feat: WP-0004 T01-T04 — stable corpus, ADRs, regression test

- corpus/markidocx-docs/manifest.yaml: specs as live markidocx project (FR-1101)
- corpus/markidocx-docs/known-drift.md: documented structural drift
- workflows.py: release-regression accepts manifest path; emits corpus_id (FR-1109)
- tests/regression/test_corpus_regression.py: corpus regression suite (FR-1102–1110)
- architecture/ADR-002: python-docx as conversion engine
- architecture/ADR-003: manifest YAML schema
- workplans/MRKD-WP-0004: T01–T04 done; T05 blocked (SBOM path mapping needed)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tests/regression/test_corpus_regression.py

@@ -0,0 +1,89 @@
+"""Corpus regression test — markidocx-docs (FR-1101 through FR-1110).
+
+Runs the release-regression workflow against the real product documentation
+corpus (corpus/markidocx-docs/manifest.yaml). This test validates that the
+markidocx specs themselves survive a round-trip within documented tolerance.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import pytest
+
+from markidocx.workflows import run_workflow
+
+REPO_ROOT = Path(__file__).parent.parent.parent
+CORPUS_MANIFEST = REPO_ROOT / "corpus" / "markidocx-docs" / "manifest.yaml"
+
+# Drift tolerance per known-drift.md: 902 elements preserved, ~71 broken.
+# Gate: preserve at least 800 elements; broken must not exceed 150.
+MIN_PRESERVED = 800
+MAX_BROKEN = 150
+
+
+@pytest.mark.skipif(
+    not CORPUS_MANIFEST.exists(),
+    reason="Corpus manifest not found — run from repo root after WP-0004-T01",
+)
+class TestCorpusRegression:
+    def test_workflow_completes(self) -> None:
+        """release-regression workflow must not be classified as 'failed' (FR-1102)."""
+        result = run_workflow("release-regression", CORPUS_MANIFEST)
+        assert result.classification != "failed", (
+            f"release-regression workflow failed: {result.aggregate_output}"
+        )
+
+    def test_workflow_classification_acceptable(self) -> None:
+        """Workflow result must be 'full' or 'with-fallback' (FR-1305)."""
+        result = run_workflow("release-regression", CORPUS_MANIFEST)
+        assert result.classification in {"full", "with-fallback"}, (
+            f"Unexpected classification: {result.classification}"
+        )
+
+    def test_all_steps_executed(self) -> None:
+        """All four steps must be executed (FR-1304): validate, build, import, compare."""
+        result = run_workflow("release-regression", CORPUS_MANIFEST)
+        executed = {s.name for s in result.steps if s.status == "executed"}
+        for step in ("validate", "build", "import", "compare"):
+            assert step in executed, f"Step '{step}' was not executed"
+
+    def test_corpus_identity_disclosed(self) -> None:
+        """Workflow result must carry corpus_id with manifest_path and git_sha (FR-1109)."""
+        result = run_workflow("release-regression", CORPUS_MANIFEST)
+        corpus_id = result.aggregate_output.get("corpus_id")
+        assert corpus_id is not None, "corpus_id missing from aggregate_output"
+        assert "manifest_path" in corpus_id, "corpus_id missing manifest_path"
+        assert "git_sha" in corpus_id, "corpus_id missing git_sha"
+
+    def test_evidence_artefacts_written(self) -> None:
+        """Evidence store must contain build, import, and drift reports (FR-1107, FR-1110)."""
+        from markidocx.evidence import EvidenceStore
+
+        store = EvidenceStore()
+        result = run_workflow("release-regression", CORPUS_MANIFEST, evidence_store=store)
+        reports = store.list_reports(result.run_id)
+        report_types = {r.report_type for r in reports}
+        for expected in ("build", "import", "drift"):
+            assert expected in report_types, (
+                f"Evidence missing '{expected}' report. Found: {report_types}"
+            )
+
+    def test_drift_within_tolerance(self) -> None:
+        """Structural drift must stay within documented tolerance from known-drift.md."""
+        result = run_workflow("release-regression", CORPUS_MANIFEST)
+        compare_step = next(
+            (s for s in result.steps if s.name == "compare"), None
+        )
+        assert compare_step is not None, "compare step not found"
+        output = compare_step.output or {}
+        preserved = output.get("preserved", [])
+        broken = output.get("broken", [])
+        n_preserved = preserved if isinstance(preserved, int) else len(preserved)
+        n_broken = broken if isinstance(broken, int) else len(broken)
+        assert n_preserved >= MIN_PRESERVED, (
+            f"Preserved elements ({n_preserved}) below tolerance ({MIN_PRESERVED})"
+        )
+        assert n_broken <= MAX_BROKEN, (
+            f"Broken elements ({n_broken}) exceeds tolerance ({MAX_BROKEN})"
+        )