branch
-  pull-requests: write  # needed to open the PR and enable auto-merge
-
-jobs:
-  regenerate-lock:
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.11"
-
-      - name: Install Poetry
-        run: pip install poetry
-
-      - name: Regenerate poetry.lock
-        run: poetry lock
-
-      - name: Check whether poetry.lock actually changed
-        id: diff
-        run: |
-          if git diff --quiet poetry.lock; then
-            echo "changed=false" >> "$GITHUB_OUTPUT"
-          else
-            echo "changed=true" >> "$GITHUB_OUTPUT"
-          fi
-
-      - name: Open PR with the refreshed lock file
-        if: steps.diff.outputs.changed == 'true'
-        id: open-pr
-        run: |
-          BRANCH="auto/regenerate-poetry-lock-$(date +'%Y%m%d%H%M%S')"
-          git config user.name "github-actions[bot]"
-          git config user.email "github-actions[bot]@users.noreply.github.com"
-          git checkout -b "$BRANCH"
-          git add poetry.lock
-          git commit -m "chore: regenerate poetry.lock to match pyproject.toml"
-          git push -f origin "$BRANCH"
-
-          cat > /tmp/pr-body.md << 'BODY'
-          Automated regeneration of `poetry.lock` after `pyproject.toml` was updated on `main`.
-
-          Fixes the recurring CI failure:
-          ```
-          pyproject.toml changed significantly since poetry.lock was last generated.
-          Run `poetry lock` to fix the lock file.
-          ```
-          BODY
-
-          PR_URL=$(gh pr create \
-            --title "chore: regenerate poetry.lock to match pyproject.toml" \
-            --body-file /tmp/pr-body.md \
-            --head "$BRANCH" \
-            --base main)
-          echo "pr_url=$PR_URL" >> "$GITHUB_OUTPUT"
-        env:
-          GH_TOKEN: ${{ github.token }}
-
-      - name: Enable auto-merge
-        if: steps.diff.outputs.changed == 'true'
-        run: |
-          gh pr merge "${{ steps.open-pr.outputs.pr_url }}" --auto --squash
-        env:
-          GH_TOKEN: ${{ github.token }}

.github/workflows/reset_stable.yml

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

.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/run_observatory_tests.yml

@@ -0,0 +1,229 @@
+name: Run Observatory Tests
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: "Docker image tag to test (e.g. v1.61.0.rc1)"
+        required: true
+        type: string
+      commit_hash:
+        description: "Commit hash (defaults to HEAD of current branch)"
+        required: false
+        type: string
+  workflow_call:
+    inputs:
+      tag:
+        description: "Docker image tag to test"
+        required: true
+        type: string
+      commit_hash:
+        description: "Commit hash of the release"
+        required: true
+        type: string
+
+permissions:
+  contents: read
+
+env:
+  LITELLM_MASTER_KEY: ${{ secrets.LITELLM_MASTER_KEY_STAGING }}
+
+jobs:
+  observatory-tests:
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Validate tag input
+        env:
+          TAG: ${{ inputs.tag }}
+        run: |
+          if [[ ! "$TAG" =~ ^v[0-9]+\.[0-9]+\.[0-9]+ ]]; then
+            echo "Invalid tag format: $TAG (expected vX.Y.Z...)"
+            exit 1
+          fi
+
+      - name: Start LiteLLM container
+        env:
+          TAG: ${{ inputs.tag }}
+          AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
+          AZURE_API_BASE: ${{ secrets.AZURE_API_BASE }}
+          WORKSPACE: ${{ github.workspace }}
+        run: |
+          docker run -d \
+            --name litellm-rc \
+            -p 4000:4000 \
+            -v "${WORKSPACE}/.github/observatory/litellm_config.yaml:/app/config.yaml" \
+            -e LITELLM_MASTER_KEY="${LITELLM_MASTER_KEY}" \
+            -e AZURE_API_KEY="${AZURE_API_KEY}" \
+            -e AZURE_API_BASE="${AZURE_API_BASE}" \
+            "litellm/litellm:${TAG}" \
+            --config /app/config.yaml --port 4000
+
+      - name: Wait for LiteLLM health check
+        run: |
+          echo "Waiting for LiteLLM to be ready..."
+          for i in $(seq 1 30); do
+            if curl -s -f http://localhost:4000/health/liveliness > /dev/null 2>&1; then
+              echo "LiteLLM is healthy"
+              exit 0
+            fi
+            echo "Attempt $i/30 - not ready yet, waiting 10s..."
+            sleep 10
+          done
+          echo "LiteLLM failed to start within 5 minutes"
+          docker logs litellm-rc
+          exit 1
+
+      - name: Start cloudflared tunnel
+        run: |
+          # Install cloudflared (pinned version + checksum)
+          curl -sL https://github.com/cloudflare/cloudflared/releases/download/2025.2.1/cloudflared-linux-amd64 -o /usr/local/bin/cloudflared
+          echo "afdfadd1ef552e66bffc35246fe30a9bd578356d2d386de95585ccfc432472b8  /usr/local/bin/cloudflared" | sha256sum -c -
+          chmod +x /usr/local/bin/cloudflared
+
+          # Start a quick tunnel (no account needed) and capture the URL
+          cloudflared tunnel --url http://localhost:4000 --no-autoupdate > /tmp/cloudflared.log 2>&1 &
+          CLOUDFLARED_PID=$!
+          echo "CLOUDFLARED_PID=$CLOUDFLARED_PID" >> $GITHUB_ENV
+
+          # Wait for tunnel URL to appear in logs
+          echo "Waiting for tunnel URL..."
+          for i in $(seq 1 30); do
+            TUNNEL_URL=$(grep -oP 'https://[a-z0-9-]+\.trycloudflare\.com' /tmp/cloudflared.log | head -1 || true)
+            if [ -n "$TUNNEL_URL" ]; then
+              echo "Tunnel URL: $TUNNEL_URL"
+              echo "TUNNEL_URL=$TUNNEL_URL" >> $GITHUB_ENV
+              exit 0
+            fi
+            sleep 2
+          done
+          echo "Failed to get tunnel URL"
+          cat /tmp/cloudflared.log
+          exit 1
+
+      - name: Verify tunnel connectivity
+        run: |
+          echo "Testing tunnel at ${TUNNEL_URL}..."
+          # Quick tunnels need time for DNS propagation; retry to avoid
+          # transient NXDOMAIN (curl exit code 6) on first attempt.
+          for i in $(seq 1 10); do
+            if curl -sf "${TUNNEL_URL}/health/liveliness" > /dev/null 2>&1; then
+              echo "Tunnel is working (attempt $i)"
+              exit 0
+            fi
+            echo "Attempt $i/10 - tunnel not routable yet, waiting 5s..."
+            sleep 5
+          done
+          echo "Tunnel failed to become reachable after 50s"
+          cat /tmp/cloudflared.log
+          exit 1
+
+      - name: Trigger observatory test run
+        id: trigger
+        env:
+          OBSERVATORY_URL: ${{ secrets.OBSERVATORY_URL }}
+          OBSERVATORY_API_KEY: ${{ secrets.OBSERVATORY_API_KEY }}
+        run: |
+          PAYLOAD=$(jq -n \
+            --arg url "${TUNNEL_URL}" \
+            --arg key "${LITELLM_MASTER_KEY}" \
+            '{
+              deployment_url: $url,
+              api_key: $key,
+              test_suite: "TestOAIAzureRelease",
+              models: ["gpt-4o-mini", "gpt-4o"]
+            }')
+          RESPONSE=$(curl -s -w "\n%{http_code}" -X POST "${OBSERVATORY_URL}/run-test" \
+            -H "Content-Type: application/json" \
+            -H "X-LiteLLM-Observatory-API-Key: ${OBSERVATORY_API_KEY}" \
+            -d "$PAYLOAD")
+          HTTP_CODE=$(echo "$RESPONSE" | tail -1)
+          BODY=$(echo "$RESPONSE" | head -n -1)
+          echo "Response ($HTTP_CODE): $BODY"
+          if [ "$HTTP_CODE" -ge 400 ]; then
+            echo "Failed to trigger test run"
+            exit 1
+          fi
+
+          # Extract request_id for polling this specific run
+          REQUEST_ID=$(echo "$BODY" | jq -r '.results.request_id')
+          if [ -z "$REQUEST_ID" ] || [ "$REQUEST_ID" = "null" ]; then
+            echo "Failed to extract request_id from response"
+            exit 1
+          fi
+          echo "Request ID: $REQUEST_ID"
+          echo "request_id=$REQUEST_ID" >> $GITHUB_OUTPUT
+
+      - name: Poll for test completion
+        id: poll
+        env:
+          OBSERVATORY_URL: ${{ secrets.OBSERVATORY_URL }}
+          OBSERVATORY_API_KEY: ${{ secrets.OBSERVATORY_API_KEY }}
+          REQUEST_ID: ${{ steps.trigger.outputs.request_id }}
+        run: |
+          TIMEOUT=900  # 15 minutes
+          INTERVAL=30
+          ELAPSED=0
+          while [ $ELAPSED -lt $TIMEOUT ]; do
+            STATUS=$(curl -s "${OBSERVATORY_URL}/run-status/${REQUEST_ID}" \
+              -H "X-LiteLLM-Observatory-API-Key: ${OBSERVATORY_API_KEY}")
+            RUN_STATUS=$(echo "$STATUS" | jq -r '.status')
+            echo "Run status (${ELAPSED}s elapsed): $RUN_STATUS"
+
+            if [ "$RUN_STATUS" = "completed" ] || [ "$RUN_STATUS" = "failed" ]; then
+              echo "Test finished with status: $RUN_STATUS"
+              echo "$STATUS" > /tmp/observatory_result.json
+              exit 0
+            fi
+
+            sleep $INTERVAL
+            ELAPSED=$((ELAPSED + INTERVAL))
+          done
+          echo "Timed out waiting for test to complete after ${TIMEOUT}s"
+          exit 1
+
+      - name: Verify test results
+        run: |
+          RESULT=$(cat /tmp/observatory_result.json)
+          echo "Full result: $RESULT"
+
+          STATUS=$(echo "$RESULT" | jq -r '.status')
+          TEST_PASSED=$(echo "$RESULT" | jq -r '.result.test_passed // false')
+          FAILURE_RATE=$(echo "$RESULT" | jq -r '.result.failure_rate // "N/A"')
+          ERROR=$(echo "$RESULT" | jq -r '.error // empty')
+
+          echo "Status: $STATUS"
+          echo "Test passed: $TEST_PASSED"
+          echo "Failure rate: $FAILURE_RATE"
+
+          if [ -n "$ERROR" ]; then
+            echo "Error: $ERROR"
+          fi
+
+          if [ "$STATUS" = "failed" ]; then
+            echo "Test run failed"
+            exit 1
+          fi
+
+          if [ "$TEST_PASSED" != "true" ]; then
+            echo "Tests did not pass (failure rate: $FAILURE_RATE)"
+            exit 1
+          fi
+
+          echo "All tests passed!"
+
+      - name: Print LiteLLM logs on failure
+        if: failure()
+        run: |
+          docker logs litellm-rc 2>/dev/null || true
+          cat /tmp/cloudflared.log 2>/dev/null || true
+
+      - name: Cleanup
+        if: always()
+        run: |
+          kill "$CLOUDFLARED_PID" 2>/dev/null || true
+          docker rm -f litellm-rc 2>/dev/null || true

