ci: move provider-independent MCP tests into tests/unit and run mcp-integration from litellm-tests (#42904)

* ci: fix the litellm-tests unit job with sysmon coverage, an env allowlist and coverage upload on failure

* test: replace key-dependent proxy, enterprise and mcp unit tests with synthetic values and integration and e2e coverage

* test: drop key reads at the legacy proxy, enterprise and mcp paths and wire the gemini pass-through split

* ci: move caching, proxy-extras, gateway and enterprise tests into tests/unit and run them from litellm-tests under their legacy flags

* ci: move caching, proxy-extras, gateway and enterprise tests into tests/unit and run them from litellm-tests under their legacy flags

* ci: move tests/proxy_unit_tests to tests/unit/proxy and run the proxy-db shards from litellm-tests

* ci: move provider-independent MCP tests into tests/unit and run mcp-integration from litellm-tests

* ci: fail the unit shard when circleci tests split errors

* test: drop restating comments from the gemini pass-through split

* build: point the local proxy unit targets at the nested tests/unit/proxy tree

* ci: exit the unit shard cleanly when circleci tests split assigns it no files

---------

Co-authored-by: yuneng <yuneng@berri.ai>

.circleci/scripts/unit_selection.sh

@@ -7,6 +7,7 @@ legacy_flags=(
   caching-local
   enterprise-package
   enterprise-routing
+  mcp-integration
   proxy-db-auth-checks
   proxy-db-budgets
   proxy-db-custom-logging
@@ -46,6 +47,10 @@ legacy_paths() {
       echo tests/unit/enterprise/proxy/test_file_deletion_blocking.py
       echo tests/unit/enterprise/proxy/test_managed_files_access_check.py
       echo tests/unit/enterprise/proxy/test_managed_files_hook.py ;;
+    mcp-integration)
+      echo tests/unit/proxy/_experimental/mcp_server
+      echo tests/unit/responses/mcp
+      echo tests/mcp_tests/test_proxy_mcp_e2e.py ;;
     proxy-db-auth-checks)
       echo tests/unit/proxy/auth/test_auth_checks.py
       echo tests/unit/proxy/auth/test_user_api_key_auth.py

.circleci/tests.yml

@@ -183,6 +183,9 @@ jobs:
       pull_request_url:
         type: string
         default: ""
+      legacy_mcp_peer:
+        type: boolean
+        default: false
       reruns:
         type: integer
         default: 0
@@ -200,6 +203,15 @@ jobs:
           base_ref: << parameters.base_ref >>
           pull_request_url: << parameters.pull_request_url >>
       - setup_test_deps
+      - when:
+          condition: << parameters.legacy_mcp_peer >>
+          steps:
+            - run:
+                name: Install MCP SDK1 peer
+                command: |
+                  uv venv --python 3.12 .venv-mcp-peer
+                  uv pip install --python .venv-mcp-peer 'mcp==1.28.1' 'langchain-mcp-adapters==0.2.1'
+                  echo "export MCP_TEST_PEER_PYTHON=$PWD/.venv-mcp-peer/bin/python" >> "$BASH_ENV"
       - run:
           name: "Run << parameters.flag >> shard"
           no_output_timeout: 20m
@@ -215,6 +227,7 @@ jobs:
             rerun_args=(-p no:rerunfailures)
             if [ "<< parameters.reruns >>" -gt 0 ]; then rerun_args=(--reruns << parameters.reruns >> --reruns-delay 1 --rerun-except "from pytest-timeout"); fi
             test_env=(PATH="$PATH" HOME="$HOME" CI=true COVERAGE_CORE="$COVERAGE_CORE" LITELLM_LOCAL_MODEL_COST_MAP="$LITELLM_LOCAL_MODEL_COST_MAP")
+            if [ -n "${MCP_TEST_PEER_PYTHON:-}" ]; then test_env+=(MCP_TEST_PEER_PYTHON="$MCP_TEST_PEER_PYTHON"); fi
             set +e
             env -i "${test_env[@]}" \
               uv run --no-sync pytest "${files[@]}" "${rerun_args[@]}" -p no:pytest-retry --timeout=90 "${xdist_args[@]}" --tb=short --durations=20 -o junit_family=xunit1 --junitxml=test-results/<< parameters.flag >>/junit.xml --cov=./litellm --cov=./enterprise/litellm_enterprise --cov-report=xml:coverage.xml --cov-config=pyproject.toml
@@ -311,6 +324,14 @@ workflows:
               flag: [caching-local, proxy-extras, enterprise-routing]
           base_ref: << pipeline.event.name == "pull_request" and pipeline.event.github.pull_request.base.ref or "" >>
           pull_request_url: << pipeline.event.name == "pull_request" and pipeline.event.github.pull_request.url or "" >>
+      - unit:
+          name: unit-mcp-integration
+          flag: mcp-integration
+          shards: 1
+          workers: 2
+          legacy_mcp_peer: true
+          base_ref: << pipeline.event.name == "pull_request" and pipeline.event.github.pull_request.base.ref or "" >>
+          pull_request_url: << pipeline.event.name == "pull_request" and pipeline.event.github.pull_request.url or "" >>
       - unit:
           name: unit-<< matrix.flag >>
           shards: 1

