fix: resolve all ruff lint errors across repo (#38)

* fix: resolve all ruff lint errors across repo

Auto-fixed 31 errors (unused imports, formatting, simplifications).
Manually fixed 14 remaining:
- EXE001: removed shebangs from non-executable bench scripts
- C417: replaced map(lambda) with generator expression
- C901/PLR0915: extracted _write_and_instrument_tests from generate_ai_tests
- C901/PLR0912: extracted _parse_toml_addopts and _ini_section_name from modify_addopts
- RUF001/RUF002: replaced ambiguous Unicode chars (en dash, multiplication sign)
- FBT002: made boolean params keyword-only in report functions
- E402: moved `import re` to top of file in security reports

* fix: resolve pre-existing mypy errors across packages

- _testgen.py: annotate `generated` as `str` to avoid no-any-return
- _test_runner.py: use str() for TimeoutExpired stdout/stderr (bytes|str),
  remove unused type: ignore on proc.kill()
- _candidate_eval.py: annotate `speedup` as `float` to avoid no-any-return
  from lazy-loaded performance_gain

.codeflash/krrt7/plotly/plotly.py/bench/bench_split_multichar.py

@@ -1,4 +1,3 @@
-#!/usr/bin/env python
 """Benchmark for split_multichar optimization (Target 6)"""
 
 import sys
@@ -12,7 +11,7 @@ def split_multichar_original(ss, chars):
     if len(chars) == 0:
         return ss
     c = chars.pop()
-    ss = reduce(lambda x, y: x + y, map(lambda x: x.split(c), ss))
+    ss = reduce(lambda x, y: x + y, (x.split(c) for x in ss))
     return split_multichar_original(ss, chars)
 
 
@@ -70,7 +69,7 @@ def main():
 
         # Verify results match
         if orig_result != opt_result:
-            print(f"  ERROR: Results don't match!")
+            print("  ERROR: Results don't match!")
             print(f"    Original: {orig_result}")
             print(f"    Optimized: {opt_result}")
             sys.exit(1)
@@ -78,8 +77,8 @@ def main():
         # Report results
         speedup = orig_time / opt_time
         print(f"  Result: {opt_result}")
-        print(f"  Original:  {orig_time*1e6:.2f} µs")
+        print(f"  Original:  {orig_time * 1e6:.2f} µs")
-        print(f"  Optimized: {opt_time*1e6:.2f} µs")
+        print(f"  Optimized: {opt_time * 1e6:.2f} µs")
         print(f"  Speedup:   {speedup:.2f}x")
 
     print("\n" + "=" * 60)

.codeflash/krrt7/plotly/plotly.py/bench/bench_vals_equal.py

@@ -1,8 +1,8 @@
-#!/usr/bin/env python
 """Benchmark for _vals_equal optimization (Target 5)"""
 
 import sys
 import time
+
 import numpy as np
 
 
@@ -13,20 +13,19 @@ def vals_equal_original(v1, v2):
         isinstance(v1, np.ndarray) or isinstance(v2, np.ndarray)
     ):
         return np.array_equal(v1, v2)
-    elif isinstance(v1, (list, tuple)):
+    if isinstance(v1, (list, tuple)):
         return (
             isinstance(v2, (list, tuple))
             and len(v1) == len(v2)
             and all(vals_equal_original(e1, e2) for e1, e2 in zip(v1, v2))
         )
-    elif isinstance(v1, dict):
+    if isinstance(v1, dict):
         return (
             isinstance(v2, dict)
             and set(v1.keys()) == set(v2.keys())
             and all(vals_equal_original(v1[k], v2[k]) for k in v1)
         )
-    else:
+    return v1 == v2
-        return v1 == v2
 
 
 # Optimized implementation with early exits
@@ -43,20 +42,19 @@ def vals_equal_optimized(v1, v2):
             return False
         # Now do element-wise comparison (np.array_equal handles dtype conversion)
         return np.array_equal(v1, v2)
-    elif isinstance(v1, (list, tuple)):
+    if isinstance(v1, (list, tuple)):
         return (
             isinstance(v2, (list, tuple))
             and len(v1) == len(v2)
             and all(vals_equal_optimized(e1, e2) for e1, e2 in zip(v1, v2))
         )
-    elif isinstance(v1, dict):
+    if isinstance(v1, dict):
         return (
             isinstance(v2, dict)
             and set(v1.keys()) == set(v2.keys())
             and all(vals_equal_optimized(v1[k], v2[k]) for k in v1)
         )
-    else:
+    return v1 == v2
-        return v1 == v2
 
 
 def benchmark(func, v1, v2, iterations=10000):
@@ -77,29 +75,28 @@ def main():
 