.github/workflows/scan_duplicate_issues.yml

@@ -0,0 +1,48 @@
+name: Scan Duplicate Issues (One-Time)
+
+on:
+  workflow_dispatch:
+    inputs:
+      threshold:
+        description: "Similarity threshold (0-1)"
+        required: false
+        default: "0.85"
+      close:
+        description: "Actually close duplicates (false = dry run)"
+        required: false
+        type: boolean
+        default: false
+
+jobs:
+  scan:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      contents: read
+    steps:
+      - name: Checkout scripts
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          sparse-checkout: .github/scripts
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: Scan for duplicate issues
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          INPUT_THRESHOLD: ${{ inputs.threshold }}
+          INPUT_CLOSE: ${{ inputs.close }}
+        run: |
+          CLOSE_FLAG=""
+          if [ "$INPUT_CLOSE" = "true" ]; then
+            CLOSE_FLAG="--close"
+          fi
+          python3 .github/scripts/close_duplicate_issues.py \
+            --scan \
+            --repo ${{ github.repository }} \
+            --threshold "$INPUT_THRESHOLD" \
+            $CLOSE_FLAG

.github/workflows/scorecard.yml

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

.github/workflows/simple_pypi_publish.yml

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

.github/workflows/stale.yml

@@ -2,19 +2,24 @@ name: "Stale Issue Management"
 
 on:
   schedule:
-    - cron: '0 0 * * *' # Runs daily at midnight UTC
+    - cron: "0 0 * * *" # Runs daily at midnight UTC
   workflow_dispatch:
 
+permissions:
+  issues: write
+  pull-requests: write
+
 jobs:
   stale:
+    if: github.repository == 'BerriAI/litellm'
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v8
+      - uses: actions/stale@1160a2240286f5da8ec72b1c0816ce2481aabf84 # v8
         with:
           repo-token: "${{ secrets.GITHUB_TOKEN }}"
           stale-issue-message: "This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs."
           stale-pr-message: "This pull request has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs."
-          days-before-stale: 90        # Revert to 60 days
-          days-before-close: 7         # Revert to 7 days
+          days-before-stale: 90 # Revert to 60 days
+          days-before-close: 7 # Revert to 7 days
           stale-issue-label: "stale"
-          operations-per-run: 1000
+          operations-per-run: 1000

.github/workflows/sync-schema.yml

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

.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 +2,14 @@ name: LiteLLM Linting
 
 on:
   pull_request:
-    branches: [ main ]
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
 
 jobs:
   lint:
@@ -10,67 +17,108 @@ jobs:
     timeout-minutes: 5
 
     steps:
-    - uses: actions/checkout@v4
-      with:
-        fetch-depth: 0
-        clean: true
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          fetch-depth: 0
+          clean: true
+          persist-credentials: false
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.12'
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
 
-    - name: Install Poetry
-      uses: snok/install-poetry@v1
+      - 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: Clean Python cache
+        run: |
+          find . -type d -name "__pycache__" -exec rm -rf {} + || true
+          find . -name "*.pyc" -delete || true
 
-    - name: Install dependencies
-      run: |
-        poetry lock
-        poetry install --with dev
-        poetry run pip install openai==1.100.1
+      - name: Check uv.lock is up to date
+        run: |
+          uv lock --check || (echo "❌ uv.lock is out of sync with pyproject.toml. Run 'uv lock' locally and commit the result." && exit 1)
 
-    - name: Run Black formatting
-      run: |
-        cd litellm
-        poetry run black .
-        cd ..
+      - name: Install dependencies
+        run: |
+          uv sync --frozen
 
-    - name: Debug - Check file state
-      run: |
-        echo "Current branch:"
-        git branch --show-current
-        echo "Last 3 commits:"
-        git log --oneline -3
-        echo "File content around line 43:"
-        head -50 litellm/litellm_core_utils/custom_logger_registry.py | tail -10
-        
-    - name: Run Ruff linting
-      run: |
-        cd litellm
-        poetry run ruff check .
-        cd ..
+      - name: Check Black formatting
+        run: |
+          cd litellm
+          uv run --no-sync black --check --exclude '/enterprise/' .
+          cd ..
 
-    - name: Print OpenAI version
-      run: |
-        poetry run python -c "import openai; print(f'OpenAI version: {openai.__version__}')"
+      - name: Debug - Check file state
+        run: |
+          echo "Current branch:"
+          git branch --show-current
+          echo "Last 3 commits:"
+          git log --oneline -3
+          echo "File content around line 43:"
+          head -50 litellm/litellm_core_utils/custom_logger_registry.py | tail -10
 
-    - name: Run MyPy type checking
-      run: |
-        cd litellm
-        poetry run mypy . 
-        cd ..
+      - name: Run Ruff linting
+        run: |
+          cd litellm
+          uv run --no-sync ruff check .
+          cd ..
 
-    - name: Check for circular imports
-      run: |
-        cd litellm
-        poetry run python ../tests/documentation_tests/test_circular_imports.py
-        cd ..
+      - name: Print OpenAI version
+        run: |
+          uv run --no-sync python -c "import openai; print(f'OpenAI version: {openai.__version__}')"
 
-    - name: Check import safety
-      run: |
-        poetry run python -c "from litellm import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
+      - name: Run MyPy type checking
+        run: |
+          cd litellm
+          uv run --no-sync mypy .
+          cd ..
+
+      - name: Check for circular imports
+        run: |
+          cd litellm
+          uv run --no-sync python ../tests/documentation_tests/test_circular_imports.py
+          cd ..
+
+      - name: Check import safety
+        run: |
+          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
+    timeout-minutes: 5
+    permissions:
+      contents: read
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        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: |
+          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
+            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-matrix.yml

