Merge pull request #301 from ggozad/chore/test-cleanup

Test suite cleanup & parallelization

.github/workflows/test.yml

@@ -68,8 +68,6 @@ jobs:
         run: uv run python -c "from transformers import AutoTokenizer; AutoTokenizer.from_pretrained('Qwen/Qwen3-Embedding-0.6B')"
       - name: Run tests with coverage
         run: uv run pytest -m "not integration" --cov=haiku --cov-report=xml
-        env:
-          HF_HUB_OFFLINE: "1"
       - name: Upload coverage to Codecov
         uses: codecov/codecov-action@v5
         with:

CHANGELOG.md

@@ -1,6 +1,11 @@
 # Changelog
 ## [Unreleased]
 
+### Changed
+
+- **Test suite cleanup**: Removed stale VCR cassettes, dead fixtures, orphaned directories, and redundant tests. Strengthened weak assertions across search, context enhancement, and converter tests. Relocated misplaced `SearchResult._get_primary_label` test to `test_search.py`
+- **Parallel test execution**: Added `pytest-xdist` and enabled parallel test runs by default (`-n auto`), reducing test suite time from ~3.5 min to ~2 min
+
 ## [0.33.0] - 2026-03-04
 
 ### Added

pyproject.toml

@@ -80,6 +80,7 @@ dev = [
     "pytest-asyncio>=1.3.0",
     "pytest-cov>=7.0.0",
     "pytest-recording>=0.13.4",
+    "pytest-xdist>=3.0",
     "ruff>=0.14.13",
 ]
 
@@ -120,6 +121,7 @@ python = ".venv"
 [tool.pytest.ini_options]
 asyncio_default_fixture_loop_scope = "session"
 asyncio_mode = "auto"
+addopts = "-n auto"
 testpaths = ["tests"]
 norecursedirs = ["examples", "docs", "evaluations", ".git", ".venv"]
 markers = [

tests/conftest.py

@@ -17,13 +17,14 @@ embeddings:
     vector_dim: 2560
 """)
 os.environ["HAIKU_RAG_CONFIG_PATH"] = str(_test_config_path)
+os.environ["HF_HUB_OFFLINE"] = "1"
 
 import pydantic_ai.models  # noqa: E402
 import pytest  # noqa: E402
 import yaml  # noqa: E402
-from datasets import Dataset, load_dataset, load_from_disk  # noqa: E402
 
 if TYPE_CHECKING:
+    from datasets import Dataset
     from vcr import VCR
 
 setattr(pydantic_ai.models, "ALLOW_MODEL_REQUESTS", False)
@@ -31,7 +32,9 @@ logging.getLogger("vcr.cassette").setLevel(logging.WARNING)
 
 
 @pytest.fixture(scope="session")
-def qa_corpus() -> Dataset:
+def qa_corpus() -> "Dataset":
+    from datasets import Dataset, load_dataset, load_from_disk
+
     ds_path = Path(__file__).parent / "data" / "dataset"
     ds_path.mkdir(parents=True, exist_ok=True)
     try:

tests/test_client_research.py

@@ -1,17 +1,9 @@
-from pathlib import Path
 from unittest.mock import AsyncMock, patch
 
-import pytest
-
 from haiku.rag.agents.research.models import ResearchReport
 from haiku.rag.client import HaikuRAG
 
 
-@pytest.fixture(scope="module")
-def vcr_cassette_dir():
-    return str(Path(__file__).parent / "cassettes" / "test_client_research")
-
-
 async def test_client_research_report(temp_db_path):
     """Test client.research() delegates to research graph in report mode."""
     mock_report = ResearchReport(

tests/test_context_enhancement.py

@@ -335,60 +335,6 @@ async def test_max_items_limit_caps_expansion(temp_db_path):
         assert item_count <= 2, f"Expected at most 2 items, got {item_count}"
 
 
-@pytest.mark.vcr()
-async def test_search_result_get_primary_label():
-    """Test _get_primary_label prioritizes structural labels correctly."""
-    # Table should be prioritized
-    result = SearchResult(
-        content="test",
-        score=0.5,
-        chunk_id="c1",
-        document_id="d1",
-        labels=["paragraph", "table", "text"],
-    )
-    assert result._get_primary_label() == "table"
-
-    # Code should be prioritized over paragraph
-    result = SearchResult(
-        content="test",
-        score=0.5,
-        chunk_id="c2",
-        document_id="d2",
-        labels=["paragraph", "code"],
-    )
-    assert result._get_primary_label() == "code"
-
-    # list_item should be prioritized
-    result = SearchResult(
-        content="test",
-        score=0.5,
-        chunk_id="c3",
-        document_id="d3",
-        labels=["text", "list_item"],
-    )
-    assert result._get_primary_label() == "list_item"
-
-    # Returns first label when no priority match
-    result = SearchResult(
-        content="test",
-        score=0.5,
-        chunk_id="c4",
-        document_id="d4",
-        labels=["paragraph", "text"],
-    )
-    assert result._get_primary_label() == "paragraph"
-
-    # Returns None for empty labels
-    result = SearchResult(
-        content="test",
-        score=0.5,
-        chunk_id="c5",
-        document_id="d5",
-        labels=[],
-    )
-    assert result._get_primary_label() is None
-
-
 @pytest.mark.vcr()
 async def test_expand_context_radius_zero(temp_db_path):
     """Test expand_context with radius 0 returns original results."""
@@ -696,6 +642,10 @@ First paragraph of results.
                 assert len(r.content) > 0
                 # Score should be preserved (best score)
                 assert r.score in [0.9, 0.8]
+                # Expanded content should have docling refs
+                assert r.doc_item_refs is not None and len(r.doc_item_refs) > 0
+                # Document has headings, expanded result should too
+                assert r.headings is not None and len(r.headings) > 0
 
