feat(ingest): resolve project labels with Jev

src/gewu/application/ports.py

@@ -9,7 +9,7 @@ from dataclasses import dataclass
 from pathlib import Path, PurePosixPath
 from typing import Protocol
 
-from gewu.domain.contracts import AutoAcceptPolicy, ProjectRecord
+from gewu.domain.contracts import AutoAcceptPolicy, ProjectFacetLabel, ProjectRecord
 
 
 class CanonicalRepositoryError(RuntimeError):
@@ -74,10 +74,16 @@ class ProjectRegistry(Protocol):
 
     def create(self, project: ProjectRecord, policy: AutoAcceptPolicy) -> ProjectRecord: ...
 
-    def update_content(self, project_id: str, *, description: str, north_star: str, key_questions: tuple[str, ...]) -> ProjectRecord: ...
+    def update_content(
+        self, project_id: str, *, description: str, north_star: str, key_questions: tuple[str, ...]
+    ) -> ProjectRecord: ...
 
     def archive(self, project_id: str) -> ProjectRecord: ...
 
+    def add_facet_labels(
+        self, project_id: str, labels: tuple[ProjectFacetLabel, ...]
+    ) -> ProjectRecord: ...
+
 
 class EmbeddingProvider(Protocol):
     """Replaceable, normalized text-vector provider for derived retrieval indexes."""

src/gewu/application/registry.py

@@ -3,6 +3,7 @@
 from __future__ import annotations
 
 import json
+import unicodedata
 from contextlib import AbstractContextManager
 from dataclasses import dataclass
 from pathlib import Path
@@ -20,6 +21,7 @@ from gewu.domain.contracts import (
     AutoAcceptPolicy,
     ExtractionRecord,
     KnowledgeNode,
+    ProjectFacetLabel,
     ProjectRecord,
     ProjectStatus,
     SourceRevisionRecord,
@@ -307,15 +309,23 @@ class LocalProjectRegistry:
         self, project_id: str, *, description: str, north_star: str, key_questions: tuple[str, ...]
     ) -> ProjectRecord:
         """Update a project's human-authored description and research questions."""
-        if self.repository is None or self.index_directory is None or self.authority_lock_path is None:
+        if (
+            self.repository is None
+            or self.index_directory is None
+            or self.authority_lock_path is None
+        ):
             raise RegistryError("Canonical project publication is not configured")
         with self._write_lock():
             project = _index(self._projects(), "project_id").get(project_id)
             if project is None:
                 raise RegistryNotFound("Project is not registered")
-            updated = project.model_copy(update={
-                "description": description, "north_star": north_star, "key_questions": key_questions,
-            })
+            updated = project.model_copy(
+                update={
+                    "description": description,
+                    "north_star": north_star,
+                    "key_questions": key_questions,
+                }
+            )
             try:
                 self.repository.publish_files(
                     expected_head=self.repository.head(),
@@ -324,7 +334,9 @@ class LocalProjectRegistry:
                     index_directory=self.index_directory,
                 )
             except CanonicalConflictError as error:
-                raise RegistryConflict("Canonical project registry changed during update") from error
+                raise RegistryConflict(
+                    "Canonical project registry changed during update"
+                ) from error
         return updated
 
     def archive(self, project_id: str) -> ProjectRecord:
@@ -359,6 +371,72 @@ class LocalProjectRegistry:
                 ) from error
         return archived
 
+    def add_facet_labels(
+        self, project_id: str, labels: tuple[ProjectFacetLabel, ...]
+    ) -> ProjectRecord:
+        """Atomically add bounded Jev-qualified labels to the canonical project record."""
+
+        if not labels or len(labels) > 20:
+            raise ValueError("Facet label additions must contain between 1 and 20 labels")
+        if (
+            self.repository is None
+            or self.index_directory is None
+            or self.authority_lock_path is None
+        ):
+            raise RegistryError("Canonical project publication is not configured")
+        with self._write_lock():
+            project = _index(self._projects(), "project_id").get(project_id)
+            if project is None:
+                raise RegistryNotFound("Project is not registered")
+            existing = {
+                (label.facet, _normalize_facet_label(label.canonical_label))
+                for label in project.facet_labels
+                if label.status == "active"
+            }
+            existing.update(
+                (label.facet, _normalize_facet_label(alias))
+                for label in project.facet_labels
+                if label.status == "active"
+                for alias in label.aliases
+            )
+            accepted: list[ProjectFacetLabel] = []
+            known_ids = {label.label_id for label in project.facet_labels}
+            for label in labels:
+                if label.status != "active" or label.merged_into is not None:
+                    raise ValueError("Only active new facet labels may be added")
+                if label.label_id in known_ids:
+                    raise RegistryConflict("Facet label ID is already registered")
+                normalized_names = (
+                    label.canonical_label,
+                    *label.aliases,
+                )
+                if any(
+                    (label.facet, _normalize_facet_label(name)) in existing
+                    for name in normalized_names
+                ):
+                    raise RegistryConflict("Facet label duplicates an existing project label")
+                for name in normalized_names:
+                    existing.add((label.facet, _normalize_facet_label(name)))
+                known_ids.add(label.label_id)
+                accepted.append(label)
+            if len(project.facet_labels) + len(accepted) > 2_000:
+                raise RegistryError("Project facet label catalog exceeds its configured limit")
+            updated = project.model_copy(
+                update={"facet_labels": (*project.facet_labels, *accepted)}
+            )
+            try:
+                self.repository.publish_files(
+                    expected_head=self.repository.head(),
+                    files={_project_record_path(project_id): _project_markdown(updated)},
+                    message=f"Add qualified facet labels to {project_id}",
+                    index_directory=self.index_directory,
+                )
+            except CanonicalConflictError as error:
+                raise RegistryConflict(
+                    "Canonical project registry changed while adding facet labels"
+                ) from error
+        return updated
+
     def _write_lock(self) -> AbstractContextManager[Any]:
         lock_path = self.authority_lock_path
         if lock_path is None:
@@ -381,6 +459,10 @@ def _project_record_path(project_id: str) -> str:
     return f"projects/{project_id}/project.md"
 
 
+def _normalize_facet_label(value: str) -> str:
+    return " ".join(unicodedata.normalize("NFC", value).casefold().split())
+
+
 def _policy_record_path(policy_id: str) -> str:
     import hashlib