@@ -1,166 +0,0 @@
-name: LiteLLM Unit Tests (Matrix)
-
-on:
-  pull_request:
-    branches: [main]
-
-# Cancel in-progress runs for the same PR
-concurrency:
-  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  test:
-    runs-on: ubuntu-latest
-    timeout-minutes: 20  # Increased from 15 to 20
-    strategy:
-      fail-fast: false
-      matrix:
-        test-group:
-          # tests/test_litellm split by subdirectory (~560 files total)
-          # Vertex AI tests separated for better isolation (prevent auth/env pollution)
-          - name: "llms-vertex"
-            path: "tests/test_litellm/llms/vertex_ai"
-            workers: 1
-            reruns: 2
-          - name: "llms-other"
-            path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
-            workers: 2
-            reruns: 2
-          # tests/test_litellm/proxy split by subdirectory (~180 files total)
-          - name: "proxy-guardrails"
-            path: "tests/test_litellm/proxy/guardrails tests/test_litellm/proxy/management_endpoints tests/test_litellm/proxy/management_helpers"
-            workers: 2
-            reruns: 2
-          - name: "proxy-core"
-            path: "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"
-            workers: 2
-            reruns: 2
-          - name: "proxy-misc"
-            path: "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"
-            workers: 2
-            reruns: 2
-          - name: "integrations"
-            path: "tests/test_litellm/integrations"
-            workers: 2
-            reruns: 3  # Integration tests tend to be flakier
-          - name: "core-utils"
-            path: "tests/test_litellm/litellm_core_utils"
-            workers: 2
-            reruns: 1
-          - name: "other-1"
-            # responses (5942) + caching (1723) + types (819) ≈ 8.5k lines
-            path: "tests/test_litellm/responses tests/test_litellm/caching tests/test_litellm/types"
-            workers: 2
-            reruns: 2
-          - name: "other-2"
-            # enterprise (3062) + google_genai (2511) + router_utils (1982) ≈ 7.6k lines
-            path: "tests/test_litellm/enterprise tests/test_litellm/google_genai tests/test_litellm/router_utils"
-            workers: 2
-            reruns: 2
-          - name: "other-3"
-            # remaining dirs ≈ 8.0k lines
-            path: "tests/test_litellm/router_strategy tests/test_litellm/secret_managers tests/test_litellm/a2a_protocol tests/test_litellm/anthropic_interface tests/test_litellm/completion_extras tests/test_litellm/containers tests/test_litellm/experimental_mcp_client tests/test_litellm/images tests/test_litellm/interactions tests/test_litellm/passthrough tests/test_litellm/vector_stores"
-            workers: 2
-            reruns: 2
-          - name: "root"
-            path: "tests/test_litellm/test_*.py"
-            workers: 2
-            reruns: 2
-          # tests/proxy_unit_tests split alphabetically (~48 files total)
-          - name: "proxy-unit-a1"
-            # test_[a-j]*.py: jwt (1564) + auth_checks (978) + google_gemini (478) + e2e_pod_lock (437) + rest
-            path: "tests/proxy_unit_tests/test_[a-j]*.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-a2"
-            # test_[k-o]*.py: key_generate_prisma (4346) + key_generate_dynamodb + models_fallback
-            path: "tests/proxy_unit_tests/test_[k-o]*.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b1"
-            # lighter config/utility proxy tests (prisma, project, prompt, proxy_[c-r]*)
-            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"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b2"
-            # proxy_server.py alone (2750 lines) - isolated to avoid blocking smaller tests
-            path: "tests/proxy_unit_tests/test_proxy_server.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b3"
-            # proxy_server_* (618) + proxy_setting_guardrails (71) - smaller server-related tests
-            path: "tests/proxy_unit_tests/test_proxy_server_*.py tests/proxy_unit_tests/test_proxy_setting_guardrails.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b4"
-            # proxy_utils.py alone (2339 lines) - isolated to avoid blocking token counter
-            path: "tests/proxy_unit_tests/test_proxy_utils.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b5"
-            # proxy_token_counter (1279) - runs independently from utils
-            path: "tests/proxy_unit_tests/test_proxy_token_counter.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b6"
-            # test_[r-t]*.py: response_polling (1399) + search_api_logging (202) + server_root (64) + skills_db (261) + realtime_cache (62)
-            path: "tests/proxy_unit_tests/test_[r-t]*.py"
-            workers: 2
-            reruns: 1
-          - name: "proxy-unit-b7"
-            # test_[u-z]*.py: user_api_key_auth (1136) + zero_cost (590) + update_spend (305) + unit_test_* (206) + ui_path (157)
-            path: "tests/proxy_unit_tests/test_[u-z]*.py"
-            workers: 2
-            reruns: 1
-
-    name: test (${{ matrix.test-group.name }})
-
-    steps:
-      - uses: actions/checkout@v4
-
-      - name: Set up Python
-        uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-
-      - name: Install Poetry
-        uses: snok/install-poetry@v1
-
-      - name: Cache Poetry dependencies
-        uses: actions/cache@v4
-        with:
-          path: |
-            ~/.cache/pypoetry
-            ~/.cache/pip
-            .venv
-          key: ${{ runner.os }}-poetry-${{ hashFiles('poetry.lock') }}
-          restore-keys: |
-            ${{ runner.os }}-poetry-
-
-      - name: Install dependencies
-        run: |
-          poetry config virtualenvs.in-project true
-          poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          # pytest-rerunfailures and pytest-xdist are in pyproject.toml dev dependencies
-          poetry run pip install google-genai==1.22.0 \
-            google-cloud-aiplatform>=1.38 fastapi-offline==1.7.3 python-multipart==0.0.22 openapi-core
-
-      - name: Setup litellm-enterprise
-        run: |
-          poetry run pip install --force-reinstall --no-deps -e enterprise/
-
-      - name: Generate Prisma client
-        run: |
-          poetry run prisma generate --schema litellm/proxy/schema.prisma
-
-      - name: Run tests - ${{ matrix.test-group.name }}
-        run: |
-          poetry run pytest ${{ matrix.test-group.path }} \
-            --tb=short -vv \
-            --maxfail=10 \
-            -n ${{ matrix.test-group.workers }} \
-            --reruns ${{ matrix.test-group.reruns }} \
-            --reruns-delay 1 \
-            --dist=loadscope \
-            --durations=20

.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:
@@ -16,17 +20,19 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
       - name: Setup Node.js
-        uses: actions/setup-node@v4
+        uses: actions/setup-node@a0853c24544627f65ddf259abe73b1d18a591444 # v5.0
         with:
           node-version: "20"
           cache: "npm"
           cache-dependency-path: ui/litellm-dashboard/package-lock.json
 
       - name: Install dependencies
-        run: npm install
+        run: npm ci
 
       - name: Build
         run: npm run build

.github/workflows/test-litellm.yml

@@ -4,45 +4,42 @@ name: LiteLLM Mock Tests (folder - tests/test_litellm)
 # the same tests in parallel across 10 jobs for faster CI times.
 # Kept for manual debugging only.
 on:
-  workflow_dispatch:  # Manual trigger only
+  workflow_dispatch: # Manual trigger only
   # pull_request:
   #   branches: [ main ]
 
+permissions:
+  contents: read
+
 jobs:
   test:
     runs-on: ubuntu-latest
     timeout-minutes: 25
 
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
-    - name: Thank You Message
-      run: |
-        echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
-        echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
+      - name: Thank You Message
+        run: |
+          echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
+          echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.12'
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
 
-    - name: Install Poetry
-      uses: snok/install-poetry@v1
+      - 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
-        poetry run pip install "google-genai==1.22.0"
-        poetry run pip install "google-cloud-aiplatform>=1.38"
-        poetry run pip install "fastapi-offline==1.7.3"
-        poetry run pip install "python-multipart==0.0.22"
-        poetry run pip install "openapi-core"
-    - name: Setup litellm-enterprise as local package
-      run: |
-        poetry run pip install --force-reinstall --no-deps -e enterprise/
-    - name: Run tests
-      run: |
-        poetry run pytest tests/test_litellm --tb=short -vv --maxfail=10 -n 4 --durations=50
+      - name: Install dependencies
+        run: |
+          uv lock --check
+          uv sync --frozen --group ci --group proxy-dev --extra google --extra proxy --extra semantic-router
+      - name: Run tests
+        run: |
+          uv run --no-sync pytest tests/test_litellm --tb=short -vv --maxfail=10 -n 4 --durations=50

.github/workflows/test-mcp.yml

@@ -2,7 +2,14 @@ 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
 
 jobs:
   test:
@@ -10,38 +17,30 @@ jobs:
     timeout-minutes: 25
 
     steps:
-    - uses: actions/checkout@v4
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
-    - name: Thank You Message
-      run: |
-        echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
-        echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
+      - name: Thank You Message
+        run: |
+          echo "### 🙏 Thank you for contributing to LiteLLM!" >> $GITHUB_STEP_SUMMARY
+          echo "Your PR is being tested now. We appreciate your help in making LiteLLM better!" >> $GITHUB_STEP_SUMMARY
 
-    - name: Set up Python
-      uses: actions/setup-python@v4
-      with:
-        python-version: '3.12'
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
 
-    - name: Install Poetry
-      uses: snok/install-poetry@v1
+      - 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
+      - name: Install dependencies
+        run: |
+          uv lock --check
+          uv sync --frozen --group proxy-dev --extra proxy --extra semantic-router
 
-    - name: Setup litellm-enterprise as local package
-      run: |
-        poetry run pip install --force-reinstall --no-deps -e enterprise/
-
-    - name: Run MCP tests
-      run: |
-        poetry run pytest tests/mcp_tests -x -vv -n 4 --cov=litellm --cov-report=xml --durations=5
+      - name: Run MCP tests
+        run: |
+          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

@@ -2,13 +2,22 @@ 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
 
 jobs:
   validate-model-prices-json:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
 
