Improved datamodel and deterministic generation

src/repo_registry/core/models.py

@@ -161,6 +161,8 @@ class CandidateFeature:
     status: str
     source_refs: list[SourceReference]
     confidence_label: str = ""
+    primary_class: str = ""
+    attributes: list[str] = field(default_factory=list)
 
 
 @dataclass(frozen=True)
@@ -174,6 +176,8 @@ class CandidateCapability:
     status: str
     source_refs: list[SourceReference]
     confidence_label: str = ""
+    primary_class: str = "capability"
+    attributes: list[str] = field(default_factory=list)
     features: list[CandidateFeature] = field(default_factory=list)
     evidence: list[CandidateEvidence] = field(default_factory=list)
 
@@ -187,6 +191,8 @@ class CandidateAbility:
     status: str
     source_refs: list[SourceReference]
     confidence_label: str = ""
+    primary_class: str = "ability"
+    attributes: list[str] = field(default_factory=list)
     capabilities: list[CandidateCapability] = field(default_factory=list)
 
 
@@ -228,6 +234,8 @@ class Feature:
     confidence: float
     confidence_label: str = ""
     source_refs: list[SourceReference] = field(default_factory=list)
+    primary_class: str = ""
+    attributes: list[str] = field(default_factory=list)
 
 
 @dataclass(frozen=True)
@@ -239,6 +247,8 @@ class Capability:
     outputs: list[str]
     confidence: float
     confidence_label: str = ""
+    primary_class: str = "capability"
+    attributes: list[str] = field(default_factory=list)
     features: list[Feature] = field(default_factory=list)
     evidence: list[Evidence] = field(default_factory=list)
 
@@ -250,6 +260,8 @@ class Ability:
     description: str
     confidence: float
     confidence_label: str = ""
+    primary_class: str = "ability"
+    attributes: list[str] = field(default_factory=list)
     capabilities: list[Capability] = field(default_factory=list)
 
 

src/repo_registry/core/service.py

@@ -369,6 +369,8 @@ class RegistryService:
                         location=feature.location,
                         confidence=feature.confidence,
                         source_refs=feature.source_refs,
+                        primary_class=feature.primary_class,
+                        attributes=feature.attributes,
                     )
                 for evidence in capability.evidence:
                     if evidence.status != "candidate":
@@ -512,6 +514,8 @@ class RegistryService:
             location=feature.location,
             confidence=feature.confidence,
             source_refs=feature.source_refs,
+            primary_class=feature.primary_class,
+            attributes=feature.attributes,
         )
         self.store.mark_candidate_feature_status(
             repository_id,
@@ -655,6 +659,8 @@ class RegistryService:
             inputs=capability.inputs,
             outputs=capability.outputs,
             confidence=capability.confidence,
+            primary_class=capability.primary_class,
+            attributes=capability.attributes,
         )
         for feature in capability.features:
             if feature.status != "candidate":
@@ -667,6 +673,8 @@ class RegistryService:
                 location=feature.location,
                 confidence=feature.confidence,
                 source_refs=feature.source_refs,
+                primary_class=feature.primary_class,
+                attributes=feature.attributes,
             )
         for evidence in capability.evidence:
             if evidence.status != "candidate":
@@ -702,6 +710,8 @@ class RegistryService:
             name=candidate_ability.name,
             description=candidate_ability.description,
             confidence=candidate_ability.confidence,
+            primary_class=candidate_ability.primary_class,
+            attributes=candidate_ability.attributes,
         )
 
     def _ensure_approved_capability(
@@ -726,6 +736,8 @@ class RegistryService:
             inputs=candidate_capability.inputs,
             outputs=candidate_capability.outputs,
             confidence=candidate_capability.confidence,
+            primary_class=candidate_capability.primary_class,
+            attributes=candidate_capability.attributes,
         )
 
     def _candidate_capability_with_parent(
@@ -884,6 +896,8 @@ class RegistryService:
         name: str,
         description: str,
         confidence: float,
+        primary_class: str = "ability",
+        attributes: Sequence[str] = (),
         notes: str = "",
     ) -> CandidateGraph:
         self.store.update_candidate_ability(
@@ -893,6 +907,8 @@ class RegistryService:
             name=name,
             description=description,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
         )
         self.store.create_review_decision(
             repository_id,
@@ -912,6 +928,8 @@ class RegistryService:
         name: str,
         description: str,
         confidence: float,
+        primary_class: str = "capability",
+        attributes: Sequence[str] = (),
         notes: str = "",
     ) -> CandidateGraph:
         self.store.update_candidate_capability(
@@ -921,6 +939,8 @@ class RegistryService:
             name=name,
             description=description,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
         )
         self.store.create_review_decision(
             repository_id,
@@ -931,6 +951,40 @@ class RegistryService:
         self.store.update_repository_status(repository_id, "reviewing")
         return self.store.get_candidate_graph(repository_id, analysis_run_id)
 