     # Test cases
     test_cases = [
-        ("Equal arrays (same data)",
+        (
-         np.array([1, 2, 3, 4, 5] * 100),
+            "Equal arrays (same data)",
-         np.array([1, 2, 3, 4, 5] * 100)),
+            np.array([1, 2, 3, 4, 5] * 100),
-
+            np.array([1, 2, 3, 4, 5] * 100),
-        ("Different shapes (early exit)",
+        ),
-         np.array([1, 2, 3, 4, 5] * 100),
+        (
-         np.array([1, 2, 3, 4] * 100)),
+            "Different shapes (early exit)",
-
+            np.array([1, 2, 3, 4, 5] * 100),
-        ("Different dtypes (but same values)",
+            np.array([1, 2, 3, 4] * 100),
-         np.array([1, 2, 3, 4, 5] * 100, dtype=np.int32),
+        ),
-         np.array([1, 2, 3, 4, 5] * 100, dtype=np.float64)),
+        (
-
+            "Different dtypes (but same values)",
-        ("Different values (late difference)",
+            np.array([1, 2, 3, 4, 5] * 100, dtype=np.int32),
-         np.array([1, 2, 3, 4, 5] * 100),
+            np.array([1, 2, 3, 4, 5] * 100, dtype=np.float64),
-         np.array([1, 2, 3, 4, 6] * 100)),
+        ),
-
+        (
-        ("Large equal arrays",
+            "Different values (late difference)",
-         np.arange(10000),
+            np.array([1, 2, 3, 4, 5] * 100),
-         np.arange(10000)),
+            np.array([1, 2, 3, 4, 6] * 100),
-
+        ),
-        ("Array vs scalar (type mismatch)",
+        ("Large equal arrays", np.arange(10000), np.arange(10000)),
-         np.array([1, 2, 3]),
+        ("Array vs scalar (type mismatch)", np.array([1, 2, 3]), [1, 2, 3]),
-         [1, 2, 3]),
     ]
 
     for name, v1, v2 in test_cases:
@@ -113,16 +110,16 @@ def main():
 
         # Verify results match
         if orig_result != opt_result:
-            print(f"  ERROR: Results don't match!")
+            print("  ERROR: Results don't match!")
             print(f"    Original: {orig_result}")
             print(f"    Optimized: {opt_result}")
             sys.exit(1)
 
         # Report results
-        speedup = orig_time / opt_time if opt_time > 0 else float('inf')
+        speedup = orig_time / opt_time if opt_time > 0 else float("inf")
         print(f"  Result: {orig_result}")
-        print(f"  Original:  {orig_time*1e6:.2f} µs")
+        print(f"  Original:  {orig_time * 1e6:.2f} µs")
-        print(f"  Optimized: {opt_time*1e6:.2f} µs")
+        print(f"  Optimized: {opt_time * 1e6:.2f} µs")
         print(f"  Speedup:   {speedup:.2f}x")
 
     print("\n" + "=" * 60)

packages/codeflash-api/tests/test_repair.py

@@ -11,9 +11,9 @@ from codeflash_api.repair._context import (
     is_valid_repair,
 )
 from codeflash_api.repair.schemas import (
-    CodeRepairRequest,
     BehaviorDiff,
     BehaviorDiffScope,
+    CodeRepairRequest,
 )
 
 # -------------------------------------------------------------------

packages/codeflash-python/src/codeflash_python/analysis/_discovery_worker.py

@@ -57,7 +57,9 @@ class PytestCollectionPlugin:
         global pytest_rootdir, collected_tests
 
         collected_tests.extend(session.items)
-        pytest_rootdir = getattr(session.config, "rootdir", None) or getattr(session.config, "rootpath", None)
+        pytest_rootdir = getattr(session.config, "rootdir", None) or getattr(
+            session.config, "rootpath", None
+        )
 
         # Write results immediately since pytest.main() will exit after
         # this callback, not always with a success code.
@@ -87,7 +89,8 @@ if __name__ == "__main__":
                 tests_root,
                 "-p",
                 "no:logging",
-                "-o", "addopts=",
+                "-o",
+                "addopts=",
                 "--collect-only",
                 "-m",
                 "not skip",

packages/codeflash-python/src/codeflash_python/pipeline/_candidate_eval.py

@@ -168,7 +168,7 @@ async def run_tests_and_benchmark(  # noqa: PLR0913
             optimized_runtime,
         )
 
-    speedup = performance_gain(
+    speedup: float = performance_gain(
         original_runtime_ns=baseline.runtime,
         optimized_runtime_ns=optimized_runtime,
     )

packages/codeflash-python/src/codeflash_python/pipeline/_test_orchestrator.py

@@ -362,9 +362,7 @@ def generate_ai_tests(  # noqa: PLR0913
         AIServiceError,
     )
 
-    from ..test_discovery.models import TestType  # noqa: PLC0415
     from ..testing._testgen import generate_tests  # noqa: PLC0415
-    from ..testing.models import TestFile  # noqa: PLC0415
 
     n_tests = 2  # matches original effort default
     testgen_source = code_context.testgen_context.markdown
@@ -444,10 +442,7 @@ def generate_ai_tests(  # noqa: PLR0913
 
     pending: list[PendingTest] = []
     with ThreadPoolExecutor(max_workers=n_tests) as pool:
-        futures = {
+        futures = {pool.submit(_generate_one, i): i for i in range(n_tests)}
-            pool.submit(_generate_one, i): i
-            for i in range(n_tests)
-        }
         for future in as_completed(futures):
             p = future.result()
             if p is not None:
@@ -467,19 +462,24 @@ def generate_ai_tests(  # noqa: PLR0913
         fn_input=fn_input,
     )
 
-    # Phase 4: write files, instrument client-side, create TestFile objects.
+    return _write_and_instrument_tests(pending, func, tests_rootdir)
+
+
+def _write_and_instrument_tests(
+    pending: list[PendingTest],
+    func: FunctionToOptimize,
+    tests_rootdir: Path,
+) -> list[TestFile]:
+    """Write generated tests to disk and instrument for behavior/perf capture."""
     from .._model import TestingMode  # noqa: PLC0415
+    from ..test_discovery.models import TestType  # noqa: PLC0415
     from ..testing._instrumentation import (  # noqa: PLC0415
         inject_profiling_into_existing_test,
     )
+    from ..testing.models import TestFile  # noqa: PLC0415
 
     test_file_objects: list[TestFile] = []
-    for (
+    for _idx, generated_source, test_path, test_perf_path in pending:
-        _idx,
-        generated_source,
-        test_path,
-        test_perf_path,
-    ) in pending:
         test_path.write_text(generated_source, encoding="utf-8")
 
         ok_beh, beh_src = inject_profiling_into_existing_test(
@@ -497,10 +497,10 @@ def generate_ai_tests(  # noqa: PLR0913
             mode=TestingMode.PERFORMANCE,
         )
 