       - name: Validate model_prices_and_context_window.json
         run: |

.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

@@ -0,0 +1,27 @@
+name: "Unit Tests: Core Utilities"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  core-utils:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/litellm_core_utils"
+      workers: 2
+      reruns: 1
+      artifact-name: core-utils

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

@@ -0,0 +1,71 @@
+name: "Unit Tests: Documentation Validation"
+
+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:
+  documentation:
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+
+    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 --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: |
+          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: |
+          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

@@ -0,0 +1,31 @@
+name: "Unit Tests: Enterprise, Google GenAI & Routing"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  enterprise-routing:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/enterprise
+        tests/test_litellm/google_genai
+        tests/test_litellm/router_utils
+        tests/test_litellm/router_strategy
+      workers: 2
+      reruns: 2
+      artifact-name: enterprise-routing

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

@@ -0,0 +1,27 @@
+name: "Unit Tests: Integrations (Callbacks & Logging)"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  integrations:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/integrations"
+      workers: 2
+      reruns: 3
+      artifact-name: integrations

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

@@ -0,0 +1,43 @@
+name: "Unit Tests: LLM Provider Transformations"
+
+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:
+  vertex-ai:
+    name: Vertex AI
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/llms/vertex_ai"
+      workers: 1
+      reruns: 2
+      artifact-name: llm-vertex-ai
+
+  other-providers:
+    name: All Other Providers
+    permissions:
+      contents: read
+      id-token: write
+      pull-requests: write
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/llms --ignore=tests/test_litellm/llms/vertex_ai"
+      workers: 2
+      reruns: 2
+      artifact-name: llm-other-providers

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

@@ -0,0 +1,38 @@
+name: "Unit Tests: MCP, Secrets, Containers & Misc"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  misc:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/secret_managers
+        tests/test_litellm/a2a_protocol
+        tests/test_litellm/anthropic_interface
+        tests/test_litellm/completion_extras
+        tests/test_litellm/containers
+        tests/test_litellm/experimental_mcp_client
+        tests/test_litellm/images
+        tests/test_litellm/interactions
+        tests/test_litellm/passthrough
+        tests/test_litellm/vector_stores
+        tests/test_litellm/test_*.py
+      workers: 2
+      reruns: 2
+      artifact-name: misc

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

@@ -0,0 +1,27 @@
+name: "Unit Tests: Proxy Auth & Key Management"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-auth:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/proxy/auth tests/test_litellm/proxy/hooks tests/test_litellm/proxy/policy_engine tests/test_litellm/proxy/client"
+      workers: 2
+      reruns: 2
+      artifact-name: proxy-auth

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

@@ -0,0 +1,238 @@
+name: "Unit Tests: Proxy DB Operations"
+
+# Uses DATABASE_URL secret — only runs on trusted branches, not PRs.
+on:
+  push:
+    branches: [main, "litellm_**"]
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+# 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
+      pull-requests: write
+    strategy:
+      fail-fast: false
+      matrix:
+        include:
+          # 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
+            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: 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 }}
+      workers: ${{ matrix.workers }}
+      reruns: 2
+      timeout-minutes: ${{ matrix.timeout }}
+      enable-postgres: true
+      dist: ${{ matrix.dist }}
+      artifact-name: proxy-db-${{ matrix.test-group }}

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

@@ -0,0 +1,44 @@
+name: "Unit Tests: Proxy API Endpoints"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-endpoints:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/proxy/management_endpoints
+        tests/test_litellm/proxy/guardrails
+        tests/test_litellm/proxy/management_helpers
+        tests/test_litellm/proxy/anthropic_endpoints
+        tests/test_litellm/proxy/google_endpoints
+        tests/test_litellm/proxy/openai_files_endpoint
+        tests/test_litellm/proxy/response_api_endpoints
+        tests/test_litellm/proxy/image_endpoints
+        tests/test_litellm/proxy/vector_store_endpoints
+        tests/test_litellm/proxy/agent_endpoints
+        tests/test_litellm/proxy/discovery_endpoints
+        tests/test_litellm/proxy/health_endpoints
+        tests/test_litellm/proxy/public_endpoints
+        tests/test_litellm/proxy/prompts
+        tests/test_litellm/proxy/rag_endpoints
+        tests/test_litellm/proxy/realtime_endpoints
+        tests/test_litellm/proxy/ui_crud_endpoints
+      workers: 2
+      reruns: 2
+      artifact-name: proxy-endpoints

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

@@ -0,0 +1,35 @@
+name: "Unit Tests: Proxy Infrastructure"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  proxy-infra:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: >-
+        tests/test_litellm/proxy/db
+        tests/test_litellm/proxy/middleware
+        tests/test_litellm/proxy/spend_tracking
+        tests/test_litellm/proxy/pass_through_endpoints
+        tests/test_litellm/proxy/_experimental
+        tests/test_litellm/proxy/experimental
+        tests/test_litellm/proxy/common_utils
+        tests/test_litellm/proxy/test_*.py
+      workers: 2
+      reruns: 2
+      artifact-name: proxy-infra

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

@@ -0,0 +1,93 @@
+name: "Unit Tests: Proxy Legacy Tests"
+
+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:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 20
+    strategy:
+      fail-fast: false
+      matrix:
+        test-group:
+          - name: "auth-and-jwt"
+            path: "tests/proxy_unit_tests/test_[a-j]*.py"
+          - name: "key-generation"
+            path: "tests/proxy_unit_tests/test_[k-o]*.py"
+          - name: "proxy-config"
+            path: "tests/proxy_unit_tests/test_prisma*.py tests/proxy_unit_tests/test_prompt*.py tests/proxy_unit_tests/test_proxy_[c-r]*.py"
+          - name: "proxy-server"
+            path: "tests/proxy_unit_tests/test_proxy_server.py"
+          - name: "proxy-server-extras"
+            path: "tests/proxy_unit_tests/test_proxy_server_*.py tests/proxy_unit_tests/test_proxy_setting_guardrails.py"
+          - name: "proxy-utils"
+            path: "tests/proxy_unit_tests/test_proxy_utils.py"
+          - name: "proxy-token-counter"
+            path: "tests/proxy_unit_tests/test_proxy_token_counter.py"
+          - name: "proxy-response-and-misc"
+            path: "tests/proxy_unit_tests/test_[r-t]*.py"
+          - name: "proxy-user-auth-and-spend"
+            path: "tests/proxy_unit_tests/test_[u-z]*.py"
+
+    name: ${{ matrix.test-group.name }}
+
+    steps:
+      - uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Set up Python
+        uses: actions/setup-python@a26af69be951a213d495a4c3e4e4022e16d87065 # v5.6.0
+        with:
+          python-version: "3.12"
+
+      - name: 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 --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: |
+          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: |
+          uv run --no-sync pytest ${TEST_PATH} \
+            --tb=short -vv \
+            --maxfail=10 \
+            -n 2 \
+            --reruns 1 \
+            --reruns-delay 1 \
+            --dist=loadscope \
+            --durations=20

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

@@ -0,0 +1,27 @@
+name: "Unit Tests: Responses, Caching & Types"
+
+on:
+  pull_request:
+    branches:
+      - main
+      - litellm_internal_staging
+      - litellm_oss_branch
+      - "litellm_**"
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  responses-caching-types:
+    uses: ./.github/workflows/_test-unit-base.yml
+    with:
+      test-path: "tests/test_litellm/responses tests/test_litellm/caching tests/test_litellm/types"
+      workers: 2
+      reruns: 2
+      artifact-name: responses-caching-types

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

@@ -0,0 +1,28 @@
+name: "Unit Tests: Security"
+
+# 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_**"]
+
+permissions:
+  contents: read
+  id-token: write
+  pull-requests: write
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  security:
+    uses: ./.github/workflows/_test-unit-services-base.yml
+    with:
+      test-path: "tests/proxy_security_tests/"
+      workers: 1
+      reruns: 2
+      timeout-minutes: 20
+      enable-postgres: true
+      artifact-name: security

.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:
@@ -17,13 +21,21 @@ jobs:
 
     steps:
       - name: Checkout repository
-        uses: actions/checkout@v4
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        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@v3
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f # v3.12
 
       - name: Build Docker image
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@0adf9959216b96bec444f325f1e493d4aa344497 #v6.14
         with:
           context: .
           file: ./docker/Dockerfile.non_root

.github/workflows/zizmor.yml

@@ -0,0 +1,31 @@
+name: GitHub Actions Security Analysis
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+permissions: {}
+
+jobs:
+  zizmor:
+    name: zizmor
+    runs-on: ubuntu-latest
+    timeout-minutes: 5
+    permissions:
+      security-events: write
+      contents: read
+      actions: read
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # v4.3.0
+        with:
+          persist-credentials: false
+
+      - name: Run zizmor
+        uses: zizmorcore/zizmor-action@71321a20a9ded102f6e9ce5718a2fcec2c4f70d8 # v0.5.2

