Merge pull request #58 from redhat-performance/feat/RPOPC-1347-uuid-fields

RPOPC-1347: Add UUID tracking fields to Chronicler schema

Author: grdumas

src/chronicler/schema.py

@@ -46,6 +46,11 @@ class Metadata:
     # URL to the Performance CoPilot (PCP) archive for this test run (e.g. internal server, S3).
     pcp_archive_url: Optional[str] = None
 
+    # UUIDs for tracking (Zathras integration)
+    project_uuid: Optional[str] = None
+    run_uuid: Optional[str] = None
+    result_uuid: Optional[str] = None
+
     def to_dict(self) -> Dict[str, Any]:
         return {k: v for k, v in asdict(self).items() if v is not None}
 
@@ -389,6 +394,7 @@ def calculate_content_hash(self, exclude_processing_timestamp: bool = True) -> s
         The hash excludes:
         - All timestamps (test_timestamp, processing_timestamp, collection_timestamp)
         - Document ID (computed from hash)
+        - UUIDs (project_uuid, run_uuid, result_uuid - identifiers, not content)
         - Timeseries data (stored separately, often has synthetic timestamps)
 
         Args:
@@ -402,15 +408,21 @@ def calculate_content_hash(self, exclude_processing_timestamp: bool = True) -> s
         doc_dict = copy.deepcopy(self.to_dict_summary_only())
 
         # Remove fields that change on re-processing or are metadata-only
-        if exclude_processing_timestamp and 'metadata' in doc_dict:
-            # Remove ALL timestamps - they're metadata, not test results
-            doc_dict['metadata'].pop('processing_timestamp', None)
-            doc_dict['metadata'].pop('test_timestamp', None)
-            doc_dict['metadata'].pop('collection_timestamp', None)
-            # Also remove document_id as we're computing it
+        if 'metadata' in doc_dict:
+            if exclude_processing_timestamp:
+                # Remove ALL timestamps - they're metadata, not test results
+                doc_dict['metadata'].pop('processing_timestamp', None)
+                doc_dict['metadata'].pop('test_timestamp', None)
+                doc_dict['metadata'].pop('collection_timestamp', None)
+            # Always remove these fields regardless of timestamp flag
+            # Document ID is computed from hash, so it shouldn't be in the hash
             doc_dict['metadata'].pop('document_id', None)
             # PCP archive URL is storage location, not part of result identity
             doc_dict['metadata'].pop('pcp_archive_url', None)
+            # UUIDs are identifiers, not content - always exclude from hash
+            doc_dict['metadata'].pop('project_uuid', None)
+            doc_dict['metadata'].pop('run_uuid', None)
+            doc_dict['metadata'].pop('result_uuid', None)
 
         # Sort keys for deterministic ordering
         sorted_json = json.dumps(doc_dict, sort_keys=True, separators=(',', ':'))

tests/test_schema.py

@@ -72,6 +72,27 @@ def test_to_dict_includes_optional_when_set(self):
         assert d["instance_type"] == "m5.large"
         assert d["iteration"] == 1
 
+    def test_to_dict_includes_uuids_when_set(self):
+        """Test that UUID fields are included in to_dict() when present."""
+        meta = Metadata(
+            document_id="doc123",
+            project_uuid="550e8400-e29b-41d4-a716-446655440000",
+            run_uuid="660e8400-e29b-41d4-a716-446655440001",
+            result_uuid="770e8400-e29b-41d4-a716-446655440002",
+        )
+        d = meta.to_dict()
+        assert d["project_uuid"] == "550e8400-e29b-41d4-a716-446655440000"
+        assert d["run_uuid"] == "660e8400-e29b-41d4-a716-446655440001"
+        assert d["result_uuid"] == "770e8400-e29b-41d4-a716-446655440002"
+
+    def test_to_dict_excludes_uuids_when_not_set(self):
+        """Test backward compatibility: UUID fields are excluded when None."""
+        meta = Metadata(document_id="doc123")
+        d = meta.to_dict()
+        assert "project_uuid" not in d
+        assert "run_uuid" not in d
+        assert "result_uuid" not in d
+
 
 class TestTestInfo:
     """Tests for TestInfo dataclass."""
@@ -521,6 +542,68 @@ def test_calculate_content_hash_different_for_different_content(self):
         )
         assert doc1.calculate_content_hash() != doc2.calculate_content_hash()
 
+    def test_calculate_content_hash_excludes_uuids(self):
+        """Test that UUID fields don't affect content hash (they're identifiers, not content)."""
+        doc1 = ZathrasDocument(
+            metadata=Metadata(
+                document_id="doc123",
+                project_uuid="550e8400-e29b-41d4-a716-446655440000",
+                run_uuid="660e8400-e29b-41d4-a716-446655440001",
+                result_uuid="770e8400-e29b-41d4-a716-446655440002",
+            ),
+            test=TestInfo(name="test", version="1.0"),
+            system_under_test=SystemUnderTest(),
+            test_configuration=TestConfiguration(),
+            results=Results(status="PASS"),
+        )
+        doc2 = ZathrasDocument(
+            metadata=Metadata(
+                document_id="doc456",
+                project_uuid="880e8400-e29b-41d4-a716-446655440003",
+                run_uuid="990e8400-e29b-41d4-a716-446655440004",
+                result_uuid="aa0e8400-e29b-41d4-a716-446655440005",
+            ),
+            test=TestInfo(name="test", version="1.0"),
+            system_under_test=SystemUnderTest(),
+            test_configuration=TestConfiguration(),
+            results=Results(status="PASS"),
+        )
+        # Same content, different UUIDs - should produce same hash
+        assert doc1.calculate_content_hash() == doc2.calculate_content_hash()
+
+    def test_calculate_content_hash_excludes_uuids_regardless_of_timestamp_flag(self):
+        """Test that UUIDs are excluded even when exclude_processing_timestamp=False."""
+        doc1 = ZathrasDocument(
+            metadata=Metadata(
+                document_id="doc123",
+                test_timestamp="2026-03-17T10:00:00Z",
+                project_uuid="550e8400-e29b-41d4-a716-446655440000",
+                run_uuid="660e8400-e29b-41d4-a716-446655440001",
+                result_uuid="770e8400-e29b-41d4-a716-446655440002",
+            ),
+            test=TestInfo(name="test", version="1.0"),
+            system_under_test=SystemUnderTest(),
+            test_configuration=TestConfiguration(),
+            results=Results(status="PASS"),
+        )
+        doc2 = ZathrasDocument(
+            metadata=Metadata(
+                document_id="doc456",
+                test_timestamp="2026-03-17T10:00:00Z",
+                project_uuid="880e8400-e29b-41d4-a716-446655440003",
+                run_uuid="990e8400-e29b-41d4-a716-446655440004",
+                result_uuid="aa0e8400-e29b-41d4-a716-446655440005",
+            ),
+            test=TestInfo(name="test", version="1.0"),
+            system_under_test=SystemUnderTest(),
+            test_configuration=TestConfiguration(),
+            results=Results(status="PASS"),
+        )
+        # Same content, different UUIDs, timestamp flag False - UUIDs still excluded
+        hash1 = doc1.calculate_content_hash(exclude_processing_timestamp=False)
+        hash2 = doc2.calculate_content_hash(exclude_processing_timestamp=False)
+        assert hash1 == hash2
+
     def test_extract_timeseries_documents(self, full_document):
         ts_docs = full_document.extract_timeseries_documents()
         assert len(ts_docs) == 2