-        beh_path: _Path | None = test_path.parent / (
+        beh_path: Path | None = test_path.parent / (
             test_path.stem + "__perfinstrumented" + test_path.suffix
         )
-        perf_path: _Path | None = test_perf_path
+        perf_path: Path | None = test_perf_path
 
         if ok_beh and beh_src is not None:
             beh_path.write_text(beh_src, encoding="utf-8")  # type: ignore[union-attr]
@@ -694,9 +694,7 @@ def build_test_env(
         module_root = str(_Path(test_cfg.module_root))
         existing = env.get("PYTHONPATH", "")
         env["PYTHONPATH"] = (
-            f"{module_root}{os.pathsep}{existing}"
+            f"{module_root}{os.pathsep}{existing}" if existing else module_root
-            if existing
-            else module_root
         )
     return env
 

packages/codeflash-python/src/codeflash_python/test_discovery/discovery.py

@@ -93,7 +93,9 @@ def discover_unit_tests(
             for func in funcs
         ]
     return discover_tests_pytest(
-        cfg, discover_only_these_tests, functions_to_optimize,
+        cfg,
+        discover_only_these_tests,
+        functions_to_optimize,
     )
 
 
@@ -229,5 +231,3 @@ def discover_tests_pytest(  # noqa: C901, PLR0912, PLR0915
         functions_to_optimize,
     )
     return _count_results(function_to_tests)
-
-

packages/codeflash-python/src/codeflash_python/test_discovery/linking.py

@@ -62,7 +62,6 @@ def module_name_from_file_path(
     return relative_path.with_suffix("").as_posix().replace("/", ".")
 
 
-
 def add_test_entries(  # noqa: PLR0913
     function_to_test_map: dict[str, set[FunctionCalledInTest]],
     qualified_name: str,

packages/codeflash-python/src/codeflash_python/testing/_pytest_config.py

@@ -85,85 +85,75 @@ def filter_args(addopts_args: list[str]) -> list[str]:
     return filtered_args
 
 
+def _parse_toml_addopts(
+    content: str,
+) -> tuple[list[str], tomlkit.TOMLDocument, bool] | None:
+    """Parse addopts from pyproject.toml, return (args, doc, uses_ini_options)."""
+    data = tomlkit.parse(content)
+    pytest_section = data.get("tool", {}).get("pytest", {})
+    original_addopts = pytest_section.get("ini_options", {}).get(
+        "addopts", ""
+    ) or pytest_section.get("addopts", "")
+    if original_addopts == "":
+        return None
+    uses_ini_options = (
+        "ini_options" in pytest_section
+        and "addopts" in pytest_section.get("ini_options", {})
+    )
+    if isinstance(original_addopts, list):
+        original_addopts = " ".join(original_addopts)
+    addopts_args = original_addopts.replace("=", " ").split()
+    return addopts_args, data, uses_ini_options
+
+
+def _ini_section_name(filename: str) -> str:
+    """Return the config section name that holds pytest addopts."""
+    if filename in {"pytest.ini", ".pytest.ini", "tox.ini"}:
+        return "pytest"
+    return "tool:pytest"
+
+
 def modify_addopts(
     config_file: Path,
 ) -> tuple[str, bool]:
     """Modify addopts in *config_file*, return (original_content, was_modified)."""
     file_type = config_file.suffix.lower()
     filename = config_file.name
-    config = None
     if file_type not in {".toml", ".ini", ".cfg"} or not config_file.exists():
         return "", False
     with config_file.open(encoding="utf-8") as f:
         content = f.read()
     try:
         if filename == "pyproject.toml":
-            data = tomlkit.parse(content)
+            parsed = _parse_toml_addopts(content)
-            pytest_section = data.get("tool", {}).get("pytest", {})
+            if parsed is None:
-            original_addopts = (
-                pytest_section.get("ini_options", {}).get("addopts", "")
-                or pytest_section.get("addopts", "")
-            )
-            if original_addopts == "":
                 return content, False
-            uses_ini_options = "ini_options" in pytest_section and "addopts" in pytest_section.get("ini_options", {})
+            addopts_args, data, uses_ini_options = parsed
-            if isinstance(original_addopts, list):
-                original_addopts = " ".join(original_addopts)
-            original_addopts = original_addopts.replace("=", " ")
-            addopts_args = original_addopts.split()
         else:
             config = configparser.ConfigParser()
             config.read_string(content)
+            section = _ini_section_name(filename)
             cfg_data: dict[str, dict[str, str]] = {
-                section: dict(config[section]) for section in config.sections()
+                s: dict(config[s]) for s in config.sections()
             }
-            if filename in {
+            original = cfg_data.get(section, {}).get("addopts", "")
-                "pytest.ini",
+            addopts_args = original.replace("=", " ").split()
-                ".pytest.ini",
-                "tox.ini",
-            }:
-                original_addopts = cfg_data.get(
-                    "pytest",
-                    {},
-                ).get("addopts", "")
-            else:
-                original_addopts = cfg_data.get(
-                    "tool:pytest",
-                    {},
-                ).get("addopts", "")
-            original_addopts = original_addopts.replace("=", " ")
-            addopts_args = original_addopts.split()
         new_addopts_args = filter_args(addopts_args)
         if new_addopts_args == addopts_args:
             return content, False
+        new_value = " ".join(new_addopts_args)
         if file_type == ".toml":
             if uses_ini_options:
-                data["tool"]["pytest"]["ini_options"]["addopts"] = (  # type: ignore[index]
+                data["tool"]["pytest"]["ini_options"]["addopts"] = new_value  # type: ignore[index]
-                    " ".join(new_addopts_args)
-                )
             else:
-                data["tool"]["pytest"]["addopts"] = (  # type: ignore[index]
+                data["tool"]["pytest"]["addopts"] = new_value  # type: ignore[index]
-                    " ".join(new_addopts_args)
-                )
             with config_file.open("w", encoding="utf-8") as f:
                 f.write(tomlkit.dumps(data))
                 return content, True
-        if filename in {"pytest.ini", ".pytest.ini", "tox.ini"}:
+        section = _ini_section_name(filename)
-            config.set(  # type: ignore[union-attr]
+        config.set(section, "addopts", new_value)
-                "pytest",
-                "addopts",
-                " ".join(new_addopts_args),
-            )
-            with config_file.open("w", encoding="utf-8") as f:
-                config.write(f)  # type: ignore[union-attr]
-                return content, True
-        config.set(  # type: ignore[union-attr]
-            "tool:pytest",
-            "addopts",
-            " ".join(new_addopts_args),
-        )
         with config_file.open("w", encoding="utf-8") as f:
-            config.write(f)  # type: ignore[union-attr]
+            config.write(f)
             return content, True
 
