julee 0.1.3__py3-none-any.whl → 0.1.5__py3-none-any.whl

julee/repositories/memory/document.py

@@ -60,46 +60,52 @@ class MemoryDocumentRepository(DocumentRepository, MemoryRepositoryMixin[Documen
     async def save(self, document: Document) -> None:
         """Save a document with its content and metadata.
 
-        If the document has content_string, it will be converted to a
-        ContentStream and the content hash will be calculated automatically.
+        If the document has content_bytes, it will be normalized to bytes
+        (encoding str as UTF-8), converted to a ContentStream and the
+        content hash will be calculated automatically.
 
         Args:
             document: Document object to save
 
         Raises:
-            ValueError: If document has no content or content_string
+            ValueError: If document has no content or content_bytes
+            TypeError: If content_bytes is not bytes or str
         """
         # Handle content_string conversion (only if no content provided)
-        if document.content_string is not None:
-            # Convert content_string to ContentStream
-            assert document.content_string is not None  # For MyPy
-            content_bytes = document.content_string.encode("utf-8")
-            content_stream = ContentStream(io.BytesIO(content_bytes))
+        if document.content_bytes is not None:
+            if isinstance(document.content_bytes, str):
+                raw_bytes = document.content_bytes.encode("utf-8")
+            elif isinstance(document.content_bytes, bytes):
+                raw_bytes = document.content_bytes
+            else:
+                raise TypeError("content_bytes must be of type 'bytes' or 'str'.")
+
+            content_stream = ContentStream(io.BytesIO(raw_bytes))
 
             # Calculate content hash
-            content_hash = hashlib.sha256(content_bytes).hexdigest()
+            content_hash = hashlib.sha256(raw_bytes).hexdigest()
 
             # Create new document with ContentStream and calculated hash
             document = document.model_copy(
                 update={
                     "content": content_stream,
                     "content_multihash": content_hash,
-                    "size_bytes": len(content_bytes),
+                    "size_bytes": len(raw_bytes),
                 }
             )
 
             self.logger.debug(
-                "Converted content_string to ContentStream for document save",
+                "Converted content_bytes to ContentStream for document save",
                 extra={
                     "document_id": document.document_id,
                     "content_hash": content_hash,
-                    "content_length": len(content_bytes),
+                    "content_length": len(raw_bytes),
                 },
             )
 
         # Create a copy without content_string (content saved
         # in separate content-addressable storage)
-        document_for_storage = document.model_copy(update={"content_string": None})
+        document_for_storage = document.model_copy(update={"content_bytes": None})
         self.save_entity(document_for_storage, "document_id")
 
     async def generate_id(self) -> str:

julee/repositories/memory/tests/test_document.py

@@ -3,7 +3,7 @@ Unit tests for MemoryDocumentRepository.
 
 These tests verify the memory implementation logic without requiring external
 dependencies. They follow the Clean Architecture testing patterns and verify
-idempotency, error handling, and content operations including content_string.
+idempotency, error handling, and content operations including content_bytes.
 """
 
 import io
@@ -18,6 +18,8 @@ from julee.repositories.memory.document import (
     MemoryDocumentRepository,
 )
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def repository() -> MemoryDocumentRepository:
@@ -46,16 +48,16 @@ def sample_document(sample_content: ContentStream) -> Document:
     )
 
 
-class TestMemoryDocumentRepositoryContentString:
-    """Test content_string functionality."""
+class TestMemoryDocumentRepositoryContentBytes:
+    """Test content_bytes functionality."""
 
