python-harness 0.0.10__tar.gz → 0.0.11__tar.gz

{python_harness-0.0.10/python_harness.egg-info → python_harness-0.0.11}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-harness
-Version: 0.0.10
+Version: 0.0.11
 Summary: An agentic codebase evaluation and evolution tool for Python projects.
 Author-email: Mingli Yuan <mingli.yuan@gmail.com>
 License: MIT
@@ -15,13 +15,13 @@ Requires-Dist: anthropic>=0.18.0
 Requires-Dist: tenacity>=8.2.0
 Requires-Dist: tiktoken>=0.6.0
 Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pytest>=8.0.0
+Requires-Dist: pytest-cov>=4.1.0
+Requires-Dist: ruff>=0.3.0
+Requires-Dist: mypy>=1.9.0
+Requires-Dist: radon>=6.0.1
 Provides-Extra: dev
-Requires-Dist: pytest>=8.0.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
-Requires-Dist: ruff>=0.3.0; extra == "dev"
-Requires-Dist: mypy>=1.9.0; extra == "dev"
 Requires-Dist: ty>=0.0.1; extra == "dev"
-Requires-Dist: radon>=6.0.1; extra == "dev"
 Dynamic: license-file
 
 # Python Harness

{python_harness-0.0.10 → python_harness-0.0.11}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "python-harness"
-version = "0.0.10"
+version = "0.0.11"
 description = "An agentic codebase evaluation and evolution tool for Python projects."
 requires-python = ">=3.10"
 readme = "README.md"
@@ -17,18 +17,18 @@ dependencies = [
     "tenacity>=8.2.0",
     "tiktoken>=0.6.0",
     "python-dotenv>=1.0.0",
-]
-
-[project.optional-dependencies]
-dev = [
     "pytest>=8.0.0",
     "pytest-cov>=4.1.0",
     "ruff>=0.3.0",
     "mypy>=1.9.0",
-    "ty>=0.0.1", # Assuming ty is available or will be replaced with actual LSP integration
     "radon>=6.0.1",
 ]
 
+[project.optional-dependencies]
+dev = [
+    "ty>=0.0.1", # Assuming ty is available or will be replaced with actual LSP integration
+]
+
 [build-system]
 requires = ["setuptools>=61.0"]
 build-backend = "setuptools.build_meta"

{python_harness-0.0.10 → python_harness-0.0.11}/python_harness/__init__.py

@@ -2,4 +2,4 @@
 Python Harness - An agentic evaluation tool for codebases.
 """
 
-__version__ = "0.0.10"
+__version__ = "0.0.11"

{python_harness-0.0.10 → python_harness-0.0.11}/python_harness/cli.py

@@ -33,13 +33,18 @@ def _print_detail_block(title: str, details: str, color: str) -> None:
     console.print()
 
 
-def _print_ruff_issues(issues: list[dict[str, Any]]) -> None:
+def _print_ruff_issues(
+    issues: list[dict[str, Any]],
+    error_message: str = "",
+) -> None:
     console.print("[red]Ruff issues found:[/red]")
     for issue in issues:
         file = issue.get("filename", "unknown")
         line = issue.get("location", {}).get("row", "?")
         msg = issue.get("message", "unknown issue")
         console.print(f"  - {file}:{line} {msg}")
+    if not issues and error_message:
+        console.print(f"  {error_message}")
     console.print()
 
 
@@ -99,7 +104,10 @@ def _print_hard_failure_details(hard_results: dict[str, Any]) -> None:
 
     ruff_issues = hard_results.get("ruff", {}).get("issues", [])
     if hard_results.get("ruff", {}).get("status") != "success":
-        _print_ruff_issues(ruff_issues)
+        _print_ruff_issues(
+            ruff_issues,
+            str(hard_results.get("ruff", {}).get("error_message", "")),
+        )
 
     if hard_results.get("mypy", {}).get("status") != "success":
         output = str(hard_results.get("mypy", {}).get("output", ""))