     except Exception:  # noqa: BLE001

packages/codeflash-python/src/codeflash_python/testing/_test_runner.py

@@ -71,8 +71,8 @@ def execute_test_subprocess(
         return subprocess.CompletedProcess(
             args=cmd_list,
             returncode=-1,
-            stdout=exc.stdout or "",
+            stdout=str(exc.stdout) if exc.stdout else "",
-            stderr=exc.stderr or "",
+            stderr=str(exc.stderr) if exc.stderr else "",
         )
 
 
@@ -383,7 +383,7 @@ async def async_execute_test_subprocess(
             timeout,
             " ".join(cmd_list),
         )
-        proc.kill()  # type: ignore[union-attr]
+        proc.kill()
         return subprocess.CompletedProcess(
             args=cmd_list,
             returncode=-1,

packages/codeflash-python/src/codeflash_python/testing/_testgen.py

@@ -204,7 +204,7 @@ def repair_generated_tests(
         data = client.post("/testgen_repair", payload)
     except (AIServiceError, AIServiceConnectionError):
         return None
-    generated = data.get("generated_tests", "")
+    generated: str = data.get("generated_tests", "")
     if not generated:
         return None
     return generated
@@ -272,9 +272,7 @@ def merge_unit_tests(
     )
 
     for node in ast.iter_child_nodes(modified_ast):
-        if isinstance(node, ast.FunctionDef) and node.name.startswith(
+        if isinstance(node, ast.FunctionDef) and node.name.startswith("test_"):
-            "test_"
-        ):
             node.name = node.name + "__inspired"
 
     unit_test_source_ast.body.extend(modified_ast.body)

packages/codeflash-python/src/codeflash_python/testing/_xml_parser.py

@@ -95,7 +95,9 @@ def parse_test_xml(  # noqa: C901, PLR0912, PLR0915
             )
             log.debug(
                 "XML parse: suite_file=%r, classname=%r, testcase=%r, tc_attribs=%s",
-                test_file_name, class_name, testcase.name,
+                test_file_name,
+                class_name,
+                testcase.name,
                 dict(testcase._elem.attrib),  # noqa: SLF001
             )
 
@@ -194,8 +196,14 @@ def parse_test_xml(  # noqa: C901, PLR0912, PLR0915
                     "Known instrumented: %s, known original: %s",
                     test_file_path,
                     class_name,
-                    [str(tf.instrumented_behavior_file_path) for tf in test_files.test_files],
+                    [
-                    [str(tf.original_file_path) for tf in test_files.test_files],
+                        str(tf.instrumented_behavior_file_path)
+                        for tf in test_files.test_files
+                    ],
+                    [
+                        str(tf.original_file_path)
+                        for tf in test_files.test_files
+                    ],
                 )
                 log.warning(
                     "Test type not found for %s, skipping.",

packages/codeflash-python/tests/test_baseline.py

@@ -494,8 +494,12 @@ class TestEstablishOriginalCodeBaseline:
         return test_files, test_config, test_env
 
     @patch("codeflash_python.testing._parse_results.parse_test_results")
-    @patch("codeflash_python.testing._test_runner.async_run_line_profile_tests")
+    @patch(
-    @patch("codeflash_python.testing._test_runner.async_run_benchmarking_tests")
+        "codeflash_python.testing._test_runner.async_run_line_profile_tests"
+    )
+    @patch(
+        "codeflash_python.testing._test_runner.async_run_benchmarking_tests"
+    )
     @patch("codeflash_python.testing._test_runner.async_run_behavioral_tests")
     async def test_successful_baseline(
         self,
@@ -551,8 +555,12 @@ class TestEstablishOriginalCodeBaseline:
         assert result.runtime > 0
 
