Migrate TRACE TROs to canonical TROv 0.1 namespace

changelog.d/migrate-trov-namespace-canonical.changed.md

@@ -0,0 +1 @@
+Migrated TRACE TRO emission from the prerelease TROv namespace `https://w3id.org/trace/2023/05/trov#` to the canonical `https://w3id.org/trace/trov/0.1#`. This aligns policyengine.py with policyengine-us-data (which already uses the canonical namespace per us-data PR #746), so both sides can share SHACL validators and TROs emitted by either side validate against the same vocabulary. Fixes #313.

docs/release-bundles.md

@@ -205,7 +205,7 @@ composition pins four artifacts by sha256:
   when present, otherwise fetched from the PyPI JSON API at emit time)
 
 TROs use the public TROv vocabulary at
-`https://w3id.org/trace/2023/05/trov#`. Every artifact location in the TRO
+`https://w3id.org/trace/trov/0.1#`. Every artifact location in the TRO
 is a dereferenceable HTTPS URI or a local path relative to the shipped
 wheel. Certification metadata is carried as structured `pe:*` fields on
 the `trov:TransparentResearchPerformance` node so downstream tooling can

pyproject.toml

@@ -24,6 +24,7 @@ dependencies = [
     "pydantic>=2.0.0",
     "pandas>=2.0.0",
     "microdf_python>=1.2.1",
+    "jsonschema>=4.0.0",
     "requests>=2.31.0",
     "psutil>=5.9.0",
     "packaging>=23.0",
@@ -55,7 +56,6 @@ dev = [
     "yaml-changelog>=0.1.7",
     "itables",
     "build",
-    "jsonschema>=4.0.0",
     "plotly>=5.0.0",
     "pytest-asyncio>=0.26.0",
     "ruff>=0.9.0",

src/policyengine/data/schemas/trace_tro.schema.json

@@ -15,7 +15,7 @@
         "properties": {
           "trov": {
             "type": "string",
-            "const": "https://w3id.org/trace/2023/05/trov#"
+            "const": "https://w3id.org/trace/trov/0.1#"
           },
           "schema": {
             "type": "string",

src/policyengine/provenance/trace.py

@@ -1,7 +1,7 @@
 """TRACE Transparent Research Object (TRO) export.
 
 Emits JSON-LD that conforms to the TRACE TROv vocabulary
-(https://w3id.org/trace/2023/05/trov#) for a PolicyEngine certified
+(https://w3id.org/trace/trov/0.1#) for a PolicyEngine certified
 runtime bundle or a PolicyEngine simulation result. The bundle TRO pins
 the country model wheel, the country data release manifest, the
 certified dataset, and the bundle manifest itself by sha256. The
@@ -33,7 +33,7 @@
     https_release_manifest_uri,
 )
 
-TRACE_TROV_NAMESPACE = "https://w3id.org/trace/2023/05/trov#"
+TRACE_TROV_NAMESPACE = "https://w3id.org/trace/trov/0.1#"
 POLICYENGINE_TRACE_NAMESPACE = "https://policyengine.org/trace/0.1#"
 
 TRACE_CONTEXT: list[dict[str, str]] = [

tests/test_graph/test_extractor.py

@@ -102,7 +102,6 @@ class TestDirectEntityReference:
     """Pattern 1: ``entity("<var>", period)`` produces an edge."""
 
     def test_single_direct_reference(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         _write_variable(
             root,
@@ -153,7 +152,6 @@ class TestAddHelperReference:
     """Pattern 2: ``add(entity, period, [...])`` emits one edge per list item."""
 
     def test_add_helper_list(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         _write_variable(
             root,
@@ -175,7 +173,6 @@ class TestImpactAnalysis:
     """``impact(var)`` returns variables that depend on ``var`` transitively."""
 
     def test_transitive_upstream(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         _write_variable(root, "wages", "return 0")
         _write_variable(
@@ -228,7 +225,6 @@ class TestMultipleFormulas:
     """Year-specific ``formula_YYYY`` methods contribute edges too."""
 
     def test_year_specific_formula_contributes_edges(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         (root / "ctc.py").parent.mkdir(parents=True, exist_ok=True)
         (root / "ctc.py").write_text(
@@ -260,7 +256,6 @@ class TestPath:
     """``path(src, dst)`` returns a dependency chain if one exists."""
 
     def test_path_two_hops(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         _write_variable(root, "wages", "return 0")
         _write_variable(root, "gross_income", 'return tax_unit("wages", period)')
@@ -278,7 +273,6 @@ def test_path_two_hops(self, tmp_path: Path) -> None:
         ]
 
     def test_path_returns_none_if_unreachable(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         _write_variable(root, "island_a", "return 0")
         _write_variable(root, "island_b", "return 0")
@@ -295,7 +289,6 @@ class TestRequiresVariableSubclass:
     """
 
     def test_non_variable_classes_are_ignored(self, tmp_path: Path) -> None:
-
         root = tmp_path / "variables"
         root.mkdir(parents=True, exist_ok=True)
         # Looks like a variable body but the class is not a Variable.

tests/test_trace_tro.py

@@ -118,7 +118,7 @@ class TestBundleTRO:
     def test__given_context__then_uses_public_trov_namespace(self, us_bundle_tro):
         context = us_bundle_tro["@context"][0]
         assert context["trov"] == TRACE_TROV_NAMESPACE
-        assert context["trov"] == "https://w3id.org/trace/2023/05/trov#"
+        assert context["trov"] == "https://w3id.org/trace/trov/0.1#"
 
     def test__given_root_type__then_is_single_transparent_research_object(
         self, us_bundle_tro