Reorganize tests to match src directory structure and add comprehensive test coverage with CI improvements

.github/workflows/ci.yml

@@ -17,11 +17,33 @@ jobs:
         run: |
           python -m pip install --upgrade pip
           pip install -e .[dev]
-          pip install pytest ruff mypy
       - name: Run linter
         run: ruff check .
       - name: Run type checks
         run: |
           PYTHONPATH=src mypy --ignore-missing-imports src tests
       - name: Run tests
         run: pytest -q
+
+  # Build with coverage for PRs only
+  build-with-coverage:
+    runs-on: ubuntu-latest
+    if: github.event_name == 'pull_request'
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install -e .[dev]
+      - name: Run tests with coverage
+        run: |
+          PYTHONPATH=src python -m pytest --cov=src --cov-report=term-missing --cov-report=html --cov-fail-under=39
+      - name: Upload coverage reports
+        if: always()
+        uses: actions/upload-artifact@v4
+        with:
+          name: coverage-report
+          path: coverage_html_report/

pyproject.toml

@@ -14,13 +14,16 @@ dependencies = [
     "anthropic>=0.7.0",
     "openai>=1.0.0",
     "google-generativeai>=0.3.0",
-    "types-requests>=2.32",
 ]
 
 [project.optional-dependencies]
 dev = [
+    "pytest>=7.0",
     "pytest-cov>=5.0",
-    "pre-commit>=3.0",
+    "ruff>=0.3.0",
+    "mypy>=1.0",
+    "types-requests>=2.32",
+    "pre-commit>=3.0"
 ]
 
 [project.scripts]
@@ -33,3 +36,38 @@ packages = ["src"]
 [tool.ruff]
 line-length = 120
 target-version = "py311"
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+pythonpath = ["src"]
+addopts = "--strict-markers --strict-config"
+
+[tool.coverage.run]
+source = ["src"]
+branch = true
+omit = [
+    "*/tests/*",
+    "*/test_*",
+    "*/__pycache__/*",
+    "*/conftest.py",
+    "*/cli/*",                  # Exclude CLI tools
+    "*/bench/*",               # Exclude benchmark tools
+    "*/validators/*",          # Exclude validators (placeholder code)
+]
+
+[tool.coverage.report]
+fail_under = 39
+show_missing = true
+skip_covered = false
+precision = 2
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "@abstract",
+]
+
+[tool.coverage.html]
+directory = "coverage_html_report"

tests/agentNodes/test_hld_designer.py

@@ -1,13 +1,13 @@
-from agentNodes.hld_designer import HLDDesigner
+from src.agentNodes.hld_designer import HLDDesigner
 from pydantic import TypeAdapter
 
-from dataModel.task import Task, TaskType
-from dataModel.model_response import (
+from src.dataModel.task import Task, TaskType
+from src.dataModel.model_response import (
     DecomposedResponse,
     ImplementedResponse,
-    DesignerResponse,
+    ModelResponse,
 )
-from modelAccessors.base_accessor import BaseModelAccessor
+from src.modelAccessors.base_accessor import BaseModelAccessor
 
 
 class _StubAccessor(BaseModelAccessor):
@@ -18,12 +18,12 @@ def call_model(
         self,
         prompt: str,
         *,
-        adapter: TypeAdapter[DesignerResponse],
+        adapter: TypeAdapter[ModelResponse],
         schema: dict,
         model: str = "gpt-4",
         system_prompt: str = "",
         tools=None,
-    ) -> DesignerResponse:
+    ) -> ModelResponse:
         return self._result
 
 

tests/agentNodes/test_implementer.py

@@ -1,9 +1,9 @@
 from pydantic import TypeAdapter
 
-from agentNodes.implementer import Implementer
-from modelAccessors.base_accessor import BaseModelAccessor
-from dataModel.model_response import ImplementedResponse
-from dataModel.task import Task, TaskType
+from src.agentNodes.implementer import Implementer
+from src.modelAccessors.base_accessor import BaseModelAccessor
+from src.dataModel.model_response import ImplementedResponse, ModelResponse
+from src.dataModel.task import Task, TaskType
 
 
 class _StubAccessor(BaseModelAccessor):
@@ -14,12 +14,12 @@ def call_model(
         self,
         prompt: str,
         *,
-        adapter: TypeAdapter[ImplementedResponse],
+        adapter: TypeAdapter[ModelResponse],
         schema: dict,
         model: str = "gpt-4",
         system_prompt: str = "",
         tools=None,
-    ) -> ImplementedResponse:
+    ) -> ModelResponse:
         return self._result
 