-    async def test_save_document_with_content_string(
+    async def test_save_document_with_content_bytes(
         self, repository: MemoryDocumentRepository
     ) -> None:
-        """Test saving document with content_string (small content)."""
+        """Test saving document with content_bytes."""
         content = '{"assembled": "document", "data": "test"}'
 
-        # Create document with content_string
+        # Create document with content_bytes
         document = Document(
             document_id="test-doc-content-string",
             original_filename="assembled.json",
@@ -63,10 +65,10 @@ class TestMemoryDocumentRepositoryContentString:
             size_bytes=100,  # Will be updated automatically
             content_multihash="placeholder",  # Will be updated automatically
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
-        # Act - save should convert content_string to ContentStream
+        # Act - save should convert content_bytes to ContentStream
         await repository.save(document)
 
         # Assert document was saved successfully
@@ -80,10 +82,10 @@ class TestMemoryDocumentRepositoryContentString:
         retrieved_content = retrieved.content.read().decode("utf-8")
         assert retrieved_content == content
 
-    async def test_save_document_with_content_string_unicode(
+    async def test_save_document_with_content_bytes_unicode(
         self, repository: MemoryDocumentRepository
     ) -> None:
-        """Test saving document with unicode content_string."""
+        """Test saving document with unicode content_bytes."""
         content = '{"title": "测试文档", "emoji": "🚀", "content": "éñ"}'
 
         document = Document(
@@ -93,7 +95,7 @@ class TestMemoryDocumentRepositoryContentString:
             size_bytes=100,
             content_multihash="placeholder",
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
         await repository.save(document)
@@ -107,10 +109,10 @@ class TestMemoryDocumentRepositoryContentString:
     # Note: Empty content test removed because domain model requires
     # size_bytes > 0
 
-    async def test_save_excludes_content_string_from_storage(
+    async def test_save_excludes_content_bytes_from_storage(
         self, repository: MemoryDocumentRepository
     ) -> None:
-        """Test that content_string is not stored in memory storage."""
+        """Test that content_bytes is not stored in memory storage."""
         content = '{"test": "data that should not be in storage"}'
 
         document = Document(
@@ -120,7 +122,7 @@ class TestMemoryDocumentRepositoryContentString:
             size_bytes=100,
             content_multihash="placeholder",
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
         await repository.save(document)
@@ -129,8 +131,8 @@ class TestMemoryDocumentRepositoryContentString:
         stored_document = repository.storage_dict.get("test-storage-exclusion")
         assert stored_document is not None
 
-        # Verify content_string is not in stored document
-        assert stored_document.content_string is None
+        # Verify content_bytes is not in stored document
+        assert stored_document.content_bytes is None
 
         # Verify essential fields are still present
         assert stored_document.document_id == "test-storage-exclusion"
@@ -195,7 +197,7 @@ class TestMemoryDocumentRepositoryErrorHandling:
                 size_bytes=100,
                 content_multihash="test_hash",
                 status=DocumentStatus.CAPTURED,
-                content_string="test content",
+                content_bytes="test content",
             )
 
     async def test_save_handles_empty_filename(
@@ -210,5 +212,5 @@ class TestMemoryDocumentRepositoryErrorHandling:
                 size_bytes=100,
                 content_multihash="test_hash",
                 status=DocumentStatus.CAPTURED,
-                content_string="test content",
+                content_bytes="test content",
             )

julee/repositories/memory/tests/test_document_policy_validation.py

@@ -19,6 +19,8 @@ from julee.repositories.memory.document_policy_validation import (
     MemoryDocumentPolicyValidationRepository,
 )
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def validation_repo() -> MemoryDocumentPolicyValidationRepository:

julee/repositories/memory/tests/test_policy.py

@@ -13,6 +13,8 @@ import pytest
 from julee.domain.models.policy import Policy, PolicyStatus
 from julee.repositories.memory.policy import MemoryPolicyRepository
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def policy_repo() -> MemoryPolicyRepository:

julee/repositories/minio/document.py

@@ -175,27 +175,7 @@ class MinioDocumentRepository(DocumentRepository, MinioRepositoryMixin):
 
         try:
             # Handle content_string conversion (only if no content provided)
-            if document.content_string is not None:
-                # Convert content_string to ContentStream
-                assert document.content_string is not None  # For MyPy
-                content_bytes = document.content_string.encode("utf-8")
-                content_stream = ContentStream(io.BytesIO(content_bytes))
-
-                # Create new document with ContentStream
-                document = document.model_copy(
-                    update={
-                        "content": content_stream,
-                        "size_bytes": len(content_bytes),
-                    }
-                )
-
-                self.logger.debug(
-                    "Converted content_string to ContentStream",
-                    extra={
-                        "document_id": document.document_id,
-                        "content_length": len(content_bytes),
-                    },
-                )
+            document = self._normalize_document_content(document)
 
