week_3: address CodeRabbit findings on #937

- config_loader_test: assert retriever_backend in both the defaults and the
  override tests (was the only LibrarianConfig field left unchecked).
- __init__.py: refresh the stale 'No linking logic yet' scope note to reflect
  W1 contracts + W2 C.0 boundary + W3 C.1 retriever.

Other #937 CodeRabbit findings were already addressed on this branch
(knowledge_source model_validate_json error handling, schemas AnyUrl/datetime
fields, section_validator assert->if, test_config_is_frozen isolation +
FrozenInstanceError, dataset_test subprocess timeout, build_golden_dataset
unused loop var).

Author: PRAteek-singHWY

application/tests/librarian/config_loader_test.py

@@ -10,6 +10,7 @@ class TestConfigLoaderDefaults(unittest.TestCase):
     def test_defaults_when_env_unset(self):
         with mock.patch.dict(os.environ, {}, clear=True):
             cfg = load_config()
+        self.assertEqual(cfg.retriever_backend, "in_memory")
         self.assertEqual(cfg.crossencoder_model, "cross-encoder/ms-marco-MiniLM-L-6-v2")
         self.assertEqual(cfg.top_k_retrieval, 20)
         self.assertEqual(cfg.top_k_rerank, 5)
@@ -27,6 +28,7 @@ def test_config_is_frozen(self):
 
 class TestConfigLoaderOverrides(unittest.TestCase):
     OVERRIDES = {
+        "CRE_LIBRARIAN_RETRIEVER_BACKEND": "pgvector",
         "CRE_LIBRARIAN_CROSSENCODER_MODEL": "cross-encoder/other",
         "CRE_LIBRARIAN_TOP_K_RETRIEVAL": "50",
         "CRE_LIBRARIAN_TOP_K_RERANK": "10",
@@ -39,6 +41,7 @@ class TestConfigLoaderOverrides(unittest.TestCase):
     def test_env_overrides_apply(self):
         with mock.patch.dict(os.environ, self.OVERRIDES, clear=True):
             cfg = load_config()
+        self.assertEqual(cfg.retriever_backend, "pgvector")
         self.assertEqual(cfg.crossencoder_model, "cross-encoder/other")
         self.assertEqual(cfg.top_k_retrieval, 50)
         self.assertEqual(cfg.top_k_rerank, 10)

application/utils/librarian/__init__.py

@@ -13,7 +13,9 @@
   W1 (C.-1): contracts + config + eval harness + golden dataset.
   W2 (C.0):  input boundary — SectionValidator (validate/adapt without
              re-normalizing text) and ExplicitLinkResolver (fail-safe
-             explicit-link resolution). No retrieval/ranking logic yet.
+             explicit-link resolution).
+  W3 (C.1):  candidate retriever (in-memory + pgvector) + pipeline switch.
+Cross-encoder rerank (C.2, W4) onward is not built yet.
 
 Vendored RFC JSON schemas live under ``_rfc_schemas/``. They are pinned to
 upstream/owasp-graph @ 2b1437987768d5ed20fe9ee721ab9a898c4b84af (PR #734).