.github/workflows/test-unit.yml

@@ -53,6 +53,7 @@ jobs:
           - shard: mcp-integration
             artifact-name: mcp-integration
             test-path: "tests/mcp_tests tests/test_litellm/experimental_mcp_client"
+            fork-flag: mcp-integration
             workers: 2
             reruns: 0
             timeout-minutes: 20

tests/unit/proxy/_experimental/mcp_server/conftest.py

@@ -0,0 +1,78 @@
+import asyncio
+import importlib
+
+import pytest
+
+import litellm
+from litellm.litellm_core_utils.logging_worker import GLOBAL_LOGGING_WORKER
+
+
+@pytest.fixture(scope="session")
+def event_loop():
+    try:
+        loop = asyncio.get_running_loop()
+    except RuntimeError:
+        loop = asyncio.new_event_loop()
+    yield loop
+    loop.close()
+
+
+@pytest.fixture(scope="function", autouse=True)
+def setup_and_teardown():
+    """
+    This fixture reloads litellm before every function. To speed up testing by removing callbacks being chained.
+    """
+    importlib.reload(litellm)
+    import asyncio
+
+    loop = asyncio.get_event_loop_policy().new_event_loop()
+    asyncio.set_event_loop(loop)
+    yield
+
+    # Teardown code (executes after the yield point)
+    # LoggingWorker carries still-queued coroutines onto the next test's loop, where they'd log into that test's callbacks
+    asyncio.run(GLOBAL_LOGGING_WORKER.clear_queue())
+    loop.close()  # Close the loop created earlier
+    asyncio.set_event_loop(None)  # Remove the reference to the loop
+
+
+@pytest.fixture(scope="function", autouse=True)
+async def drain_logging_worker():
+    """
+    The logging queue is bound to the running loop, so anything left queued when a test's loop
+    goes away is carried onto the next test's loop and fires against its callbacks.
+    """
+    from litellm.litellm_core_utils.logging_worker import GLOBAL_LOGGING_WORKER
+
+    yield
+
+    try:
+        await asyncio.wait_for(GLOBAL_LOGGING_WORKER.clear_queue(), timeout=10)
+    except asyncio.TimeoutError:
+        pass
+
+
+def pytest_collection_modifyitems(config, items):
+    # Separate tests in 'test_amazing_proxy_custom_logger.py' and other tests
+    custom_logger_tests = [
+        item for item in items if "custom_logger" in item.parent.name
+    ]
+    other_tests = [item for item in items if "custom_logger" not in item.parent.name]
+
+    # Sort tests based on their names
+    custom_logger_tests.sort(key=lambda x: x.name)
+    other_tests.sort(key=lambda x: x.name)
+
+    # Reorder the items list
+    items[:] = custom_logger_tests + other_tests
+
+
+@pytest.fixture
+def config_only_mcp_manager_factory():
+    from litellm.proxy._experimental.mcp_server.mcp_server_manager import MCPServerManager
+
+    class ConfigOnlyManager(MCPServerManager):
+        def initialize_tool_name_to_mcp_server_name_mapping(self):
+            return None
+
+    return ConfigOnlyManager