fix: Apply pre-commit formatting and linting fixes

- Remove trailing whitespace from CI workflow, noxfile, and tox.ini
- Add newline at end of tox.ini
- Reformat assert statements in tests for better readability
- Apply ruff formatting standards across all files

Author: brightlikethelight

.github/workflows/ci.yml

@@ -76,7 +76,7 @@ jobs:
           python-version: ${{ matrix.python-version }}
       - name: Install dependencies
         run: pipx install pdm && pipx install nox
-      - name: Run OpenLLM async tests  
+      - name: Run OpenLLM async tests
         run: nox --session openllm-async-${{ matrix.python-version }}
       - name: Disambiguate coverage filename
         run: mv .coverage ".coverage.async-patterns.${{ matrix.os }}.${{ matrix.python-version }}"

noxfile.py

@@ -123,7 +123,7 @@ def run_async_llm_pattern_tests(session: nox.Session):
     )
 
 
-@nox.session(name="transformers-async-local", python=PYTHON_VERSIONS)  
+@nox.session(name="transformers-async-local", python=PYTHON_VERSIONS)
 def run_transformers_async_tests_local(session: nox.Session):
     """Run full transformers async tests locally (not in CI due to resource constraints)."""
     session.run("pdm", "sync", "-G", "testing", external=True)

tests/unit/test_openllm_run.py

@@ -85,9 +85,9 @@ async def test_run_async_concurrent(self):
             assert "generated_text" in result
 
         # Performance requirement: complete within 60 seconds
-        assert (
-            elapsed_time < 60
-        ), f"Async operations took {elapsed_time:.2f}s, exceeding 60s limit"
+        assert elapsed_time < 60, (
+            f"Async operations took {elapsed_time:.2f}s, exceeding 60s limit"
+        )
 
         # For mock operations, should be very fast
         assert elapsed_time < 1.0, f"Mock operations took {elapsed_time:.3f}s, too slow"
@@ -162,12 +162,12 @@ def test_performance_requirements(self):
         elapsed_time = time.time() - start_time
 
         # Should complete well within 60 seconds
-        assert (
-            elapsed_time < 60
-        ), f"Performance test took {elapsed_time:.2f}s, exceeding 60s limit"
-        assert (
-            elapsed_time < 1.0
-        ), f"Mock operations took {elapsed_time:.3f}s, expected faster"
+        assert elapsed_time < 60, (
+            f"Performance test took {elapsed_time:.2f}s, exceeding 60s limit"
+        )
+        assert elapsed_time < 1.0, (
+            f"Mock operations took {elapsed_time:.3f}s, expected faster"
+        )
 
     @pytest.mark.asyncio
     async def test_async_performance_requirements(self):
@@ -184,12 +184,12 @@ async def test_async_performance_requirements(self):
         assert len(results) == 10
 
         # Performance requirements
-        assert (
-            elapsed_time < 60
-        ), f"Async performance test took {elapsed_time:.2f}s, exceeding 60s limit"
-        assert (
-            elapsed_time < 1.0
-        ), f"Async mock operations took {elapsed_time:.3f}s, expected faster"
+        assert elapsed_time < 60, (
+            f"Async performance test took {elapsed_time:.2f}s, exceeding 60s limit"
+        )
+        assert elapsed_time < 1.0, (
+            f"Async mock operations took {elapsed_time:.3f}s, expected faster"
+        )
 
 
 class TestHttpxAsyncClient:
@@ -280,9 +280,9 @@ async def test_httpx_concurrent_requests(self):
                     assert result["prompt"] == prompts[i]
 
                 # Performance check
-                assert (
-                    elapsed_time < 60
-                ), f"HTTP requests took {elapsed_time:.2f}s, exceeding 60s limit"
+                assert elapsed_time < 60, (
+                    f"HTTP requests took {elapsed_time:.2f}s, exceeding 60s limit"
+                )
 
     @pytest.mark.asyncio
     async def test_httpx_batch_requests(self):

tox.ini

@@ -3,67 +3,67 @@ envlist = py{39,310,311,312}, openllm-async-tests
 skipsdist = True
 
 [testenv]
-deps = 
+deps =
     -e .[testing]
-commands = 
+commands =
     pytest {posargs}
 
 [testenv:openllm-async-tests]
-deps = 
+deps =
     -e .[testing]
     pytest-asyncio>=0.21.1
     httpx
     pytest-cov>=4.1.0
-commands = 
+commands =
     pytest tests/unit/test_openllm_run.py --cov=bentoml.openllm --cov-fail-under=90 --cov-report=term-missing -v --timeout=60
 setenv =
     PYTEST_TIMEOUT = 60
 passenv = *
 enable_parallel = true
 
 [testenv:transformers-local]
-deps = 
+deps =
     -e .[testing]
     pytest-asyncio>=0.21.1
     transformers
     torch
     tokenizers
     pytest-cov>=4.1.0
-commands = 
+commands =
     pytest tests/integration/frameworks/test_transformers_async.py --cov=bentoml._internal.frameworks.transformers --cov-report=term-missing -v --timeout=300
 
 [testenv:lint]
-deps = 
+deps =
     ruff
     black
     mypy
-commands = 
+commands =
     ruff check src/ tests/
     black --check src/ tests/
     mypy src/
 
 [testenv:format]
-deps = 
+deps =
     ruff
     black
-commands = 
+commands =
     ruff check --fix src/ tests/
     black src/ tests/
 
 [coverage:run]
 branch = True
 source = bentoml
-omit = 
+omit =
     */tests/*
     */__pycache__/*
     */site-packages/*
 
 [coverage:report]
-exclude_lines = 
+exclude_lines =
     pragma: no cover
     def __repr__
     raise AssertionError
     raise NotImplementedError
     if __name__ == .__main__.:
     if TYPE_CHECKING:
-precision = 2
+precision = 2