Wired optional LLM extraction into the analysis path

tests/test_registry_service.py

@@ -1,6 +1,7 @@
 import subprocess
 
 from repo_registry.core.service import RegistryService
+from repo_registry.llm_extraction import ExtractedAbility, ExtractedCapability
 from repo_registry.repo_ingestion.git import GitIngestionService
 from repo_registry.storage.sqlite import NotFoundError, RegistryStore
 
@@ -11,6 +12,16 @@ def make_service(tmp_path):
     return RegistryService(store, ingestion=GitIngestionService(tmp_path / "checkouts"))
 
 
+class FakeLLMExtractor:
+    def __init__(self, abilities):
+        self.abilities = abilities
+        self.calls = []
+
+    def extract(self, repository, chunks):
+        self.calls.append((repository, chunks))
+        return self.abilities
+
+
 def test_manual_registry_builds_ability_map(tmp_path):
     service = make_service(tmp_path)
 
@@ -363,6 +374,67 @@ def test_analyze_repository_records_snapshot_and_observed_facts(tmp_path):
     assert "Expose Repository Interface" in capability_names
 
 
+def test_analyze_repository_can_use_optional_llm_extractor(tmp_path):
+    source = tmp_path / "repo"
+    source.mkdir()
+    (source / "README.md").write_text(
+        "# Email Router\nRoutes incoming customer email.\n",
+        encoding="utf-8",
+    )
+    store = RegistryStore(tmp_path / "registry.sqlite3")
+    store.initialize()
+    extractor = FakeLLMExtractor(
+        [
+            ExtractedAbility(
+                name="Business Email Routing",
+                description="Route incoming messages.",
+                source_paths=["README.md"],
+                capabilities=[
+                    ExtractedCapability(
+                        name="Classify Incoming Email",
+                        description="Classify messages by intent.",
+                        source_paths=["README.md"],
+                    )
+                ],
+            )
+        ]
+    )
+    service = RegistryService(
+        store,
+        ingestion=GitIngestionService(tmp_path / "checkouts"),
+        llm_extractor=extractor,
+    )
+    repository = service.register_repository(name="Email Router", url=str(source))
+
+    summary = service.analyze_repository(repository.id)
+    graph = service.candidate_graph(repository.id, summary.analysis_run.id)
+
+    assert extractor.calls
+    assert extractor.calls[0][1]
+    assert graph.abilities[0].name == "Business Email Routing"
+    assert graph.abilities[0].capabilities[0].name == "Classify Incoming Email"
+    assert graph.abilities[0].source_refs[0].path == "README.md"
+
+
+def test_analyze_repository_falls_back_when_optional_llm_extractor_returns_no_candidates(tmp_path):
+    source = tmp_path / "repo"
+    source.mkdir()
+    (source / "README.md").write_text("# Fallback\n", encoding="utf-8")
+    store = RegistryStore(tmp_path / "registry.sqlite3")
+    store.initialize()
+    service = RegistryService(
+        store,
+        ingestion=GitIngestionService(tmp_path / "checkouts"),
+        llm_extractor=FakeLLMExtractor([]),
+    )
+    repository = service.register_repository(name="Fallback", url=str(source))
+
+    summary = service.analyze_repository(repository.id)
+    graph = service.candidate_graph(repository.id, summary.analysis_run.id)
+
+    assert graph.abilities[0].name == "Review Fallback Repository Usefulness"
+
+
 def test_approve_candidate_graph_publishes_ability_map_once(tmp_path):
     source = tmp_path / "repo"
     source.mkdir()