.gitignore

@@ -72,8 +72,7 @@ tests/local_testing/log.txt
 .codegpt
 litellm/proxy/_new_new_secret_config.yaml
 litellm/proxy/custom_guardrail.py
-.mypy_cache/*
-.mypy_cache/*
+**/.mypy_cache/
 litellm/proxy/application.log
 tests/llm_translation/vertex_test_account.json
 tests/llm_translation/test_vertex_key.json
@@ -89,6 +88,7 @@ tests/test_custom_dir/*
 test.py
 
 litellm_config.yaml
+!.github/observatory/litellm_config.yaml
 .cursor
 .vscode/launch.json
 litellm/proxy/to_delete_loadtest_work/*

.npmrc

@@ -0,0 +1,5 @@
+# Supply-chain hardening
+# 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=3

.pre-commit-config.yaml

@@ -1,40 +0,0 @@
-repos:
--   repo: local
-    hooks:
-    -   id: pyright
-        name: pyright
-        entry: pyright
-        language: system
-        types: [python]
-        files: ^(litellm/|litellm_proxy_extras/|enterprise/)
-    -   id: isort
-        name: isort
-        entry: isort
-        language: system
-        types: [python]
-        files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
-        exclude: ^litellm/__init__.py$
-    # -   id: black
-    #     name: black
-    #     entry: poetry run black
-    #     language: system
-    #     types: [python]
-    #     files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
--   repo: https://github.com/pycqa/flake8
-    rev: 7.0.0  # The version of flake8 to use
-    hooks:
-    -  id: flake8
-       exclude: ^litellm/tests/|^litellm/proxy/tests/|^litellm/tests/test_litellm/|^tests/test_litellm/|^tests/enterprise/
-       additional_dependencies: [flake8-print]
-       files: (litellm/|litellm_proxy_extras/|enterprise/).*\.py
--   repo: https://github.com/python-poetry/poetry
-    rev: 1.8.0
-    hooks:
-      - id: poetry-check
-        files: ^(pyproject.toml|litellm-proxy-extras/pyproject.toml)$
--   repo: local
-    hooks:
-    -   id: check-files-match
-        name: Check if files match
-        entry: python3 ci_cd/check_files_match.py
-        language: system

.semgrep/rules/security/no-claude-directory.yml

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

.trivyignore

@@ -1,12 +0,0 @@
-# LiteLLM Trivy Ignore File
-# CVEs listed here are temporarily allowlisted pending fixes
-
-# Next.js vulnerabilities in UI dashboard (next@14.2.35)
-# Allowlisted: 2026-01-31, 7-day fix timeline
-# Fix: Upgrade to Next.js 15.5.10+ or 16.1.5+
-
-# HIGH: DoS via request deserialization
-GHSA-h25m-26qc-wcjf
-
-# MEDIUM: Image Optimizer DoS
-CVE-2025-59471

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**:
@@ -109,6 +112,8 @@ Key files:
 - `litellm/proxy/auth/` - Authentication logic
 - `litellm/proxy/management_endpoints/` - Admin API endpoints
 
+**Database (proxy)**: Use Prisma model methods (`prisma_client.db.<model>.upsert`, `.find_many`, `.find_unique`, etc.), not raw SQL (`execute_raw`/`query_raw`). See COMMON PITFALLS for details.
+
 ## MCP (MODEL CONTEXT PROTOCOL) SUPPORT
 
 LiteLLM supports MCP for agent workflows:
@@ -119,7 +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
 
@@ -174,11 +179,48 @@ When opening issues or pull requests, follow these templates:
 3. **Rate Limits**: Respect provider rate limits in tests
 4. **Memory Usage**: Be mindful of memory usage in streaming scenarios
 5. **Dependencies**: Keep dependencies minimal and well-justified
+6. **UI/Backend Contract Mismatch**: When adding a new entity type to the UI, always check whether the backend endpoint accepts a single value or an array. Match the UI control accordingly (single-select vs. multi-select) to avoid silently dropping user selections
+7. **Missing Tests for New Entity Types**: When adding a new entity type (e.g., in `EntityUsage`, `UsageViewSelect`), always add corresponding tests in the existing test files and update any icon/component mocks
+8. **Raw SQL in proxy DB code**: Do not use `execute_raw` or `query_raw` for proxy database access. Use Prisma model methods (e.g. `prisma_client.db.litellm_tooltable.upsert()`, `.find_many()`, `.find_unique()`) so behavior stays consistent with the schema, the client stays mockable in tests, and you avoid the pitfalls of hand-written SQL (parameter ordering, type casting, schema drift)
+
+8. **Do not hardcode model-specific flags**: Put model-specific capability flags in `model_prices_and_context_window.json` and read them via `get_model_info` (or existing helpers like `supports_reasoning`). This prevents users from needing to upgrade LiteLLM each time a new model supports a feature.
+
+   **Example of BAD** (hardcoded model checks):
+
+   ```python
+   @staticmethod
+   def _is_effort_supported_model(model: str) -> bool:
+       """Check if the model supports the output_config.effort parameter..."""
+       model_lower = model.lower()
+       if AnthropicConfig._is_claude_4_6_model(model):
+           return True
+       return any(
+           v in model_lower for v in ("opus-4-5", "opus_4_5", "opus-4.5", "opus_4.5")
+       )
+   ```
+
+   **Example of GOOD** (config-driven or helper that reads from config):
+
+   ```python
+   if (
+       "claude-3-7-sonnet" in model
+       or AnthropicConfig._is_claude_4_6_model(model)
+       or supports_reasoning(
+           model=model,
+           custom_llm_provider=self.custom_llm_provider,
+       )
+   ):
+       ...
+   ```
+
+   Using helpers like `supports_reasoning` (which read from `model_prices_and_context_window.json` / `get_model_info`) allows future model updates to "just work" without code changes.
+
+9. **Never close HTTP/SDK clients on cache eviction**: Do not add `close()`, `aclose()`, or `create_task(close_fn())` inside `LLMClientCache._remove_key()` or any cache eviction path. Evicted clients may still be held by in-flight requests; closing them causes `RuntimeError: Cannot send a request, as the client has been closed.` in production after the cache TTL (1 hour) expires. Connection cleanup is handled at shutdown by `close_litellm_async_clients()`. See PR #22247 for the full incident history.
 
 ## 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
@@ -187,4 +229,48 @@ When opening issues or pull requests, follow these templates:
 - Check similar provider implementations
 - Ensure comprehensive test coverage
 - Update documentation appropriately
-- Consider backward compatibility impact 
+- Consider backward compatibility impact
+
+## Cursor Cloud specific instructions
+
+### Environment
+
+- uv is installed in `~/.local/bin`; the update script ensures it is on `PATH`.
+- Python 3.12, Node 22 are pre-installed.
+- The project virtual environment lives under `.venv/`.
+
+### Running the proxy server
+
+Start the proxy with a config file:
+
+```bash
+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.
+
+### Running tests
+
+See `CLAUDE.md` and the `Makefile` for standard commands. Key notes:
+
+- `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: `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 && 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`.
+
+### UI Dashboard development
+
+- The UI is at `ui/litellm-dashboard/`. Run `npm run dev` from that directory for the Next.js dev server on port 3000.
+- 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`

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
@@ -20,13 +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 `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:
@@ -91,19 +96,85 @@ LiteLLM is a unified interface for 100+ LLM providers with two main components:
 - Async/await patterns throughout
 - Type hints required for all public APIs
 - **Avoid imports within methods** — place all imports at the top of the file (module-level). Inline imports inside functions/methods make dependencies harder to trace and hurt readability. The only exception is avoiding circular imports where absolutely necessary.
+- **Use dict spread for immutable copies** — prefer `{**original, "key": new_value}` over `dict(obj)` + mutation. The spread produces the final dict in one step and makes intent clear.
+- **Guard at resolution time** — when resolving an optional value through a fallback chain (`a or b or ""`), raise immediately if the resolved result being empty is an error. Don't pass empty strings or sentinel values downstream for the callee to deal with.
+- **Extract complex comprehensions to named helpers** — a set/dict comprehension that calls into the DB or manager (e.g. "which of these server IDs are OAuth2?") belongs in a named helper function, not inline in the caller.
+- **FastAPI parameter declarations** — mark required query/form params with `= Query(...)` / `= Form(...)` explicitly when other params in the same handler are optional. Mixing `str` (required) with `Optional[str] = None` in the same signature causes silent 422s when the required param is missing.
 