     @patch("codeflash_python.testing._parse_results.parse_test_results")
-    @patch("codeflash_python.testing._test_runner.async_run_line_profile_tests")
+    @patch(
-    @patch("codeflash_python.testing._test_runner.async_run_benchmarking_tests")
+        "codeflash_python.testing._test_runner.async_run_line_profile_tests"
+    )
+    @patch(
+        "codeflash_python.testing._test_runner.async_run_benchmarking_tests"
+    )
     @patch("codeflash_python.testing._test_runner.async_run_behavioral_tests")
     async def test_empty_behavioral_returns_none(
         self,
@@ -585,8 +593,12 @@ class TestEstablishOriginalCodeBaseline:
         assert result is None
 
     @patch("codeflash_python.testing._parse_results.parse_test_results")
-    @patch("codeflash_python.testing._test_runner.async_run_line_profile_tests")
+    @patch(
-    @patch("codeflash_python.testing._test_runner.async_run_benchmarking_tests")
+        "codeflash_python.testing._test_runner.async_run_line_profile_tests"
+    )
+    @patch(
+        "codeflash_python.testing._test_runner.async_run_benchmarking_tests"
+    )
     @patch("codeflash_python.testing._test_runner.async_run_behavioral_tests")
     async def test_zero_benchmark_runtime_returns_none(
         self,
@@ -641,8 +653,12 @@ class TestEstablishOriginalCodeBaseline:
         assert result is None
 
     @patch("codeflash_python.testing._parse_results.parse_test_results")
-    @patch("codeflash_python.testing._test_runner.async_run_line_profile_tests")
+    @patch(
-    @patch("codeflash_python.testing._test_runner.async_run_benchmarking_tests")
+        "codeflash_python.testing._test_runner.async_run_line_profile_tests"
+    )
+    @patch(
+        "codeflash_python.testing._test_runner.async_run_benchmarking_tests"
+    )
     @patch("codeflash_python.testing._test_runner.async_run_behavioral_tests")
     async def test_precomputed_behavioral_skips_behavioral_run(
         self,
@@ -689,8 +705,12 @@ class TestEstablishOriginalCodeBaseline:
         assert precomputed is result.behavior_test_results
 
     @patch("codeflash_python.testing._parse_results.parse_test_results")
-    @patch("codeflash_python.testing._test_runner.async_run_line_profile_tests")
+    @patch(
-    @patch("codeflash_python.testing._test_runner.async_run_benchmarking_tests")
+        "codeflash_python.testing._test_runner.async_run_line_profile_tests"
+    )
+    @patch(
+        "codeflash_python.testing._test_runner.async_run_benchmarking_tests"
+    )
     @patch("codeflash_python.testing._test_runner.async_run_behavioral_tests")
     async def test_failed_regression_in_functions_to_remove(
         self,

packages/codeflash-python/tests/test_eval_worktree.py

@@ -33,9 +33,7 @@ def _make_project(tmp_path: Path) -> tuple[Path, Path]:
 class TestCreateProjectOverlay:
     """create_project_overlay directory structure."""
 
-    def test_overlay_contains_candidate_code(
+    def test_overlay_contains_candidate_code(self, tmp_path: Path) -> None:
-        self, tmp_path: Path
-    ) -> None:
         """The target module file has the candidate code."""
         root, mod = _make_project(tmp_path)
         overlay = create_project_overlay(mod, root, "def fast(): ...")
@@ -61,9 +59,7 @@ class TestCreateProjectOverlay:
         finally:
             cleanup_overlay(overlay)
 
-    def test_project_root_siblings_are_symlinked(
+    def test_project_root_siblings_are_symlinked(self, tmp_path: Path) -> None:
-        self, tmp_path: Path
-    ) -> None:
         """Files at project root level are symlinked."""
         root, mod = _make_project(tmp_path)
         overlay = create_project_overlay(mod, root, "code")
@@ -95,9 +91,7 @@ class TestCreateProjectOverlay:
         root, mod = _make_project(tmp_path)
         overlay = create_project_overlay(mod, root, "def fast(): ...")
         try:
-            assert not (
+            assert not (overlay / "src" / "mypkg" / "core.py").is_symlink()
-                overlay / "src" / "mypkg" / "core.py"
-            ).is_symlink()
         finally:
             cleanup_overlay(overlay)
 
@@ -145,9 +139,7 @@ class TestCreateProjectOverlay:
         import sys
 
         root, mod = _make_project(tmp_path)
-        overlay = create_project_overlay(
+        overlay = create_project_overlay(mod, root, "VALUE = 42\n")
-            mod, root, "VALUE = 42\n"
-        )
         try:
             result = subprocess.run(
                 [

packages/codeflash-python/tests/test_function_optimizer.py

@@ -156,16 +156,29 @@ class TestNoGenTests:
         fn_input.function.is_async = False
 
         with (
-            patch("codeflash_python.pipeline._test_orchestrator.generate_ai_tests") as mock_gen,
+            patch(
-            patch("codeflash_python.pipeline._test_orchestrator.instrument_tests_for_function", return_value=None),
+                "codeflash_python.pipeline._test_orchestrator.generate_ai_tests"
-            patch("codeflash_python.pipeline._test_orchestrator.generate_concolic_tests", return_value=({}, "", None)),
+            ) as mock_gen,
+            patch(
+                "codeflash_python.pipeline._test_orchestrator.instrument_tests_for_function",
+                return_value=None,
+            ),
+            patch(
+                "codeflash_python.pipeline._test_orchestrator.generate_concolic_tests",
+                return_value=({}, "", None),
+            ),
             patch(
                 "codeflash_python.context.pipeline.get_code_optimization_context",
                 return_value=MagicMock(),
             ),
-            patch("codeflash_python.pipeline._module_prep.resolve_python_function_ast", return_value=None),
+            patch(
+                "codeflash_python.pipeline._module_prep.resolve_python_function_ast",
+                return_value=None,
+            ),
             patch(f"{_mod}.is_numerical_code", return_value=False),
-            patch("codeflash_python.verification._baseline.establish_original_code_baseline"),
+            patch(
+                "codeflash_python.verification._baseline.establish_original_code_baseline"
+            ),
         ):
             ctx = OptimizationContext(
                 plugin=MagicMock(),