 
 def create_picture_document() -> DoclingDocument:

tests/test_converters.py

@@ -1067,6 +1067,8 @@ class TestDoclingServeConverterIntegration:
 
         doc = await converter.convert_file(pdf_path)
         assert isinstance(doc, DoclingDocument)
+        assert len(doc.pages) > 0
+        assert len(doc.export_to_markdown().strip()) > 100
 
     @pytest.mark.xfail(
         reason="docling-serve does not return picture image data in JSON response "

tests/test_download_models.py

@@ -1,5 +1,4 @@
 from contextlib import asynccontextmanager
-from pathlib import Path
 from unittest.mock import AsyncMock, patch
 
 import httpx
@@ -8,11 +7,6 @@ import pytest
 from haiku.rag.client import HaikuRAG
 
 
-@pytest.fixture(scope="module")
-def vcr_cassette_dir():
-    return str(Path(__file__).parent / "cassettes" / "test_download_models")
-
-
 @pytest.fixture
 def mock_to_thread():
     """Patch asyncio.to_thread to skip docling/tokenizer downloads."""

tests/test_embedder.py

@@ -154,8 +154,7 @@ async def test_embed_chunks_returns_new_objects(allow_model_requests):
     assert embedded[0] is not original
 
 
-@pytest.mark.vcr()
+async def test_embed_chunks_empty_list():
-async def test_embed_chunks_empty_list(allow_model_requests):
     """Test that embed_chunks handles empty list."""
     result = await embed_chunks([])
     assert result == []

tests/test_search.py

@@ -60,11 +60,11 @@ async def test_search_qa_corpus(qa_corpus: Dataset, temp_db_path):
 
 
 @pytest.mark.vcr()
-async def test_chunks_include_document_info(temp_db_path):
+async def test_search_chunk_includes_document_provenance(temp_db_path):
-    """Test that search results include document URI and metadata."""
+    """Test that raw chunk search results include document URI, metadata, and ID."""
     client = HaikuRAG(db_path=temp_db_path, config=Config, create=True)
 
-    # Create a document with URI and metadata
+    # Create a document with URI and metadata but no title
     created_document = await client.create_document(
         content="This is a test document with some content for searching.",
         uri="https://example.com/test.html",
@@ -87,32 +87,7 @@ async def test_chunks_include_document_info(temp_db_path):
     assert chunk.document_uri == "https://example.com/test.html"
     assert chunk.document_meta == {"title": "Test Document", "author": "Test Author"}
     assert chunk.document_id == created_document.id
-
+    assert chunk.document_title is None
-    client.close()
-
-
-@pytest.mark.vcr()
-async def test_chunks_include_document_title(temp_db_path):
-    """Test that search results include the parent document title when present."""
-    client = HaikuRAG(db_path=temp_db_path, config=Config, create=True)
-
-    # Create a document with URI and title
-    await client.create_document(
-        content="This is a test document with a custom title to verify enrichment.",
-        uri="file:///tmp/title-test.md",
-        title="My Custom Title",
-    )
-
-    # Perform a search that should find this document
-    results = await client.chunk_repository.search(
-        "custom title", limit=3, search_type="hybrid"
-    )
-
-    assert results, "Expected at least one search result"
-    for chunk, _ in results:
-        # All returned chunks for this doc should carry the document title
-        if chunk.document_uri == "file:///tmp/title-test.md":
-            assert chunk.document_title == "My Custom Title"
 
     client.close()
 
@@ -207,9 +182,12 @@ async def test_search_returns_search_result(temp_db_path):
     assert result.score > 0
     assert result.document_uri == "https://example.com/ml.html"
     assert result.document_title == "ML Guide"
+    assert result.chunk_id is not None
+    assert result.document_id is not None
     # page_numbers and headings come from chunk metadata
     assert isinstance(result.page_numbers, list)
     assert isinstance(result.labels, list)
+    assert len(result.labels) > 0
 
     client.close()
 