 ### Testing Strategy
 - Unit tests in `tests/test_litellm/`
 - Integration tests for each provider in `tests/llm_translation/`
 - Proxy tests in `tests/proxy_unit_tests/`
 - Load tests in `tests/load_tests/`
+- **Always add tests when adding new entity types or features** — if the existing test file covers other entity types, add corresponding tests for the new one
+- **Keep monkeypatch stubs in sync with real signatures** — when a function gains a new optional parameter, update every `fake_*` / `stub_*` in tests that patch it to also accept that kwarg (even as `**kwargs`). Stale stubs fail with `unexpected keyword argument` and mask real bugs.
+- **Test all branches of name→ID resolution** — when adding server/resource lookup that resolves names to UUIDs, test: (1) name resolves and UUID is allowed, (2) name resolves but UUID is not allowed, (3) name does not resolve at all. The silent-fallback path is where access-control bugs hide.
+
+### 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.
+- When an MCP server already has `authorization_url` stored, skip OAuth discovery (`_discovery_metadata`) — the server URL for OpenAPI MCPs is the spec file, not the API base, and fetching it causes timeouts.
+- `client_id` should be optional in the `/authorize` endpoint — if the server has a stored `client_id` in credentials, use that. Never require callers to re-supply it.
+
+### MCP Credential Storage
+- OAuth credentials and BYOK credentials share the `litellm_mcpusercredentials` table, distinguished by a `"type"` field in the JSON payload (`"oauth2"` vs plain string).
+- When deleting OAuth credentials, check type before deleting to avoid accidentally deleting a BYOK credential for the same `(user_id, server_id)` pair.
+- Always pass the raw `expires_at` timestamp to the client — never set it to `None` for expired credentials. Let the frontend compute the "Expired" display state from the timestamp.
+- Use `RecordNotFoundError` (not bare `except Exception`) when catching "already deleted" in credential delete endpoints.
+
+### Browser Storage Safety (UI)
+- Never write LiteLLM access tokens or API keys to `localStorage` — use `sessionStorage` only. `localStorage` survives browser close and is readable by any injected script (XSS).
+- Shared utility functions (e.g. `extractErrorMessage`) belong in `src/utils/` — never define them inline in hooks or duplicate them across files.
 
 ### Database Migrations
 - Prisma handles schema migrations
 - Migration files auto-generated with `prisma migrate dev`
 - Always test migrations against both PostgreSQL and SQLite
 
+### Proxy database access
+- **Do not write raw SQL** for proxy DB operations. Use Prisma model methods instead of `execute_raw` / `query_raw`.
+- Use the generated client: `prisma_client.db.<model>` (e.g. `litellm_tooltable`, `litellm_usertable`) with `.upsert()`, `.find_many()`, `.find_unique()`, `.update()`, `.update_many()` as appropriate. This avoids schema/client drift, keeps code testable with simple mocks, and matches patterns used in spend logs and other proxy code.
+- **No N+1 queries.** Never query the DB inside a loop. Batch-fetch with `{"in": ids}` and distribute in-memory.
+- **Batch writes.** Use `create_many`/`update_many`/`delete_many` instead of individual calls (these return counts only; `update_many`/`delete_many` no-op silently on missing rows). When multiple separate writes target the same table (e.g. in `batch_()`), order by primary key to avoid deadlocks.
+- **Push work to the DB.** Filter, sort, group, and aggregate in SQL, not Python. Verify Prisma generates the expected SQL — e.g. prefer `group_by` over `find_many(distinct=...)` which does client-side processing.
+- **Bound large result sets.** Prisma materializes full results in memory. For results over ~10 MB, paginate with `take`/`skip` or `cursor`/`take`, always with an explicit `order`. Prefer cursor-based pagination (`skip` is O(n)). Don't paginate naturally small result sets.
+- **Limit fetched columns on wide tables.** Use `select` to fetch only needed fields — returns a partial object, so downstream code must not access unselected fields.
+- **Check index coverage.** For new or modified queries, check `schema.prisma` for a supporting index. Prefer extending an existing index (e.g. `@@index([a])` → `@@index([a, b])`) over adding a new one, unless it's a `@@unique`. Only add indexes for large/frequent queries.
+- **Keep schema files in sync.** Apply schema changes to all `schema.prisma` copies (`schema.prisma`, `litellm/proxy/`, `litellm-proxy-extras/`, `litellm-js/spend-logs/` for SpendLogs) with a migration under `litellm-proxy-extras/litellm_proxy_extras/migrations/`.
+
+### Setup Wizard (`litellm/setup_wizard.py`)
+- The wizard is implemented as a single `SetupWizard` class with `@staticmethod` methods — keep it that way. No module-level functions except `run_setup_wizard()` (the public entrypoint) and pure helpers (color, ANSI).
+- Use `litellm.utils.check_valid_key(model, api_key)` for credential validation — never roll a custom completion call.
+- Do not hardcode provider env-key names or model lists that already exist in the codebase. Add a `test_model` field to each provider entry to drive `check_valid_key`; set it to `None` for providers that can't be validated with a single API key (Azure, Bedrock, Ollama).
+
 ### 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
+
+### 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()`.
+
+### Troubleshooting: DB schema out of sync after proxy restart
+`litellm-proxy-extras` runs `prisma migrate deploy` on startup using **its own** bundled migration files, which may lag behind schema changes in the current worktree. Symptoms: `Unknown column`, `Invalid prisma invocation`, or missing data on new fields.
+
+**Diagnose:** Run `\d "TableName"` in psql and compare against `schema.prisma` — missing columns confirm the issue.
+
+**Fix options:**
+1. **Create a Prisma migration** (permanent) — run `prisma migrate dev --name <description>` in the worktree. The generated file will be picked up by `prisma migrate deploy` on next startup.
+2. **Apply manually for local dev** — `psql -d litellm -c "ALTER TABLE ... ADD COLUMN IF NOT EXISTS ..."` after each proxy start. Fine for dev, not for production.
+3. **Update litellm-proxy-extras** — if the package is installed from PyPI, its migration directory must include the new file. Either update the package or run the migration manually until the next release ships it.

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
@@ -149,6 +157,19 @@ Apply formatting (auto-fixes issues):
 make format
 ```
 
+> **Black formatting is enforced in CI.** All PRs must pass the Black formatting check.
+>
+> - **AI coding agents** (Claude Code, Copilot, Cursor, etc.): `AGENTS.md` and `CLAUDE.md` instruct agents to run `poetry run black .` before committing.
+> - **VS Code users**: Install the [Black Formatter extension](https://marketplace.visualstudio.com/items?itemName=ms-python.black-formatter) and enable format-on-save:
+>   ```json
+>   {
+>     "[python]": {
+>       "editor.defaultFormatter": "ms-python.black-formatter",
+>       "editor.formatOnSave": true
+>     }
+>   }
+>   ```
+
 ### CI Compatibility
 
 To ensure your changes will pass CI, run the exact same checks locally:
@@ -172,7 +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
@@ -234,7 +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
@@ -319,4 +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

@@ -1,121 +1,101 @@
 # Base image for building
-ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base
+ARG LITELLM_BUILD_IMAGE=cgr.dev/chainguard/wolfi-base@sha256:f26d42a15d09d9a643b231df929fa3cf609bedc58a728eb445be89a9d8d1da9f
 
 # Runtime image
-ARG LITELLM_RUNTIME_IMAGE=cgr.dev/chainguard/wolfi-base
+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
+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==2.9.0 --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@latest tar@7.5.7 glob@11.1.0 @isaacs/brace-expansion@5.0.1 && \
-    # 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 && \
-    npm cache clean --force
+    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/ && 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)" && \
-    find /usr/lib -path "*/nodejs_wheel/*/node_modules/tar" -type d | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/tar" "$d"; \
-    done && \
-    find /usr/lib -path "*/nodejs_wheel/*/node_modules/glob" -type d | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/glob" "$d"; \
-    done && \
-    find /usr/lib -path "*/nodejs_wheel/*/node_modules/@isaacs/brace-expansion" -type d | while read d; do \
-        rm -rf "$d" && cp -rL "$GLOBAL/@isaacs/brace-expansion" "$d"; \
-    done
-
-# Install semantic_router and aurelio-sdk using script
-# Convert Windows line endings to Unix and make executable
-RUN sed -i 's/\r$//' 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

@@ -2,20 +2,24 @@
         🚅 LiteLLM
     </h1>
     <p align="center">
-        <p align="center">Call 100+ LLMs in OpenAI format. [Bedrock, Azure, OpenAI, VertexAI, Anthropic, Groq, etc.]
+        <p align="center">LiteLLM AI Gateway
         </p>
+        <p align="center">Open Source AI Gateway for 100+ LLMs. Self-hosted. Enterprise-ready. Call any LLM in OpenAI format.</p>
         <p align="center">
         <a href="https://render.com/deploy?repo=https://github.com/BerriAI/litellm" target="_blank" rel="nofollow"><img src="https://render.com/images/deploy-to-render-button.svg" alt="Deploy to Render"></a>
-        <a href="https://railway.app/template/HLP0Ub?referralCode=jch2ME">
-          <img src="https://railway.app/button.svg" alt="Deploy on Railway">
+        <a href="https://railway.com/deploy/RhvhdC?referralCode=7mRv9K&utm_medium=integration&utm_source=template&utm_campaign=generic">
+          <img src="https://railway.com/button.svg" alt="Deploy on Railway">
         </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://docs.litellm.ai/docs/enterprise"target="_blank">Enterprise Tier</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">
     </a>
+    <a href="https://github.com/BerriAI/litellm" target="_blank">
+        <img src="https://img.shields.io/github/stars/BerriAI/litellm.svg?style=social" alt="GitHub Stars">
+    </a>
     <a href="https://www.ycombinator.com/companies/berriai">
         <img src="https://img.shields.io/badge/Y%20Combinator-W23-orange?style=flat-square" alt="Y Combinator W23">
     </a>
@@ -28,12 +32,52 @@
     <a href="https://www.litellm.ai/support">
         <img src="https://img.shields.io/static/v1?label=Chat%20on&message=Slack&color=black&logo=Slack&style=flat-square" alt="Slack">
     </a>
+    <a href="https://codspeed.io/BerriAI/litellm?utm_source=badge">
+        <img src="https://img.shields.io/endpoint?url=https://codspeed.io/badge.json" alt="CodSpeed"/>
+    </a>
 </h4>
 
 <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>
@@ -43,7 +87,7 @@
 ### Python SDK
 
