ci(circleci): enable Rerun Failed Tests for all pytest jobs (#27155)

* ci(circleci): enable Rerun Failed Tests for all pytest suites Migrated every pytest-based CircleCI job that uploads JUnit results to use 'circleci tests run' instead of invoking pytest directly. This is the prerequisite for CircleCI's 'Rerun failed tests' feature to be available on each job in the pipeline. For each job: - Glob test files via 'circleci tests glob' and pipe them into 'circleci tests run --command="xargs ... pytest ..."' so the agent can feed the failed-test subset on rerun. - Preserve all original pytest flags (parallelism, timeouts, retries, coverage, junit output paths). - For jobs that previously lacked 'store_test_results' (proxy spend accuracy, proxy_build_from_pip, db_migration_disable_update_check), add the step so JUnit XML is uploaded and rerun is actually wired up. - Replace the dynamic IGNORE_DIRS shell array in llm_translation_testing with a 'grep -v' filter on the glob output, matching the previous behavior of skipping tests/llm_translation/realtime. - For 'build_and_test', glob 'tests/test_*.py' (top-level only) which matches the prior 'tests/*.py' shell glob; the long list of '--ignore=tests/<subdir>' flags was vestigial and is dropped. Jobs already using 'circleci tests run' (local_testing_part1/2, litellm_router_testing) are unchanged. * fix(ci): convert classnames to file paths on rerun CircleCI's Rerun Failed Tests sends each previously failed test as a JUnit classname (e.g. 'tests.otel_tests.test_key_logging_callbacks'), but pytest needs a file path. Without the awk preprocess step, rerun runs fail with 'file or directory not found'. Mirror the awk transform that local_testing_part1, local_testing_part2, and litellm_router_testing already use, so rerun works in every job that this PR migrated to 'circleci tests run'. * ci: drop -x from OTEL pytest run so all failures are reported --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-05-05 17:27:09 -07:00 · 2026-05-05 17:27:09 -07:00 · fdaa288607
commit fdaa288607
parent fd7ff0f269
1 changed files with 298 additions and 43 deletions
--- a/.circleci/config.yml
+++ b/.circleci/config.yml
@ -350,7 +350,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/local_testing -x --junitxml=test-results/junit.xml --durations=5 -k "langfuse"
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/local_testing/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -k \"langfuse\""
          no_output_timeout: 15m
      # Store test results
      - store_test_results:
@ -395,7 +403,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/proxy_admin_ui_tests -x --junitxml=test-results/junit.xml --durations=5 -n 2
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/proxy_admin_ui_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 2"
          no_output_timeout: 15m

      # Store test results
@ -471,7 +487,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/router_unit_tests -x --junitxml=test-results/junit.xml --durations=5 -n 4
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/router_unit_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 4"
          no_output_timeout: 15m
      # Store test results
      - store_test_results:
@ -495,7 +519,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest tests/local_testing/ -v -k "assistants" -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/local_testing/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -k \"assistants\""
          no_output_timeout: 15m
      # Store test results
      - store_test_results:
@ -528,14 +560,19 @@ jobs:
            # Add --timeout to kill hanging tests after 120s (2 min)
            # Add --durations=20 to show 20 slowest tests for debugging
            # Subdirectories with dedicated jobs (maintain this list as new jobs are added)
-            IGNORE_DIRS=(
-              "tests/llm_translation/realtime"
-            )
-            IGNORE_ARGS=""
-            for dir in "${IGNORE_DIRS[@]}"; do
-              IGNORE_ARGS="$IGNORE_ARGS --ignore=$dir"
-            done
-            uv run --no-sync python -m pytest -v tests/llm_translation $IGNORE_ARGS --junitxml=test-results/junit.xml --durations=20 -n 4 --timeout=120 --timeout_method=thread --retries 2 --retry-delay 5 --max-worker-restart=5
+            mkdir -p test-results
+            # Glob excludes the realtime/ subdirectory since it has its own job
+            TEST_FILES=$(circleci tests glob "tests/llm_translation/**/test_*.py" | grep -v "^tests/llm_translation/realtime/")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v \
+                --junitxml=test-results/junit.xml \
+                --durations=20 \
+                -n 4 \
+                --timeout=120 --timeout_method=thread \
+                --retries 2 --retry-delay 5 \
+                --max-worker-restart=5"
          no_output_timeout: 15m

