Merge pull request #21394 from BerriAI/fix/ci-test-improvements

fix(ci): reduce parallelism and add retry logic to improve test stability

.github/workflows/test-litellm-matrix.yml

@@ -12,7 +12,7 @@ concurrency:
 jobs:
   test:
     runs-on: ubuntu-latest
-    timeout-minutes: 15
+    timeout-minutes: 20  # Increased from 15 to 20
     strategy:
       fail-fast: false
       matrix:
@@ -20,36 +20,46 @@ jobs:
           # tests/test_litellm split by subdirectory (~560 files total)
           - name: "llms"
             path: "tests/test_litellm/llms"
-            workers: 4
+            workers: 2  # Reduced from 4 to 2 to avoid race conditions
+            reruns: 2   # Retry flaky tests twice
           # 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: 4
+            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: 4
+            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: 4
+            workers: 2
+            reruns: 2
           - name: "integrations"
             path: "tests/test_litellm/integrations"
-            workers: 4
+            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"
             path: "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"
-            workers: 4
+            workers: 2
+            reruns: 2
           - name: "root"
             path: "tests/test_litellm/test_*.py"
-            workers: 4
+            workers: 2
+            reruns: 2
           # tests/proxy_unit_tests split alphabetically (~48 files total)
           - name: "proxy-unit-a"
             path: "tests/proxy_unit_tests/test_[a-o]*.py"
             workers: 2
+            reruns: 1
           - name: "proxy-unit-b"
             path: "tests/proxy_unit_tests/test_[p-z]*.py"
             workers: 2
+            reruns: 1
 
     name: test (${{ matrix.test-group.name }})
 
@@ -79,7 +89,8 @@ jobs:
         run: |
           poetry config virtualenvs.in-project true
           poetry install --with dev,proxy-dev --extras "proxy semantic-router"
-          poetry run pip install pytest-retry==1.6.3 pytest-xdist google-genai==1.22.0 \
+          # 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
@@ -92,4 +103,6 @@ jobs:
             --tb=short -vv \
             --maxfail=10 \
             -n ${{ matrix.test-group.workers }} \
+            --reruns ${{ matrix.test-group.reruns }} \
+            --reruns-delay 1 \
             --durations=20

poetry.lock

@@ -5524,6 +5524,22 @@ psycopg = ">=3.0.0"
 pytest = ">=6.2"
 setuptools = "*"
 
+[[package]]
+name = "pytest-rerunfailures"
+version = "14.0"
+description = "pytest plugin to re-run tests to eliminate flaky failures"
+optional = false
+python-versions = ">=3.8"
+groups = ["dev"]
+files = [
+    {file = "pytest-rerunfailures-14.0.tar.gz", hash = "sha256:4a400bcbcd3c7a4ad151ab8afac123d90eca3abe27f98725dc4d9702887d2e92"},
+    {file = "pytest_rerunfailures-14.0-py3-none-any.whl", hash = "sha256:4197bdd2eaeffdbf50b5ea6e7236f47ff0e44d1def8dae08e409f536d84e7b32"},
+]
+
+[package.dependencies]
+packaging = ">=17.1"
+pytest = ">=7.2"
+
 [[package]]
 name = "pytest-retry"
 version = "1.7.0"
@@ -7934,4 +7950,4 @@ utils = ["numpydoc"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.9,<4.0"
-content-hash = "dfaf1eabfd17db5e30a8dda813872507aa38664fe7681ece2f8fa06ba035d3cf"
+content-hash = "d99036fc86de60170dde4a1a9b3f9fdac6eb3610edb6177e70ca86133b71703e"

pyproject.toml

@@ -151,7 +151,7 @@ pytest = "^7.4.3"
 pytest-mock = "^3.12.0"
 pytest-asyncio = "^0.21.1"
 pytest-postgresql = "^6.0.0"
-pytest-retry = "^1.6.3"
+pytest-xdist = "^3.5.0"
 requests-mock = "^1.12.1"
 responses = "^0.25.7"
 respx = "^0.22.0"
@@ -166,6 +166,7 @@ opentelemetry-exporter-otlp = "^1.28.0"
 langfuse = "^2.45.0"
 fastapi-offline = "^1.7.3"
 fakeredis = "^2.27.1"
+pytest-rerunfailures = "^14.0"
 
 [tool.poetry.group.proxy-dev.dependencies]
 prisma = "0.11.0"
@@ -192,8 +193,6 @@ plugins = "pydantic.mypy"
 
 [tool.pytest.ini_options]
 asyncio_mode = "auto"
-retries = 20
-retry_delay = 5
 markers = [
     "asyncio: mark test as an asyncio test",
     "limit_leaks: mark test with memory limit for leak detection (e.g., '40 MB')",