 ```shell
-pip install litellm
+uv add litellm
 ```
 
 ```python
@@ -65,7 +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
 ```
 
@@ -203,7 +247,7 @@ curl -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
 {
   "mcpServers": {
     "LiteLLM": {
-      "url": "http://localhost:4000/mcp",
+      "url": "http://localhost:4000/mcp/",
       "headers": {
         "x-litellm-api-key": "Bearer sk-1234"
       }
@@ -216,62 +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="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` |
 |-------------------------------------------------------------------------------------|---------------------|-------------|--------------|---------------|----------------------|-------------------------|-----------------|----------------|-----------|-----------|
@@ -378,28 +367,94 @@ 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
+
+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`).
+
+---
+
 # Enterprise
 For companies that need better security, user management and professional support
 
-[Talk to founders](https://calendly.com/d/cx9p-5yf-2nm/litellm-introductions)
+[Get an Enterprise License](https://litellm.ai/enterprise)
+[Talk to founders](https://enterprise.litellm.ai/demo)
 
 This covers:
 - ✅ **Features under the [LiteLLM Commercial License](https://docs.litellm.ai/docs/proxy/enterprise):**
@@ -415,7 +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
@@ -429,6 +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).
@@ -449,13 +506,8 @@ All these checks must pass before your PR can be merged.
 - [Schedule Demo 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
 - [Community Discord 💭](https://discord.gg/wuPM9dRgDw)
 - [Community Slack 💭](https://www.litellm.ai/support)
-- Our numbers 📞 +1 (770) 8783-106 / ‭+1 (412) 618-6238‬
 - Our emails ✉️ ishaan@berri.ai / krrish@berri.ai
 
-# Why did we build this
-
-- **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 -->
@@ -470,4 +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/.grype.yaml

@@ -1,36 +0,0 @@
-ignore:
-  - vulnerability: CVE-2026-22184
-    reason: no fixed zlib package is available yet in the Wolfi repositories, so this is ignored temporarily until an upstream release exists
-  # Wolfi base image: Python 3.13 and Node from apk have no fixed builds in Wolfi yet / not applicable
-  - vulnerability: CVE-2025-55130
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-59465
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-55131
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-59466
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2026-21637
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: CVE-2025-55132
-    reason: Node in Wolfi apk; only used for Admin UI build/prisma
-  - vulnerability: GHSA-hx9q-6w63-j58v
-    reason: orjson dumps recursion; allowlisted
-  - vulnerability: GHSA-73rr-hh4g-fpgx
-    reason: diff npm transitive dep; override in package.json, allowlisted
-  - vulnerability: CVE-2026-0865
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15282
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2026-0672
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15366
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-15367
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-11468
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2025-12781
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet
-  - vulnerability: CVE-2026-1299
-    reason: Python 3.13 in Wolfi base; no fixed apk build yet

ci_cd/publish-proxy-extras.sh

@@ -1,19 +0,0 @@
-#!/bin/bash
-
-# Exit on error
-set -e
-
-echo "🚀 Building and publishing litellm-proxy-extras"
-
-# Navigate to litellm-proxy-extras directory
-cd "$(dirname "$0")/../litellm-proxy-extras"
-
-# Build the package
-echo "📦 Building package..."
-poetry build
-
-# Publish to PyPI
-echo "🌎 Publishing to PyPI..."
-poetry publish
-
-echo "✅ Done! Package published successfully"

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,
+    )

ci_cd/security_scans.sh

@@ -1,256 +0,0 @@
-#!/bin/bash
-
-# Security Scans Script for LiteLLM
-# This script runs comprehensive security scans including Trivy and Grype
-
-set -e
-
-echo "Starting security scans for LiteLLM..."
-
-# Function to install Trivy and required tools
-install_trivy() {
-    echo "Installing Trivy and required tools..."
-    sudo apt-get update
-    sudo apt-get install -y wget apt-transport-https gnupg lsb-release jq curl
-    wget -qO - https://aquasecurity.github.io/trivy-repo/deb/public.key | sudo apt-key add -
-    echo "deb https://aquasecurity.github.io/trivy-repo/deb $(lsb_release -sc) main" | sudo tee -a /etc/apt/sources.list.d/trivy.list
-    sudo apt-get update
-    sudo apt-get install trivy
-    echo "Trivy and required tools installed successfully"
-}
-
-# Function to install Grype
-install_grype() {
-    echo "Installing Grype..."
-    curl -sSfL https://raw.githubusercontent.com/anchore/grype/main/install.sh | sudo sh -s -- -b /usr/local/bin
-    echo "Grype installed successfully"
-}
-
-# Function to install ggshield
-install_ggshield() {
-    echo "Installing ggshield..."
-    pip3 install --upgrade pip
-    pip3 install ggshield
-    echo "ggshield installed successfully"
-}
-
-# # Function to run secret detection scans
-# run_secret_detection() {
-#     echo "Running secret detection scans..."
-    
-#     if ! command -v ggshield &> /dev/null; then
-#         install_ggshield
-#     fi
-    
-#     # Check if GITGUARDIAN_API_KEY is set (required for CI/CD)
-#     if [ -z "$GITGUARDIAN_API_KEY" ]; then
-#         echo "Warning: GITGUARDIAN_API_KEY environment variable is not set."
-#         echo "ggshield requires a GitGuardian API key to scan for secrets."
-#         echo "Please set GITGUARDIAN_API_KEY in your CI/CD environment variables."
-#         exit 1
-#     fi
-    
-#     echo "Scanning codebase for secrets..."
-#     echo "Note: Large codebases may take several minutes due to API rate limits (50 requests/minute on free plan)"
-#     echo "ggshield will automatically handle rate limits and retry as needed."
-#     echo "Binary files, cache files, and build artifacts are excluded via .gitguardian.yaml"
-    
-#     # Use --recursive for directory scanning and auto-confirm if prompted
-#     # .gitguardian.yaml will automatically exclude binary files, wheel files, etc.
-#     # GITGUARDIAN_API_KEY environment variable will be used for authentication
-#     echo y | ggshield secret scan path . --recursive || {
-#         echo ""
-#         echo "=========================================="
-#         echo "ERROR: Secret Detection Failed"
-#         echo "=========================================="
-#         echo "ggshield has detected secrets in the codebase."
-#         echo "Please review discovered secrets above, revoke any actively used secrets"
-#         echo "from underlying systems and make changes to inject secrets dynamically at runtime."
-#         echo ""
-#         echo "For more information, see: https://docs.gitguardian.com/secrets-detection/"
-#         echo "=========================================="
-#         echo ""
-#         exit 1
-#     }
-    
-#     echo "Secret detection scans completed successfully"
-# }
-
-# Function to run Trivy scans
-run_trivy_scans() {
-    echo "Running Trivy scans..."
-    
-    echo "Scanning LiteLLM Docs..."
-    trivy fs --ignorefile .trivyignore --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./docs/
-    
-    echo "Scanning LiteLLM UI..."
-    trivy fs --ignorefile .trivyignore --scanners vuln --dependency-tree --exit-code 1 --severity HIGH,CRITICAL,MEDIUM ./ui/
-    
-    echo "Trivy scans completed successfully"
-}
-
-# Function to build and scan Docker images with Grype
-run_grype_scans() {
-    echo "Running Grype scans..."
-    
-    # Temporarily add wheel files to .dockerignore for security scans
-    echo "Temporarily modifying .dockerignore to exclude problematic wheel files..."
-    cp .dockerignore .dockerignore.backup 2>/dev/null || touch .dockerignore.backup
-    echo "/*.whl" >> .dockerignore
-    
-    # Build and scan Dockerfile.database
-    echo "Building and scanning Dockerfile.database..."
-    docker build --no-cache -t litellm-database:latest -f ./docker/Dockerfile.database .
-    grype litellm-database:latest --config ci_cd/.grype.yaml --fail-on critical
-    
-    # Build and scan main Dockerfile
-    echo "Building and scanning main Dockerfile..."
-    docker build --no-cache -t litellm:latest .
-    grype litellm:latest --config ci_cd/.grype.yaml --fail-on critical
-    
-    # Restore original .dockerignore
-    echo "Restoring original .dockerignore..."
-    mv .dockerignore.backup .dockerignore
-    
-    # Scan the locally built LiteLLM image for vulnerabilities with CVSS >= 4.0