packages/codeflash-python/tests/test_ranking_boost.py

@@ -235,7 +235,8 @@ def test_trace_ranking_keeps_addressable_time_primary_over_test_count(
             return addressable_times[function.function_name]
 
     with patch(
-        "codeflash_python.analysis._function_ranking.FunctionRanker", FakeRanker
+        "codeflash_python.analysis._function_ranking.FunctionRanker",
+        FakeRanker,
     ):
         ranked = rank_functions_globally(
             {project_root / "mod.py": funcs},
@@ -288,7 +289,8 @@ def test_trace_ranking_uses_test_count_as_tiebreaker(
             return addressable_times[function.function_name]
 
     with patch(
-        "codeflash_python.analysis._function_ranking.FunctionRanker", FakeRanker
+        "codeflash_python.analysis._function_ranking.FunctionRanker",
+        FakeRanker,
     ):
         ranked = rank_functions_globally(
             {project_root / "mod.py": funcs},

packages/codeflash-python/tests/test_testgen.py

@@ -239,6 +239,7 @@ class TestModifyInspiredTests:
         assert 2 == len(import_list)
         assert all(isinstance(n, ast.ImportFrom) for n in import_list)
 
+
 class TestMergeUnitTests:
     """merge_unit_tests test merging."""
 

packages/codeflash-python/tests/test_verification.py

@@ -17,9 +17,9 @@ from codeflash_python.verification._verification import (
     performance_gain,
 )
 from codeflash_python.verification.models import (
-    OptimizedCandidateResult,
     BehaviorDiff,
     BehaviorDiffScope,
+    OptimizedCandidateResult,
 )
 
 

packages/github-app/tests/test_auth.py

@@ -5,13 +5,13 @@ from __future__ import annotations
 import httpx
 import jwt as pyjwt
 import respx
+from helpers import WEBHOOK_SECRET
 
 from github_app.auth import (
     generate_jwt,
     get_installation_token,
     verify_signature,
 )
-from helpers import WEBHOOK_SECRET
 
 
 def test_generate_jwt_structure(mock_config):

packages/github-app/tests/test_config.py

@@ -7,9 +7,9 @@ from pathlib import Path
 from unittest.mock import patch
 
 import pytest
+from helpers import FAKE_RSA_PEM
 
 from github_app.config import Config, default_plugin_dir, load_private_key
-from helpers import FAKE_RSA_PEM
 
 
 def test_load_private_key_from_env():

reports/unstructured-security/app.py

@@ -9,9 +9,10 @@ findings identified during the performance engagement:
 """
 
 import json
+import re
 from pathlib import Path
 
-from dash import Dash, clientside_callback, html, Input, Output
+from dash import Dash, Input, Output, clientside_callback, html
 from theme import (
     ACCENT,
     AMBER,
@@ -20,15 +21,12 @@ from theme import (
     CARD,
     CARD_BG,
     CARD_BORDER,
-    DARK,
     FONT,
     GRAY,
     GREEN,
     LIGHT_GRAY,
-    LIGHT_GREEN,
     LIGHT_RED,
     MONO,
-    PURPLE,
     RED,
     SLATE,
     WHITE,
@@ -60,10 +58,10 @@ SEVERITY_BG = {
 }
 
 STATUS_COLORS = {
-    "fixed": "#34d399",        # emerald-400 (distinct from severity green)
+    "fixed": "#34d399",  # emerald-400 (distinct from severity green)
     "partially-fixed": "#c084fc",  # purple-400 (avoids orange/amber overlap)
-    "open": "#f87171",         # red-400 (open = still a problem)
+    "open": "#f87171",  # red-400 (open = still a problem)
-    "active": "#22d3ee",       # cyan-400 (distinct from severity blue)
+    "active": "#22d3ee",  # cyan-400 (distinct from severity blue)
 }
 
 _TAB_BTN_STYLE = {
@@ -122,11 +120,11 @@ def card(children, **kw):
 
 
 SEVERITY_ICONS = {
-    "critical": "\u25cf",   # filled circle
+    "critical": "\u25cf",  # filled circle
-    "high": "\u25b2",       # filled triangle
+    "high": "\u25b2",  # filled triangle
-    "medium": "\u25c6",     # filled diamond
+    "medium": "\u25c6",  # filled diamond
-    "low": "\u25cb",        # open circle
+    "low": "\u25cb",  # open circle
-    "info": "\u2139",       # info symbol
+    "info": "\u2139",  # info symbol
 }
 
 
@@ -170,8 +168,6 @@ def status_badge(status):
     )
 