+    def edit_candidate_feature(
+        self,
+        repository_id: int,
+        analysis_run_id: int,
+        candidate_feature_id: int,
+        *,
+        name: str,
+        type: str,
+        location: str,
+        confidence: float,
+        primary_class: str | None = None,
+        attributes: Sequence[str] = (),
+        notes: str = "",
+    ) -> CandidateGraph:
+        self.store.update_candidate_feature(
+            repository_id,
+            analysis_run_id,
+            candidate_feature_id,
+            name=name,
+            type=type,
+            location=location,
+            confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
+        )
+        self.store.create_review_decision(
+            repository_id,
+            analysis_run_id,
+            action="edit_candidate_feature",
+            notes=notes,
+        )
+        self.store.update_repository_status(repository_id, "reviewing")
+        return self.store.get_candidate_graph(repository_id, analysis_run_id)
+
     def relink_candidate_capability(
         self,
         repository_id: int,
@@ -1106,6 +1160,8 @@ class RegistryService:
         name: str,
         description: str = "",
         confidence: float = 1.0,
+        primary_class: str = "ability",
+        attributes: Sequence[str] = (),
     ) -> int:
         self.store.get_repository(repository_id)
         return self.store.create_ability(
@@ -1113,6 +1169,8 @@ class RegistryService:
             name=name,
             description=description,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
         )
 
     def update_ability(
@@ -1123,6 +1181,8 @@ class RegistryService:
         name: str | None = None,
         description: str | None = None,
         confidence: float | None = None,
+        primary_class: str | None = None,
+        attributes: Sequence[str] | None = None,
     ) -> RepositoryAbilityMap:
         self.store.update_ability(
             repository_id,
@@ -1130,6 +1190,8 @@ class RegistryService:
             name=name,
             description=description,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes) if attributes is not None else None,
         )
         return self.store.get_ability_map(repository_id)
 
@@ -1151,6 +1213,8 @@ class RegistryService:
         inputs: Sequence[str] = (),
         outputs: Sequence[str] = (),
         confidence: float = 1.0,
+        primary_class: str = "capability",
+        attributes: Sequence[str] = (),
     ) -> int:
         self.store.ensure_ability(repository_id, ability_id)
         return self.store.create_capability(
@@ -1161,6 +1225,8 @@ class RegistryService:
             inputs=list(inputs),
             outputs=list(outputs),
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
         )
 
     def update_capability(
@@ -1173,6 +1239,8 @@ class RegistryService:
         inputs: Sequence[str] | None = None,
         outputs: Sequence[str] | None = None,
         confidence: float | None = None,
+        primary_class: str | None = None,
+        attributes: Sequence[str] | None = None,
     ) -> RepositoryAbilityMap:
         self.store.update_capability(
             repository_id,
@@ -1182,6 +1250,8 @@ class RegistryService:
             inputs=list(inputs) if inputs is not None else None,
             outputs=list(outputs) if outputs is not None else None,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes) if attributes is not None else None,
         )
         return self.store.get_ability_map(repository_id)
 
@@ -1202,6 +1272,8 @@ class RegistryService:
         type: str,
         location: str = "",
         confidence: float = 1.0,
+        primary_class: str | None = None,
+        attributes: Sequence[str] = (),
     ) -> int:
         self.store.ensure_capability(repository_id, capability_id)
         return self.store.create_feature(
@@ -1211,6 +1283,8 @@ class RegistryService:
             type=type,
             location=location,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes),
         )
 
     def update_feature(
@@ -1222,6 +1296,8 @@ class RegistryService:
         type: str | None = None,
         location: str | None = None,
         confidence: float | None = None,
+        primary_class: str | None = None,
+        attributes: Sequence[str] | None = None,
     ) -> RepositoryAbilityMap:
         self.store.update_feature(
             repository_id,
@@ -1230,6 +1306,8 @@ class RegistryService:
             type=type,
             location=location,
             confidence=confidence,
+            primary_class=primary_class,
+            attributes=list(attributes) if attributes is not None else None,
         )
         return self.store.get_ability_map(repository_id)