@@ -272,3 +250,56 @@ async def test_search_result_format_includes_metadata(temp_db_path):
         # Should include content
         assert "Content:" in formatted
         assert "machine learning" in formatted.lower()
+
+
+def test_search_result_primary_label_prioritizes_structural_types():
+    """Test _get_primary_label prioritizes structural labels correctly."""
+    # Table should be prioritized
+    result = SearchResult(
+        content="test",
+        score=0.5,
+        chunk_id="c1",
+        document_id="d1",
+        labels=["paragraph", "table", "text"],
+    )
+    assert result._get_primary_label() == "table"
+
+    # Code should be prioritized over paragraph
+    result = SearchResult(
+        content="test",
+        score=0.5,
+        chunk_id="c2",
+        document_id="d2",
+        labels=["paragraph", "code"],
+    )
+    assert result._get_primary_label() == "code"
+
+    # list_item should be prioritized
+    result = SearchResult(
+        content="test",
+        score=0.5,
+        chunk_id="c3",
+        document_id="d3",
+        labels=["text", "list_item"],
+    )
+    assert result._get_primary_label() == "list_item"
+
+    # Returns first label when no priority match
+    result = SearchResult(
+        content="test",
+        score=0.5,
+        chunk_id="c4",
+        document_id="d4",
+        labels=["paragraph", "text"],
+    )
+    assert result._get_primary_label() == "paragraph"
+
+    # Returns None for empty labels
+    result = SearchResult(
+        content="test",
+        score=0.5,
+        chunk_id="c5",
+        document_id="d5",
+        labels=[],
+    )
+    assert result._get_primary_label() is None

uv.lock

@@ -984,6 +984,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/8a/0e/97c33bf5009bdbac74fd2beace167cab3f978feb69cc36f1ef79360d6c4e/exceptiongroup-1.3.1-py3-none-any.whl", hash = "sha256:a7a39a3bd276781e98394987d3a5701d0c4edffb633bb7a5144577f82c773598", size = 16740, upload-time = "2025-11-21T23:01:53.443Z" },
 ]
 
+[[package]]
+name = "execnet"
+version = "2.1.2"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/bf/89/780e11f9588d9e7128a3f87788354c7946a9cbb1401ad38a48c4db9a4f07/execnet-2.1.2.tar.gz", hash = "sha256:63d83bfdd9a23e35b9c6a3261412324f964c2ec8dcd8d3c6916ee9373e0befcd", size = 166622, upload-time = "2025-11-12T09:56:37.75Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ab/84/02fc1827e8cdded4aa65baef11296a9bbe595c474f0d6d758af082d849fd/execnet-2.1.2-py3-none-any.whl", hash = "sha256:67fba928dd5a544b783f6056f449e5e3931a5c378b128bc18501f7ea79e296ec", size = 40708, upload-time = "2025-11-12T09:56:36.333Z" },
+]
+
 [[package]]
 name = "executing"
 version = "2.2.1"
@@ -1365,6 +1374,7 @@ dev = [
     { name = "pytest-asyncio" },
     { name = "pytest-cov" },
     { name = "pytest-recording" },
+    { name = "pytest-xdist" },
     { name = "ruff" },
     { name = "ty" },
 ]
@@ -1391,6 +1401,7 @@ dev = [
     { name = "pytest-asyncio", specifier = ">=1.3.0" },
     { name = "pytest-cov", specifier = ">=7.0.0" },
     { name = "pytest-recording", specifier = ">=0.13.4" },
+    { name = "pytest-xdist", specifier = ">=3.0" },
     { name = "ruff", specifier = ">=0.14.13" },
     { name = "ty", specifier = ">=0.0.16" },
 ]
@@ -4063,6 +4074,19 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/42/c2/ce34735972cc42d912173e79f200fe66530225190c06655c5632a9d88f1e/pytest_recording-0.13.4-py3-none-any.whl", hash = "sha256:ad49a434b51b1c4f78e85b1e6b74fdcc2a0a581ca16e52c798c6ace971f7f439", size = 13723, upload-time = "2025-05-08T10:41:09.684Z" },
 ]
 
+[[package]]
+name = "pytest-xdist"
+version = "3.8.0"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "execnet" },
+    { name = "pytest" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/78/b4/439b179d1ff526791eb921115fca8e44e596a13efeda518b9d845a619450/pytest_xdist-3.8.0.tar.gz", hash = "sha256:7e578125ec9bc6050861aa93f2d59f1d8d085595d6551c2c90b6f4fad8d3a9f1", size = 88069, upload-time = "2025-07-01T13:30:59.346Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ca/31/d4e37e9e550c2b92a9cbc2e4d0b7420a27224968580b5a447f420847c975/pytest_xdist-3.8.0-py3-none-any.whl", hash = "sha256:202ca578cfeb7370784a8c33d6d05bc6e13b4f25b5053c30a152269fd10f0b88", size = 46396, upload-time = "2025-07-01T13:30:56.632Z" },
+]
+
 [[package]]
 name = "python-dateutil"
 version = "2.9.0.post0"