 
-import re
-
 _REPO_URLS = {
     "core-product": "https://github.com/Unstructured-IO/core-product/pull",
     "github-workflows": "https://github.com/Unstructured-IO/github-workflows/pull",
@@ -213,7 +209,9 @@ def _linkify_fixed_by(text, repo):
                 )
             else:
                 result.append(
-                    html.Span(part, style={"color": GREEN, "fontWeight": "600"})
+                    html.Span(
+                        part, style={"color": GREEN, "fontWeight": "600"}
+                    )
                 )
         else:
             result.append(
@@ -387,7 +385,11 @@ def finding_card(f):
                     severity_badge(sev),
                     status_badge(f["status"]),
                 ],
-                style={"display": "flex", "gap": "8px", "alignItems": "center"},
+                style={
+                    "display": "flex",
+                    "gap": "8px",
+                    "alignItems": "center",
+                },
             ),
         ],
         style={
@@ -592,7 +594,10 @@ _SEV_PRIORITY = {"critical": 0, "high": 1, "medium": 2, "low": 3, "info": 4}
 
 
 def _finding_sort_key(f):
-    return (_SEV_PRIORITY.get(f["severity"], 9), _CATEGORY_PRIORITY.get(f["category"], 9))
+    return (
+        _SEV_PRIORITY.get(f["severity"], 9),
+        _CATEGORY_PRIORITY.get(f["category"], 9),
+    )
 
 
 _CRITICAL_HIGH = sorted(
@@ -654,7 +659,10 @@ def _build_summary_tab():
                             " and ",
                             html.Span(
                                 f"{SUMMARY['high']} high",
-                                style={"fontWeight": "700", "color": "#f97316"},
+                                style={
+                                    "fontWeight": "700",
+                                    "color": "#f97316",
+                                },
                             ),
                             " severity issues. The lockfile-bypass pattern you fixed in core-product "
                             "(PR #1465) still persists in CI steps and Makefiles across the org. "
@@ -738,7 +746,7 @@ def _build_summary_tab():
                         },
                     ),
                     html.Div(
-                        f"of findings remain unresolved",
+                        "of findings remain unresolved",
                         style={
                             "fontSize": "20px",
                             "fontWeight": "600",
@@ -781,7 +789,7 @@ def _build_critical_high_tab():
         style={"display": "none"},
         children=[
             section(
-                f"Critical & High Findings",
+                "Critical & High Findings",
                 f"{n} findings \u2014 supply chain, container, CI/CD, and secrets",
             ),
             *[finding_card(f) for f in _CRITICAL_HIGH],
@@ -797,7 +805,7 @@ def _build_medium_low_tab():
         style={"display": "none"},
         children=[
             section(
-                f"Medium & Low Findings",
+                "Medium & Low Findings",
                 f"{n} findings for planned remediation",
             ),
             *[finding_card(f) for f in _MEDIUM_LOW],
@@ -999,7 +1007,9 @@ app.layout = html.Div(
                         "zIndex": "1",
                     },
                     children=[
-                        _hero_metric(str(SUMMARY["critical"]), "Critical", RED),
+                        _hero_metric(
+                            str(SUMMARY["critical"]), "Critical", RED
+                        ),
                         _hero_metric(str(SUMMARY["high"]), "High", "#f97316"),
                         _hero_metric(str(SUMMARY["medium"]), "Medium", AMBER),
                         _hero_metric(str(SUMMARY["low"]), "Low", BLUE),
@@ -1027,10 +1037,30 @@ app.layout = html.Div(
                                 "border": f"1px solid {CARD_BORDER}",
                             },
                             children=[
-                                html.Button("Summary", id="btn-summary", n_clicks=1, style=_TAB_BTN_ACTIVE),
+                                html.Button(
-                                html.Button(f"Critical & High ({len(_CRITICAL_HIGH)})", id="btn-crit-high", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    "Summary",
-                                html.Button(f"Medium & Low ({len(_MEDIUM_LOW)})", id="btn-med-low", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    id="btn-summary",
-                                html.Button("By Category", id="btn-category", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    n_clicks=1,
+                                    style=_TAB_BTN_ACTIVE,
+                                ),
+                                html.Button(
+                                    f"Critical & High ({len(_CRITICAL_HIGH)})",
+                                    id="btn-crit-high",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
+                                html.Button(
+                                    f"Medium & Low ({len(_MEDIUM_LOW)})",
+                                    id="btn-med-low",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
+                                html.Button(
+                                    "By Category",
+                                    id="btn-category",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
                             ],
                         ),
                     ],

reports/unstructured/security_report.py

@@ -9,9 +9,10 @@ findings identified during the performance engagement:
 """
 
 import json
+import re
 from pathlib import Path
 
-from dash import Dash, clientside_callback, html, Input, Output
+from dash import Dash, Input, Output, clientside_callback, html
 from theme import (
     ACCENT,
     AMBER,
@@ -20,15 +21,12 @@ from theme import (
     CARD,
     CARD_BG,
     CARD_BORDER,
-    DARK,
     FONT,
     GRAY,
     GREEN,
     LIGHT_GRAY,
-    LIGHT_GREEN,
     LIGHT_RED,
     MONO,
-    PURPLE,
     RED,
     SLATE,
     WHITE,
@@ -60,10 +58,10 @@ SEVERITY_BG = {
 }
 
 STATUS_COLORS = {
-    "fixed": "#34d399",        # emerald-400 (distinct from severity green)
+    "fixed": "#34d399",  # emerald-400 (distinct from severity green)
     "partially-fixed": "#c084fc",  # purple-400 (avoids orange/amber overlap)
-    "open": "#f87171",         # red-400 (open = still a problem)
+    "open": "#f87171",  # red-400 (open = still a problem)
-    "active": "#22d3ee",       # cyan-400 (distinct from severity blue)
+    "active": "#22d3ee",  # cyan-400 (distinct from severity blue)
 }
 
