Add TRACE TRO export for certified bundles

.github/workflows/push.yaml

@@ -81,10 +81,8 @@ jobs:
       - uses: actions/setup-node@v4
         with:
           node-version: 18.x
-      - name: Install MyST
-        run: npm install -g mystmd
       - name: Build HTML Assets
-        run: cd docs && myst build --html
+        run: make docs
       - name: Upload artifact
         uses: actions/upload-pages-artifact@v3
         with:

Makefile

@@ -1,9 +1,15 @@
-.PHONY: docs
+.PHONY: docs docs-serve
+
+MYSTMD_VERSION ?= 1.8.3
+MYST_CMD = npx --yes mystmd@$(MYSTMD_VERSION)
 
 all: build-package
 
 docs:
-	cd docs && jupyter book start
+	cd docs && $(MYST_CMD) build --html
+
+docs-serve:
+	cd docs && $(MYST_CMD) start
 
 install:
 	uv pip install -e .[dev]
@@ -27,4 +33,4 @@ build-package:
 	python -m build
 
 test:
-	pytest tests --cov=policyengine --cov-report=term-missing
+	pytest tests --cov=policyengine --cov-report=term-missing

README.md

@@ -86,7 +86,8 @@ uv pip install -e .[dev]        # install with dev dependencies (pytest, ruff, m
 ```bash
 make format           # ruff format
 make test             # pytest with coverage
-make docs             # build Jupyter Book documentation
+make docs             # build static MyST/Jupyter Book 2 HTML docs
+make docs-serve       # preview the docs locally
 make clean            # remove caches, build artifacts, .h5 files
 ```
 

changelog.d/codex-trace-tro-export.changed.md

@@ -0,0 +1 @@
+Add TRACE TRO export helpers for certified runtime bundles and expose them through `policyengine.core`.

docs/dev.md

@@ -23,7 +23,8 @@ dependencies used in CI (pytest, ruff, mypy, towncrier).
 ```bash
 make format           # ruff format
 make test             # pytest with coverage
-make docs             # run the MyST docs build used in CI via npx
+make docs             # build static MyST/Jupyter Book 2 HTML docs
+make docs-serve       # preview the docs locally
 make clean            # remove caches, build artifacts, .h5 files
 ```
 

docs/release-bundles.md

@@ -186,6 +186,55 @@ Notes:
 - apps and APIs should surface this bundle, not only country package versions
 - a bundle may reuse a previously staged data artifact if compatibility is explicitly certified
 
+## TRACE export
+
+The internal build manifest and certified runtime bundle remain the operational source of
+truth.
+
+TRACE sits on top of those manifests as a standards-based export layer.
+
+### What gets exported
+
+Country `*-data` repos should emit a `trace.tro.jsonld` file for each published data
+release. That TRO should cover:
+
+- the release manifest itself
+- each published artifact hash listed in the release manifest
+- the build-time model provenance recorded in the release manifest
+
+`policyengine.py` should emit a separate certified-bundle TRO. That TRO should cover:
+
+- the bundled country release manifest shipped in `policyengine.py`
+- the country data release manifest resolved for the certified data package version
+- the certified dataset artifact hash
+- the certification basis used to allow runtime reuse
+
+### What TRACE does not replace
+
+TRACE is not the source of truth for compatibility policy.
+
+In particular, TRACE does not decide:
+
+- whether a new model version can safely reuse an existing data artifact
+- how `data_build_fingerprint` is computed
+- which staged artifact becomes a supported runtime default
+
+Those decisions still belong to the country data build manifest and the
+`policyengine.py` certified runtime bundle.
+
+### Why we still want it
+
+TRACE adds three things our internal manifests do not provide by themselves:
+
+- a standard declaration format for provenance exchange
+- a composition fingerprint over the exact artifacts in scope
+- a better external surface for papers, audits, and reproducibility reviews
+
+That is why the recommended design is:
+
+- internal manifests for build/certification control
+- generated TRACE TROs for standards-based export
+
 ## Compatibility rule
 
 The architecture should avoid forcing a new data build for every harmless country model release.

src/policyengine/core/__init__.py

@@ -36,6 +36,13 @@
 from .tax_benefit_model_version import (
     TaxBenefitModelVersion as TaxBenefitModelVersion,
 )
+from .trace_tro import (
+    build_trace_tro_from_release_bundle as build_trace_tro_from_release_bundle,
+)
+from .trace_tro import (
+    compute_trace_composition_fingerprint as compute_trace_composition_fingerprint,
+)
+from .trace_tro import serialize_trace_tro as serialize_trace_tro
 from .variable import Variable as Variable
 
 # Rebuild models to resolve forward references

src/policyengine/core/tax_benefit_model_version.py

@@ -4,8 +4,14 @@
 
 from pydantic import BaseModel, Field
 
-from .release_manifest import CountryReleaseManifest, DataCertification, PackageVersion
+from .release_manifest import (
+    CountryReleaseManifest,
+    DataCertification,
+    PackageVersion,
+    get_data_release_manifest,
+)
 from .tax_benefit_model import TaxBenefitModel
+from .trace_tro import build_trace_tro_from_release_bundle
 
 if TYPE_CHECKING:
     from .parameter import Parameter
@@ -201,6 +207,22 @@ def release_bundle(self) -> dict[str, str | None]:
             ),
         }
 
+    @property
+    def trace_tro(self) -> dict:
+        if self.release_manifest is None:
+            raise ValueError(
+                "TRACE TRO export requires a bundled country release manifest."
+            )
+
+        data_release_manifest = get_data_release_manifest(
+            self.release_manifest.country_id
+        )
+        return build_trace_tro_from_release_bundle(
+            self.release_manifest,
+            data_release_manifest,
+            certification=self.data_certification,
+        )
+
     def __repr__(self) -> str:
         # Give the id and version, and the number of variables, parameters, parameter nodes, parameter values
         return f"<TaxBenefitModelVersion id={self.id} variables={len(self.variables)} parameters={len(self.parameters)} parameter_nodes={len(self.parameter_nodes)} parameter_values={len(self.parameter_values)}>"