             # Store content first and get calculated multihash
             calculated_multihash = await self._store_content(document)
@@ -449,6 +429,29 @@ class MinioDocumentRepository(DocumentRepository, MinioRepositoryMixin):
             )
             raise
 
+    def _normalize_document_content(self, document: Document) -> Document:
+        """Ensure document has a ContentStream in content"""
+        if document.content is not None:
+            return document
+
+        content_bytes = document.content_bytes
+        if content_bytes is not None:
+            if isinstance(content_bytes, str):
+                content_bytes = content_bytes.encode("utf-8")
+
+            stream = ContentStream(io.BytesIO(content_bytes))
+            size_bytes = len(content_bytes)
+            return document.model_copy(
+                update={
+                    "content": stream,
+                    "size_bytes": size_bytes,
+                }
+            )
+
+        raise ValueError(
+            f"Document {document.document_id} has no content, content_bytes"
+        )
+
     def _calculate_multihash_from_stream(self, content_stream: ContentStream) -> str:
         """Calculate multihash from content stream."""
         if not content_stream:
@@ -471,7 +474,7 @@ class MinioDocumentRepository(DocumentRepository, MinioRepositoryMixin):
 
         # Serialize metadata (content stream and content_string excluded)
         metadata_json = document.model_dump_json(
-            exclude={"content", "content_string"}
+            exclude={"content", "content_string", "content_bytes"}
         ).encode("utf-8")
 
         try:

julee/repositories/minio/tests/test_assembly.py

@@ -15,6 +15,8 @@ from julee.repositories.minio.assembly import MinioAssemblyRepository
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/repositories/minio/tests/test_assembly_specification.py

@@ -20,6 +20,8 @@ from julee.repositories.minio.assembly_specification import (
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/repositories/minio/tests/test_client_protocol.py

@@ -6,10 +6,13 @@ MinioClient protocol, ensuring that our protocol definition matches the
 actual interface.
 """
 
+import pytest
 from minio import Minio
 
 from ..client import MinioClient
 
+pytestmark = pytest.mark.unit
+
 
 class TestMinioClientProtocol:
     """Test that the real Minio client implements our protocol."""

julee/repositories/minio/tests/test_document.py

@@ -23,6 +23,8 @@ from julee.repositories.minio.document import MinioDocumentRepository
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_minio_client() -> FakeMinioClient:
@@ -429,16 +431,16 @@ class TestMinioDocumentRepositoryMultihash:
         assert len(multihash_result) > 0
 
 
-class TestMinioDocumentRepositoryContentString:
-    """Test content_string functionality."""
+class TestMinioDocumentRepositoryContentBytes:
+    """Test content_bytes functionality."""
 
-    async def test_save_document_with_content_string(
+    async def test_save_document_with_content_bytes(
         self, repository: MinioDocumentRepository
     ) -> None:
-        """Test saving document with content_string (small content)."""
+        """Test saving document with content_bytes (small content)."""
         content = '{"assembled": "document", "data": "test"}'
 
-        # Create document with content_string
+        # Create document with content_bytes
         document = Document(
             document_id="test-doc-content-string",
             original_filename="assembled.json",
@@ -446,27 +448,27 @@ class TestMinioDocumentRepositoryContentString:
             size_bytes=100,  # Will be updated automatically
             content_multihash="placeholder",  # Will be updated automatically
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
-        # Act - save should convert content_string to ContentStream
+        # Act - save should convert content_bytes to ContentStream
         await repository.save(document)
 
         # Assert document was saved successfully
         retrieved = await repository.get(document.document_id)
         assert retrieved is not None
         assert retrieved.content_multihash != "placeholder"  # Hash was calculated
-        assert retrieved.size_bytes == len(content.encode("utf-8"))
+        assert retrieved.size_bytes == len(content)
 
         # Verify content can be read
         assert retrieved.content is not None
         retrieved_content = retrieved.content.read().decode("utf-8")
         assert retrieved_content == content
 