 _TAB_BTN_STYLE = {
@@ -122,11 +120,11 @@ def card(children, **kw):
 
 
 SEVERITY_ICONS = {
-    "critical": "\u25cf",   # filled circle
+    "critical": "\u25cf",  # filled circle
-    "high": "\u25b2",       # filled triangle
+    "high": "\u25b2",  # filled triangle
-    "medium": "\u25c6",     # filled diamond
+    "medium": "\u25c6",  # filled diamond
-    "low": "\u25cb",        # open circle
+    "low": "\u25cb",  # open circle
-    "info": "\u2139",       # info symbol
+    "info": "\u2139",  # info symbol
 }
 
 
@@ -170,8 +168,6 @@ def status_badge(status):
     )
 
 
-import re
-
 _REPO_URLS = {
     "core-product": "https://github.com/Unstructured-IO/core-product/pull",
     "github-workflows": "https://github.com/Unstructured-IO/github-workflows/pull",
@@ -213,7 +209,9 @@ def _linkify_fixed_by(text, repo):
                 )
             else:
                 result.append(
-                    html.Span(part, style={"color": GREEN, "fontWeight": "600"})
+                    html.Span(
+                        part, style={"color": GREEN, "fontWeight": "600"}
+                    )
                 )
         else:
             result.append(
@@ -387,7 +385,11 @@ def finding_card(f):
                     severity_badge(sev),
                     status_badge(f["status"]),
                 ],
-                style={"display": "flex", "gap": "8px", "alignItems": "center"},
+                style={
+                    "display": "flex",
+                    "gap": "8px",
+                    "alignItems": "center",
+                },
             ),
         ],
         style={
@@ -592,7 +594,10 @@ _SEV_PRIORITY = {"critical": 0, "high": 1, "medium": 2, "low": 3, "info": 4}
 
 
 def _finding_sort_key(f):
-    return (_SEV_PRIORITY.get(f["severity"], 9), _CATEGORY_PRIORITY.get(f["category"], 9))
+    return (
+        _SEV_PRIORITY.get(f["severity"], 9),
+        _CATEGORY_PRIORITY.get(f["category"], 9),
+    )
 
 
 _CRITICAL_HIGH = sorted(
@@ -654,7 +659,10 @@ def _build_summary_tab():
                             " and ",
                             html.Span(
                                 f"{SUMMARY['high']} high",
-                                style={"fontWeight": "700", "color": "#f97316"},
+                                style={
+                                    "fontWeight": "700",
+                                    "color": "#f97316",
+                                },
                             ),
                             " severity issues. The lockfile-bypass pattern you fixed in core-product "
                             "(PR #1465) still persists in CI steps and Makefiles across the org. "
@@ -738,7 +746,7 @@ def _build_summary_tab():
                         },
                     ),
                     html.Div(
-                        f"of findings remain unresolved",
+                        "of findings remain unresolved",
                         style={
                             "fontSize": "20px",
                             "fontWeight": "600",
@@ -781,7 +789,7 @@ def _build_critical_high_tab():
         style={"display": "none"},
         children=[
             section(
-                f"Critical & High Findings",
+                "Critical & High Findings",
                 f"{n} findings \u2014 supply chain, container, CI/CD, and secrets",
             ),
             *[finding_card(f) for f in _CRITICAL_HIGH],
@@ -797,7 +805,7 @@ def _build_medium_low_tab():
         style={"display": "none"},
         children=[
             section(
-                f"Medium & Low Findings",
+                "Medium & Low Findings",
                 f"{n} findings for planned remediation",
             ),
             *[finding_card(f) for f in _MEDIUM_LOW],
@@ -999,7 +1007,9 @@ app.layout = html.Div(
                         "zIndex": "1",
                     },
                     children=[
-                        _hero_metric(str(SUMMARY["critical"]), "Critical", RED),
+                        _hero_metric(
+                            str(SUMMARY["critical"]), "Critical", RED
+                        ),
                         _hero_metric(str(SUMMARY["high"]), "High", "#f97316"),
                         _hero_metric(str(SUMMARY["medium"]), "Medium", AMBER),
                         _hero_metric(str(SUMMARY["low"]), "Low", BLUE),
@@ -1027,10 +1037,30 @@ app.layout = html.Div(
                                 "border": f"1px solid {CARD_BORDER}",
                             },
                             children=[
-                                html.Button("Summary", id="btn-summary", n_clicks=1, style=_TAB_BTN_ACTIVE),
+                                html.Button(
-                                html.Button(f"Critical & High ({len(_CRITICAL_HIGH)})", id="btn-crit-high", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    "Summary",
-                                html.Button(f"Medium & Low ({len(_MEDIUM_LOW)})", id="btn-med-low", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    id="btn-summary",
-                                html.Button("By Category", id="btn-category", n_clicks=0, style=_TAB_BTN_STYLE),
+                                    n_clicks=1,
+                                    style=_TAB_BTN_ACTIVE,
+                                ),
+                                html.Button(
+                                    f"Critical & High ({len(_CRITICAL_HIGH)})",
+                                    id="btn-crit-high",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
+                                html.Button(
+                                    f"Medium & Low ({len(_MEDIUM_LOW)})",
+                                    id="btn-med-low",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
+                                html.Button(
+                                    "By Category",
+                                    id="btn-category",
+                                    n_clicks=0,
+                                    style=_TAB_BTN_STYLE,
+                                ),
                             ],
                         ),
                     ],