{python_harness-0.0.10 → python_harness-0.0.11}/python_harness/hard_evaluator.py

@@ -47,6 +47,7 @@ class HardEvaluator:
                 "status": status,
                 "issues": issues,
                 "return_code": result.returncode,
+                "error_message": result.stderr.strip(),
             }
         except Exception as e:
             return {"status": "error", "error_message": str(e)}
@@ -65,7 +66,7 @@ class HardEvaluator:
             status = "success" if result.returncode == 0 else "failed"
             return {
                 "status": status,
-                "output": result.stdout,
+                "output": result.stdout or result.stderr,
                 "return_code": result.returncode,
             }
         except Exception as e:
@@ -243,6 +244,7 @@ class HardEvaluator:
                 "output": result.stdout,
                 "return_code": result.returncode,
                 "coverage_percentage": coverage_percentage,
+                "error_message": result.stderr.strip(),
             }
         except subprocess.TimeoutExpired:
             return {

{python_harness-0.0.10 → python_harness-0.0.11/python_harness.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: python-harness
-Version: 0.0.10
+Version: 0.0.11
 Summary: An agentic codebase evaluation and evolution tool for Python projects.
 Author-email: Mingli Yuan <mingli.yuan@gmail.com>
 License: MIT
@@ -15,13 +15,13 @@ Requires-Dist: anthropic>=0.18.0
 Requires-Dist: tenacity>=8.2.0
 Requires-Dist: tiktoken>=0.6.0
 Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: pytest>=8.0.0
+Requires-Dist: pytest-cov>=4.1.0
+Requires-Dist: ruff>=0.3.0
+Requires-Dist: mypy>=1.9.0
+Requires-Dist: radon>=6.0.1
 Provides-Extra: dev
-Requires-Dist: pytest>=8.0.0; extra == "dev"
-Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
-Requires-Dist: ruff>=0.3.0; extra == "dev"
-Requires-Dist: mypy>=1.9.0; extra == "dev"
 Requires-Dist: ty>=0.0.1; extra == "dev"
-Requires-Dist: radon>=6.0.1; extra == "dev"
 Dynamic: license-file
 
 # Python Harness

{python_harness-0.0.10 → python_harness-0.0.11}/tests/test_cli.py

@@ -427,3 +427,77 @@ def test_refine_reports_suggestions(monkeypatch: Any) -> None:
     assert result.exit_code == 0
     assert "Found 2 suggestions. Starting evolution branches..." in result.stdout
     assert "Evolution engine skeleton ready." in result.stdout
+
+
+def test_measure_surfaces_hard_tool_errors(monkeypatch: Any) -> None:
+    """
+    Test that measure prints hard-tool error details when tool invocations fail early.
+    """
+    class DummyHardEvaluator:
+        def evaluate(self) -> dict[str, Any]:
+            return {
+                "all_passed": False,
+                "ruff": {
+                    "status": "failed",
+                    "issues": [],
+                    "error_message": "No module named ruff",
+                },
+                "mypy": {"status": "failed", "output": "No module named mypy"},
+                "ty": {
+                    "status": "warning",
+                    "error_message": "ty executable not found. Skipping ty checks.",
+                },
+                "radon_cc": {
+                    "status": "warning",
+                    "issues": [],
+                    "error_message": "No module named radon",
+                },
+                "radon_mi": {"status": "success", "mi_scores": {}},
+                "pytest": {
+                    "status": "failed",
+                    "error_message": "No module named pytest",
+                },
+            }
+
+    class DummyQcEvaluator:
+        def evaluate(self) -> dict[str, Any]:
+            return {"all_passed": True, "failures": []}
+
+    class DummySoftEvaluator:
+        def evaluate(self) -> dict[str, Any]:
+            return {
+                "package_summary": {
+                    "total_files": 1,
+                    "total_tokens": 1,
+                    "package_understanding": "Mock understanding",
+                },
+                "understandability_score": 100.0,
+                "qa_results": {"sampled_entities": []},
+            }
+
+        def generate_final_report(
+            self,
+            hard_results: dict[str, Any],
+            qc_results: dict[str, Any],
+            soft_results: dict[str, Any],
+        ) -> dict[str, Any]:
+            return {"verdict": "Fail", "summary": "Mock summary", "suggestions": []}
+
+    class DummyEvaluator:
+        def __init__(self, path: str):
+            self.path = path
+            self.hard_evaluator = DummyHardEvaluator()
+            self.qc_evaluator = DummyQcEvaluator()
+            self.soft_evaluator = DummySoftEvaluator()
+
+    monkeypatch.setattr(cli_module, "Evaluator", DummyEvaluator)
+
+    result = runner.invoke(app, ["measure", "."])
+
+    assert result.exit_code == 1
+    assert "Ruff issues found" in result.stdout
+    assert "No module named ruff" in result.stdout
+    assert "Mypy issues found" in result.stdout
+    assert "No module named mypy" in result.stdout
+    assert "Pytest/Coverage issues found" in result.stdout
+    assert "No module named pytest" in result.stdout