-    async def test_save_document_with_content_string_unicode(
+    async def test_save_document_with_content_bytes_unicode(
         self, repository: MinioDocumentRepository
     ) -> None:
-        """Test saving document with unicode content_string."""
+        """Test saving document with unicode content_bytes."""
         content = '{"title": "测试文档", "emoji": "🚀", "content": "éñ"}'
 
         document = Document(
@@ -476,7 +478,7 @@ class TestMinioDocumentRepositoryContentString:
             size_bytes=100,
             content_multihash="placeholder",
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
         await repository.save(document)
@@ -490,12 +492,12 @@ class TestMinioDocumentRepositoryContentString:
     # Note: Empty content test removed because domain model requires
     # size_bytes > 0
 
-    async def test_save_excludes_content_string_from_metadata(
+    async def test_save_excludes_content_bytes_from_metadata(
         self,
         repository: MinioDocumentRepository,
         fake_minio_client: FakeMinioClient,
     ) -> None:
-        """Test that content_string is not stored in metadata."""
+        """Test that content_bytes is not stored in metadata."""
         content = '{"test": "data that should not be in metadata"}'
 
         document = Document(
@@ -505,7 +507,7 @@ class TestMinioDocumentRepositoryContentString:
             size_bytes=100,
             content_multihash="placeholder",
             status=DocumentStatus.CAPTURED,
-            content_string=content,
+            content_bytes=content,
         )
 
         await repository.save(document)
@@ -521,8 +523,8 @@ class TestMinioDocumentRepositoryContentString:
 
         metadata_dict = json.loads(metadata_json)
 
-        # Verify content_string is not in stored metadata
-        assert "content_string" not in metadata_dict
+        # Verify content_bytes is not in stored metadata
+        assert "content_bytes" not in metadata_dict
         assert "content" not in metadata_dict
 
         # Verify essential fields are still present

julee/repositories/minio/tests/test_document_policy_validation.py

@@ -21,6 +21,8 @@ from julee.repositories.minio.document_policy_validation import (
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/repositories/minio/tests/test_knowledge_service_config.py

@@ -20,6 +20,8 @@ from julee.repositories.minio.knowledge_service_config import (
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/repositories/minio/tests/test_knowledge_service_query.py

@@ -19,6 +19,8 @@ from julee.repositories.minio.knowledge_service_query import (
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/repositories/minio/tests/test_policy.py

@@ -15,6 +15,8 @@ from julee.repositories.minio.policy import MinioPolicyRepository
 
 from .fake_client import FakeMinioClient
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def fake_client() -> FakeMinioClient:

julee/services/knowledge_service/anthropic/tests/test_knowledge_service.py

@@ -27,6 +27,8 @@ from julee.services.knowledge_service.anthropic import (
     knowledge_service as anthropic_ks_module,
 )
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def test_document() -> Document:

julee/services/knowledge_service/memory/test_knowledge_service.py

@@ -23,6 +23,8 @@ from julee.domain.models.knowledge_service_config import (
 from ..knowledge_service import QueryResult
 from .knowledge_service import MemoryKnowledgeService
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def test_document() -> Document:

julee/services/knowledge_service/test_factory.py

@@ -26,6 +26,8 @@ from julee.services.knowledge_service.factory import (
     knowledge_service_factory,
 )
 
+pytestmark = pytest.mark.unit
+
 
 @pytest.fixture
 def test_document() -> Document:

julee/util/tests/test_decorators.py

@@ -34,6 +34,8 @@ from julee.util.temporal.decorators import (
     temporal_workflow_proxy,
 )
 