 

tests/agentNodes/test_lld_designer.py

@@ -1,10 +1,10 @@
 import pytest
 from pydantic import TypeAdapter, ValidationError
 
-from agentNodes.lld_designer import LLDDesigner
-from dataModel.model_response import ImplementedResponse
-from dataModel.task import Task, TaskType
-from modelAccessors.base_accessor import BaseModelAccessor
+from src.agentNodes.lld_designer import LLDDesigner
+from src.dataModel.model_response import ImplementedResponse, ModelResponse
+from src.dataModel.task import Task, TaskType
+from src.modelAccessors.base_accessor import BaseModelAccessor
 
 
 class _StubAccessor(BaseModelAccessor):
@@ -15,12 +15,12 @@ def call_model(
         self,
         prompt: str,
         *,
-        adapter: TypeAdapter[ImplementedResponse],
+        adapter: TypeAdapter[ModelResponse],
         schema: dict,
         model: str = "gpt-4",
         system_prompt: str = "",
         tools=None,
-    ) -> ImplementedResponse:
+    ) -> ModelResponse:
         return self._result
 
 

tests/agentNodes/test_researcher.py

@@ -1,11 +1,11 @@
 import pytest
 from pydantic import TypeAdapter, ValidationError
 
-from agentNodes.researcher import Researcher
-from tools.web_search import WEB_SEARCH_TOOL
-from dataModel.model_response import ImplementedResponse
-from dataModel.task import Task, TaskType
-from modelAccessors.base_accessor import BaseModelAccessor
+from src.agentNodes.researcher import Researcher
+from src.tools.web_search import WEB_SEARCH_TOOL
+from src.dataModel.model_response import ImplementedResponse, ModelResponse
+from src.dataModel.task import Task, TaskType
+from src.modelAccessors.base_accessor import BaseModelAccessor
 
 
 class _StubAccessor(BaseModelAccessor):
@@ -16,12 +16,12 @@ def call_model(
         self,
         prompt: str,
         *,
-        adapter: TypeAdapter[ImplementedResponse],
+        adapter: TypeAdapter[ModelResponse],
         schema: dict,
         model: str = "gpt-4",
         system_prompt: str = "",
         tools=None,
-    ) -> ImplementedResponse:
+    ) -> ModelResponse:
         return self._result
 
 

tests/dataModel/test_validation_result.py

@@ -0,0 +1,51 @@
+import pytest
+
+from src.dataModel.validation_result import ValidationResult
+
+
+def test_validation_result_valid_with_no_errors():
+    """Test creating a valid ValidationResult with no errors."""
+    result = ValidationResult(is_valid=True, errors=None)
+    assert result.is_valid is True
+    assert result.errors is None
+
+
+def test_validation_result_valid_with_empty_errors():
+    """Test creating a valid ValidationResult with empty errors list."""
+    result = ValidationResult(is_valid=True, errors=[])
+    assert result.is_valid is True
+    assert result.errors == []
+
+
+def test_validation_result_invalid_with_errors():
+    """Test creating an invalid ValidationResult with errors."""
+    errors = ["Error 1", "Error 2"]
+    result = ValidationResult(is_valid=False, errors=errors)
+    assert result.is_valid is False
+    assert result.errors == errors
+
+
+def test_validation_result_invalid_with_single_error():
+    """Test creating an invalid ValidationResult with a single error."""
+    error = ["Single error"]
+    result = ValidationResult(is_valid=False, errors=error)
+    assert result.is_valid is False
+    assert result.errors == error
+
+
+def test_validation_result_invalid_valid_true_with_errors_raises_error():
+    """Test that ValidationResult raises error when is_valid=True but errors are present."""
+    with pytest.raises(ValueError, match="Cannot have both is_valid=True and an error_message"):
+        ValidationResult(is_valid=True, errors=["Some error"])
+
+
+def test_validation_result_invalid_valid_false_with_no_errors_raises_error():
+    """Test that ValidationResult raises error when is_valid=False but no errors provided."""
+    with pytest.raises(ValueError, match="Must provide an error_message when is_valid=False"):
+        ValidationResult(is_valid=False, errors=None)
+
+
+def test_validation_result_invalid_valid_false_with_empty_errors_raises_error():
+    """Test that ValidationResult raises error when is_valid=False but empty errors provided."""
+    with pytest.raises(ValueError, match="Must provide an error_message when is_valid=False"):
+        ValidationResult(is_valid=False, errors=[])