{python_harness-0.0.10 → python_harness-0.0.11}/tests/test_hard_evaluator.py

@@ -287,6 +287,49 @@ def test_run_mypy_returns_stdout(monkeypatch: Any) -> None:
     assert "error: nope" in result["output"]
 
 
+def test_run_ruff_surfaces_stderr_when_no_json_issues(monkeypatch: Any) -> None:
+    """
+    Test that run_ruff preserves stderr when Ruff fails before emitting JSON.
+    """
+    def mock_run(args: Any, **kwargs: Any) -> Any:
+        class MockResult:
+            returncode = 1
+            stdout = ""
+            stderr = "No module named ruff"
+
+        return MockResult()
+
+    monkeypatch.setattr("subprocess.run", mock_run)
+
+    evaluator = HardEvaluator(".")
+    result = evaluator.run_ruff()
+
+    assert result["status"] == "failed"
+    assert result["issues"] == []
+    assert result["error_message"] == "No module named ruff"
+
+
+def test_run_mypy_surfaces_stderr(monkeypatch: Any) -> None:
+    """
+    Test that run_mypy preserves stderr when mypy fails before stdout output.
+    """
+    def mock_run(args: Any, **kwargs: Any) -> Any:
+        class MockResult:
+            returncode = 1
+            stdout = ""
+            stderr = "No module named mypy"
+
+        return MockResult()
+
+    monkeypatch.setattr("subprocess.run", mock_run)
+
+    evaluator = HardEvaluator(".")
+    result = evaluator.run_mypy()
+
+    assert result["status"] == "failed"
+    assert result["output"] == "No module named mypy"
+
+
 def test_run_radon_mi_reads_scores(monkeypatch: Any) -> None:
     """
     Test that run_radon_mi parses maintainability scores from JSON.
@@ -308,6 +351,27 @@ def test_run_radon_mi_reads_scores(monkeypatch: Any) -> None:
     assert result["mi_scores"] == {"a.py": 77.0}
 
 
+def test_run_pytest_surfaces_stderr(monkeypatch: Any, tmp_path: Path) -> None:
+    """
+    Test that run_pytest preserves stderr when pytest fails early.
+    """
+    def mock_run(args: Any, **kwargs: Any) -> Any:
+        class MockResult:
+            returncode = 1
+            stdout = ""
+            stderr = "No module named pytest"
+
+        return MockResult()
+
+    monkeypatch.setattr("subprocess.run", mock_run)
+
+    evaluator = HardEvaluator(str(tmp_path))
+    result = evaluator.run_pytest()
+
+    assert result["status"] == "failed"
+    assert result["error_message"] == "No module named pytest"
+
+
 def test_evaluate_fails_when_coverage_report_missing(monkeypatch: Any) -> None:
     """
     Test that missing coverage data fails the hard gate even when tests pass.

{python_harness-0.0.10 → python_harness-0.0.11}/python_harness.egg-info/requires.txt

@@ -6,11 +6,11 @@ anthropic>=0.18.0
 tenacity>=8.2.0
 tiktoken>=0.6.0
 python-dotenv>=1.0.0
-
-[dev]
 pytest>=8.0.0
 pytest-cov>=4.1.0
 ruff>=0.3.0
 mypy>=1.9.0
-ty>=0.0.1
 radon>=6.0.1
+
+[dev]
+ty>=0.0.1