      # Store test results
@ -560,7 +597,17 @@ jobs:
          command: |
            # Add --timeout to kill hanging tests after 120s (2 min)
            # Add --durations=20 to show 20 slowest tests for debugging
-            uv run --no-sync python -m pytest -vv tests/llm_translation/realtime --cov=litellm --cov-report=xml -v --junitxml=test-results/junit.xml --durations=20 -n 4 --timeout=120 --timeout_method=thread
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/llm_translation/realtime/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=20 \
+                -n 4 \
+                --timeout=120 --timeout_method=thread"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -593,7 +640,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/agent_tests --ignore=tests/agent_tests/local_only_agent_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/agent_tests/**/test_*.py" | grep -v "^tests/agent_tests/local_only_agent_tests/")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -626,7 +681,18 @@ jobs:
      - run:
          name: Run tests
          command: |
-            LITELLM_LOG=WARNING uv run --no-sync python -m pytest tests/guardrails_tests -vv --cov=litellm --cov-report=xml --junitxml=test-results/junit.xml --durations=5 -n 2 --timeout=120 --timeout_method=thread
+            mkdir -p test-results
+            export LITELLM_LOG=WARNING
+            TEST_FILES=$(circleci tests glob "tests/guardrails_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 2 \
+                --timeout=120 --timeout_method=thread"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -660,7 +726,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/unified_google_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5 --retries 3 --retry-delay 5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/unified_google_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                --retries 3 --retry-delay 5"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -702,7 +777,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/llm_responses_api_testing -x --junitxml=test-results/junit.xml --durations=5 -n 8
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/llm_responses_api_testing/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 8"
          no_output_timeout: 15m

      # Store test results
@ -725,7 +808,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/ocr_tests --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5 -n 4
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/ocr_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 4"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -758,7 +850,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/search_tests --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5 -n 4
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/search_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 4"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -793,7 +894,15 @@ jobs:
          name: Run enterprise tests
          command: |
            uv run --no-sync python -m prisma generate
-            uv run --no-sync python -m pytest -v tests/enterprise -x --junitxml=test-results/junit-enterprise.xml --durations=10 -n 4
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/enterprise/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit-enterprise.xml \
+                --durations=10 \
+                -n 4"
          no_output_timeout: 15m
      # Store test results
      - store_test_results:
@ -815,7 +924,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/batches_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5 -n 2
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/batches_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 2"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -848,7 +966,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/litellm_utils_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5 -n 2
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/litellm_utils_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 2"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -882,7 +1009,16 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/pass_through_unit_tests --cov=litellm --cov-report=xml -x -v --junitxml=test-results/junit.xml --durations=5 -n 4
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/pass_through_unit_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 4"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -916,7 +1052,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/image_gen_tests -n 4 -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/image_gen_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                -n 4"
          no_output_timeout: 15m
      # Store test results
      - store_test_results:
@ -939,7 +1083,18 @@ jobs:
      - run:
          name: Run tests
          command: |
-            LITELLM_LOG=WARNING uv run --no-sync python -m pytest tests/logging_callback_tests -vv --cov=litellm --cov-report=xml -n 4 --junitxml=test-results/junit.xml --durations=5 --timeout=120 --timeout_method=thread
+            mkdir -p test-results
+            export LITELLM_LOG=WARNING
+            TEST_FILES=$(circleci tests glob "tests/logging_callback_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv \
+                --cov=litellm --cov-report=xml \
+                -n 4 \
+                --junitxml=test-results/junit.xml \
+                --durations=5 \
+                --timeout=120 --timeout_method=thread"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -972,7 +1127,15 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/audio_tests --cov=litellm --cov-report=xml -x -s -v --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/audio_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
      - run:
          name: Rename the coverage files
@ -1012,14 +1175,19 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv \
+            mkdir -p test-results
+            TEST_FILES=$(printf "%s\n" \
              tests/local_testing/test_dual_cache.py \
              tests/local_testing/test_redis_batch_optimizations.py \
-              tests/local_testing/test_router_utils.py \
-              --cov=litellm --cov-report=xml \
-              -x -s -v --junitxml=test-results/junit.xml \
-              --durations=5 -n 2 \
-              --reruns 2 --reruns-delay 1
+              tests/local_testing/test_router_utils.py)
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --cov=litellm --cov-report=xml \
+                --junitxml=test-results/junit.xml \
+                --durations=5 -n 2 \
+                --reruns 2 --reruns-delay 1"
          no_output_timeout: 20m
      - run:
          name: Rename the coverage files
@ -1260,8 +1428,17 @@ jobs:
      - run:
          name: Run Basic Proxy Startup Tests (Health Readiness and Chat Completion)
          command: |
-            uv run --no-sync python -m pytest -v tests/basic_proxy_startup_tests -x --junitxml=test-results/junit-2.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/basic_proxy_startup_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit-2.xml \
+                --durations=5"
          no_output_timeout: 15m
+      - store_test_results:
+          path: test-results

