Merge branch 'main' into feat/remove-servername-prefix-mcp_tools

Author: krrishdholakia

.circleci/config.yml

@@ -1050,6 +1050,51 @@ jobs:
             ls
             python -m pytest -vv tests/test_litellm --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit-litellm.xml --durations=10 -n 8
           no_output_timeout: 120m
+      - run:
+          name: Rename the coverage files
+          command: |
+            mv coverage.xml litellm_mapped_tests_coverage.xml
+            mv .coverage litellm_mapped_tests_coverage
+
+      # Store test results
+      - store_test_results:
+          path: test-results
+      - persist_to_workspace:
+          root: .
+          paths:
+            - litellm_mapped_tests_coverage.xml
+            - litellm_mapped_tests_coverage
+  litellm_mapped_enterprise_tests:
+    docker:
+      - image: cimg/python:3.11
+        auth:
+          username: ${DOCKERHUB_USERNAME}
+          password: ${DOCKERHUB_PASSWORD}
+    working_directory: ~/project
+
+    steps:
+      - checkout
+      - setup_google_dns
+      - run:
+          name: Install Dependencies
+          command: |
+            python -m pip install --upgrade pip
+            python -m pip install -r requirements.txt
+            pip install "pytest-mock==3.12.0"
+            pip install "pytest==7.3.1"
+            pip install "pytest-retry==1.6.3"
+            pip install "pytest-cov==5.0.0"
+            pip install "pytest-asyncio==0.21.1"
+            pip install "respx==0.22.0"
+            pip install "hypercorn==0.17.3"
+            pip install "pydantic==2.10.2"
+            pip install "mcp==1.10.1"
+            pip install "requests-mock>=1.12.1"
+            pip install "responses==0.25.7"
+            pip install "pytest-xdist==3.6.1"
+            pip install "semantic_router==0.1.10"
+            pip install "fastapi-offline==1.7.3"
+      - setup_litellm_enterprise_pip
       - run:
           name: Run enterprise tests
           command: |
@@ -1779,8 +1824,8 @@ jobs:
             docker run -d \
               -p 4000:4000 \
               -e DATABASE_URL=postgresql://postgres:[email protected]:5432/circle_test \
-              -e AZURE_API_KEY=$AZURE_BATCHES_API_KEY \
-              -e AZURE_API_BASE=$AZURE_BATCHES_API_BASE \
+              -e AZURE_API_KEY=$AZURE_API_KEY \
+              -e AZURE_API_BASE=$AZURE_API_BASE \
               -e AZURE_API_VERSION="2024-05-01-preview" \
               -e REDIS_HOST=$REDIS_HOST \
               -e REDIS_PASSWORD=$REDIS_PASSWORD \
@@ -3175,6 +3220,12 @@ workflows:
               only:
                 - main
                 - /litellm_.*/
+      - litellm_mapped_enterprise_tests:
+          filters:
+            branches:
+              only:
+                - main
+                - /litellm_.*/
       - litellm_mapped_tests:
           filters:
             branches:
@@ -3219,6 +3270,7 @@ workflows:
             - guardrails_testing
             - llm_responses_api_testing
             - litellm_mapped_tests
+            - litellm_mapped_enterprise_tests
             - batches_testing
             - litellm_utils_testing
             - pass_through_unit_testing
@@ -3279,6 +3331,7 @@ workflows:
             - google_generate_content_endpoint_testing
             - llm_responses_api_testing
             - litellm_mapped_tests
+            - litellm_mapped_enterprise_tests
             - batches_testing
             - litellm_utils_testing
             - pass_through_unit_testing

.github/workflows/test-mcp.yml

@@ -0,0 +1,48 @@
+name: LiteLLM MCP Tests (folder - tests/mcp_tests)
+
+on:
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    timeout-minutes: 25
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - 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: Install Poetry
+      uses: snok/install-poetry@v1
+
+    - name: Install dependencies
+      run: |
+        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==2.10.2"
+        poetry run pip install "mcp==1.10.1"
+        poetry run pip install pytest-xdist
+
+    - name: Setup litellm-enterprise as local package
+      run: |
+        cd enterprise
+        python -m pip install -e .
+        cd ..
+
+    - name: Run MCP tests
+      run: |
+        poetry run pytest tests/mcp_tests -x -vv -n 4 --cov=litellm --cov-report=xml --durations=5

Dockerfile

@@ -41,9 +41,6 @@ RUN pip uninstall jwt -y
 RUN pip uninstall PyJWT -y
 RUN pip install PyJWT==2.9.0 --no-cache-dir
 
-# Build Admin UI
-RUN chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
-
 # Runtime stage
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 

README.md

@@ -37,7 +37,7 @@ LiteLLM manages:
 - Retry/fallback logic across multiple deployments (e.g. Azure/OpenAI) - [Router](https://docs.litellm.ai/docs/routing)
 - Set Budgets & Rate limits per project, api key, model [LiteLLM Proxy Server (LLM Gateway)](https://docs.litellm.ai/docs/simple_proxy)
 
-[**Jump to LiteLLM Proxy (LLM Gateway) Docs**](https://github.com/BerriAI/litellm?tab=readme-ov-file#openai-proxy---docs) <br>
+[**Jump to LiteLLM Proxy (LLM Gateway) Docs**](https://github.com/BerriAI/litellm?tab=readme-ov-file#litellm-proxy-server-llm-gateway---docs) <br>
 [**Jump to Supported LLM Providers**](https://github.com/BerriAI/litellm?tab=readme-ov-file#supported-providers-docs)
 
 🚨 **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)

cookbook/litellm_proxy_server/cli_token_usage.py

@@ -0,0 +1,62 @@
+#!/usr/bin/env python3
+"""
+Example: Using CLI token with LiteLLM SDK
+
+This example shows how to use the CLI authentication token
+in your Python scripts after running `litellm-proxy login`.
+"""
+
+from textwrap import indent
+import litellm
+LITELLM_BASE_URL = "http://localhost:4000/"
+
+
+def main():
+    """Using CLI token with LiteLLM SDK"""
+    print("🚀 Using CLI Token with LiteLLM SDK")
+    print("=" * 40)
+    #litellm._turn_on_debug()
+    
+    # Get the CLI token
+    api_key = litellm.get_litellm_gateway_api_key()
+    
+    if not api_key:
+        print("❌ No CLI token found. Please run 'litellm-proxy login' first.")
+        return
+    
+    print("✅ Found CLI token.")
+
+    available_models = litellm.get_valid_models(
+        check_provider_endpoint=True,
+        custom_llm_provider="litellm_proxy",
+        api_key=api_key,
+        api_base=LITELLM_BASE_URL
+    )
+    
+    print("✅ Available models:")
+    if available_models:
+        for i, model in enumerate(available_models, 1):
+            print(f"   {i:2d}. {model}")
+    else:
+        print("   No models available")
+    
+    # Use with LiteLLM
+    try:
+        response = litellm.completion(
+            model="litellm_proxy/gemini/gemini-2.5-flash",
+            messages=[{"role": "user", "content": "Hello from CLI token!"}],
+            api_key=api_key,
+            base_url=LITELLM_BASE_URL
+        )
+        print(f"✅ LLM Response: {response.model_dump_json(indent=4)}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+
+
+if __name__ == "__main__":
+    main()
+    
+    print("\n💡 Tips:")
+    print("1. Run 'litellm-proxy login' to authenticate first")
+    print("2. Replace 'https://your-proxy.com' with your actual proxy URL")
+    print("3. The token is stored locally at ~/.litellm/token.json")