baseline repo characteristics no longer crowd the candidate graph

tests/test_registry_service.py

@@ -15,6 +15,7 @@ from tests.fixtures import (
     write_javascript_typescript_package_repo,
     write_key_cape_like_repo,
     write_llm_connect_like_repo,
+    write_ops_bridge_like_repo,
     write_misleading_docs_repo,
     write_python_cli_repo,
     write_readme_only_repo,
@@ -27,6 +28,32 @@ def make_service(tmp_path):
     return RegistryService(store, ingestion=GitIngestionService(tmp_path / "checkouts"))
 
 
+def add_candidate_capability(service, repository_id, analysis_run_id, ability_id, name):
+    with service.store.connect() as connection:
+        cursor = connection.execute(
+            """
+            INSERT INTO candidate_capabilities
+              (repository_id, analysis_run_id, ability_id, name, description,
+               inputs, outputs, primary_class, attributes, confidence, source_refs)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+            """,
+            (
+                repository_id,
+                analysis_run_id,
+                ability_id,
+                name,
+                "Review target capability inserted for review workflow tests.",
+                "[]",
+                "[]",
+                "test-capability",
+                json.dumps(["test-review-target"]),
+                0.5,
+                "[]",
+            ),
+        )
+        return int(cursor.lastrowid)
+
+
 class FakeLLMExtractor:
     def __init__(self, abilities):
         self.abilities = abilities
@@ -298,12 +325,12 @@ def test_search_filters_by_status_language_and_framework(tmp_path):
     service.approve_candidate_graph(repository.id, summary.analysis_run.id)
 
     results = service.search(
-        "repository",
+        "health",
         status="indexed",
         language="Python",
         framework="FastAPI",
         ability="Support Filterable",
-        capability="Repository Structure",
+        capability="Repository Interface",
     )
     wrong_language_results = service.search(
         "repository",
@@ -380,7 +407,6 @@ def test_fixture_breadth_javascript_typescript_package_extracts_structure_and_ap
     assert ("framework", "React", "package.json") in fact_names
     assert ("framework", "Vitest", "package.json") in fact_names
     assert "Expose Repository Interface" in capability_names
-    assert "Describe Repository Structure" in capability_names
     assert "API" in feature_types
     assert service.ability_map(repository.id).abilities == []
 
@@ -468,10 +494,36 @@ def test_regression_dependency_only_repo_keeps_libraries_as_context(tmp_path):
         for capability in ability.capabilities
     }
     assert "Route LLM Requests Across Providers" not in capability_names
-    assert capability_names == {"Describe Repository Structure"}
-    structure = graph.abilities[0].capabilities[0]
-    assert "utility-dependency" in structure.attributes
-    assert "review-required-structural-context" in structure.attributes
+    assert capability_names == set()
+    assert any(fact.kind == "manifest" for fact in summary.facts)
+
+
+def test_regression_ops_bridge_like_repo_is_it_operations_not_llm_provider(tmp_path):
+    source = write_ops_bridge_like_repo(tmp_path)
+    service = make_service(tmp_path)
+    repository = service.register_repository(name="Ops Bridge Marketing Name", url=str(source))
+
+    summary = service.analyze_repository(repository.id, use_llm_assistance=False)
+    graph = service.candidate_graph(repository.id, summary.analysis_run.id)
+
+    ability = graph.abilities[0]
+    capability_names = {
+        capability.name
+        for candidate_ability in graph.abilities
+        for capability in candidate_ability.capabilities
+    }
+    facts = {(fact.kind, fact.name, fact.path) for fact in summary.facts}
+    assert ability.name == "Manage SSH Reverse Tunnel Connectivity"
+    assert ability.primary_class == "it-operations"
+    assert {"remote-access", "connectivity", "operations"} <= set(ability.attributes)
+    assert "repository" not in ability.attributes
+    assert "llm-provider" not in ability.attributes
+    assert "Route LLM Requests Across Providers" not in capability_names
+    assert "Maintain Continuous Connectivity Between Remote Systems And Central Hub" in capability_names
+    assert "Make Connectivity Observable Auditable And Controllable" in capability_names
+    assert "Expose CLI And MCP Accessible Service" in capability_names
+    assert ("llm_provider", "Claude", "scripts/register_mcp.py") not in facts
+    assert ("llm_provider", "Claude", "workplans/BRIDGE-WP-0003.md") not in facts
 
 
 def test_fixture_breadth_empty_repo_produces_no_candidate_claims(tmp_path):
@@ -933,20 +985,14 @@ def test_analyze_repository_can_trusted_auto_approve_candidates(tmp_path):
         for capability in graph.abilities[0].capabilities
     }
     assert statuses_by_capability["Expose Repository Interface"] == "approved"
-    assert statuses_by_capability["Describe Repository Structure"] == "candidate"
     assert ability_map.abilities[0].name == "Report Health Over HTTP"
     assert decisions[0].action == "trusted_auto_approve_candidate_graph"
     assert "deterministic candidate generation" in decisions[0].notes
-    assert "Auto-approved 1 safe candidate capability(s); left 1 for review." in decisions[0].notes
+    assert "Auto-approved 1 safe candidate capability(s); left 0 for review." in decisions[0].notes
     assert (
         "Approved: Expose Repository Interface: owned interface with sufficient confidence."
         in decisions[0].notes
     )
-    assert (
-        "Skipped: Describe Repository Structure: structural/dependency context "
-        "requires curator review."
-        in decisions[0].notes
-    )
 
 
 def test_rebuild_characteristics_dry_run_preserves_approved_map(tmp_path):
@@ -1523,6 +1569,14 @@ def test_relink_candidate_feature_and_evidence_to_another_capability(tmp_path):
     repository = service.register_repository(name="Relink Leaves", url=str(source))
     summary = service.analyze_repository(repository.id)
     graph = service.candidate_graph(repository.id, summary.analysis_run.id)
+    add_candidate_capability(
+        service,
+        repository.id,
+        summary.analysis_run.id,
+        graph.abilities[0].id,
+        "Review Target Capability",
+    )
+    graph = service.candidate_graph(repository.id, summary.analysis_run.id)
     source_capability = graph.abilities[0].capabilities[0]
     target_capability = graph.abilities[0].capabilities[1]
     feature = source_capability.features[0]
@@ -1625,6 +1679,14 @@ def test_merge_candidate_capability_moves_children_to_target(tmp_path):
     repository = service.register_repository(name="Merge Capability", url=str(source))
     summary = service.analyze_repository(repository.id)
     graph = service.candidate_graph(repository.id, summary.analysis_run.id)
+    add_candidate_capability(
+        service,
+        repository.id,
+        summary.analysis_run.id,
+        graph.abilities[0].id,
+        "Review Target Capability",
+    )
+    graph = service.candidate_graph(repository.id, summary.analysis_run.id)
     source_capability = graph.abilities[0].capabilities[0]
     target_capability = graph.abilities[0].capabilities[1]