  build_and_test:
    machine:
@ -1331,7 +1508,18 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -s -v tests/*.py -x --junitxml=test-results/junit.xml -n 4 --durations=5 --ignore=tests/otel_tests --ignore=tests/spend_tracking_tests --ignore=tests/pass_through_tests --ignore=tests/proxy_admin_ui_tests --ignore=tests/load_tests --ignore=tests/llm_translation --ignore=tests/llm_responses_api_testing --ignore=tests/mcp_tests --ignore=tests/guardrails_tests --ignore=tests/image_gen_tests --ignore=tests/pass_through_unit_tests
+            mkdir -p test-results
+            # Original used `tests/*.py` (top-level only); the `--ignore=...`
+            # flags were vestigial since shell globbing did not descend into
+            # subdirectories. Replicate by globbing only top-level test files.
+            TEST_FILES=$(circleci tests glob "tests/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -s -v -x \
+                --junitxml=test-results/junit.xml \
+                -n 4 \
+                --durations=5"
          no_output_timeout: 15m

      # Store test results
@ -1406,7 +1594,14 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -s -vv tests/openai_endpoints_tests --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/openai_endpoints_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -s -vv \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m

      # Store test results
@ -1475,7 +1670,14 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/otel_tests --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/otel_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
            # Clean up first container
      - run:
@ -1518,7 +1720,14 @@ jobs:
      - run:
          name: Run second round of tests
          command: |
-            uv run --no-sync python -m pytest -v tests/basic_proxy_startup_tests -x --junitxml=test-results/junit-2.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/basic_proxy_startup_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit-2.xml \
+                --durations=5"
          no_output_timeout: 15m

      # Store test results
@ -1587,8 +1796,17 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/spend_tracking_tests -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/spend_tracking_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
+      - store_test_results:
+          path: test-results
      - run:
          name: Stop and remove first container
          when: always
@ -1676,7 +1894,14 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/multi_instance_e2e_tests -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/multi_instance_e2e_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
            # Clean up first container
      # Store test results
@ -1732,7 +1957,14 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/store_model_in_db_tests -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/store_model_in_db_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m
      - run:
          name: Stop and remove containers
@ -1805,9 +2037,18 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -vv tests/basic_proxy_startup_tests -x --junitxml=test-results/junit-2.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/basic_proxy_startup_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x \
+                --junitxml=test-results/junit-2.xml \
+                --durations=5"
          no_output_timeout: 15m
            # Clean up first container
+      - store_test_results:
+          path: test-results
      - run:
          name: Stop and remove first container
          command: |
@ -1940,7 +2181,14 @@ jobs:
      - run:
          name: Run tests
          command: |
-            uv run --no-sync python -m pytest -v tests/pass_through_tests/ -x --junitxml=test-results/junit.xml --durations=5
+            mkdir -p test-results
+            TEST_FILES=$(circleci tests glob "tests/pass_through_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -v -x \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m

      # Store test results
@ -1997,9 +2245,16 @@ jobs:
      - run:
          name: Run Claude Agent SDK E2E Tests
          command: |
+            mkdir -p test-results
            export LITELLM_PROXY_URL="http://localhost:4000"
            export LITELLM_API_KEY="sk-1234"
-            uv run --no-sync python -m pytest -vv tests/proxy_e2e_anthropic_messages_tests/ -x -s --junitxml=test-results/junit.xml --durations=5
+            TEST_FILES=$(circleci tests glob "tests/proxy_e2e_anthropic_messages_tests/**/test_*.py")
+            echo "$TEST_FILES" | circleci tests run \
+              --verbose \
+              --command="awk '/\\.py/ {print; next} {sub(/\\.[A-Z][^.]*$/, \"\"); gsub(/\\./, \"/\"); print \$0 \".py\"}' | xargs uv run --no-sync python -m pytest \
+                -vv -x -s \
+                --junitxml=test-results/junit.xml \
+                --durations=5"
          no_output_timeout: 15m

      # Store test results