WIP simplifying load/startup

tests/registry/models/test_document_validation.py

@@ -8,8 +8,9 @@ import yaml
 from pydantic import ValidationError
 
 from personal_mcp.registry.ingest.document import MarkdownDocument
-from personal_mcp.registry.load import _parse_frontmatter
-from personal_mcp.registry.models.common import _normalize_docs_path
+from personal_mcp.registry.models.common import ReferenceEntry
+from personal_mcp.registry.models.common import parse_docs_path
+from personal_mcp.registry.models.common import parse_reference_path
 from personal_mcp.registry.models.registry import DocsRegistry
 
 pytestmark = pytest.mark.unit
@@ -95,37 +96,43 @@ def assert_model_is_frozen(instance: Any, *, attr: str, value: Any) -> None:
         setattr(instance, attr, value)
 
 
-class TestGate1LayoutValidation:
-    """Gate 1: source layout and parse shape constraints."""
-
-    def test_parse_frontmatter_requires_payload(self) -> None:
-        """Ensures missing frontmatter fails before metadata validation."""
-        with pytest.raises(ValueError, match="missing YAML frontmatter"):
-            _parse_frontmatter(None, path=PurePosixPath("skills/alpha/SKILL.md"))
-
-    def test_parse_frontmatter_requires_mapping(self) -> None:
-        """Ensures non-object YAML payloads are rejected at parse time."""
-        with pytest.raises(TypeError, match="frontmatter must parse to an object"):
-            _parse_frontmatter("- one\n- two\n", path=PurePosixPath("skills/alpha/SKILL.md"))
-
-    def test_parse_frontmatter_accepts_mapping(self) -> None:
-        """Ensures valid mapping payload is returned for downstream validation."""
-        parsed = _parse_frontmatter("name: alpha\n", path=PurePosixPath("skills/alpha/SKILL.md"))
-
-        assert parsed == {"name": "alpha"}
-
-
 class TestGate5ContractValidation:
-    """Gate 5: canonical resource-path contract normalization."""
+    """Gate 5: canonical resource-path contracts."""
 
-    def test_normalize_docs_path_keeps_posix_relative_paths(self) -> None:
-        """Ensures docs paths remain normalized before registry publication."""
-        assert _normalize_docs_path("skills/demo/SKILL.md") == "skills/demo/SKILL.md"
+    def test_parse_docs_path_returns_pure_posix_path(self) -> None:
+        """Ensures boundary strings become path objects before publication."""
+        path = parse_docs_path("skills/demo/SKILL.md")
 
-    def test_normalize_docs_path_rejects_parent_traversal(self) -> None:
-        """Ensures traversal attempts fail contract validation."""
-        with pytest.raises(ValueError, match="normalized docs-relative path"):
-            _normalize_docs_path("../outside.md")
+        assert path == PurePosixPath("skills/demo/SKILL.md")
+        assert isinstance(path, PurePosixPath)
+
+    @pytest.mark.parametrize(
+        "value",
+        (
+            "/absolute.md",
+            "../outside.md",
+            "skills\\demo\\SKILL.md",
+            "skills//demo/SKILL.md",
+            "skills/demo/README.txt",
+        ),
+    )
+    def test_parse_docs_path_rejects_invalid_paths(self, value: str) -> None:
+        """Ensures non-canonical docs paths fail contract validation."""
+        with pytest.raises(ValueError):
+            parse_docs_path(value)
+
+    def test_reference_entry_materializes_reference_path(self) -> None:
+        """Ensures authored reference strings become constrained path objects."""
+        entry = ReferenceEntry.model_validate({"path": "references/guides/setup.md"})
+
+        assert entry.path == PurePosixPath("references/guides/setup.md")
+        assert parse_reference_path(entry.path) == entry.path
+
+    @pytest.mark.parametrize("value", ("guide.md", "other/guide.md", "references.md"))
+    def test_reference_path_stays_under_references(self, value: str) -> None:
+        """Ensures in-skill references remain below the references directory."""
+        with pytest.raises(ValueError, match="stay under references"):
+            parse_reference_path(value)
 
 
 class TestGate6FreezeValidation:
@@ -133,13 +140,14 @@ class TestGate6FreezeValidation:
 
     def test_docs_registry_copies_mapping_inputs(self) -> None:
         """Ensures registry snapshots are isolated from caller-owned mapping mutations."""
-        source_docs = {"index.md": "# index\n"}
+        index_path = PurePosixPath("index.md")
+        source_docs = {index_path: "# index\n"}
         registry = DocsRegistry(
             skills_by_id={},
             skills_in_load_order=(),
             skills_summary_in_load_order=(),
             docs_markdown_by_path=source_docs,
-            docs_markdown_path_index=("index.md",),
+            docs_markdown_path_index=(index_path,),
             tag_to_skill_ids={},
             capability_to_skill_ids={},
             prompts_by_id={},
@@ -148,9 +156,10 @@ class TestGate6FreezeValidation:
             tag_to_prompt_ids={},
         )
 
-        source_docs["other.md"] = "# other\n"
+        source_docs[PurePosixPath("other.md")] = "# other\n"
 
-        assert "other.md" not in registry.docs_markdown_by_path
+        assert PurePosixPath("other.md") not in registry.docs_markdown_by_path
+        assert registry.docs_markdown_path_index == (index_path,)
 
     def test_docs_registry_instance_is_frozen(self) -> None:
         """Ensures frozen model prevents attribute reassignment."""
@@ -168,4 +177,8 @@ class TestGate6FreezeValidation:
             tag_to_prompt_ids={},
         )
 
-        assert_model_is_frozen(registry, attr="docs_markdown_path_index", value=("index.md",))
+        assert_model_is_frozen(
+            registry,
+            attr="docs_markdown_path_index",
+            value=(PurePosixPath("index.md"),),
+        )