+pytestmark = pytest.mark.unit
+
 
 @runtime_checkable
 class MockBaseRepositoryProtocol(Protocol):

julee-0.1.5.dist-info/METADATA

@@ -0,0 +1,103 @@
+Metadata-Version: 2.4
+Name: julee
+Version: 0.1.5
+Summary: Julee - Clean architecture for accountable and transparent digital supply chains
+Author-email: Pyx Industries <chris@pyx.io>
+License: GPL-3.0
+Project-URL: Homepage, https://github.com/pyx-industries/julee
+Project-URL: Repository, https://github.com/pyx-industries/julee
+Project-URL: Documentation, https://github.com/pyx-industries/julee#readme
+Project-URL: Issues, https://github.com/pyx-industries/julee/issues
+Keywords: temporal,workflow,document-processing,ai,supply-chain
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastapi>=0.100.0
+Requires-Dist: uvicorn>=0.20.0
+Requires-Dist: python-multipart
+Requires-Dist: fastapi-pagination>=0.12.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: temporalio[pydantic]>=1.3.0
+Requires-Dist: minio>=7.0.0
+Requires-Dist: anthropic>=0.66.0
+Requires-Dist: click>=0.8.0
+Requires-Dist: Jinja2>=3.0.0
+Requires-Dist: PyYAML>=6.0.0
+Requires-Dist: python-magic>=0.4.27
+Requires-Dist: multihash>=0.1.1
+Requires-Dist: six>=1.16.0
+Requires-Dist: jsonschema>=4.0.0
+Requires-Dist: jsonpointer>=3.0.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-asyncio>=1.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.1.0; extra == "dev"
+Requires-Dist: pytest-xdist>=3.5.0; extra == "dev"
+Requires-Dist: hypothesis>=6.0.0; extra == "dev"
+Requires-Dist: factory-boy>=3.2.0; extra == "dev"
+Requires-Dist: mypy>=1.7.0; extra == "dev"
+Requires-Dist: types-PyYAML; extra == "dev"
+Requires-Dist: types-jsonschema; extra == "dev"
+Requires-Dist: types-python-dateutil; extra == "dev"
+Requires-Dist: black>=24.0.0; extra == "dev"
+Requires-Dist: ruff>=0.5.0; extra == "dev"
+Requires-Dist: pre-commit>=3.0.0; extra == "dev"
+Requires-Dist: bandit; extra == "dev"
+Requires-Dist: pip-tools>=7.0.0; extra == "dev"
+Requires-Dist: asyncpg; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: sphinx>=7.0.0; extra == "docs"
+Requires-Dist: sphinx-autobuild>=2021.3.14; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=2.0.0; extra == "docs"
+Requires-Dist: furo>=2023.9.10; extra == "docs"
+Requires-Dist: sphinx-autodoc-typehints>=1.25.0; extra == "docs"
+Requires-Dist: sphinxcontrib-mermaid>=0.9.2; extra == "docs"
+Requires-Dist: sphinxcontrib-plantuml>=0.25; extra == "docs"
+Requires-Dist: sphinx-autoapi>=3.0.0; extra == "docs"
+Dynamic: license-file
+
+# Julee
+
+Clean architecture for accountable and transparent digital supply chains.
+
+Julee is a Python framework for building resilient, auditable business processes using Temporal workflows. Solutions are organized around your business domain—your bounded contexts become "accelerators" that speak your business language, not framework jargon.
+
+**Use Julee when:** processes must be done correctly, may be complex or long-running, need compliance audit trails (responsible AI, algorithmic due-diligence), or depend on unreliable services that may fail, timeout, or be rate-limited.
+
+**Core concepts:** Accelerators are collections of pipelines that automate a business area. Pipelines are use cases wrapped with Temporal, providing durability (survives crashes), reliability (automatic retries), observability (complete execution history), and supply chain provenance (audit trails that become "digital product passports").
+
+## Installation
+
+```bash
+pip install julee
+```
+
+## Runtime Dependencies
+
+Julee applications require: [Temporal](https://temporal.io/) (workflow orchestration), S3-compatible object storage (e.g. MinIO), PostgreSQL (for Temporal).
+
+## Documentation
+
+Full documentation at [julee.readthedocs.io](https://julee.readthedocs.io), package on [PyPI](https://pypi.org/project/julee/).
+
+## Example
+
+This repository includes a Docker Compose example demonstrating a meeting minutes extraction system:
+
+```bash
+cp .env.example .env  # Add your ANTHROPIC_API_KEY
+docker compose up --build
+```
+
+See the `demo-ui/` directory for the UI source.
+
+## License
+
+GPL-3.0 — see [LICENSE](LICENSE) for details.