-    echo "Scanning locally built LiteLLM image for high-severity vulnerabilities..."
-    echo "Using locally built image: litellm:latest"
-    
-    # Allowlist of CVEs to be ignored in failure threshold/reporting
-    # - CVE-2025-8869: Not applicable on Python >=3.13 (PEP 706 implemented); pip fallback unused; no OS-level fix
-    # - GHSA-4xh5-x5gv-qwph: GitHub Security Advisory alias for CVE-2025-8869
-    # - GHSA-5j98-mcp5-4vw2: glob CLI command injection via -c/--cmd; glob CLI is not used in the litellm runtime image,
-    #   and the vulnerable versions are pulled in only via OS-level/node tooling outside of our application code
-    ALLOWED_CVES=(
-        "CVE-2025-8869"
-        "GHSA-4xh5-x5gv-qwph"
-        "CVE-2025-8291" # no fix available as of Oct 11, 2025
-        "GHSA-5j98-mcp5-4vw2"
-        "CVE-2025-13836" # Python 3.13 HTTP response reading OOM/DoS - no fix available in base image
-        "CVE-2025-12084" # Python 3.13 xml.dom.minidom quadratic algorithm - no fix available in base image
-        "CVE-2025-60876" # BusyBox wget HTTP request splitting - no fix available in Chainguard Wolfi base image
-        "CVE-2026-0861" # Wolfi glibc still flagged even on 2.42-r5; upstream patched build unavailable yet
-        "CVE-2010-4756" # glibc glob DoS - awaiting patched Wolfi glibc build
-        "CVE-2019-1010022" # glibc stack guard bypass - awaiting patched Wolfi glibc build
-        "CVE-2019-1010023" # glibc ldd remap issue - awaiting patched Wolfi glibc build
-        "CVE-2019-1010024" # glibc ASLR mitigation bypass - awaiting patched Wolfi glibc build
-        "CVE-2019-1010025" # glibc pthread heap address leak - awaiting patched Wolfi glibc build
-        "CVE-2026-22184" # zlib untgz buffer overflow - untgz unused + no fixed Wolfi build yet
-        "GHSA-58pv-8j8x-9vj2" # jaraco.context path traversal - setuptools vendored only (v5.3.0), not used in application code (using v6.1.0+)
-        "GHSA-34x7-hfp2-rc4v" # node-tar hardlink path traversal - not applicable, tar CLI not exposed in application code
-        "GHSA-r6q2-hw4h-h46w" # node-tar not used by application runtime, Linux-only container, not affect by macOS APFS-specific exploit
-        "GHSA-8rrh-rw8j-w5fx" # wheel is from chainguard and will be handled by then TODO: Remove this after Chainguard updates the wheel
-        "CVE-2025-59465" # Node only used for Admin UI build/prisma
-        "CVE-2025-55131" # Node only used for Admin UI build/prisma
-        "CVE-2025-59466" # Node only used for Admin UI build/prisma
-        "CVE-2025-55130" # Node only used for Admin UI build/prisma
-        "CVE-2025-59467" # Node only used for Admin UI build/prisma
-        "CVE-2026-21637" # Node only used for Admin UI build/prisma
-        "CVE-2025-55132" # Node only used for Admin UI build/prisma
-        "GHSA-hx9q-6w63-j58v" # orjson dumps recursion; allowlisted
-        "CVE-2025-15281" # No fix available yet
-        "CVE-2026-0865" # No fix available yet
-        "CVE-2025-15282" # No fix available yet
-        "CVE-2026-0672" # No fix available yet
-        "CVE-2025-15366" # No fix available yet
-        "CVE-2025-15367" # No fix available yet
-        "CVE-2025-12781" # No fix available yet
-        "CVE-2025-11468" # No fix available yet
-        "CVE-2026-1299" # Python 3.13 email module header injection - not applicable, LiteLLM doesn't use BytesGenerator for email serialization
-        "CVE-2026-0775" # npm cli incorrect permission assignment - no fix available yet, npm is only used at build/prisma-generate time
-        "GHSA-3ppc-4f35-3m26" # minimatch ReDoS via repeated wildcards - from nodejs_wheel bundled npm, not used in application runtime code
-        "GHSA-83g3-92jg-28cx" # tar arbitrary file read/write via hardlink - from nodejs_wheel bundled npm, not used in application runtime code
-    )
-
-    # Build JSON array of allowlisted CVE IDs for jq
-    ALLOWED_IDS_JSON=$(printf '%s\n' "${ALLOWED_CVES[@]}" | jq -R . | jq -s .)
-
-    echo "Checking for vulnerabilities with CVSS score >= 4.0..."
-    echo "Allowlisted CVEs (ignored in threshold): ${ALLOWED_CVES[*]}"
-    echo ""
-    
-    # Show all high-severity vulnerabilities for transparency
-    TOTAL_HIGH_SEVERITY=$(grype litellm:latest -o json | jq -r '
-        .matches[]
-        | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-        | .vulnerability.id' | wc -l)
-    
-    if [ "$TOTAL_HIGH_SEVERITY" -gt 0 ]; then
-        echo "Total vulnerabilities found with CVSS >= 4.0: $TOTAL_HIGH_SEVERITY"
-        echo ""
-        echo "All high-severity vulnerabilities (including allowlisted):"
-        grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        ["Package", "Version", "Vulnerability ID", "CVSS Score", "Allowlisted"],
-        (.matches[]
-          | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-          | [.artifact.name, .artifact.version, .vulnerability.id, .vulnerability.cvss[0].metrics.baseScore, (if (.vulnerability.id as $id | $allow | index($id)) then "YES" else "NO" end)])
-        | @tsv' | column -t -s $'\t'
-        echo ""
-    fi
-
-    HIGH_SEVERITY_COUNT=$(grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        .matches[]
-        | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-        | select((.vulnerability.id as $id | $allow | index($id) | not))
-        | .vulnerability.id' | wc -l)
-    
-    if [ "$HIGH_SEVERITY_COUNT" -gt 0 ]; then
-        echo ""
-        echo "=========================================="
-        echo "ERROR: Security Scan Failed"
-        echo "=========================================="
-        echo "Found $HIGH_SEVERITY_COUNT non-allowlisted vulnerabilities with CVSS score >= 4.0 in litellm:latest"
-        echo ""
-        echo "These vulnerabilities are NOT in the allowlist and must be addressed."
-        echo "Current allowlisted CVEs: ${ALLOWED_CVES[*]}"
-        echo ""
-        echo "Detailed vulnerability report:"
-        echo ""
-        grype litellm:latest -o json | jq --argjson allow "$ALLOWED_IDS_JSON" -r '
-        ["Package", "Version", "Vulnerability ID", "CVSS Score", "Severity", "Fix Version", "Description"],
-        (.matches[]
-          | select(.vulnerability.cvss[]?.metrics.baseScore >= 4.0)
-          | select((.vulnerability.id as $id | $allow | index($id) | not))
-          | [.artifact.name, .artifact.version, .vulnerability.id, .vulnerability.cvss[0].metrics.baseScore, .vulnerability.severity, (.vulnerability.fix.versions[0] // "No fix available"), .vulnerability.description])
-        | @tsv' | column -t -s $'\t'
-        echo ""
-        echo "=========================================="
-        echo "Action Required:"
-        echo "=========================================="
-        echo "1. If a fix is available, update the package to the fixed version"
-        echo "2. If the vulnerability is not applicable or has no fix:"
-        echo "   - Add the CVE/GHSA ID to ALLOWED_CVES array in ci_cd/security_scans.sh"
-        echo "   - Add a comment explaining why it's safe to ignore"
-        echo ""
-        echo "Note: Some vulnerabilities may have multiple IDs (CVE-XXXX and GHSA-XXXX)."
-        echo "Add all relevant IDs to the allowlist if they refer to the same issue."
-        echo "=========================================="
-        echo ""
-        exit 1
-    else
-        echo "No high-severity vulnerabilities (CVSS >= 4.0) found in litellm:latest"
-    fi
-    
-    echo "Grype scans completed successfully"
-}
-
-# Main execution
-main() {
-    echo "Installing security scanning tools..."
-    install_trivy
-    install_grype
-    
-    # echo "Running secret detection scans..."
-    # run_secret_detection
-    
-    echo "Running filesystem vulnerability scans..."
-    run_trivy_scans
-    
-    echo "Running Docker image vulnerability scans..."
-    run_grype_scans
-    
-    echo "All security scans completed successfully!"
-}
-
-# Execute main function
-main "$@"

codecov.yaml

@@ -17,6 +17,9 @@ component_management:
     - component_id: "Proxy_Authentication"
       paths:
         - "*/proxy/auth/**"
+    - component_id: "Enterprise"
+      paths:
+        - "enterprise/**"
 comment:
   layout: "header, diff, flags, components"  # show component info in the PR comment
 

cookbook/ai_coding_tool_guides/claude_code_quickstart/guide.md

@@ -230,7 +230,7 @@ model_list:
   # AWS Bedrock
   - model_name: claude-bedrock
     litellm_params:
-      model: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
+      model: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0
       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

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/benchmark/readme.md

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